First device, second device, first network node, second network node and methods performed thereby, for handling information pertaining to reference signals

Abstract

A method, performed by a first device (131), for handling information pertaining to Reference Signals (RSs). The first device (131) operates in a communications system (100). The first device (131) obtains (704) a first indication indicating a first set of frequency resources out of one or more frequency resources configured for reception of DL RSs. The first device (131) also obtains a second indication indicating a second set of frequency resources out of the one or more frequency resources, and a third indication indicating a correspondence between the first set and the second set. The first set is larger than the second set. The first device (131) performs (705), on the DL RSs, as transmitted by a first network node (111) operating in the communications system (100), one or more first measurements on the first set of frequency resources, and one or more second measurements on the second set of frequency resources.

Description

[0001] FIRST DEVICE, SECOND DEVICE, FIRST NETWORK NODE, SECOND NETWORK NODE AND METHODS PERFORMED THEREBY, FOR HANDLING INFORMATION PERTAINING TO REFERENCE SIGNALS

[0002] TECHNICAL FIELD

[0003] The present disclosure relates generally to a first device and methods performed thereby for handling information pertaining to Reference Signals (RSs). The present disclosure further relates generally to a second device and methods performed thereby for handling information pertaining to RSs. The present disclosure also relates generally to a first network node and methods performed thereby for handling information pertaining to RSs. The present disclosure also relates generally to a second network node and methods performed thereby for handling information pertaining to RSs.

[0004] BACKGROUND

[0005] Devices within a communications system may be e.g., wireless devices, User Equipments (UEs), stations (STAs), mobile terminals, wireless terminals, terminals, and / or Mobile Stations (MS). Wireless devices are enabled to communicate wirelessly in a cellular communications network or wireless communication network, sometimes also referred to as a cellular radio system, cellular system, or cellular network. The communication may be performed e.g., between two wireless devices, between a wireless device and a regular telephone and / or between a wireless device and a server via a Radio Access Network (RAN) and possibly one or more core networks, comprised within the wireless communications network. Devices may further be referred to as mobile telephones, cellular telephones, laptops, or tablets with wireless capability, just to mention some further examples. The devices in the present context may be, for example, portable, pocket-storable, hand-held, computer-comprised, or vehicle-mounted mobile devices, enabled to communicate voice and / or data, via the RAN, with another entity, such as another terminal or a server.

[0006] The wireless communications network covers a geographical area which may be divided into cell areas, each cell area being served by a network node, which may be an access node such as a radio network node, radio node or a base station (BS), e.g., a Radio Base Station (RBS), which sometimes may be referred to as e.g., gNB, evolved Node B (“eNB”), “eNodeB”, “NodeB”, “B node”, Transmission Point (TP), or Base Transceiver Station (BTS), depending on the technology and terminology used. The base stations may be of different classes such as e.g., Wide Area Base Stations, Medium Range Base Stations, Local Area Base Stations, Home Base Stations, pico base stations, etc... , based on transmission power and thereby also cell size. A cell is the geographical area where radio coverage is provided by the base station orradio node at a base station site, or radio node site, respectively. One base station, situated on the base station site, may serve one or several cells. Further, each base station may support one or several communication technologies. The base stations may communicate over the air interface operating on radio frequencies with the terminals within range of the base stations. The wireless communications network may also comprise network nodes which may serve receiving nodes, such as wireless devices, with serving beams. In 3rd Generation Partnership Project (3GPP) Long Term Evolution (LTE), base stations, which may be referred to as eNodeBs or even eNBs, may be directly connected to one or more core networks. In the context of this disclosure, the expression Downlink (DL) may be used for the transmission path from the base station to the wireless device. The expression Uplink (UL) may be used for the transmission path in the opposite direction i.e., from the wireless device to the base station.

[0007] The standardization organization 3GPP is currently in the process of specifying a New Radio Interface called NR or 5G-UTRA, as well as a Fifth Generation (5G) Packet Core Network (CN), which may be referred to as Next Generation (NG) Core Network, abbreviated as NG-CN, NGC, 5G CN or 5G Core (5GC). NG may be understood to refer to the interface / reference point between the Radio Access Network (RAN) and the CN in 5G / NR. In a 5G System (5GS), a radio base station in NR may be referred to as a gNB or 5G Node B. An NR UE may be referred to as an nUE.

[0008] Codebook-based precoding

[0009] Multi-antenna techniques may significantly increase the data rates and reliability of a wireless communication system. The performance may be improved if both the transmitter and the receiver are equipped with multiple antennas, which may result in a multiple-input multipleoutput (MIMO) communication channel. Such systems and / or related techniques may be commonly referred to as MIMO systems.

[0010] A core component of NR may be understood to be the support of MIMO related techniques. NR may be understood to support up to 8-layer spatial multiplexing for up to 32 transmit antenna ports at the gNB with channel dependent precoding. Figure 1 is a schematic diagram illustrating a non-limiting example of data transmission with spatial multiplexing where the information carrying symbol vectors = [s1,s2, ...,sr]Tmay be first multiplied (or precoded) by a precoding matrix IV e cNrXrbefore being sent over NT antenna ports. Each symbol in s may be associated to a data layer and rmay be understood to be the number of data layers or rank, which may be understood to be a property of the wireless channel between the transmitter and the receiver. W may be understood to serve to beamform each data layer towards the UE such that signal to interference plus noise ratio (SI NR) may be maximized and cross layer interference may be minimized at the UE receiver. Spatial multiplexing may be achieved since multiple symbols may be transmitted simultaneously in a same time and frequency resource element (RE).Figure 1 is a schematic diagram illustrating a non-limiting example of data transmission with spatial multiplexing.

[0011] The received NR X 1 signal vector x at the UE equipped with R receive antennas may be expressed as:

[0012] x = HWs + e

[0013] where H e CNRXNTmay be understood to be the MIMO channel between the transmit and receive antennas, e may be understood to be a noise plus interference vector due to receiver noise and interference.

[0014] The precoder matrix W may be chosen to match the characteristics of the NRXNT MIMO channel matrix H resulting in so-called channel dependent precoding. The precoder W may be a wideband precoder, e.g., the same precoder applied over a whole bandwidth, or a subband precoder, e.g., optimized per subband. W may be typically selected from a codebook of precoding matrices by the UE and reported to the gNB in terms of a precoding matrix indicator (PMI).

[0015] One example method for a UE to select a precoder matrix W may be to select the Wkfrom a codebook that may maximize the Frobenius norm of the hypothesized equivalent channel:

[0016]

[0017] Where

[0018] H may be understood to be a channel estimate

[0019] Wkmay be understood to be a hypothesized precoder matrix with index k.

[0020] In addition to W feedback, a UE may typically also feedback a rank indicator (Rl) and channel quality indicator(s) (CQI) as part of channel state information (CSI) feedback. Given the CSI feedback from the UE, the gNB may determine the transmission parameters to use for data transmissions to the UE.

[0021] For channel estimation purposes, a so-called channel state information reference signal (CSI-RS) may be typically transmitted to the UE.

[0022] Two dimensional (2D) Antenna arrays

[0023] The antennas with NT antenna ports discussed above may be either a linear antenna array or 2D plenary antenna array. A linear antenna array may be understood to be a special case of a 2D antenna array. A 2D antenna array may be described by Nhcolumns, corresponding to the horizontal dimension, Nvrows, corresponding to the vertical dimension, and Nppolarizations. The total number of antenna ports may thus be N = NhNvNp. An example of a cross polarized, e.g., Np= 2, antenna array with Nh,Nv) = (4,4) is illustrated in Figure 2.Figure 2 is a schematic diagram illustrating a non-limiting example of a two-dimensional antenna array of cross-polarized antenna elements (NP= 2), with Nh= 4 horizontal antenna elements and Nv= 4 vertical antenna elements.

[0024] It may be noted that the 2D antenna array may be rotated at any angle. In this case, the row and columns may no longer correspond to vertical and horizontal directions. To reflect this more general case in NR, a 2D antenna array may be simply defined by a number of antenna ports in each of two dimensions, e.g., N±and N2, and Npmay be understood to always be 2. Thus, the total number of antenna ports may be understood to be N = 2N1N2.

[0025] The concept of an antenna port may be understood to be non-limiting in the sense that it may refer to any virtualization, e.g., linear mapping, of the physical antenna elements. For example, pairs of physical sub-elements may be fed the same signal, and hence share the same virtualized antenna port.

[0026] Reference signal

[0027] Reference signal configurations

[0028] Channel State Information (CSI)-Reference Signal (RS)

[0029] A CSI-RS may be transmitted over each transmit (Tx) antenna port at the network node and for different antenna ports. The CSI-RS may be multiplexed in time, frequency, and code domain such that the channel between each Tx antenna port at the network node and each receive antenna port at a UE may be measured by the UE. The time-frequency resource used for transmitting CSI-RS may be referred to as a CSI-RS resource.

[0030] In NR, the CSI-RS for beam management may be defined as a 1- or 2-port CSI-RS resource in a CSI-RS resource set where the field repetition may be present. The following three types of CSI-RS transmissions may be supported. One type of CSI-RS transmission may be periodic CSI-RS, according to which CSI-RS may be transmitted periodically in certain slots. This CSI-RS transmission may be semi-statically configured using Radio Resource Control (RRC) signaling with parameters such as CSI-RS resource, periodicity, and slot offset. Another type of CSI-RS transmission may be semi-persistent CSI-RS. Similar to periodic CSI-RS, resources for semi-persistent CSI-RS transmissions may be semi-statically configured using RRC signaling with parameters such as periodicity and slot offset. However, unlike periodic CSI-RS, dynamic signaling may be needed to activate and deactivate the CSI-RS transmission. Yet another type of CSI-RS transmission may be aperiodic CSI-RS. This may be understood to be a one-shot CSI-RS transmission that may happen in any slot. Here, one-shot may be understood to mean that CSI-RS transmission may only happen once per trigger. The CSI-RS resources, e.g., the Resource Element (RE) locations which may consist of subcarrier locations and OFDM symbol locations, for aperiodic CSI-RS may be semi-statically configured. The transmission of aperiodic CSI-RS may be triggered by dynamic signaling through Physical Downlink Control CHannel (PDCCH) using the CSI request field in UL Downlink Control Information (DCI), in the same DCIwhere the UL resources for the measurement report may be scheduled. Multiple aperiodic CSI-RS resources may be included in a CSI-RS resource set and the triggering of aperiodic CSI-RS may be on a resource set basis.

[0031] Synchronization Signal Block (SSB)

[0032] In NR, an SSB may consist of a pair of synchronization signals (SSs), physical broadcast channel (PBCH), and DeModulation Reference Signal (DMRS) for PBCH. An SSB may be mapped to 4 consecutive Orthogonal Frequency Division Multiplexing (OFDM) symbols in the time domain and 240 contiguous subcarriers, 20 Resource Blocks (RBs) in the frequency domain.

[0033] To support beamforming and beam-sweeping for SSB transmission, in NR, a cell may transmit multiple SSBs in different narrow-beams in a time multiplexed fashion. The transmission of these SSBs may be confined to a half frame time interval, 5 ms. It may also be possible to configure a cell to transmit multiple SSBs in a single wide-beam with multiple repetitions. The design of beamforming parameters for each of the SSBs within a half frame may be up to network implementation. The SSBs within a half frame may be broadcasted periodically from each cell. The periodicity of the half frames with Synchronization Signal (SS) / PBCH blocks may be referred to as SSB periodicity, which may be indicated by System Information Block 1 (SIB1).

[0034] The maximum number of SSBs within a half frame, denoted by L, may be understood to depend on the frequency band, and the time locations for these L candidate SSBs within a half frame may be understood to depend on the Subcarrier Spacing (SCS) of the SSBs. The L candidate SSBs within a half frame may be indexed in an ascending order in time from 0 to L-1. By successfully detecting PBCH and its associated DMRS, a UE may know the SSB index. A cell may not necessarily transmit SS / PBCH blocks in all L candidate locations in a half frame, and the resource of the un-used candidate positions may be used for the transmission of data or control signaling instead. It may be up to network implementation to decide which candidate time locations to select for SSB transmission within a half frame, and which beam to use for each SSB transmission.

[0035] Measurement resource configurations

[0036] In NR, a UE may be configured with N>1 CSI reporting settings, e.g., alternatively referred to as CSI-ReportConfig, M>1 resource settings, e.g., alternatively referred to as CSI-ResourceConfig, where each CSI reporting setting may be linked to one or more resource settings for channel and / or interference measurement. The CSI framework may be modular, meaning that several CSI reporting settings may be associated with the same Resource Setting.

[0037] The measurement resource configurations for beam management may be provided to the UE by RRC Information Elements (lEs) CSI-ResourceConfigs. One CSI-ResourceConfig may contain several Non Zero Power (NZP)-CSI-RS-ResourceSets and / or CSI-SSB-ResourceSets.A UE may be configured to perform measurement on CSI-RSs. Here the RRC information element (IE) NZP-CSI-RS-ResourceSet may be used. A NZP CSI-RS resource set may contain the configuration of Ks >1 CSI-RS resources, where the configuration of each CSI-RS resource may include at least: mapping to REs, the number of antenna ports, time-domain behavior, etc. Up to 64 CSI-RS resources may be grouped to an NZP-CSI-RS-ResourceSet. A UE may also be configured to perform measurements on SSBs. Here, the RRC IE CSI-SSB-ResourceSet may be used. Resource sets comprising SSB resources may be defined in a similar manner.

[0038] In the case of aperiodic CSI-RS and / or aperiodic CSI reporting, the network node may configure the UE with ScCSI triggering states. Each triggering state may contain the aperiodic CSI report setting to be triggered along with the associated aperiodic CSI-RS resource sets.

[0039] Periodic and semi-persistent Resource Settings may only comprise a single resource set, e.g., S=1, while S>=1 for aperiodic Resource Settings. This may be understood to be because in the aperiodic case, one out of the S resource sets comprised in the Resource Setting may be indicated by the aperiodic triggering state that may trigger a CSI report.

[0040] The RRC lEs described above may be defined in 3GPP 38.331 v. 18.0.0.

[0041] Measurement Reporting

[0042] Three types of CSI reporting may be supported in NR as follows. One type of CSI-RS reporting may be periodic CSI reporting on Physical Uplink Control Channel (PUCCH), according to which CSI may be reported periodically by a UE. Parameters such as periodicity and slot offset may be configured semi-statically by higher layer RRC signaling from the network node to the UE. Another type of CSI-RS reporting may be semi-persistent CSI reporting on Physical Uplink Shared Channel (PUSCH) or PUCCH. Similar to periodic CSI reporting, semi-persistent CSI reporting may be understood to have a periodicity and slot offset which may be semi-statically configured. However, a dynamic trigger from network node to UE may be needed to allow the UE to begin semi-persistent CSI reporting. A dynamic trigger from network node to UE may be needed to request the UE to stop the semi-persistent CSI reporting. Yet another type of CSI-RS reporting may be aperiodic CSI reporting on PUSCH. This type of CSI reporting may involve a single-shot, that is, one time, CSI report by a UE which may be dynamically triggered by the network node using DCI. Some of the parameters related to the configuration of the aperiodic CSI report may be semi-statically configured by RRC but the triggering may be done dynamically via DCI.

[0043] Machine Learning

[0044] Machine learning (ML) may be understood as the study of computer algorithms that may improve automatically through experience. It is seen as a part of Artificial Intelligence (Al). ML algorithms may build a model based on sample data, known as "training data", in order to make predictions or decisions without being explicitly programmed to do so. ML algorithms may be used in a wide variety of applications, such as email filtering and computer vision, where it maybe difficult or unfeasible to develop conventional algorithms to perform the needed tasks.

[0045] There may be basically three types of ML Algorithms: Supervised Learning, Unsupervised Learning, and Reinforcement Learning (RL).

[0046] Supervised Learning algorithms may comprise a target / outcome variable, or dependent variable, which may have to be predicted from a given set of predictors, that is, independent variables. Using this set of variables, a function may be generated that may map inputs to desired outputs. The training process may continue until the model may achieve a desired level of accuracy on the training data. Once an ML model may have been trained, an inference process may begin, whereby new data may be run through the ML model to calculate an output. Examples of Supervised Learning may be Regression, Decision Tree, Random Forest, KNN, Logistic Regression etc.

[0047] In Unsupervised Learning algorithms, there may be no target or outcome variable to predict / estimate. It may be used for clustering a population into different groups, which may be widely used for segmenting customers in different groups for specific intervention. Examples of Unsupervised Learning may be K-means, mean-shift clustering, Density-Based Spatial Clustering of Applications with Noise (DBSCAN), Expectation-Maximization (EM) Clustering using Gaussian Mixture Models (GMM), Agglomerative Hierarchical Clustering, etc....

[0048] Cluster analysis or clustering may be understood as an ML technique which may comprise grouping a set of objects in such a way that objects in the same group, which may be called a cluster, may be understood to be more similar, in some sense, to each other than to those in other groups, that is, other clusters. It may be understood as a main task of exploratory data mining, and a common technique for statistical data analysis, used in many fields, including pattern recognition, image analysis, information retrieval, bioinformatics, data compression, computer graphics and ML.

[0049] Reinforcement learning (RL) may be understood to be a type of ML where an agent may learn to make decisions by taking actions in an environment to achieve some goal. The agent may receive feedback in the form of rewards, which it may use to learn the best strategy, or policy, to accumulate the most reward over time.

[0050] Reinforcement learning may involve the following. An agent may be understood to be a learner or decision maker that may interact with the environment. The environment may be understood to refer to the world that the agent may interact with and learn from. A state (s) may be understood to refer to a representation of the current situation that the agent may be in. It may be understood to be the context within which the agent may make decisions. An action (a) may be understood to refer to a choice made by the agent that may affect the state. A reward (r) : may be understood to refer to feedback from the environment in response to the actions taken by the agent. It may be a scalar signal that may indicate how well the agent is doing at a given moment. A Policy may be understood to be a strategy used by the agent,which may map states to actions. The policy may be deterministic, that is, always the same action for a given state, or stochastic, that is, probabilistic actions for a given state. A value function may be understood to refer to a function that may estimate how good it may be for the agent to be in a given state, or how good it may be to perform a certain action in a given state. The "goodness" may be typically measured as the expected return, e.g., the cumulative reward, that may be achieved. A Q-function, an Action-Value Function, may be understood to refer to a function that may estimate the value of taking a certain action in a given state, and then following the current policy thereafter. A model of the environment may be understood to refer to the fact that some RL approaches may involve learning a model that may predict the next state (s’) and the reward for the current state and action. This may be understood to allow for planning and reasoning about the future without needing to actually take the action.

[0051] RL may involve making decisions in regard to exploration vs. exploitation. In reinforcement learning, the agent may need to balance exploration, that is, trying new things to discover better rewards, with exploitation, that is, using known information to maximize rewards. This may be understood to be a trade-off in RL.

[0052] In the reinforcement learning problem, the state may change every time the agent may apply a new action. The problem may be represented in the following way: The agent may receive the state of the environment at a certain time (s). Then the agent may select on action (a) and apply it in the environment. When this action is applied, the environment may provide a reward (r) and change to a new state (s’), the reward and state may be provided finally by an interpreter. In reinforcement learning, the term "interpreter" may be used to describe a component of a reinforcement learning system that may interpret the state of the environment and the actions of an agent. It may be understood to be the part of the system that may bridge the agent with the environment it may be trying to learn from.

[0053] This cyclic procedure may be understood to bring a sequence of states, actions and rewards: s1, a1,r1;...;sT,aT,rT. The agent may use different learning algorithms to learn the most appropriate action to take on every different state of the NW, e.g., policy-learning based, such as actor-critic approaches, or value-based learning, such as deep-q networks.

[0054] Rel-18 / Rel-19 AI / ML for CSI feedback enhancements

[0055] Artificial Intelligence (Al) and Machine Learning (ML) have been investigated, both in academia and industry, as promising tools to optimize the design of the air-interface in wireless communication networks. Example use cases may include using autoencoders for Channel State Information (CSI) compression to reduce the feedback overhead and improve channel prediction accuracy; using deep neural networks for classifying Line-of-Sight (LOS) and Non-LOS (NLOS) conditions to enhance the positioning accuracy; using reinforcement learning for beam selection at the network side and / or the User Equipment (UE) side to reduce the signaling overhead andbeam alignment latency; and using deep reinforcement learning to learn an optimal precoding policy for complex Multiple Input Multiple Output (MIMO) precoding problems.

[0056] In 3rd Generation Partnership Project (3GPP) New Radio (NR) standardization work, a release 18 study item on AI / ML for the NR air interface started in May 2022 and completed in December 2023. This study item explored the benefits of augmenting the air-interface with features enabling improved support of AI / ML based algorithms for enhanced performance and / or reduced complexity and / or overhead. Through studying a few selected use cases, CSI feedback, beam management, and positioning, this study item may be understood to aim at laying the foundation for future air-interface use cases leveraging AI / ML techniques.

[0057] Terminologies such as AI / ML model, AI / ML model inference, which may be henceforth referred to as inference, AI / ML model training, which may be henceforth referred to as training, data collection, and model monitoring may be as defined in Section 3.1 of 3GPP TR38.843 v.

[0058] 18.0.0.

[0059] Two Al CSI use cases, that is, CSI prediction and CSI compression, were studied in 3GPP Rel-18. After continued study in Rel-19, the CSI prediction use case may start its normative work since the beginning of 2025, while the CSI compression use case may be under continue study in for the whole release of 3GPP Rel-19.

[0060] The CSI prediction use case using one or more one-sided UE-sided models, where the model inference may be performed entirely at the UE. One or more AI / ML models may be trained and deployed at a UE for the Al-based CSI-prediction feature. During model inference, a UE may be configured by the gNB to measure a set of historical CSI-RSs and then report a predicted CSI for one or multiple future time instances using its AI / ML model(s). Figure 3 provides a non-limiting example for the inference procedure for CSI prediction. For generating the input of CSI prediction model, it may need some further pre-processing on the measured channel; for the output of the CSI prediction model, some further post-processing may also be applied.

[0061] Figure 3 is a schematic diagram illustrating a non-limiting example of the CSI prediction using UE-sided Al model(s).

[0062] The CSI compressing use case using one or more two-sided AI / ML models. A two-sided AI / ML model may be understood to refer to a paired AI / ML Model(s) over which joint inference may be performed across the UE and the network (NW), e.g., the first part of the inference may be firstly performed by UE and then the remaining part may be performed by gNB, or vice versa. As an example, Figure 4 shows a non-limiting example of the autoencoder (AE)-based CSI compression, where an encoder, a UE-part of the two-sided AE model, may be operated at a UE to compress the estimated wireless channel, and the output of the encoder, the compressed wireless channel information estimates, may be reported from the UE to a gNB. The gNB may use a decoder, the NW-part of the two-sided AE model, to reconstruct the estimated wireless channel information. Here, the two-sided AI / ML model may be composed of the encoder at theUE side and the decoder at the base station, e.g., a gNB, side. Note that in the case of a two-sided model, the code may be generated by the encoder and only interpretable by a jointly trained decoder. The situation may be understood to be different from running an AI / ML model in the UE, reporting the output over the air in a fully standardized format, and running a separate AI / ML model at the base station.

[0063] Figure 4 is a schematic diagram illustrating a non-limiting example of an autoencoder (AE)-based CSI compression using two-sided AI / ML model use case.

[0064] CSI-RS resource indicator (CRI) based CSI reporting

[0065] When multiple CSI-RS resources are configured for channel measurement in a CSI report configuration in NR up to Release-18 for CSI feedback, one of the CSI-RS resources may be first selected by the UE and CSI associated to the selected CSI-RS resource may be computed and reported. In this case, a CRI may be also reported to indicate the selected CSI-RS resource.

[0066] One use case of such CSI reporting may be to support hybrid analog and digital beamforming due to hardware restrictions. For example, analog beam may be implemented for elevation beamforming where multiple analog beams, one at a time, may be formed in elevation domain while within each of the analog beams, digital beamforming may be performed in the azimuth direction. Another use case may be to support hybrid time-domain and frequency-domain digital beamforming. For example, different elevation beams may be formed in digital time-domain, one in each time instance. For each such elevation beam, frequency-domain digital beamforming may be performed in the azimuth direction.

[0067] An example is shown in Figure 5, where four analog beams are formed in the elevation dimension: Beam #1, Beam #2, Beam #3 and Beam #4, each represented with different line patterns. Figure 5 is a schematic diagram illustrating a non-limiting example of CSI report for hybrid beamforming with multiple Non-Zero Power (NZP) CSI-RS resources, one NZP CSI-RS resource per beam. The four beams may be transmitted at different time instances. Each of the analog beams may be associated to a NZP CSI-RS resource, NZP CSI-RS #1, NZP CSI-RS #2, NZP CSI-RS #3 and NZP CSI-RS #4, comprising eight beamformed CSI-RS antenna ports in NR up to Release-18. In this case, a UE may measure downlink channels based on the four NZP CSI-RS resources and may determine a best beam among the four beams. The CSI feedback may comprise a CRI indicating the selected beam or the associated NZP CSI-RS resource, Rl, PMI and one or two CQIs associated with the NZP CSI-RS resource. The PMI may indicate a precoding matrix for the beamformed antenna ports.

[0068] In NR up to Release 18, two, four or eight NZP CSI-RS resources may be configured for the purpose and up to eight CSI-RS ports per NZP CSI-RS resource may be configured. In addition, the total number of NZP CSI-RS antenna ports across all the configured NZP CSI-RS resources may not exceed 32.CRI based CSI reporting for more than 32 ports in Release-19

[0069] In Rel-19, to support CRI based CSI reporting in increasingly large gNB antenna arrays, it was agreed to extend the existing framework CRI(s)-based CSI reporting for hybrid beamforming. Release 19 may support up to a total of 128 CSI-RS ports across all resources in a CSI-RS resource set.

[0070] In the Release 19 CRI-based reporting framework, a UE may be configured to measure Ks> 1 NZP CSI-RS resources with equal number of ports, with up to 32 ports per NZP CSI-RS resource. The supported combinations of Ksvalue and the maximum number of ports per NZP CSI-RS resource may be as follows shown in Table 4.

[0071] Table 4. Supported combinations of Ksand maximum number of ports per NZP CSI-RS resource.

[0072]

[0073] The CRI-based report may contain the information of M “quadruplets” (CRIn, Rin, PMIn, CQIn), where n = 0, ...,M - 1 and where a legacy codebook, e.g., with up to 32 ports, may be configured for all M “quadruplets”. The supported codebooks may be Rel-15 Type-1 single panel codebook, as defined in Clause 5.2.2.2.1 of 3GPP TS 38.214 v.18.4.0, and Rel-16 eType-ll codebook, as defined in Clause 5.2.2.2.5 of 3GPP TS 38.214, v.18.4.0.

[0074] M may be understood to be a network-configured parameter via higher-layer RRC signaling. For Rel-15 Type-I single panel codebook, M candidate values may be between 1 and min(4, / C;). For Rel-16 eType-ll codebook, only M = {1,2} may be supported. Further, when M > 1, PMI, Rl and CQI may be independently signalled per CRI.

[0075] SUMMARY

[0076] It is an object of embodiments herein to improve the handling of information pertaining to Reference Signals (RSs).

[0077] According to a first aspect of embodiments herein, the object is achieved by a computer-implemented method, performed by a first device. The method is for handling information pertaining to Reference Signals (RSs). The first device operates in a communications system. The first device obtains a first indication and a second indication. The first indication indicates a first set of frequency resources out of one or more frequency resources configured for reception of downlink (DL) RSs. The second indication indicates a second set of frequency resources out of the one or more frequency resources. The first device also obtains a third indication. The third indication indicates a correspondence between the first set of frequency resources and thesecond set of frequency resources. The first device then performs on the DL RSs, as transmitted by the first network node operating in a communications system, one or more first measurements on the first set of frequency resources, and one or more second measurements on the second set of frequency resources.

[0078] According to a second aspect of embodiments herein, the object is achieved by a computer-implemented method, performed by a second device. The method is for handling the information pertaining to RSs. The second device operates in the communications system. The second device obtains a first first indication and a first second indication. The first first indication indicates a first first set of frequency resources out of one or more first frequency resources configured for reception of downlink (DL) RSs. The first second indication indicates a first second set of frequency resources out of the one or more first frequency resources. The first first set of frequency resources is larger than the first second set of frequency resources. The second device obtains one or more first second measurements on the first second set of frequency resources on the DL RSs, as transmitted by the first network node operating in the communications system. The second device then predicts CSI of a first channel between the second device and the first network node using first first information. The first first information indicates the one or more first second measurements as input to the trained MLM. The prediction is for the first first set of frequency resources. The prediction is based on the respective one or more first second measurements on the first second set of frequency resources.

[0079] According to a third aspect of embodiments herein, the object is achieved by a computer-implemented method, performed by the first network node. The method is for handling the information pertaining to RSs. The first network node operates in a communications system. The first network node provides the first first indication and the first second indication. The first first indication indicates the first first set of frequency resources out of the one or more first frequency resources configured for reception of DL RSs, at the second device operating in the communications system. The first second indication indicates the first second set of frequency resources out of the one or more first frequency resources. The first first set of frequency resources is larger than the first second set of frequency resources. The first network node transmits the DL RSs on the first second set of frequency resources to the second device.

[0080] According to a fourth aspect of embodiments herein, the object is achieved by a computer-implemented method, performed by the second network node. The method is for handling handling the information pertaining to RSs. The second network node operates in the communications system. The second network node obtains first information. The first information indicates: i) the one or more first measurements on the DL RSs transmitted by the first network node operating in the communications system, on the first set of frequency resources out of the one or more frequency resources configured for reception of the DL RSs,at the first device, ii) the one or more second measurements of the DL RSs, on the second set of frequency resources, out of the one or more frequency resources, wherein the first set of frequency resources is larger than the second set of frequency resources, and iii) the correspondence between the first set of frequency resources and the second set of frequency resources.

[0081] According to a fifth aspect of embodiments herein, the object is achieved by the first device. The first device is for handling the information pertaining to RSs. The first device is configured to operate in the communications system. The first device is configured to obtain the first indication configured to indicate the first set of frequency resources out of the one or more frequency resources configured for reception of DL RSs, the second indication configured to indicate the second set of frequency resources out of the one or more frequency resources, and the third indication configured to indicate the a correspondence between the first set of frequency resources and the second set of frequency resources. The first set of frequency resources is configured to be larger than the second set of frequency resources. The first device is also configured to perform, on the DL RSs, as configured to be transmitted by the first network node configured to operate in the communications system, the one or more first measurements on the first set of frequency resources, and the one or more second measurements on the second set of frequency resources.

[0082] According to a sixth aspect of embodiments herein, the object is achieved by the second device. The second device is for handling the information pertaining to RSs. The second device is configured to operate in the communications system. The second device is configured to obtain the first first configuration of the first set of one or more UL RSs. The second device is configured to obtain the first first indication configured to indicate the first first set of frequency resources out of the one or more first frequency resources configured for reception of DL RSs, and the first second indication configured to indicate the first second set of frequency resources out of the one or more first frequency resources. The second device is also configured to obtain the one or more first second measurements on the first second set of frequency resources on the DL RSs, as configured to be transmitted by the first network node configured to operate in the communications system. The first first set of frequency resources is configured to be larger than the first second set of frequency resources. The second device is configured to predict, using the first first information configured to indicate the one or more first second measurements as input to the trained MLM, CSI of the first channel between the second device and the first network node. The prediction is configured to be for the first first set of frequency resources, and based on the respective one or more first second measurements on the first second set of frequency resources.

[0083] According to a seventh aspect of embodiments herein, the object is achieved by the first network node. The first network node is for handling the information pertaining to RSs. The firstnetwork node is configured to operate in the communications system. The first network node is configured to provide the first first indication configured to indicate the first first set of frequency resources out of the one or more first frequency resources configured for reception of DL RSs, at the second device configured to operate in the communications system, and the first second indication configured to indicate the first second set of frequency resources out of the one or more first frequency resources. The first first set of frequency resources is configured to be larger than the first second set of frequency resources. The first network node is also configured to transmit the DL RSs on the first second set of frequency resources to the second device.

[0084] According to an eighth aspect of embodiments herein, the object is achieved by the second network node. The second network node is for handling the information pertaining to the RSs. The second network node is configured to operate in the communications system. The second network node is configured to obtain the first information from the first device configured to indicate: i) the one or more first measurements on DL RSs configured to be transmitted by the first network node configured to operate in a communications system, on the first set of frequency resources out of the one or more frequency resources configured for reception of the DL RSs, at the first device, ii) the one or more second measurements of the DL RSs, on the second set of frequency resources, out of the one or more frequency resources, wherein the first set of frequency resources is configured to be larger than the second set of frequency resources, and iii) the correspondence between the first set of frequency resources and the second set of frequency resources.

[0085] By obtaining the first indication indicating the first set of frequency resources out of the one or more frequency resources configured for reception of DL RSs, the second indication indicating the second set of frequency resources out of the one or more frequency resources, and the third indication indicating the correspondence between the first set of frequency resources and the second set of frequency resources, and then performing the one or more first measurements and one or more second measurements, the first device may be enabled itself or enable another network node, e.g., the second network node, to obtain data to train the MLM. The MLM may be trained to predict the CSI, e.g., between a device such as the first device or the second device, and the first network node. The prediction may be configured to be for the first set of frequency resources, and based on the one or more second measurements on the second set of frequency resources. By the second set of frequency resources being smaller than the first set of frequency resources, the MLM may be trained to predict CSI assuming only a subset of the bandwidth of DL RS resources may be transmitted by the first network node. This may in turn enable the second device, during the inference phase, to only obtain measurements on the one or more first second measurements on the first second set of frequency resources on the DL RSs, which may in turn be smaller than the first first set offrequency resources. An advantage of embodiments herein may be understood to be that CSI-RS overhead may be reduced for large arrays at the first network node, both for fully digital and hybrid beamforming architectures, which may increase spectral efficiency in the system, since saved time and / or frequency resource may be used for data.

[0086] BRIEF DESCRIPTION OF THE DRAWINGS

[0087] Examples of embodiments herein are described in more detail with reference to the accompanying drawings, according to the following description.

[0088] Figure 1 is a schematic diagram illustrating a non-limiting example of data transmission with spatial multiplexing, according to existing methods.

[0089] Figure 2 is a schematic diagram illustrating a non-limiting example of a two-dimensional antenna array of cross-polarized antenna elements, according to existing methods.

[0090] Figure 3 is a schematic diagram illustrating a non-limiting example of the CSI prediction using UE-sided Al model(s), according to existing methods.

[0091] Figure 4 is a schematic diagram showing a non-limiting example of autoencoder (AE)-based CSI compression, using two-sided AI / ML model, according to existing methods.

[0092] Figure 5 is a schematic diagram illustrating a non-limiting example of CSI report for hybrid beamforming with multiple NZP CSI-RS resources, one NZP CSI-RS resource per beam, according to existing methods.

[0093] Figure 6 is a schematic diagram depicting an example of a communications system, according to embodiments herein.

[0094] Figure 7 is a flowchart depicting a method in a first device, according to embodiments herein. Figure 8 is a flowchart depicting a method in a second device, according to embodiments herein.

[0095] Figure 9 is a flowchart depicting a method in a first network node, according to embodiments herein.

[0096] Figure 10 is a flowchart depicting a method in a second network node, according to embodiments herein.

[0097] Figure 11 is a flowchart depicting a non-limiting example of methods according to embodiments herein.

[0098] Figure 12 is a flowchart depicting another non-limiting example of methods according to embodiments herein.

[0099] Figure 13 is a schematic block diagram illustrating an embodiment of a first device, according to embodiments herein.

[0100] Figure 14 is a schematic block diagram illustrating an embodiment of a second device,

[0101] according to embodiments herein.Figure 15 is a schematic block diagram illustrating an embodiment of a first network node, according to embodiments herein.

[0102] Figure 16 is a schematic block diagram illustrating an embodiment of a second network node, according to embodiments herein.

[0103] Figure 17 is a flowchart depicting a method in a first device, according to embodiments herein. Figure 18 is a flowchart depicting a method in a second device, according to embodiments herein.

[0104] Figure 19 is a flowchart depicting a method in a first network node, according to embodiments herein.

[0105] Figure 20 is a flowchart depicting a method in a second network node, according to embodiments herein.

[0106] Figure 21 is a schematic block diagram illustrating an example of a communication system 2100 in accordance with some embodiments.

[0107] Figure 22 is a schematic block diagram illustrating another example of a communication system 2200 according to some embodiments.

[0108] Figure 23 is a schematic block diagram illustrating an example of a wireless device 2300, which may be configured to operate in communication system 2100 of Figure 21 or in communication system 2200 of Figure 22.

[0109] Figure 24 is a schematic block diagram illustrating an example of a network node 2400 in accordance with some embodiments.

[0110] Figure 25 is a schematic block diagram illustrating an example of a virtualization environment 2500 in which functions implemented by some embodiments may be virtualized.

[0111] DETAILED DESCRIPTION

[0112] As part of the development of embodiments herein, one or more challenges with the existing technology will first be identified and discussed.

[0113] CSI-RS overhead is becoming a problem due to larger Transmission Reception Points (TRPs) arrays, especially in the new frequency bands above 6 GHz, due to the system capacity loss when providing CSI-RS resources to handle an increased number of CSI-RS ports.

[0114] For DL CSI acquisition based on UE CSI report, the NW may need to transmit CSI-RS for the UE to measure. To capture the frequency-selectivity of channel, CSI-RS may be transmitted over a sufficiently large bandwidth with enough frequency domain density. Hence, CSI-RS overhead may increase and become a limiting factor for throughput, especially for transmission over large bandwidth and frequency-selective channels.

[0115] How to obtain accuracy CSI for large bandwidth and / or frequency selective channels with limited CSI-RS overhead is a problem.Certain aspects of the present disclosure and their embodiments may provide solutions to these or other challenges. Examples of embodiments herein may relate to data collection for UE-sided CSI prediction for sparse frequency domain CSI.

[0116] Signaling and configuration methods are described herein that may enable data collection for UE-sided frequency domain CSI prediction, wherein the prediction model / algorithm may predict CSI for a full bandwidth consisting of a set A of frequency resources, based on measurements over one or more CSI-RS(s) transmitted on a Set B of frequency resources. Set B may be a subset of Set A, which may be expected to be the most typical use case, or Set B may be different from Set A.

[0117] For training data collection, the UE may need to collect the following measurements. For creating model input samples: channel measurements associated to the one or more CSI-RS(s) transmitted on Set B of frequency resources. For creating the corresponding labels for model output: channel measurements associated to the one or more CSI-RS(s) transmitted on the full bandwidth consisting of set A of frequency resources.

[0118] A UE may receive from a network node a CSI-RS configuration, which may indicate the one or more CSI-RS resources and at least the Set A of frequency resources for the configured one or more CSI-RS resources. Then, the UE may obtain measurements over the set B of frequency resources of the one or more CSI-RS(s) transmitted from the network node to create the model input sample(s), and the UE may obtain measurements over the set A of frequency resources, the full bandwidth, of the one or more CSI-RS(s) transmitted from the network node to create the label(s) for the associated model output.

[0119] The UE may obtain the association between the Set A and Set B of frequency resources for the one or more CSI-RS resources either by itself, e.g., based on its own model design, or via indication signalled from the network node.

[0120] Some of the embodiments contemplated will now be described more fully hereinafter with reference to the accompanying drawings, in which examples are shown. In this section, the embodiments herein will be illustrated in more detail by a number of exemplary embodiments. Other embodiments, however, are contained within the scope of the subject matter disclosed herein. The disclosed subject matter should not be construed as limited to only the embodiments set forth herein; rather, these embodiments are provided by way of example to convey the scope of the subject matter to those skilled in the art. It should be noted that the exemplary embodiments herein are not mutually exclusive. Components from one embodiment may be tacitly assumed to be present in another embodiment and it will be obvious to a person skilled in the art how those components may be used in the other exemplary embodiments.

[0121] Figure 6 depicts two non-limiting examples, in panel a) and panel b), respectively, of a communications system 100, e.g., a wireless network or wireless communications network, sometimes also referred to as a wireless communications system, cellular radio system, orcellular network, in which embodiments herein may be implemented. The communications system 100 may be a 5G system, 5G network, or Next Gen System. In other examples, the communications system 100 may be a newer system with similar functionality, e.g., a 6G network. In other examples, the communications system 100 may, e.g., additionally, support other technologies such as, for example, Long-Term Evolution (LTE), e.g., LTE for Machines (LTE-M), LTE Frequency Division Duplex (FDD), LTE Time Division Duplex (TDD), LTE HalfDuplex Frequency Division Duplex (HD-FDD), LTE operating in an unlicensed band, such as LTE Licensed-Assisted Access (LAA), enhanced eLAA (eLAA), further enhanced LAA (feLAA) and / or MulteFire. Yet in other examples, the communications system 100 may further support other technologies such as, for example Wideband Code Division Multiple Access (WCDMA), Universal Terrestrial Radio Access (UTRA) TDD, Global System for Mobile communications (GSM) network, GSM / Enhanced Data Rates for GSM Evolution (EDGE) Radio Access Network (GERAN) network, Ultra-Mobile Broadband (UMB), EDGE network, network comprising any combination of Radio Access Technologies (RATs) such as e.g. Multi-Standard Radio (MSR) base stations, multi-RAT base stations etc., any 6rd Generation Partnership Project (3GPP) cellular network, WiFi networks, Worldwide Interoperability for Microwave Access (WiMax), or any cellular network or system. The communications system 100 may support Machine Type Communication (MTC), enhanced MTC (eMTC), Internet of Things (loT) and / or NarrowBand loT (NB-loT). Thus, although terminology from 5G / NR and LTE may be used in this disclosure to exemplify embodiments herein, this should not be seen as limiting the scope of the embodiments herein to only the aforementioned system.

[0122] The communications system 100 may comprise a first network node 111 as depicted in the non-limiting examples of Figure 6. In some embodiments, the communications system 100 may comprise a second network node 112. In other embodiments, the communications system 100 may comprise a third network node 113. Any of the first network node 111 , the second network node 112 and the third network node 113 may be a radio network node, radio access node or RAN node. That is, a transmission point such as a radio base station, for example a gNB, or any other network node with similar features capable of serving a user equipment, such as a wireless device or a machine type communication device, in the communications system 100. In some examples, any of the first network node 111, the second network node 112 and the third network node 113 may be a distributed node, and may partially perform its functions in collaboration with a virtual node in a cloud 115. Any of the first network node 111, the second network node 112 and the third network node 113 may be directly connected to one or more core networks, e.g., to one or more network nodes in the one or more core networks. Any of the first network node 111 , the second network node 112 and the third network node 113 may be of different classes, such as, e.g., macro base station, home base station or pico base station, based on transmission power and thereby also cell size. In someexamples, any of the first network node 111 , the second network node 112 and the third network node 113 may serve receiving nodes with serving beams. In the non-limiting example of Figure 6, any of the first network node 111 and the second network node 112 may serve one or more beams 121, 122, 123, depicted in Figure 6 as a first beam 121, a second beam 122, and a third beam 123. It may be understood that this is for illustration purposes and nonlimiting. Any of the first network node 111 , the second network node 112 and the third network node 113 may may serve more or fewer beams than those depicted in Figure 6. Instead of, or additionally to, beams, any of the first network node 111 , the second network node 112 and the third network node 113 may serve one or more cells. Any of the first beam 121, the second beam 122, and the third beam 123 may be associated to cells on different frequencies and the coverage of each of these cells may differ due to the propagation limitation and / or beamforming capability limitation etc. The respective area of radio coverage of each of the first beam 121 , the second beam 122, and the third beam 123 may correspond to a respective cell. In other examples, more than one beam may correspond to a cell.

[0123] In some examples, the second network node 112 may be a core network node, e.g., an Operations, Administration, and Maintenance (OAM) or a server. In some examples, as depicted in panel b) of Figure 6, the second network node 112 may be a network node in the cloud 115.

[0124] Any of the first network node 111 and the second network node 112 may be the same node or be co-localized. In some examples, as depicted in the non-limiting example of panel a) of Figure 6, the first network node 111 and the second network node 112 may be the same network node. In some examples, as depicted in the non-limiting example of panel b) of Figure 6, the first network node 111 , the second network node 112 and the third network node 113 may be different network nodes.

[0125] The communications system 100 may cover a geographical area, which in some embodiments may be divided into cell areas, wherein each cell area may be served by a radio network node, although, one radio network node may serve one or several cells.

[0126] In some examples, the communications system 100 may include an access network, such as a radio access network (RAN), and a core network, which may include one or more core network nodes. The access network may include one or more access network nodes, such as any of the first network node 111 , the second network node 112, the third network node 113, e.g., which may be generally referred to as network nodes, or any other similar 3rd Generation Partnership Project (3GPP) access nodes or non-3GPP access points. Moreover, as will be appreciated by those of skill in the art, a network node may not necessarily be limited to an implementation in which a radio portion and a baseband portion are supplied and integrated by a single vendor. Thus, it may be understood that network nodes may include disaggregated implementations or portions thereof. For example, in some embodiments, the communicationssystem 100 may include one or more Open-RAN (ORAN) network nodes. Any of the first network node 111 , the second network node 112, and the third network node 113 may be ORAN network nodes. An ORAN network node may be understood to be a node in the communications system 100 that may support an ORAN specification, e.g., a specification published by the O-RAN Alliance, or any similar organization, and may operate alone or together with other nodes to implement one or more functionalities of any node in the communications system 100, including one or more network nodes and / or core network nodes.

[0127] Examples of an ORAN network node may include an open radio unit (0-Rll), an open distributed unit (0-Dll), an open central unit (O-CU), including an O-CU control plane (O-CU-CP) or an O-CU user plane (O-CU-UP), a RAN intelligent controller, near-real time or non-real time, hosting software or software plug-ins, such as a near-real time control application, e.g., xApp, or a non-real time control application, e.g., rApp, or any combination thereof, the adjective “open” designating support of an ORAN specification. Any of the first network node 111 , the second network node 112, and the third network node 113 may support a specification by, for example, supporting an interface defined by the ORAN specification, such as an A1, F1, W1, E1, E2, X2, Xn interface, an open fronthaul user plane interface, or an open fronthaul management plane interface. Moreover, an ORAN access node may be a logical node in a physical node. Furthermore, an ORAN network node may be implemented in a virtualization environment, in which one or more network functions may be virtualized. For example, the virtualization environment may include an O-Cloud computing platform orchestrated by a Service Management and Orchestration Framework via an O-2 interface defined by the O-RAN Alliance or comparable technologies.

[0128] O-RAN may specify intent Application Programming Interfaces (APIs) toward the Service Management and Orchestration (SMO).

[0129] A plurality of devices may be located in the communication system 100, whereof a first device 131 is depicted in the non-limiting example of Figure 6. In some embodiments, as depicted in the non-limiting examples of Figure 6, the communications system 100 may comprise second device 132. Any of the first device 131 and the second device 132 may be a wireless communication device such as a UE, a 5G UE or nUE, which may also be known as e.g., mobile terminal, wireless terminal and / or mobile station, a mobile telephone, cellular telephone, or laptop with wireless capability, just to mention some further examples. Any of the first device 131 and the second device 132 may be, for example, portable, pocket-storable, hand-held, computer-comprised, or a vehicle-mounted mobile device, enabled to communicate voice and / or data, via the RAN, with another entity, such as a server, a laptop, a Personal Digital Assistant (PDA), or a tablet, Machine-to-Machine (M2M) device, a sensor, loT device, NB-loT device, device equipped with a wireless interface, such as a printer or a file storage device, modem, or any other radio network unit capable of communicating over a radio link in acommunications system. Any of the first device 131 and the second device 132 comprised in the communications system 100 may be enabled to communicate wirelessly in the communications system 100. The communication may be performed e.g., via a RAN, and possibly the one or more core networks, which may be comprised within the communications system 100. The first device 131 and the second device 132 may be the same device in some examples, as depicted in the non-limiting example of Figure 6. However, in other examples, the first device 131 may be a different device than the second device 132.

[0130] The first device 131 may be configured to communicate within the wireless communications network 100 with the first network node 111 over a first link, e.g., a radio link, via any of the one or more beams 121, 122, 123, or one or more cells. The first device 131 may be configured to communicate within the wireless communications network 100 with the second network node 112 over a second link 142, e.g., a radio link or a wired link. The second device 132 may be configured to communicate within the wireless communications network 100 with the second network node 112 over a third link 143, e.g., a radio link or a wired link. The first device 131 may be configured to communicate within the wireless communications network 100 with the third network node 113 over a fourth link 144, e.g., a radio link. The first network node 111 may be configured to communicate within the communications system 100 with the second network node 112 over a fifth link 145, e.g., a radio link or a wired link. All possible communication links are not depicted in Figure 6 to avoid overcrowding the figure.

[0131] Generally, all terms used herein are to be interpreted according to their ordinary meaning in the relevant technical field, unless a different meaning is clearly given and / or is implied from the context in which it is used. All references to a / an / the element, apparatus, component, means, step, etc. are to be interpreted openly as referring to at least one instance of the element, apparatus, component, means, step, etc., unless explicitly stated otherwise. The steps of any methods disclosed herein do not have to be performed in the exact order disclosed, unless a step is explicitly described as following or preceding another step and / or where it is implicit that a step must follow or precede another step. Any feature of any of the embodiments disclosed herein may be applied to any other embodiment, wherever appropriate. Likewise, any advantage of any of the embodiments may apply to any other embodiments, and vice versa. Other objectives, features and advantages of the enclosed embodiments will be apparent from the following description.

[0132] In general, the usage of “first”, “second”, “third”, ..., and / or “eighth” herein may be understood to be an arbitrary way to denote different elements or entities, and may be understood to not confer a cumulative or chronological character to the nouns they modify, unless otherwise noted, based on context.

[0133] Several embodiments are comprised herein. It should be noted that the examples herein are not mutually exclusive. Components from one embodiment may be tacitly assumed to bepresent in another embodiment and it will be obvious to a person skilled in the art how those components may be used in the other exemplary embodiments.

[0134] More specifically, the following are embodiments related to a device, such as the first device 131, e.g., a first UE, a second device, such as the second device 132, e.g, a second UE, a first network node, such as the first network node 111, e.g., a first gNB, and a second network node, such as the second network node 112, e.g., a second gNB or a core network node.

[0135] In the following description CSI-RS is taken an illustrative example. CSI-RS may be replaced in the following description by a / the “first reference signal” or a / the “first RS”.

[0136] Embodiments of a computer-implemented method, performed by a device, such as the first device 131 , will now be described with reference to the flowchart depicted in Figure 7. The method is for handling information pertaining to Reference Signals (RSs). The first device 131 operates in a communications system, such as the communications system 100.

[0137] In some examples, the method may be for training data collection for a UE-sided AI / ML based frequency domain CSI prediction.

[0138] In some embodiments, the communications system 100 may support New Radio (NR). Several embodiments are comprised herein. The method may comprise one or more of the following actions. In some embodiments, all the actions may be performed. In some examples, Action 704 and Action 705 may be performed. In some examples, Action 704, Action 705 and Action 706 may be performed. In some embodiments, the method may further comprise one or more of the actions 701, 702 and 703. One or more embodiments may be combined, where applicable. It should be noted that the examples herein are not mutually exclusive. One or more embodiments may be combined, where applicable. Components from one embodiment may be tacitly assumed to be present in another embodiment and it will be obvious to a person skilled in the art how those components may be used in the other exemplary embodiments. All possible combinations are not described to simplify the description. A non-limiting example of the method performed by the first device 131 is depicted in Figure 7. In Figure 7, optional actions in some embodiments may be represented with dashed lines. In some embodiments, the actions may be performed in a different order than that depicted Figure 7.

[0139] Action 701

[0140] In this Action 701, the first device 131 may provide an indication, referred to herein as a previous indication.

[0141] The providing in this Action 701 may be to the first network node 111. The previous indication may indicate a capability for the performance of measurements on DL RSs. The RSs may be CSI-RSs.Examples of embodiments herein may be understood to consider UE-sided frequency domain CSI prediction use cases, wherein a prediction model / algorithm may be used to predict CSI for a full bandwidth that may consist of a set A of frequency resources, based on measurements over one or more CSI-RS(s) transmitted on a Set B of frequency resources. In some examples, Set B may be a subsetof Set A. In some other examples, Set B may be different from Set A. In another example, Set A may be a larger set of frequency resources that may partially overlap with Set B which may contain a smaller set of frequency resources.

[0142] The predictions model may be a machine learning model (MLM). The MLM may be to predict CSI of a channel between the first device 131 and the first network node 111.

[0143] In some examples, the number of supported REs in the Set B of frequency resources and / or the Set A of frequency resources may be signaled by the first device 131 to the network node 111 as part of UE capability signaling in this Action 701.

[0144] Action 702

[0145] In this Action 702, the first device 131 may obtain one or more configurations.

[0146] The obtaining in this Action 702 may be from the first network node 111.

[0147] The one or more configurations may be of one or more frequency resources for reception of the DL RSs. In some examples, this Action 702 may comprise receiving from the first network node 111 , a CSI-RS configuration consisting of one or more CSI-RS resources.

[0148] The obtaining in this Action 702 of the one or more configurations may be based on the provided previous indication.

[0149] In particular examples, in this Action 702, the first device 131 may receive configuration from the first network node 111 , a base station (BS), of one or more CSI-RS resource(s) for training an AI / ML model for CSI prediction over frequency domain.

[0150] In an example, the first device 131 may receive configuration of one or more CSI-RS resource(s) for channel measurement for data collection.

[0151] Action 703

[0152] The first device 131 may be a device that may collect data to use as input to the MLM during a training phase of the MLM. That is, the MLM to predict CSI of a channel between the first device 131 and the first network node 111. In some examples, the first device 131 may train the MLM itself.

[0153] In this Action 703, the first device 131 may obtain second information.

[0154] The obtaining in this Action 703 may be from the first network node 111.

[0155] The second information may be to assist the first device 131 in training the MLM.

[0156] The training of the MLM may be performed based on the obtained second information.The second information may be assistance configuration associated with the training of the UE-sided AI / ML based frequency domain CSI prediction. In one example, the first device 131 may receive assistance configuration associated with the training, and / or during inference, of the UE-sided AI / ML based frequency domain CSI prediction.

[0157] The second information, e.g., the assistance configuration, may comprise one or more of the following.

[0158] According to an option, the second information may comprise one or more codebooks the second device 132 may have to assume during an inference phase of the MLM or a respective MLM. That is, its own MLM, if trained by the first device 131. In one example, the first device 131 may receive configuration from the first network node 111 of one or more non-AI / ML codebook schemes to be applied across one or more CSI-RS resource(s), and which the first device 131 may have to assume when training the AI / ML model, for example a legacy NR Type I codebook, or legacy NR Type II codebook, or similar new codebooks in 6G. In a particular example, the first device 131 may receive one or more codebooks the second device 132 may have to assume during inference, and hence train the related AI / ML model for.

[0159] According to another option, the second information may comprise another indication, referred to herein as a fifth indication, of one or more configurations of a report of the DL RSs that the second device 132 may have to assume during the inference phase, selected from: subbands the second device 132 may have to report CSI for, subband size of the report, subband Precoder Matrix Indicator (PMI) reporting, subband Channel Quality Information (CQI) reporting, wideband PMI reporting, and wideband CQI reporting.

[0160] In a particular example, the fifth indication may be an indication of one or more of the following CSI report configurations that the second device 132 may have to assume during inference, and hence train the related AI / ML model for: which subbands the second device 132 may have to report CSI for subband size of the CSI report, subband PMI reporting, subband CQI reporting, wideband PMI reporting and wideband CQI reporting.

[0161] According to yet another option, the second information may comprise third information about how one or more beams of the one or more frequency resources for reception of the DL RSs may be spatially related to each other. In a particular example, the second information may comprise information about how the TRP beams of the CSI-RS resources may be spatially related to each other, for CRI-based CSI reporting.

[0162] According to yet another option, the second information may comprise a sixth indication of one or more conditions corresponding to the transmission of the DL RSs the second device 132 may have to assume during the inference phase upon receipt of the sixth indication.

[0163] In particular examples wherein the second information may be assistance configuration, in this Action 703, the first device 131 may receive assistance configuration associated with thetraining of the UE-sided AI / ML based frequency domain CSI prediction, where the assistance configuration may contain one or more of the following options.

[0164] According to an option, the assistance configuration may comprise one or more codebooks the second device 132 may have to assume during inference and hence train the related AI / ML model for.

[0165] According to another option, the assistance configuration may comprise number of reported CRIs, for CRI-based CSI reporting.

[0166] According to another option, the assistance configuration may include a NW-sided additional condition ID, wherein the first device 131 and / or the second device 132 may assume a fixed spatial filter for the associated CSI-RS resources, which may be used both during training and inference.

[0167] According to another option, the assistance configuration may comprise indication of one or more of the following CSI report configurations that the UE may have to assume during inference, and hence train the related AI / ML model for: which subbands the first device 131 may have to report CSI for, subband size of the CSI report, subband PMI reporting, subband CQI reporting, wideband PMI reporting, and wideband CQI reporting.

[0168] According to yet another option, the assistance configuration may comprise information about how the TRP beams of the CSI-RS resources may be spatially related to each other, e.g., for CRI-based CSI reporting.

[0169] According to yet another option, the assistance configuration may comprise configuration including a NW-sided additional condition ID, wherein the UE may assume that similar properties of one or more DL Tx beams and / or similar properties of one or more Transmit-Receive Unit (TXRU) mappings and / or virtualizations for the configured CSI-RS resources and / or CSI-RS ports may be associated with the same NW-sided additional condition ID, which may be used both during training and inference.

[0170] Action 704

[0171] In this Action 704, the first device 131 obtains a first indication and a second indication. The first indication indicates a first set of frequency resources out of the one or more frequency resources configured for reception of downlink (DL) RSs. The one or more frequency resources may be configured for reception of the DL RSs at the first device 131. The first set of frequency resources may be also referred to in this document as “set A of frequency resources”, or first frequency domain resource mapping pattern. In some embodiments, e.g., the first set of frequency resources may be identical to a frequency resource configuration of the DL RSs comprised in the one or more configurations.

[0172] The second indication indicates a second set of frequency resources out of the one or more frequency resources. The second set of frequency resources may be also referred to inthis document as “set B of frequency resources”, or second frequency domain resource mapping pattern.

[0173] The second set of frequency resources may be different than the first set of frequency resources.

[0174] The one or more second frequency domain resource mapping patterns may be different from the one or more first frequency domain resource mapping patterns.

[0175] It may be understood that although terminologies ‘Set A’ and ‘Set B’ may be used in the disclosure, such terminologies may not necessarily be used in 3GPP specifications. Other equivalent terminologies such as ‘first set’ or ‘larger set’ may be used in place of the term ‘Set A’. Similarly, in place of the term ‘Set B’, other equivalent terminologies such as ‘second set’, ‘smaller set’, or ‘set B frequency occupation’ may be used.

[0176] The one or more second frequency domain resource mapping patterns and the one or more first frequency domain resource mapping patterns may be indicated via different indicators from the first network node 111. The different indicators may be configured in the CSI-RS configuration. In some examples, Action 702 and Action 704 may be combined.

[0177] The obtaining in this Action 704 also comprises obtaining a third indication. The third indication indicates a correspondence between the first set of frequency resources and the second set of frequency resources.

[0178] In some examples, this Action 704 may comprise obtaining one or more first frequency domain resource mapping patterns, e.g., set A of frequency resources, and one or more second frequency domain resource mapping patterns, e.g., set B of frequency resources, for the one or more CSI-RS resources.

[0179] The first device 131 may need to know the association between the Set A and Set B of frequency resources for the one or more CSI-RS resources to be able to create the training data samples mentioned above. The first device 131 may obtain the association in different ways.

[0180] The second set of frequency resources may be a subset of the first set of frequency resources. In some examples, the one or more second frequency domain resource mapping patterns may be a subset of the one or more first frequency domain resource mapping patterns.

[0181] As one example, set B may be a subset of set A. Based on its own AI / ML model design, when receiving a CSI-RS configuration about a CSI-RS transmission over a set A of frequency resources, the first device 131 may determine which subset(s) of these frequency resources may be used to form one or more set B(s) for creating one or more model input sample(s) for frequency domain CSI prediction model training. Hence, in an example, the first device 131 may obtain the one or more Set A of frequency domain resource mapping patterns based on the CSI-RS configuration received from the first network node 111, and the first device 131 may obtain theone or more Set B of frequency domain resource mapping patterns without indication from the network, e.g., based on its own CSI prediction AI / ML model design.

[0182] As another example, the association between Set A and Set B of frequency resources for a CSI-RS resource may be indicated by the first network node 111. This may apply for both cases, Set B may be a subset of Set A, and Set B may be different from Set A.

[0183] In some examples, the one or more second frequency domain resource mapping patterns may be obtained using one or more frequency domain resource subset indicators received from the first network node 111, wherein the one or more frequency domain resource subset indicators may indicate one or more subsets of the frequency domain resources in the one or more first frequency domain resource mapping patterns.

[0184] The one or more frequency domain resource subset(s) may be explicitly indicated with one or more bitfields, and the different bits of the one or more bitfields may indicate if an associated frequency unit may have to be used or not.

[0185] In an example, Set B may be a subset of Set A, and a frequency domain resource subset indicator may be used to indicate the subset of frequency resources of a configured CSI-RS resource to be used for forming a corresponding set B for model input. In an alternative example, a frequency domain measurement restriction may be configured that may indicate which subset of frequency resources in Set A may constitute the frequency resources in set B. For instance, a frequency domain measurement restriction may be configured in the form of a bitstring wherein each bit in the bitstring may indicate whether a corresponding RB in set A may have to be included as part of set B. When the bit is set to a first value, e.g., 0, then the corresponding RB in set A may have to not be included as part of Set B. When the bit may be set to a second value, e.g., 1, then the corresponding RB in set A may have to be included as part of Set B.

[0186] In an example, different indicators or different resource mapping parameters for frequency domain allocation may be configured for a CSI-RS resource ID, to indicate the Set B of frequency resources and the set A of frequency resources for this CSI-RS resource ID, respectively. For frequency domain CSI prediction with CSI-RS overhead reduction purpose, it may be reasonable to configure these two indicators and / or frequency resource mappings for set A and Set B, such that the number of frequency resources in Set A may be larger than the number of frequency resources in set B. This configuration method may be applicable for the case wherein Set B may be a subset of Set A and the case where Set B may be different from Set A.

[0187] The first device 131 may receive configuration of a frequency occupation indicator, e.g., a frequency domain resource subset indicator or a frequency domain measurement restriction, indicating the set B frequency occupation of the configured one or more CSI-RS resource(s) that the second device 132 may have to assume during inference. The set B frequency occupationmay indicate the frequency units in which the one or more CSI-RS resource(s) may be received by the second device 132 during inference. It may be relevant that the first device 131 knows the set B frequency occupation of CSI-RS during inference such that the first device 131 may train the AI / ML model accordingly. The same set B frequency occupation indicator pattern may also be used for inference.

[0188] In some examples, the frequency domain resource subset indicator may be common across all CSI-RS resource(s) associated with the CSI-RS configuration.

[0189] In other examples, the frequency domain resource subset indicator may be individual per CSI-RS resource associated with the CSI-RS configuration.

[0190] The frequency domain resource subset(s) may be indicated by pointing at one or more pre-specified frequency unit patterns, e.g., wherein one or more frequency unit patterns may be hardcoded in the specification.

[0191] In one detailed example, a bitstring may be used as frequency occupation indicator, and the first bit may be used to indicate if a first frequency unit may be part of set B frequency occupation or not during inference, the second bit may be used to indicate if a second frequency unit may be part of set B frequency occupation or not during inference, and so on. In one related example, the first frequency unit may be the frequency unit with lowest starting frequency position of all frequency units, e.g., set A frequency units, corresponding to the one or more CSI-RS resource(s), the second frequency unit may be the frequency unit with second lowest starting frequency position of all frequency units, e.g., set A frequency units, corresponding to the one or more CSI-RS resource(s), and so on.

[0192] In some examples, a frequency unit size may be configured and associated with the frequency domain resource subset indicator.

[0193] In one example, a frequency unit size may be configured and associated with a CSI-RS resource and / or a frequency occupation indicator. In one example, the configurable frequency unit size may depend on the serving cell (carrier) bandwidth, width of BWP and / or number of RBs of the serving cell (carrier) bandwidth, and / or the sub-carrier spacing of the carrier bandwidth. For example, the larger the bandwidth is of serving cell (carrier), the larger the smallest frequency unit size may be, in order to limit the number of frequency units, and hence limit the associated complexity of the first device 131, or the second device 132.

[0194] In one example, the subset indicator patterns for Set A and / or Set B may be indicated by pointing at one or more pre-specified frequency unit patterns, e.g., where one or more frequency unit patterns may be defined in the specification, and the NW may indicate one (or more) of these frequency unit patterns the UE may have to use for training the AI / ML model.

[0195] In some examples, Set A and Set B may be defined in units of number of resource blocks (RBs) occupied by CSI-RSs corresponding to Set A and Set B. For example, the number of RBs in set A may correspond to the width of the bandwidth part (BWP) or a serving cell, and thenumber of RBs in Set B may be smaller than the width of the BWP, or a serving cell. In some examples, the number of supported RBs in Set B and / or Set A may be signaled by the first device 131 to the first network node 111 as part of UE capability signaling in Action 701. When the first device 131 may receive configuration of the number of RBs in Set B and / or Set A from the first network node 111 in Action 702, these number of RBs may be according to the UE capability signaling signaled by the UE to the first network node 111 in Action 701.

[0196] In another example, the number RBs in set A and Set B may be configured via a frequency domain density value. For instance, a first frequency domain density value of 1 may be configured for CSI-RS(s) associated with set A. This may be understood to mean the CSI-RS(s) associated with set A may be received by the first device 131 in every Resource Block (RB) within the width of the BWP. A second frequency domain density value smaller than 1, e.g., 0.25, may be configured for CSI-RS(s) associated with set B. This may be understood to mean that the CSI-RS(s) associated with set B may be received by the UE in every 4thRB within the width of the BWP.

[0197] In some alternative examples, Set A and Set B may be defined in units of number of resource elements (REs) occupied by each port of CSI-RS. In these examples, the number of REs in Set A may be much larger than the number of REs in Set B. In some examples, the number of supported REs in Set B and / or Set A may be signaled by the first device 131 to the first network node 111 as part of UE capability signaling in Action 701. When the first device 131 may receive configuration of the number of REs in Set B and / or Set A from the first network node 111, these number of REs may be according to the UE capability signaling signaled by the first device 131 to the first network node 111 in Action 701.

[0198] In some examples, for the case wherein Set B may be a subset of Set A, the set A of frequency resources of a CSI-RS resource may correspond to the full frequency resources configured for the CSI-RS, and one or more CSI-RS frequency resource subset indicators may be introduced to indicate to the first device 131 which frequency resource subset(s) of the CSI-RS may be associated to the Set B of frequency resources.

[0199] In an example, to enable the training data collection at the first device 131, the first device 131 may receive signaling from a network node such as the first network node 111, e.g., the serving gNB of the first device 131 , of a CSI-RS configuration in Action 702, which may indicate the one or more CSI-RS resources, and in this Action 704 at least the Set A of frequency resources, as defined in earlier examples, for the configured one or more CSI-RS resources. In one related example, the Set A of frequency resources may be automatically determined by the frequency resource configuration, e.g., they may be the same.

[0200] Obtaining in this Action 704 may comprise receiving, retrieving, fetching or deriving.

[0201] In some examples, the first device 131 may obtain the one or more first frequency domain resource mapping patterns based on the CSI-RS configuration obtained in Action 702,and the first device 131 may obtain the one or more second frequency domain resource mapping patterns without indication from the network, e.g., based on its own CSI prediction AI / ML model design.

[0202] In some examples, the first device 131 may receive a time domain configuration from the first network node 111, consisting of P time configuration instances, and where different time configuration instances may be associated with different frequency occupation indicators. In one related example, the first device 131 may receive configuration from the first network node 111 of a frequency occupation indicator for each of P time configuration instances. This may be used for example to receive, during inference, one or more CSI-RS resources in a first half of the frequency units during a first time instance, and a second half of the frequency units in a second time instance, which may facilitate frequency domain CSI prediction at the first device 131, or the second device 132, compared to receiving CSI-RS(s) on the same frequency units every time instance.

[0203] In some embodiments, one or more of the following may apply: the RSs may be CSI-RSs, the second set of frequency resources may be a subset of the first set of frequency resources, the obtaining in Action 704 of the first indication and the second indication, may be based on obtaining, from the first network node 111 , a respective second indication of the respective second sets of frequency resources, and the communications system 100 may be a wireless communications system 100.

[0204] In this Action 704, as in Action 702 and Action 703, the first network node 111 may be understood to configure the first device 131 for training of UE-sided CSI prediction for sparse frequency domain CSI-RS.

[0205] Action 705

[0206] For training data collection, the first device 131 may need to collect the following measurements. For creating model input samples: channel measurements associated to the one or more CSI-RS(s) received on Set B of frequency resources. For creating the corresponding labels for model output: channel measurements associated to the one or more CSI-RS(s) received on the frequency resources spanned by set A, e.g., width of BWP.

[0207] In this Action 705, the first device 131 performs on the DL RSs, as transmitted by the first network node 111 operating in a communications system 100, one or more first measurements on the first set of frequency resources, and one or more second measurements on the second set of frequency resources.

[0208] The one or more first measurements and the one or more second measurements may be performed within a time period, e.g., close in time.In some examples, this Action 705 may comprise performing measurements on the one or more CSI-RS resources, based on the obtained first and / or second frequency domain resource mapping patterns in Action 704.

[0209] In another example, the first device 131 may obtain measurements on the set B of frequency resources of the one or more CSI-RS(s) received by the first device 131 from the first network node 111 to create the model input sample(s). In yet another example, the first device 131 may obtain measurements over the set A of frequency resources, as defined in earlier examples, of the one or more CSI-RS(s) received by the first device 131 from the first network node 111 create the label(s) for the associated model output.

[0210] Action 706

[0211] In this Action 706, the first device 131 may output first information.

[0212] The first information may indicate: the one or more first measurements, the one or more second measurements, and the correspondence.

[0213] Outputting may comprise, in some examples, sending, e.g., to the first network node 111. In some embodiments, the method may be iterated for a plurality of respective second sets of frequency resources and, optionally, a corresponding plurality of correspondences between the respective second set of frequency resources and the first set of frequency resources.

[0214] The iteration of the method may comprise the iteration of the actions described this far as Action 704, Action 705, and Action 706.

[0215] The first device 131 may obtain one or more training data samples for model input by using the measurements of the one or more CSI-RS resources with the one or more second frequency domain resource mapping patterns.

[0216] The first device 131 may obtain one or more training data samples for model output label(s) by using the measurements of the one or more CSI-RS resources with the one or more first frequency domain resource mapping patterns.

[0217] In some examples, the first device 131 may report the obtained one or more training data samples for model input and / or the obtained one or more training data samples for model output label(s) to the second network node 112.

[0218] In some examples, the second network node 112 and the first network node 111 may be the same node, e.g., the serving gNB.

[0219] In other examples, the second network node 112 may be different from the first network node 111, e.g., the first network node 111 may be the serving gNB and the second network node 112 may be a core network node or CAM or a server.

[0220] In some embodiments, one or more of the following may apply: the RSs may be CSI-RSs, the second set of frequency resources may be a subset of the first set of frequency resources,the first information may be output to the second network node 112 operating in the communications system 100, the obtaining in Action 704 of the first indication and the second indication, may be based on obtaining, from the first network node 111, a respective second indication of the respective second sets of frequency resources, and the communications system 100 may be a wireless communications system 100.

[0221] In some examples, the first device 131 may be configured to not report the collected measurements to the network, e.g., by configuring the “reportQuantity” to “none” in the CSI report configuration associated to the CSI-RS configuration.

[0222] Since the MLM may be understood to be a UE-sided AI / ML model for CSI prediction in the frequency domain, the training data sample(s) collected by the first device 131 may be further reported to a UE-side training server over-the-top outside 3GPP signaling. In this case, there may be no need for the first device 131 to report the collected training data sample(s) to the network. Hence, in an example, the first device 131 may be configured to not report the collected measurements to the network, e.g., by configuring the “reportQuantity” to “none” in the CSI report configuration associated to the CSI-RS configuration.

[0223] There may also be cases wherein training data sample(s) collected by the first device 131 may be transferred / delivered / reported to a network entity, e.g., a gNB, a core network node, Operations and Management (OAM), a server, which may be understood to be responsible for training data maintenance, and / or model training, and / or model performance monitoring, etc. Hence, in an example, the first device 131 may be configured to report the collected training data samples to a network node. The network node may or may not be the same as for the one that may provide the CSI-RS configuration, that is, the first network node 111.

[0224] In some embodiments, the method may further comprise one or more of the following two actions.

[0225] Action 707

[0226] In this Action 707, the first device 131 may initiate training of the MLM.

[0227] Initiating may comprise starting itself, or triggering or enabling that another entity, e.g., the first network node 111 or the second network node 112 may perform the training of the MLM.

[0228] The MLM may be any of, e.g., a Neural Network, a Convolutional Neural Network, a Federated Learning MLM, an Autoencoder, Decision Tree, etc.

[0229] The training of the MLM may be with the output first information for each respective iteration.

[0230] The MLM may be to predict CSI of the channel, e.g., between the first device 131 and the first network node 111. The prediction may be for the first set of frequency resources, based on the respective one or more second measurements on the second set of frequency resources.During a training phase of the MLM, the one or more second measurements on the second set of frequency resources may be used as input to the MLM, and the one or more first measurements may be used as output labels of the MLM.

[0231] An output label may be understood as the “right answers”, or ground truth, to which the MLM training process may compare the model outputs, to determine how correct the MLM output may be, and consequently how to adjust model weights.

[0232] In some examples, this Action 707 may comprise performing training of the UE-sided AI / ML model for frequency domain CSI prediction based on the measurements performed in Action 705.

[0233] In this Action 707, the first device 131 may train the AI / ML model assuming only a subset of the full bandwidth of CSI-RS resources are transmitted in each CSI-RS transmission occasion.

[0234] Action 708

[0235] In this Action 708, the first device 131 may initiate outputting a fourth indication.

[0236] The fourth indication may be of the trained MLM. The fourth indication may be output, for example, to the second device 132.

[0237] In some embodiments, the method may further comprise the following action.

[0238] Action 709

[0239] In this Action 709, the first device 131 may use the trained MLM.

[0240] The using in this Action 709 may be, e.g., to predict CSI, of the channel between the first device 131 and the first network node 111 , or a second channel between the first device 131 and the third network node 113.

[0241] Embodiments of a computer-implemented method, performed by device, such as the second device 132, will now be described with reference to the flowchart depicted in Figure 8.

[0242] The method is for handling information pertaining to RSs. The second device 132 operates in a communications system, such as the communications system 100.

[0243] In some examples, the method may be for data collection for inference of a UE-sided AI / ML based frequency domain CSI prediction.

[0244] In some embodiments, the communications system 100 may support New Radio (NR). Several embodiments are comprised herein. The method may comprise one or more of the following actions. In some embodiments, all the actions may be performed. Action 805, Action 806 and Action 807 are performed. In some examples, Action 805, Action 806, Action 807, and Action 808 may be performed. One or more embodiments may be combined, where applicable. It should be noted that the examples herein are not mutually exclusive.Components from one embodiment may be tacitly assumed to be present in another embodiment and it will be obvious to a person skilled in the art how those components may be used in the other exemplary embodiments. All possible combinations are not described to simplify the description. A non-limiting example of the method performed by the second device 132 is depicted in Figure 8. In Figure 8, optional actions in some embodiments may be represented with dashed lines. In some embodiments, the actions may be performed in a different order than that depicted Figure 8.

[0245] The detailed description of some of the following corresponds to the same references provided above, in relation to the actions described for the first device 131 and will thus not be repeated here to simplify the description. For example, the MLM may be any of, e.g., a Neural Network, a Convolutional Neural Network, a Federated Learning MLM, an Autoencoder, Decision Tree, etc.

[0246] The second device 132 may be a device that may perform inference with the MLM, once trained. The second device 132 may use similar input data to the MLM as the first measurements, using new or fresh data or measurements. Usage of the adjective “first” in front of a term that has already been used, e.g., in relation to the first device 131 , may be understood to indicate a reference to a fresh or new instance of the same term. For example “first previous indication” may be understood to relate to the same concept of “previous indication” described earlier, but in reference to the second device 132.

[0247] Action 801

[0248] In this Action 801, the second device 132 may obtain the trained MLM.

[0249] The obtaining in this Action 801 may be, e.g., from the first device 131 or the second network node 112 operating in the communications network 100.

[0250] In some embodiments, the method may further comprise one or more of the following three actions.

[0251] Action 802

[0252] In this Action 802, the second device 132 may provide a first previous indication.

[0253] The providing in this Action 802 of the first previous indication may be to the first network node 111.

[0254] The first previous indication may indicate a first capability for the performance of measurements on the DL RSs.

[0255] Action 803

[0256] In this Action 803, the second device 132 may obtain one or more first configurations. The obtaining in this Action 803 may be from the first network node 111.The one or more first configurations may be of the one or more first frequency resources for reception of the DL RSs.

[0257] The obtaining in this Action 803 of the one or more first configurations may be based on the provided first previous indication.

[0258] In an example, this Action 803 may comprise receiving from a first network node a CSI-RS configuration consisting of one or more CSI-RS resources.

[0259] Action 804

[0260] In this Action 804, the second device 132 may obtain first second information.

[0261] The obtaining in this Action 804 may be from the first network node 111.

[0262] The first second information may be the same as the second information the first device 131 may have obtained.

[0263] The first second information may be to be input by the second device 132 to the MLM for the predicting in Action 805 of the CSI.

[0264] The first second information may comprise one or more of: a) the one or more codebooks the second device 132 may have to assume for the predicting in Action 805 of the CSI, b) the fifth indication of the one or more configurations of the report of the DL RSs that the second device 132 may have to assume for the predicting in Action 805 of the CSI, selected from: i) the subbands the second device 132 may have to report CSI for, ii) the subband size of the report, the subband PMI reporting, iii) the subband CQI reporting, iv) the wideband PMI reporting, and v) the wideband CQI reporting, c) the third information about how the one or more beams of the one or more first frequency resources for reception of the DL RSs may be spatially related to each other, and d) the sixth indication of the one or more conditions corresponding to the transmission of the DL RSs the second device 132 may have to assume for the predicting in Action 805 of the CSI based on the receipt of the sixth indication.

[0265] In this Action 804, the second device 132 may receive assistance configuration associated with the inference of the UE-sided AI / ML based frequency domain CSI prediction. The assistance configuration may contain one or more of: configuration including a NW-sided additional condition ID, wherein the second device 132 may assume that similar properties of one or more DL Tx beams and / or similar properties of one or more TXRU mappings and / or virtualizations for the configured CSI-RS resources and / or / CSI-RS ports may be associated with the same NW-sided additional condition ID, which may be used both during training and inference.

[0266] Action 805

[0267] In this Action 805, the second device 132 obtains a first first indication and a first second indication.The first first indication indicates a first first set of frequency resources out of one or more first frequency resources configured for reception of downlink (DL) RSs. The one or more frequency resources may be configured for reception of the DL RSs at the second device 132. The first first set of frequency resources may be also referred to in this document as “set A of frequency resources”, or first frequency domain resource mapping pattern.

[0268] The first second indication indicates a first second set of frequency resources out of the one or more first frequency resources. The second set of frequency resources may be also referred to in this document as “set B of frequency resources”, or second frequency domain resource mapping pattern.

[0269] The RSs may be CSI-RSs.

[0270] The first first set of frequency resources is larger than the first second set of frequency resources.

[0271] The first second set of frequency resources may be a subset of the first set of frequency resources.

[0272] The second set of frequency resources may be different than the first set of frequency resources.

[0273] Obtaining in this Action 704 may comprise receiving, retrieving, fetching or deriving. In some embodiments, e.g., the first first set of frequency resources may be identical to a frequency resource first configuration of the DL RSs comprised in the one or more first configurations.

[0274] This Action 804 may comprise obtaining one or more first frequency domain resource mapping patterns, e.g., set A of frequency resources, and one or more second frequency domain resource mapping patterns, e.g., set B of frequency resources, for the one or more CSI-RS resources.

[0275] The one or more second frequency domain resource mapping patterns may be a subset of the one or more first frequency domain resource mapping patterns.

[0276] The one or more second frequency domain resource mapping patterns may be obtained using one or more frequency domain resource subset indicators received from the first network node 111. The one or more frequency domain resource subset indicators may indicate one or more subsets of the frequency domain resources in the one or more first frequency domain resource mapping patterns.

[0277] The frequency domain resource subset indicator may be common across all CSI-RS resource(s) associated with the CSI-RS configuration.

[0278] The frequency domain resource subset indicator may be individual per CSI-RS resource associated with the CSI-RS configuration.

[0279] A frequency unit size may be configured and associated with the frequency domain resource subset indicator.The one or more frequency domain resource subset(s) may be explicitly indicated with one or more bitfields. The different bits of the one or more bitfields may indicate if an associated frequency unit may have to be used or not.

[0280] The frequency domain resource subset(s) may be indicated by pointing at one or more pre-specified frequency unit patterns. One or more frequency unit patterns may be hardcoded in the specification.

[0281] The one or more second frequency domain resource mapping patterns may be different from the one or more first frequency domain resource mapping patterns.

[0282] The one or more second frequency domain resource mapping patterns and the one or more first frequency domain resource mapping patterns may be indicated via different indicators from the first network node 111.

[0283] The different indicators may be configured in the CSI-RS configuration obtained in Action 803.

[0284] The second device 132 may obtain the one or more first frequency domain resource mapping patterns based on the CSI-RS configuration obtained in Action 803, and the second device 132 may obtain the one or more second frequency domain resource mapping patterns without indication from the network, e.g., based on its own CSI prediction AI / ML model design.

[0285] For model inference, the second device 132 may be configured to measure one or more CSI-RS(s) received on Set B of frequency resources, e.g., in units of RBs or REs, use the measurements to create model input for frequency domain CSI prediction, and then report the predicted CSI for the frequency resources spanned by set A, e.g., frequency band width of BWP or serving cell.

[0286] Action 806

[0287] In this Action 806, the second device 132 obtains one or more first second measurements.

[0288] The second device 132, in this Action 806, obtains, e.g., performs, the one or more first second measurements on the first second set of frequency resources on the DL RSs, as transmitted by the first network node 111 operating in the communications system 100.

[0289] This Action 806 may comprise performing measurements on the one or more CSI-RS resources, based on the obtained second frequency domain resource mapping patterns.

[0290] Action 807

[0291] In this Action 807, the second device 132 predicts CSI.

[0292] The CSI is of a first channel between the second device 132 and, e.g., the first network node 111 , or another network node.

[0293] The predicting in this Action 807 is using first first information.The first first information indicates the one or more first second measurements as input to the trained MLM,

[0294] The prediction is for the first first set of frequency resources.

[0295] The prediction is based on the respective one or more first second measurements on the first second set of frequency resources.

[0296] The prediction may be optionally further based on a first correspondence between the first first set of frequency resources and the first second set of frequency resources.

[0297] This Action 807 may comprise predicting CSI associated with the one or more CSI-RS resources for the first frequency domain resource mapping pattern(s).

[0298] In this Action 807, the second device 132 may predict the CSI for the full bandwidth based the received CSI-RSs.

[0299] In some embodiments, one or more of the following may apply: i) the RSs may be CSI-RSs, ii) the first second set of frequency resources may be a subset of the first first set of frequency resources, iii) the obtaining in Action 805 of the first first indication and the first second indication, may be based on obtaining, from the first network node 111 , a respective first second indication of the first second set of frequency resources, iv) the predicting (807) may be further based on a first correspondence between the first first set of frequency resources and the first second set of frequency resources, and iv) the communications system 100 may be a wireless communications system 100.

[0300] Action 808

[0301] In this Action 808, the second device 132 may initiate outputting a seventh indication of the predicted CSI. This Action 808 may comprise reporting the predicted CSI, e.g., to the first network node 111.

[0302] Embodiments of a computer-implemented method, performed by a network node, such as the first network node 111, will now be described with reference to the flowchart depicted in Figure 9. The method is for handling information pertaining to RSs. The first network node 111 operates in a communications system, such as the communications system 100.

[0303] In some embodiments, the communications system 100 may support New Radio (NR). Several embodiments are comprised herein. The method may comprise one or more of the following actions. In some embodiments, all the actions may be performed. Action 910, and Action 911 are performed. In some examples, Action 910, Action 911 and Action 912 may be performed. One or more embodiments may be combined, where applicable. It should be noted that the examples herein are not mutually exclusive. Components from one embodiment may be tacitly assumed to be present in another embodiment and it will be obvious to a person skilled in the art how those components may be used in the other exemplary embodiments. Allpossible combinations are not described to simplify the description. A non-limiting example of the method performed by the first network node 111 is depicted in Figure 9. In Figure 9, optional actions in some embodiments may be represented with dashed lines. In some embodiments, the actions may be performed in a different order than that depicted Figure 9. For example, Action 902 may be performed after Action 903.

[0304] The detailed description of some of the following corresponds to the same references provided above, in relation to the actions described for the first device 131 and will thus not be repeated here to simplify the description. For example, the MLM may be any of, e.g., a Neural Network, a Convolutional Neural Network, a Federated Learning MLM, an Autoencoder, Decision Tree, etc.

[0305] The first network node 111 may be a network node that may receive an indication, e.g., a report, from the second device 132 based on predicted CSI.

[0306] In some examples, the first network node 111 may be a network node that may configure the first device 131 to collect data to use as input to the MLM during a training phase of the MLM. In some examples, the first network node 111 may train the MLM itself.

[0307] Action 901

[0308] In this Action 901 , the first network node 111 may obtain the previous indication.

[0309] The obtaining in this Action 901 may be from the first device 131.

[0310] The previous indication may indicate the capability for the performance of measurements on the DL RSs.

[0311] Action 902

[0312] In this Action 902, the first network node 111 may provide the one or more configurations. The providing in this Action 902 may be to the first device 131.

[0313] The one or more configurations may be of the one or more frequency resources for reception of the DL RSs.

[0314] The providing in this Action 902 of the one or more configurations may be based on the obtained previous indication.

[0315] Action 903

[0316] In this Action 903, the first network node 111 may provide the second information.

[0317] The providing in this Action 902 may be to the first device 131.

[0318] The second information may be to assist the first device 131 in training the respective MLM. That is, its own MLM, if trained by the first device 131. The respective MLM may be to predict CSI of the channel between the first device 131 and the first network node 111. Theprediction may be for the first set of frequency resources, based on respective one or more second measurements on the second set of frequency resources.

[0319] The training of the respective MLM may be performed, by the first device 131, based on the provided second information.

[0320] The second information may comprise one or more of: a) the one or more codebooks the second device 132 may have to assume during the inference phase of the MLM or of the respective MLM, b) the fifth indication of one or more configurations of the report of the DL RSs that the second device 132 may have to assume during the inference phase, selected from: i) the subbands the second device 132 may have to report CSI for, ii) the subband size of the report, iii) the subband PMI reporting, iv) the subband CQI reporting, v) the wideband PMI reporting, and vi) the wideband CQI reporting, c) the third information about how the one or more beams of the one or more frequency resources for reception of the DL RSs may be spatially related to each other, and d) the sixth indication of the one or more conditions corresponding to the transmission of the DL RSs the second device 132 may have to assume during the inference phase upon receipt of the sixth indication.

[0321] In some embodiments, the method may further comprise one or more of the following two actions.

[0322] Action 904

[0323] In this Action 904, the first network node 111 may provide the first indication and the second indication.

[0324] The providing, e.g., sending, in this Action 904 may be to the first device 131 operating in the communication system 100.

[0325] The first indication may indicate the first set of frequency resources out of the one or more frequency resources configured for reception of the DL RSs. The one or more frequency resources may be configured for reception of the DL RSs by the first device 131.

[0326] The second indication may indicate the second set of frequency resources out of the one or more frequency resources.

[0327] In some examples, the providing in this Action 904 may optionally comprise providing the third indication. The third indication may indicate the correspondence between the first set of frequency resources and the second set of frequency resources.

[0328] The RSs may be CSI-RSs.

[0329] The second set of frequency resources may be a subset of the first set of frequency resources.

[0330] The second set of frequency resources may be different than the first set of frequency resources.

[0331] In some embodiments, e.g., the first set of frequency resources may be identical to afrequency resource configuration of the DL RSs comprised in the one or more configurations. In some embodiments, one or more of the following may apply: the RSs may be CSI-RSs, the second set of frequency resources may be the subset of the first set of frequency resources, and the communications system 100 may be a wireless communications system 100.

[0332] In Action 902, Action 903 and Action 904, the first network node 111 may configure the first device 131 for training of UE-sided CSI prediction for sparse frequency domain CSI-RS.

[0333] Action 905

[0334] In this Action 905, the first network node 111 may transmit the DL RSs.

[0335] The transmitting in this Action 905 may be to the first device 131.

[0336] The transmitting in this Action 905 may be: on the first set of frequency resources, and on the second set of frequency resources.

[0337] In this Action 905, the first network node 111 may transmit CSI-RSs spanning the full bandwidth.

[0338] In some embodiments, the method may further comprise the following action.

[0339] Action 906

[0340] In this Action 906, the first network node 111 may receive the first information.

[0341] The receiving in this Action 906 may be from the first device 131.

[0342] The first information may indicate: the one or more first measurements, the one or more second measurements, and optionally, the correspondence.

[0343] In some embodiments, the providing 904 of the first indication, the second indication and the third indication, the transmitting 905 of the DL RSs, and the receiving 906 of the first information may be iterated for the plurality of respective second sets of frequency resources and, optionally, the corresponding plurality of correspondences between the respective second set of frequency resources and the first set of frequency resources.

[0344] In some embodiments, the method may further comprise one or more of the following two actions.

[0345] Action 907

[0346] In this Action 907, the first network node 111 may initiate training of the MLM.

[0347] The training of the MLM may be with the received first information for each respective iteration. The MLM may be to predict the CSI of the channel between the first device 131 and the first network node 111. The prediction may be for the first set of frequency resources, based on the respective one or more second measurements on the second set of frequency resources.Action 908

[0348] In this Action 908, the first network node 111 may initiate outputting the fourth indication. Initiating may comprise starting or triggering.

[0349] The fourth indication may be of the trained MLM.

[0350] In some embodiments, the method may further comprise the following action.

[0351] Action 909

[0352] In this Action 909, the first network node 111 may use the trained MLM.

[0353] The using in this Action 909 may be, e.g., to predict CSI, of the channel between the first device 131 and the first network node 111 , or the second channel between the first device 131 and the third network node 113.

[0354] During the training phase of the MLM, the one or more second measurements on the second set of frequency resources may be used as input to the MLM, and the one or more first measurements may be used as output labels of the MLM.

[0355] Action 910

[0356] In this Action 910, the first network node 111 provides the first first indication and the first second indication.

[0357] The first first indication indicates the first first set of frequency resources out of the one or more first frequency resources configured for reception of DL RSs, at the second device 132 operating in the communications system 100.

[0358] The first second indication indicates the first second set of frequency resources out of the one or more first frequency resources.

[0359] The first first set of frequency resources is larger than the first second set of frequency resources.

[0360] The providing, e.g., sending in this Action 910 may be to the second device 132 operating in the communication system 100.

[0361] In this Action 910, the first network node 111 may configure the first device 131 for inference of UE-sided CSI prediction for sparse frequency domain CSI-RS.

[0362] Action 911

[0363] In this Action 911 , the first network node 111 transmits the DL RSs.

[0364] The transmitting in this Action 911 of the DL RSs is on the first second set of frequency resources to the second device 132.

[0365] In this Action 911 , the first network node 111 may transmit CSI-RSs in a subset of the full bandwidth, that is, in a subset of all subbands. Which subbands may be transmitted may varyacross different CSI-RS transmission occasions.

[0366] In some embodiments, the method may further comprise the following actions.

[0367] Action 912

[0368] In this Action 912, the first network node 111 may receive the seventh indication.

[0369] The receiving in this Action 912 may be from the second device 132.

[0370] The seventh indication may be of the predicted CSI of the first channel between the second device 132 and the first network node 111.

[0371] The prediction may be for the first first set of frequency resources, and based on the respective one or more first second measurements performed by the second device 132 on the first second set of frequency resources.

[0372] The prediction may be optionally further based on the first correspondence between the first first set of frequency resources and the first second set of frequency resources.

[0373] Embodiments of a computer-implemented method, performed by a network node, such as the second network node 112, will now be described with reference to the flowchart depicted in Figure 10. The method is for handling the information pertaining to RSs. The second network node 112 operates in a communications system, such as the communications system 100.

[0374] In some embodiments, the communications system 100 may support New Radio (NR). Several embodiments are comprised herein. The method may comprise one or more of the following actions. In some embodiments, all the actions may be performed. In some examples, Action 1002 may be performed. It should be noted that the examples herein are not mutually exclusive. One or more embodiments may be combined, where applicable.

[0375] Components from one embodiment may be tacitly assumed to be present in another embodiment and it will be obvious to a person skilled in the art how those components may be used in the other exemplary embodiments. All possible combinations are not described to simplify the description. A non-limiting example of the method performed by the second network node 112 is depicted in Figure 10. In Figure 10, optional actions in some embodiments may be represented with dashed lines. In some embodiments, the actions may be performed in a different order than that depicted Figure 10.

[0376] The detailed description of some of the following corresponds to the same references provided above, in relation to the actions described for the first device 131 and will thus not be repeated here to simplify the description. For example, the MLM may be any of, e.g., a Neural Network, a Convolutional Neural Network, a Federated Learning MLM, an Autoencoder, Decision Tree, etc.

[0377] The second network node 112 may be a network node 112 that may collect data to use as input to the MLM during a training phase of the MLM and train the MLM.Action 1001

[0378] In this Action 1001, the second network node 112 may obtain the second information. The obtaining in this Action 1001 may be from the first network node 111.

[0379] The second information may be to assist the second network node 112 in training the MLM. The training of the MLM may be performed based on the obtained second information.

[0380] The second information may comprise one or more of: a) the one or more codebooks the second device 132 may have to assume during the inference phase of the MLM, b) the fifth indication of one or more configurations of the report of the DL RSs that the second device 132 may have to assume during the inference phase, selected from: i) the subbands the second device 132 may have to report CSI for, ii) the subband size of the report, iii) the subband PM I reporting, iv) the subband CQI reporting, v) the wideband PMI reporting, and vi) the wideband CQI reporting, c) the third information about how one or more beams of the one or more frequency resources for reception of the DL RSs may be spatially related to each other, and d) the sixth indication of the one or more conditions corresponding to the transmission of the DL RSs the second device 132 may have to assume during the inference phase based on, e.g., upon receipt of the sixth indication.

[0381] Action 1002

[0382] In this Action 1002, the second network node 112 obtains the first information.

[0383] The obtaining in this Action 1001 is at least from the first device 131. That is, the second network node 112 may receive a respective first information from every first device.

[0384] The first information may be of the first set of measurements.

[0385] The first information indicates: i) the one or more first measurements on the DL RSs transmitted by the first network node 111 operating in the communications system 100, on the first set of frequency resources out of the one or more frequency resources configured for reception of the DL RSs, at the first device 131, ii) the one or more second measurements of the DL RSs, on the second set of frequency resources, out of the one or more frequency resources, wherein the first set of frequency resources is larger than the second set of frequency resources, and iii) the correspondence between the first set of frequency resources and the second set of frequency resources.

[0386] In some embodiments, the method may be iterated for the plurality of respective second sets of frequency resources and, optionally, the corresponding plurality of correspondences between the respective second set of frequency resources and the first set of frequency resources.In some embodiments, one or more of the following may apply: the RSs may be CSI-RSs, the second set of frequency resources may be a subset of the first set of frequency resources, and the communications system 100 may be a wireless communications system 100.

[0387] In some embodiments, the method may further comprise one or more of the following two actions.

[0388] Action 1003

[0389] In this Action 1003, the second network node 112 may initiate training of the MLM.

[0390] Initiating may comprise starting itself, or triggering or enabling that another entity performs the training.

[0391] The training of the MLM may be with the obtained first information for each respective iteration.

[0392] The MLM may be to predict the CSI of the channel, e.g., between the first device 131 and the first network node 111. The prediction may be for the first set of frequency resources, based on the respective one or more second measurements on the second set of frequency resources.

[0393] During the training phase of the MLM, the one or more second measurements on the second set of frequency resources may be used as input to the MLM, and the one or more first measurements may be used as output labels of the MLM.

[0394] Action 1004

[0395] In this Action 1004, the second network node 112 may initiate outputting the fourth indication. That is, its own fourth indication.

[0396] The fourth indication may be of the trained MLM.

[0397] In some embodiments, the method may further comprise the following action.

[0398] Action 1005

[0399] In this Action 1005, the second network node 112 may use the trained MLM.

[0400] The using in this Action 1005 may be, e.g., to predict CSI, of the channel between the first device 131 and the first network node 111 , or the second channel between the first device 131 and third network node 113.

[0401] Some embodiments herein will now be further described with some non-limiting examples, which may be combined, in whole or in part, with the embodiments just described.

[0402] In the following description, any reference to a / the UE, may be understood to equally refer to any of the first device 131 and the second device 132; any reference to a / the gNB and / or a / the Radio access node and / or a / the network node and / or a / the core network access nodeand / or a / the BS and / or a / the RAN node and / or a / the base station and / or a / the NW node may be understood to equally refer to any of the first network node 111 , the second network node 112 and the third network node 113; any reference to a / the node in RAN or in the core network may be understood to equally refer to the second network node 112.

[0403] In the examples below, it may be assumed that Set B may be a subset of Set A.

[0404] In the text herein, “frequency unit” may be used to denote a number of frequency domain resources, such as RBs, REs, subcarriers, etc., that may be used for receiving the one or more CSI-RS(s).

[0405] Examples of, or related to, or combinable with, embodiments herein may include:

[0406] Training

[0407] 1. A Method in a UE, such as the first device 131, for training data collection for a UE- sided AI / ML based frequency domain CSI prediction, the method comprising:

[0408] a. Receiving from a first network node a CSI-RS configuration consisting of one or more CSI-RS resources,

[0409] b. Obtaining one or more first frequency domain resource mapping patterns, e.g., set A of frequency resources, and one or more second frequency domain resource mapping patterns, e.g., set B of frequency resources, for the one or more CSI-RS resources,

[0410] c. Performing measurements on the one or more CSI-RS resources, based on the obtained first and / or second frequency domain resource mapping patterns, d. Performing training of the UE-sided AI / ML model for frequency domain CSI prediction based on the measurements performed in step c.

[0411] 2. 1 and wherein the UE may obtain one or more training data samples for model input by using the measurements of the one or more CSI-RS resources with the one or more second frequency domain resource mapping patterns.

[0412] 3. 1 and wherein the UE may obtain one or more training data samples for model output label(s) by using the measurements of the one or more CSI-RS resources with the one or more first frequency domain resource mapping patterns.

[0413] 4. 1 and wherein the one or more second frequency domain resource mapping patterns may be a subset of the one or more first frequency domain resource mapping patterns.

[0414] 5. 4 and wherein the one or more second frequency domain resource mapping patterns may be obtained using one or more frequency domain resource subset indicators received from the first network node, wherein the one or more frequency domainresource subset indicators may indicate one or more subsets of the frequency domain resources in the one or more first frequency domain resource mapping patterns.

[0415] 6. All above and wherein the frequency domain resource subset indicator may be common across all CSI-RS resource(s) associated with the CSI-RS configuration. 7. All above and wherein the frequency domain resource subset indicator may be individual per CSI-RS resource associated with the CSI-RS configuration.

[0416] 8. All above and wherein a frequency unit size may be configured and associated with the frequency domain resource subset indicator.

[0417] 9. 8 and wherein the one or more frequency domain resource subset(s) may be explicitly indicated with one or more bitfields, and wherein the different bits of the one or more bitfields may indicate if an associated frequency unit may have to be used or not. 10. 8 and wherein the frequency domain resource subset(s) may be indicated by pointing at one or more pre-specified frequency unit patterns, e.g., wherein one or more frequency unit patterns may be hardcoded in the specification.

[0418] 11. 1 and wherein the one or more second frequency domain resource mapping patterns may be different from the one or more first frequency domain resource mapping patterns.

[0419] 12. 1 and wherein the one or more second frequency domain resource mapping patterns and the one or more first frequency domain resource mapping patterns may be indicated via different indicators from the first network node.

[0420] 13. 12 and wherein the different indicators may be configured in the CSI-RS configuration (1a).

[0421] 14. 1 and wherein the UE may obtain the one or more first frequency domain resource mapping patterns based on the CSI-RS configuration (1a), and the UE may obtain the one or more second frequency domain resource mapping patterns without indication from the network, e.g., based on its own CSI prediction AI / ML model design.

[0422] 15. 1-3 and wherein the UE may be configured to not report the collected measurements to the network, e.g., by configuring the “reportQuantity” to “none” in the CSI report configuration associated to the CSI-RS configuration.

[0423] 16. 1-3 and wherein the UE may report the obtained one or more training data samples for model input and / or the obtained one or more training data samples for model output label(s) to a second network node.

[0424] 17. 12 and wherein the second network node and the first network node are the same node, e.g., the serving gNB.

[0425] 18. 12 and wherein the second network node may be different from the first network node, e.g., the first network node may be the serving gNB and the second network node may be a core network node or CAM or a server.19. 1 and wherein the UE may receive assistance configuration associated with the training of the UE-sided AI / ML based frequency domain CSI prediction, where the assistance configuration may contain one or more of:

[0426] a. One or more codebooks the UE may have to assume during inference, and hence train the related AI / ML model for,

[0427] b. Indication of one or more of the following CSI report configurations that the UE may have to assume during inference, and hence train the related AI / ML model for:

[0428] i. Which subbands the UE may have to report CSI for, ii. Subband size of the CSI report,

[0429] iii. Subband PMI reporting,

[0430] iv. Subband CQI reporting,

[0431] v. Wideband PMI reporting,

[0432] vi. Wideband CQI reporting,

[0433] c. Information about how the TRP beams of the CSI-RS resources may be spatially related to each other, e.g., for CRI-based CSI reporting,

[0434] d. Configuration including a NW-sided additional condition ID, wherein the UE may assume that similar properties of one or more DL Tx beams and / or similar properties of one or more Transmit-Receive Unit (TXRU) mappings and / or virtualizations for the configured CSI-RS resources and / or CSI-RS ports may be associated with the same NW-sided additional condition ID, which may be used both during training and inference.

[0435] Inference

[0436] 1. A Method in a UE, such as the second device 132, for data collection for inference of a UE-sided AI / ML based frequency domain CSI prediction, the method comprising: a. Receiving from a first network node a CSI-RS configuration consisting of one or more CSI-RS resources,

[0437] b. Obtaining one or more first frequency domain resource mapping patterns, e.g., set A of frequency resources, and one or more second frequency domain resource mapping patterns, e.g., set B of frequency resources, for the one or more CSI-RS resources,

[0438] c. Performing measurements on the one or more CSI-RS resources, based on the obtained second frequency domain resource mapping patterns, d. Predicting CSI associated with the one or more CSI-RS resources for the first frequency domain resource mapping pattern(s),

[0439] e. Reporting the predicted CSI.2. 1 and wherein the one or more second frequency domain resource mapping patterns may be a subset of the one or more first frequency domain resource mapping patterns.

[0440] 3. 2 and wherein the one or more second frequency domain resource mapping patterns may be obtained using one or more frequency domain resource subset indicators received from the first network node 111, wherein the one or more frequency domain resource subset indicators may indicate one or more subsets of the frequency domain resources in the one or more first frequency domain resource mapping patterns.

[0441] 4. All above and wherein the frequency domain resource subset indicator may be common across all CSI-RS resource(s) associated with the CSI-RS configuration. 5. All above and wherein the frequency domain resource subset indicator may be individual per CSI-RS resource associated with the CSI-RS configuration.

[0442] 6. All above and wherein a frequency unit size may be configured and associated with the frequency domain resource subset indicator.

[0443] 7. 6 and wherein the one or more frequency domain resource subset(s) may be explicitly indicated with one or more bitfields, and wherein the different bits of the one or more bitfields may indicate if an associated frequency unit may have to be used or not. 8. 7 and wherein the frequency domain resource subset(s) may be indicated by pointing at one or more pre-specified frequency unit patterns, e.g., wherein one or more frequency unit patterns may be hardcoded in the specification.

[0444] 9. 1 and wherein the one or more second frequency domain resource mapping patterns may be different from the one or more first frequency domain resource mapping patterns.

[0445] 10. 1 and wherein the one or more second frequency domain resource mapping patterns and the one or more first frequency domain resource mapping patterns may be indicated via different indicators from the first network node 111.

[0446] 11. 10 and wherein the different indicators may be configured in the CSI-RS configuration (1a).

[0447] 12. 1 and wherein the UE may obtain the one or more first frequency domain resource mapping patterns based on the CSI-RS configuration (1a), and the UE may obtain the one or more second frequency domain resource mapping patterns without indication from the network, e.g., based on its own CSI prediction AI / ML model design.

[0448] 13. 1 and wherein the UE may receive assistance configuration associated with the inference of the UE-sided AI / ML based frequency domain CSI prediction, wherein the assistance configuration may contain one or more of:

[0449] a. Configuration including a NW-sided additional condition ID, wherein the UE may assume that similar properties of one or more DL Tx beams and / or similar properties of one or more TXRU mappings and / or virtualizations for theconfigured CSI-RS resources and / or / CSI-RS ports may be associated with the same NW-sided additional condition ID, which may be used both during training and inference.

[0450] Figure 11 illustrates a non-limiting example of a high-level flowchart of the training method, associated with embodiments herein. In Figure 11 , the first newtrok node 111 is depicted as a BS and the first device 131 as a UE. In Step 100, the first device 131, in accordance with Action 702, Action 703, Action 704, Action 902, Action 903 and Action 904, may receive configuration from the base station (BS) of one or more CSI-RS resource(s) for training an AI / ML model for CSI prediction over frequency domain. In addition, the first device 131 may receive configuration of a frequency occupation indicator, e.g., a frequency domain resource subset indicator or a frequency domain measurement restriction, indicating the set B frequency occupation of the configured one or more CSI-RS resource(s) that the second device 132 may have to assume during inference. The set B frequency occupation may indicate the frequency units in which the one or more CSI-RS resource(s) may be received by the second device 132 during inference. It may be relevant that the first device 131 knows the set B frequency occupation of CSI-RS during inference such that the first device 131 may train the AI / ML model accordingly. The same set B frequency occupation indicator pattern may also be used for inference. At Step 101, in accordance with Action 905 and Action 705, the first network node 111 may transmit CSI-RSs spanning the full bandwidth. At Step 102, in accordance with Action 707, the first device 131 may train the AI / ML model assuming only a subset of the full bandwidth of CSI-RS resources are transmitted in each CSI-RS transmission occasion.

[0451] Figure 12 illustrates a non-limiting example of a high-level flowchart of the inference method associated with embodiments herein. In Figure 12, the first newtrok node 111 is depicted as a BS and the second device 132 as a UE. In Step 200, in accordance with Action 910, Action 803, Action 804 and Action 805, the first network node 111 may configure the first device 131 for inference of UE-sided CSI prediction for sparse frequency domain CSI-RS. At Step 201 , in accordance with Action 911 and Action 806, the first network node 111 may transmit CSI-RSs in a subset of the full bandwidth, that is, in a subset of all subbands. Which subbands may be transmitted may vary across different CSI-RS transmission occasions. At Step 202, in accordance with Action 807, the second device 132 may predict the CSI for the full bandwidth based the received CSI-RSs.

[0452] Certain embodiments disclosed herein may provide one or more of the following technical advantage(s), which may be summarized as follows.An advantage of embodiments herein may be understood to be that CSI-RS overhead may be reduced for large arrays at the TRPs, both for fully digital and hybrid beamforming architectures, which may increase spectral efficiency in the system, since saved time and / or frequency resource may be used for data.

[0453] Figure 13 depicts an example of the arrangement that the first device 131 may comprise to perform the method actions described above in relation to Figure 7 and / or any of Figures 11-12. The first device 131 is for handling the information pertaining to RSs. The first device 131 is configured to operate in the communications system 100.

[0454] Several embodiments are comprised herein. It should be noted that the examples herein are not mutually exclusive. One or more embodiments may be combined, where applicable. All possible combinations are not described to simplify the description. Components from one embodiment may be tacitly assumed to be present in another embodiment and it will be obvious to a person skilled in the art how those components may be used in the other exemplary embodiments. The detailed description of some of the following corresponds to the same references provided above, in relation to the actions described for the first device 131 and will thus not be repeated here. For example, the MLM may configured to be any of, e.g., a Neural Network, a Convolutional Neural Network, a Federated Learning MLM, an Autoencoder, Decision Tree, etc.

[0455] In Figure 13, optional units are indicated with dashed boxes.

[0456] The first device 131 is configured to perform the obtaining in Action 704, e.g. by means of a processing circuitry 1201 within the first device 131 configured to, obtain the first indication configured to indicate the first set of frequency resources out of the one or more frequency resources configured for reception of DL RSs, the second indication configured to indicate the second set of frequency resources out of the one or more frequency resources, and the third indication configured to indicate the a correspondence between the first set of frequency resources and the second set of frequency resources. The first set of frequency resources is configured to be larger than the second set of frequency resources.

[0457] The first device 131 is configured to perform the performing in Action 705, e.g. by means of the processing circuitry 1201 within the first device 131 configured to, perform, on the DL RSs, as configured to be transmitted by the first network node 111 configured to operate in the communications system 100, the one or more first measurements on the first set of frequency resources, and the one or more second measurements on the second set of frequency resources.

[0458] The first device 131 may be configured to perform the outputting in Action 706, e.g. by means of the processing circuitry 1201 within the first device 131 configured to, output the firstinformation configured to indicate: the one or more first measurements, the one or more second measurements, and the correspondence.

[0459] In some embodiments, the first device 131 may be configured to iterate the obtaining, the performing and the outputting for the plurality of respective second sets of frequency resources and, optionally, the corresponding plurality of correspondences between the respective second set of frequency resources and the first set of frequency resources.

[0460] In some embodiments, the first device 131 may be further configured with one or more of the following two configurations.

[0461] The first device 131 may be configured to perform the initiating in Action 707, e.g. by means of the processing circuitry 1201 within the first device 131 configured to, initiate training of the MLM, with the first information configured to be output for each respective iteration. The MLM may be configured to predict CSI of the channel between the first device 131 and the first network node 111. The prediction may be configured to be for the first set of frequency resources, based on the respective one or more second measurements on the second set of frequency resources.

[0462] The first device 131 may be configured to perform the initiating in Action 708, e.g. by means of the processing circuitry 1201 within the first device 131 configured to, initiate outputting the fourth indication of the trained MLM.

[0463] The first device 131 may be configured to perform the using in Action 709, e.g. by means of the processing circuitry 1201 within the first device 131 configured to, use the trained MLM to predict CSI of the channel between the first device 131 and the first network node 111 , or the second channel between the first device 131 and the third network node 113.

[0464] In some embodiments, during the training phase of the MLM, the one or more second measurements on the second set of frequency resources may be used as input to the MLM, and the one or more first measurements may be used as output labels of the MLM.

[0465] In some embodiments, the first device 131 may be further configured with one or more of the following three configurations.

[0466] The first device 131 may be configured to perform the providing in Action 701, e.g. by means of the processing circuitry 1201 within the first device 131 configured to, provide, to the first network node 111 , the previous indication configured to indicate the capability for the performance of measurements on the DL RSs.

[0467] The first device 131 may be configured to perform the obtaining in Action 702, e.g. by means of the processing circuitry 1201 within the first device 131 configured to, obtain, from the first network node 111 , the one or more configurations of the one or more frequency resources for reception of the DL RSs. The obtaining of the one or more configurations may be configured to be based on the previous indication configured to be provided.The first device 131 may be configured to perform the obtaining in Action 703, e.g. by means of the processing circuitry 1201 within the first device 131 configured to, obtain the second information to assist the first device 131 in training the MLM. The training of the MLM may be configured to be performed based on the second information configured to be obtained.

[0468] In some embodiments, the second information may be configured to comprise one or more of: a) the one or more codebooks the second device 132 may have to assume during the inference phase of the MLM or the respective MLM, b) the fifth indication of the one or more configurations of the report of the DL RSs that the second device 132 may have to assume during the inference phase, selected from: i) the subbands the second device 132 may have to report CSI for, ii) the subband size of the report, iii) the subband PM I reporting, iv) the subband CQI reporting, v) the wideband PM I reporting, and vi) wideband CQI reporting, c) the third information about how one or more beams of the one or more frequency resources for reception of the DL RSs may be spatially related to each other, and d) the sixth indication of the one or more conditions corresponding to the transmission of the DL RSs the second device 132 may have to assume during the inference phase upon receipt of the sixth indication.

[0469] In some embodiments, one or more of: i) the RSs may be configured to be CSI RSs, ii) the second set of frequency resources may be configured to be a subset of the first set of frequency resources, iii) the first information may be configured to be output to the second network node 112 configured to operate in the communications system 100, iv) the obtaining of the first indication and the second indication may be configured to be based on obtaining, from the first network node 111 , the respective second indication of the respective second sets of frequency resources, and v) the communications system 100 may be configured to be a wireless communications system 100.

[0470] The embodiments herein in the first device 131 may be implemented through one or more processors, such as a processing circuitry 1301 in the first device 131 depicted in Figure 13, together with computer program code for performing the functions and actions of the embodiments herein. A processor, as used herein, may be understood to be a hardware component. The program code mentioned above may also be provided as a computer program product, for instance in the form of a data carrier carrying computer program code for performing the embodiments herein when being loaded into the first device 131. One such carrier may be in the form of a CD ROM disc. It is however feasible with other data carriers such as a memory stick. The computer program code may furthermore be provided as pure program code on a server and downloaded to the first device 131.

[0471] The first device 131 may further comprise a memory 1302 comprising one or more memory units. The memory 1302 is arranged to be used to store obtained information, store data, configurations, schedulings, and applications etc. to perform the methods herein when being executed in the first device 131.In some embodiments, the first device 131 may receive information from, e.g., the first network node 111 , the second network node 112, the third network node 113, the second device 132, or another structure in the communications system 100, through a receiving port 1303. In some embodiments, the receiving port 1303 may be, for example, connected to one or more antennas in the first device 131. In other embodiments, the first device 131 may receive information from another structure in the communications system 100 through the receiving port 1303. Since the receiving port 1303 may be in communication with the processing circuitry 1301, the receiving port 1303 may then send the received information to the processing circuitry 1301. The receiving port 1303 may also be configured to receive other information.

[0472] The processing circuitry 1301 in the first device 131 may be further configured to transmit or send information to e.g., the first network node 111, the second network node 112, the third network node 113, the second device 132, or another structure in the communications system 100, through a sending port 1304, which may be in communication with the processing circuitry 1301, and the memory 1302.

[0473] Those skilled in the art will also appreciate that the processing circuitry 1301 described above may comprise a combination of analog and digital modules, and / or one or more processors configured with software and / or firmware, e.g., stored in memory, that, when executed by the one or more processors such as the processing circuitry 1301, perform as described above. One or more of these processors, as well as the other digital hardware, may be included in a single Application-Specific Integrated Circuit (ASIC), or several processors and various digital hardware may be distributed among several separate components, whether individually packaged or assembled into a System-on-a-Chip (SoC).

[0474] The processing circuitry 1301 may be configured to, or operable to, perform the method actions according to Figure 7 and / or any of Figures 11-12.

[0475] Also, in some embodiments, the first device 131 may be configured to perform the actions of Figure 7 and / or any of Figures 11-12 with respective units that may be implemented as one or more applications running on one or more processors such as the processing circuitry 1301.

[0476] Thus, the methods according to the embodiments described herein for the first device 131 may be respectively implemented by means of a computer program 1305 product, comprising instructions, i.e. , software code portions, which, when executed on at least one processing circuitry 1301 , cause the at least one processing circuitry 1301 to carry out the actions described herein, as performed by the first device 131. The computer program 1305 product may be stored on a computer-readable storage medium 1306. The computer-readable storage medium 1306, having stored thereon the computer program 1305, may comprise instructions which, when executed on at least one processing circuitry 1301, cause the at least one processing circuitry 1301 to carry out the actions described herein, as performed by the first device 131. In some embodiments, the computer-readable storage medium 1306 may be a non-transitory computer-readable storage medium, such as a CD ROM disc, or a memory stick. In other embodiments, the computer program 1305 product may be stored on a carrier containing the computer program 1305 just described, wherein the carrier is one of an electronic signal, optical signal, radio signal, or the computer-readable storage medium 1306, as described above.

[0477] The first device 131 may comprise a communication interface configured to facilitate communications between the first device 131 and other nodes or devices, e.g., the first network node 111, the second network node 112, the third network node 113, the second device 132, or another structure in the communications system 100. The interface may, for example, include a transceiver configured to transmit and receive radio signals over an air interface in accordance with a suitable standard.

[0478] In other embodiments, the first device 131 may also comprise a radio circuitry 1307, which may comprise e.g., the receiving port 1303 and the sending port 1304. The radio circuitry 1307 may be configured to set up and maintain at least a wireless connection with the first network node 111 , the second network node 112, the third network node 113, the second device 132, or another structure in the communications system 100. Circuitry may be understood herein as a hardware component.

[0479] Hence, embodiments herein also relate to the first device 131 comprising the processing circuitry 1301 and the memory 1302, said memory 1302 containing instructions executable by said processing circuitry 1301, whereby the first device 131 is operative to perform the actions described herein in relation to the first device 131, e.g., in Figure 7 and / or any of Figures 11-12.

[0480] Figure 14 depicts an example of the arrangement that the second device 132 may comprise to perform the method actions described above in relation to Figure 8 and / or any of Figures 11-12. The second device 132 is for handling the information pertaining to RSs. The second device 132 is configured to operate in the communications system 100.

[0481] Several embodiments are comprised herein. It should be noted that the examples herein are not mutually exclusive. One or more embodiments may be combined, where applicable. All possible combinations are not described to simplify the description. Components from one embodiment may be tacitly assumed to be present in another embodiment and it will be obvious to a person skilled in the art how those components may be used in the other exemplary embodiments. The detailed description of some of the following corresponds to the same references provided above, in relation to the actions described for the second device 132 and will thus not be repeated here. For example, the MLM may configured to be any of, e.g., a Neural Network, a Convolutional Neural Network, a Federated Learning MLM, an Autoencoder, Decision Tree, etc.

[0482] In Figure 14, optional units are indicated with dashed boxes.The second device 132 is configured to perform the obtaining in Action 805, e.g. by means of a processing circuitry 1301 within the second device 132 configured to, obtain the first first indication configured to indicate the first first set of frequency resources out of the one or more first frequency resources configured for reception of DL RSs, and the first second indication configured to indicate the first second set of frequency resources out of the one or more first frequency resources.

[0483] The second device 132 is configured to perform the obtaining in Action 806, e.g. by means of the processing circuitry 1301 within the second device 132 configured to, obtain the one or more first second measurements on the first second set of frequency resources on the DL RSs, as configured to be transmitted by the first network node 111 configured to operate in the communications system 100. The first first set of frequency resources is configured to be larger than the first second set of frequency resources.

[0484] The second device 132 is configured to perform the predicting in Action 807, e.g. by means of the processing circuitry 1301 within the second device 132 configured to, predict, using the first first information configured to indicate the one or more first second measurements as input to the trained MLM, CSI of the first channel between the second device 132 and the first network node 111. The prediction is configured to be for the first first set of frequency resources, and based on the respective one or more first second measurements on the first second set of frequency resources.

[0485] The second device 132 may be configured to perform the initiating in Action 808, e.g. by means of the processing circuitry 1301 within the second device 132 configured to, initiate outputting the seventh indication of the predicted CSI.

[0486] The second device 132 may be configured to perform the obtaining in Action 801, e.g. by means of the processing circuitry 1301 within the second device 132 configured to, obtain the trained MLM, from the first device 131 or the second network node 112 configured to operate in the communications system 100.

[0487] In some embodiments, the second device 132 may be configured with one or more of the following three configurations.

[0488] The second device 132 may be configured to perform the providing in Action 802, e.g. by means of the processing circuitry 1301 within the second device 132 configured to, provide, to the first network node 111 , the first previous indication configured to indicate the first capability for the performance of measurements on the DL RSs.

[0489] The second device 132 may be configured to perform the obtaining in Action 803, e.g. by means of the processing circuitry 1301 within the second device 132 configured to, obtain, from the first network node 111 , the one or more first configurations of the one or more first frequency resources for reception of the DL RSs. The obtaining of the one or more firstconfigurations may be configured to be based on the first previous indication configured to be provided.

[0490] The second device 132 may be configured to perform the obtaining in Action 804, e.g. by means of the processing circuitry 1301 within the second device 132 configured to, obtain first second information to be input by the second device 132 to the MLM for the predicting of the CSI.

[0491] In some embodiments, the first second information may be configured to comprise one or more of: a) the one or more codebooks the second device 132 may have to assume for the predicting of the CSI, b) the fifth indication of the one or more configurations of the report of the DL RSs that the second device 132 may have to assume for the predicting of the CSI, configured to be selected from: the subbands the second device 132 is to report CSI for, the subband size of the report, the subband PM I reporting, the subband CQI reporting, the wideband PMI reporting, and the wideband CQI reporting, c) the third information configured to be about how one or more beams of the one or more first frequency resources for reception of the DL RSs may be spatially related to each other, and d) the sixth indication of the one or more conditions corresponding to the transmission of the DL RSs the second device 132 may have to assume for the predicting of the CSI based on the receipt of the sixth indication.

[0492] In some embodiments, one or more of the following may apply: i) the RSs may be configured to be CSI RSs, ii) the first second set of frequency resources may be configured to be the subset of the first first set of frequency resources, iii) the obtaining of the first first indication and the first second indication, may be configured to be based on obtaining, from the first network node 111 , the respective first second indication of the first second set of frequency resources, iv) the predicting may be configured to be further based on the first correspondence between the first first set of frequency resources and the first second set of frequency resources, and v) the communications system 100 may be configured to be the wireless communications system 100.

[0493] The embodiments herein in the second device 132 may be implemented through one or more processors, such as a processing circuitry 1401 in the second device 132 depicted in Figure 14, together with computer program code for performing the functions and actions of the embodiments herein. A processor, as used herein, may be understood to be a hardware component. The program code mentioned above may also be provided as a computer program product, for instance in the form of a data carrier carrying computer program code for performing the embodiments herein when being loaded into the second device 132. One such carrier may be in the form of a CD ROM disc. It is however feasible with other data carriers such as a memory stick. The computer program code may furthermore be provided as pure program code on a server and downloaded to the second device 132.The second device 132 may further comprise a memory 1402 comprising one or more memory units. The memory 1402 is arranged to be used to store obtained information, store data, configurations, schedulings, and applications etc. to perform the methods herein when being executed in the second device 132.

[0494] In some embodiments, the second device 132 may receive information from, e.g., the first network node 111 , the second network node 112, the third network node 113, the first device 131, or another structure in the communications system 100, through a receiving port 1403. In some embodiments, the receiving port 1403 may be, for example, connected to one or more antennas in the second device 132. In other embodiments, the second device 132 may receive information from another structure in the communications system 100 through the receiving port 1403. Since the receiving port 1403 may be in communication with the processing circuitry 1401, the receiving port 1403 may then send the received information to the processing circuitry 1401. The receiving port 1403 may also be configured to receive other information.

[0495] The processing circuitry 1401 in the second device 132 may be further configured to transmit or send information to e.g., the network node 111 , the second network node 112, the third network node 113, the first device 131, or another structure in the communications system 100, through a sending port 1404, which may be in communication with the processing circuitry 1401, and the memory 1402.

[0496] Those skilled in the art will also appreciate that the processing circuitry 1401 described above may comprise a combination of analog and digital modules, and / or one or more processors configured with software and / or firmware, e.g., stored in memory, that, when executed by the one or more processors such as the processing circuitry 1401, perform as described above. One or more of these processors, as well as the other digital hardware, may be included in a single Application-Specific Integrated Circuit (ASIC), or several processors and various digital hardware may be distributed among several separate components, whether individually packaged or assembled into a System-on-a-Chip (SoC).

[0497] The processing circuitry 1401 may be configured to, or operable to, perform the method actions according to Figure 8 and / or any of Figures 11-12.

[0498] Also, in some embodiments, the second device 132 may be configured to perform the actions of Figure 8 and / or any of Figures 11-12 with respective units that may be implemented as one or more applications running on one or more processors such as the processing circuitry 1401.

[0499] Thus, the methods according to the embodiments described herein for the second device 132 may be respectively implemented by means of a computer program 1405 product, comprising instructions, i.e., software code portions, which, when executed on at least one processing circuitry 1401, cause the at least one processing circuitry 1401 to carry out the actions described herein, as performed by the second device 132. The computer program 1405product may be stored on a computer-readable storage medium 1406. The computer-readable storage medium 1406, having stored thereon the computer program 1405, may comprise instructions which, when executed on at least one processing circuitry 1401, cause the at least one processing circuitry 1401 to carry out the actions described herein, as performed by the second device 132. In some embodiments, the computer-readable storage medium 1406 may be a non-transitory computer-readable storage medium, such as a CD ROM disc, or a memory stick. In other embodiments, the computer program 1405 product may be stored on a carrier containing the computer program 1405 just described, wherein the carrier is one of an electronic signal, optical signal, radio signal, or the computer-readable storage medium 1406, as described above.

[0500] The second device 132 may comprise a communication interface configured to facilitate communications between the second device 132 and other nodes or devices, e.g., the network node 111, the second network node 112, the third network node 113, the first device 131, or another structure in the communications system 100. The interface may, for example, include a transceiver configured to transmit and receive radio signals over an air interface in accordance with a suitable standard.

[0501] In other embodiments, the second device 132 may also comprise a radio circuitry 1407, which may comprise e.g., the receiving port 1403 and the sending port 1404. The radio circuitry 1407 may be configured to set up and maintain at least a wireless connection with the network node 111, the second network node 112, the third network node 113, the first device 131, or another structure in the communications system 100. Circuitry may be understood herein as a hardware component.

[0502] Hence, embodiments herein also relate to the second device 132 comprising the processing circuitry 1401 and the memory 1402, said memory 1402 containing instructions executable by said processing circuitry 1401, whereby the second device 132 is operative to perform the actions described herein in relation to the second device 132, e.g., in Figure 8 and / or any of Figures 11-12.

[0503] Figure 15 depicts an example of the arrangement that the first network node 111 may comprise to perform the method actions described above in relation to Figure 9 and / or any of Figures 11-12. The first network node 111 is for handling the information pertaining to RSs. The first network node 111 is configured to operate in the communications system 100.

[0504] Several embodiments are comprised herein. It should be noted that the examples herein are not mutually exclusive. One or more embodiments may be combined, where applicable. All possible combinations are not described to simplify the description. Components from one embodiment may be tacitly assumed to be present in another embodiment and it will be obvious to a person skilled in the art how those components may be used in the other exemplaryembodiments. The detailed description of some of the following corresponds to the same references provided above, in relation to the actions described for the first network node 111 and will thus not be repeated here. For example, the MLM may configured to be any of, e.g., a Neural Network, a Convolutional Neural Network, a Federated Learning MLM, an Autoencoder, Decision Tree, etc.

[0505] In Figure 15, optional units are indicated with dashed boxes.

[0506] The first network node 111 is configured to perform the providing in Action 910, e.g. by means of a processing circuitry 1401 within the first network node 111 configured to, provide the first first indication configured to indicate the first first set of frequency resources out of the one or more first frequency resources configured for reception of DL RSs, at the second device 132 configured to operate in the communications system 100, and the first second indication configured to indicate the first second set of frequency resources out of the one or more first frequency resources. The first first set of frequency resources is configured to be larger than the first second set of frequency resources.

[0507] The first network node 111 is configured to perform the transmitting in Action 911 , e.g. by means of the processing circuitry 1401 within the first network node 111 configured to, transmit the DL RSs on the first second set of frequency resources to the second device 132.

[0508] The first network node 111 may be configured to perform the receiving in Action 912, e.g. by means of the processing circuitry 1401 within the first network node 111 configured to, receive, from the second device 132, the seventh indication of the predicted CSI of the first channel between the second device 132 and the first network node 111. The prediction is configured to be for the first first set of frequency resources, and based on the respective one or more first second measurements configured to be performed by the second device 132 on the first second set of frequency resources, and, optionally further configured to be based on the first correspondence between the first first set of frequency resources and the first second set of frequency resources.

[0509] In some embodiments, the first network node 111 may be further configured with one or more of the following two configurations.

[0510] The first network node 111 may be configured to perform the providing in Action 904, e.g. by means of the processing circuitry 1401 within the first network node 111 configured to, provide, to the first device 131 configured to operate in the communications system 100, the first indication configured to indicate the first set of frequency resources out of the one or more frequency resources configured for reception of the DL RSs, by the first device 131, and the second indication configured to indicate the second set of frequency resources out of the one or more frequency resources, and, optionally, the third indication configured to indicate the correspondence between the first set of frequency resources and the second set of frequency resources.The first network node 111 may be configured to perform the transmitting in Action 905, e.g. by means of the processing circuitry 1401 within the first network node 111 configured to, transmit the DL RSs to the first device 131, on the first set of frequency resources, and on the second set of frequency resources.

[0511] The first network node 111 may be configured to perform the receiving in Action 906, e.g. by means of the processing circuitry 1401 within the first network node 111 configured to, receive, from the first device 131, the first information configured to indicate: i) the one or more first measurements on the first set of frequency resources, ii) the one or more second measurements on the second set of frequency resources, and optionally, the correspondence.

[0512] In some embodiments, the providing of the first indication, the second indication and the third indication, the transmitting of the DL RSs, and the receiving of the first information may be configured to be iterated for the plurality of respective second sets of frequency resources and, optionally, the corresponding plurality of correspondences between the respective second set of frequency resources and the first set of frequency resources.

[0513] In some embodiments, the first network node 111 may be further configured with one or more of the following two configurations.

[0514] The first network node 111 may be configured to perform the initiating in Action 907, e.g. by means of the processing circuitry 1401 within the first network node 111 configured to, initiate training of the MLM with the first information configured to be received for each respective iteration. The MLM may be configured to be to predict CSI of the channel between the first device 131 and the first network node 111. The prediction may be configured to be for the first set of frequency resources, based on the respective one or more second measurements on the second set of frequency resources.

[0515] The first network node 111 may be configured to perform the initiating in Action 908, e.g. by means of the processing circuitry 1401 within the first network node 111 configured to, initiate outputting the fourth indication of the trained MLM.

[0516] The first network node 111 may be configured to perform the using in Action 909, e.g. by means of the processing circuitry 1401 within the first network node 111 configured to, use the trained MLM to predict CSI of the channel between the first device 131 and the first network node 111 , or the second channel between the first device 131 and the third network node 113.

[0517] In some embodiments, during the training phase of the MLM, the one or more second measurements on the second set of frequency resources may be configured to be used as input to the MLM, and the one or more first measurements may be configured to be used as output labels of the MLM.

[0518] In some embodiments, the first network node 111 may be further configured with one or more of the following three configurations.The first network node 111 may be configured to perform the obtaining in Action 901 , e.g. by means of the processing circuitry 1401 within the first network node 111 configured to, obtain, from the first device 131, the previous indication configured to indicate the capability for the performance of measurements on the DL RSs.

[0519] The first network node 111 may be configured to perform the providing in Action 902, e.g. by means of the processing circuitry 1401 within the first network node 111 configured to, provide, to the first device 131, the one or more configurations of the one or more frequency resources for reception of the DL RSs. The providing of the one or more configurations may be configured to be based on the previous indication configured to be obtained.

[0520] The first network node 111 may be configured to perform the providing in Action 903, e.g. by means of the processing circuitry 1401 within the first network node 111 configured to, provide, to the first device 131, the second information configured to assist the first device 131 in training the respective MLM, to predict CSI of the channel between the first device 131 and the first network node 111. The prediction may be for the first set of frequency resources, based on respective one or more second measurements on the second set of frequency resources. The training of the respective MLM may be configured to be performed based on the second information configured to be provided.

[0521] In some embodiments, the second information may be configured to comprise one or more of: a) the one or more codebooks the second device 132 may have to assume during the inference phase of the respective MLM, b) the fifth indication of the one or more configurations of the report of the DL RSs that the second device 132 may have to assume during the inference phase, selected from: i) subbands the second device 132 may have to report CSI for, ii) subband size of the report, iii) subband PMI reporting, iv) subband CQI reporting, v) wideband PMI reporting, and vi) wideband CQI reporting, c) the third information configured to be about how one or more beams of the one or more frequency resources for reception of the DL RSs may be configured to be spatially related to each other, and d) the sixth indication of the one or more conditions configured to correspond to the transmission of the DL RSs the second device 132 may have to assume during the inference phase upon receipt of the sixth indication.

[0522] In some embodiments, one or more of the following may apply: the RSs may be configured to be CSI RSs, the first second set of frequency resources may be configured to be the subset of the first set of frequency resources, and the communications system 100 may be configured to be a wireless communications system 100.

[0523] The embodiments herein in the first network node 111 may be implemented through one or more processors, such as a processing circuitry 1501 in the first network node 111 depicted in Figure 15, together with computer program code for performing the functions and actions of the embodiments herein. A processor, as used herein, may be understood to be a hardware component. The program code mentioned above may also be provided as a computerprogram product, for instance in the form of a data carrier carrying computer program code for performing the embodiments herein when being loaded into the first network node 111. One such carrier may be in the form of a CD ROM disc. It is however feasible with other data carriers such as a memory stick. The computer program code may furthermore be provided as pure program code on a server and downloaded to the first network node 111.

[0524] The first network node 111 may further comprise a memory 1502 comprising one or more memory units. The memory 1502 is arranged to be used to store obtained information, store data, configurations, schedulings, and applications etc. to perform the methods herein when being executed in the first network node 111.

[0525] In some embodiments, the first network node 111 may receive information from, e.g., the second network node 112, the third network node 113, the first device 131, the second device 132, or another structure in the communications system 100, through a receiving port 1503. In some embodiments, the receiving port 1503 may be, for example, connected to one or more antennas in the first network node 111. In other embodiments, the first network node 111 may receive information from another structure in the communications system 100 through the receiving port 1503. Since the receiving port 1503 may be in communication with the processing circuitry 1501, the receiving port 1503 may then send the received information to the processing circuitry 1501. The receiving port 1503 may also be configured to receive other information.

[0526] The processing circuitry 1501 in the first network node 111 may be further configured to transmit or send information to e.g., the second network node 112, the third network node 113, the first device 131, the second device 132, or another structure in the communications system 100, through a sending port 1504, which may be in communication with the processing circuitry 1501, and the memory 1502.

[0527] Those skilled in the art will also appreciate that the processing circuitry 1501 described above may comprise a combination of analog and digital modules, and / or one or more processors configured with software and / or firmware, e.g., stored in memory, that, when executed by the one or more processors such as the processing circuitry 1501, perform as described above. One or more of these processors, as well as the other digital hardware, may be included in a single Application-Specific Integrated Circuit (ASIC), or several processors and various digital hardware may be distributed among several separate components, whether individually packaged or assembled into a System-on-a-Chip (SoC).

[0528] The processing circuitry 1501 may be configured to, or operable to, perform the method actions according to Figure 9 and / or any of Figures 11-12.

[0529] Also, in some embodiments, the first network node 111 may be configured to perform the actions of Figure 9 and / or any of Figures 11-12 with respective units that may be implemented as one or more applications running on one or more processors such as the processing circuitry 1501.Thus, the methods according to the embodiments described herein for the first network node 111 may be respectively implemented by means of a computer program 1505 product, comprising instructions, i.e., software code portions, which, when executed on at least one processing circuitry 1501, cause the at least one processing circuitry 1501 to carry out the actions described herein, as performed by the first network node 111. The computer program 1505 product may be stored on a computer-readable storage medium 1506. The computer-readable storage medium 1506, having stored thereon the computer program 1505, may comprise instructions which, when executed on at least one processing circuitry 1501, cause the at least one processing circuitry 1501 to carry out the actions described herein, as performed by the first network node 111. In some embodiments, the computer-readable storage medium 1506 may be a non-transitory computer-readable storage medium, such as a CD ROM disc, or a memory stick. In other embodiments, the computer program 1505 product may be stored on a carrier containing the computer program 1505 just described, wherein the carrier is one of an electronic signal, optical signal, radio signal, or the computer-readable storage medium 1506, as described above.

[0530] The first network node 111 may comprise a communication interface configured to facilitate communications between the first network node 111 and other nodes or devices, e.g., the second network node 112, the third network node 113, the first device 131, the second device 132, or another structure in the communications system 100. The interface may, for example, include a transceiver configured to transmit and receive radio signals over an air interface in accordance with a suitable standard.

[0531] In other embodiments, the first network node 111 may also comprise a radio circuitry 1507, which may comprise e.g., the receiving port 1503 and the sending port 1504. The radio circuitry 1507 may be configured to set up and maintain at least a wireless connection with the second network node 112, the third network node 113, the first device 131, the second device 132, or another structure in the communications system 100. Circuitry may be understood herein as a hardware component.

[0532] Hence, embodiments herein also relate to the first network node 111 comprising the processing circuitry 1501 and the memory 1502, said memory 1502 containing instructions executable by said processing circuitry 1501 , whereby the first network node 111 is operative to perform the actions described herein in relation to the first network node 111, e.g., in Figure 9 and / or any of Figures 11-12.

[0533] Figure 16 depicts an example of the arrangement that the second network node 112 may comprise to perform the method actions described above in relation to Figure 10 and / or any of Figures 11-12. The second network node 112 is for handling the information pertaining to theRSs. The second network node 112 is configured to operate via the communications system 100.

[0534] Several embodiments are comprised herein. It should be noted that the examples herein are not mutually exclusive. One or more embodiments may be combined, where applicable. All possible combinations are not described to simplify the description. Components from one embodiment may be tacitly assumed to be present in another embodiment and it will be obvious to a person skilled in the art how those components may be used in the other exemplary embodiments. The detailed description of some of the following corresponds to the same references provided above, in relation to the actions described for the second network node 112 and will thus not be repeated here. For example, the MLM may configured to be any of, e.g., a Neural Network, a Convolutional Neural Network, a Federated Learning MLM, an Autoencoder, Decision Tree, etc.

[0535] In Figure 16, optional units are indicated with dashed boxes.

[0536] The second network node 112 is configured to perform the obtaining in Action 1002, e.g. by means of the processing circuitry 1501 within the second network node 112 configured to, obtain the first information from the first device 131 configured to indicate: i) the one or more first measurements on DL RSs configured to be transmitted by the first network node 111 configured to operate in a communications system 100, on the first set of frequency resources out of the one or more frequency resources configured for reception of the DL RSs, at the first device 131, ii) the one or more second measurements of the DL RSs, on the second set of frequency resources, out of the one or more frequency resources, wherein the first set of frequency resources is configured to be larger than the second set of frequency resources, and iii) the correspondence between the first set of frequency resources and the second set of frequency resources.

[0537] In some embodiments, the second network node 112 may be configured to iterate the obtaining for the plurality of respective second sets of frequency resources and, optionally, the corresponding plurality of correspondences between the respective second set of frequency resources and the first set of frequency resources.

[0538] In some embodiments, the second network node 112 may be further configured with one or more of the following two configurations.

[0539] The second network node 112 may be configured to perform the initiating in Action 1003, e.g. by means of the processing circuitry 1501 within the second network node 112 configured to, initiate training of the MLM, with the first information configured to be obtained for each respective iteration. The MLM is configured to predict CSI of the channel between the first device 131 and the first network node 111. The prediction is configured to be for the first set of frequency resources, based on the respective one or more second measurements on the second set of frequency resources.The second network node 112 may be configured to perform the initiating in Action 1004, e.g. by means of a processing circuitry 1501 within the second network node 112 configured to, initiate outputting the fourth indication of the trained MLM.

[0540] The second network node 112 may be configured to perform the using in Action 1005, e.g. by means of the processing circuitry 1501 within the second network node 112 configured to, use the trained MLM to predict CSI of the channel between the first device 131 and the first network node 111 , or the second channel between the first device 131 and the third network node 113.

[0541] In some embodiments, during the training phase of the MLM, the one or more second measurements on the second set of frequency resources may be configured to be used as input to the MLM, and the one or more first measurements may be configured to be used as output labels of the MLM.

[0542] The second network node 112 may be configured to perform the obtaining in Action 1001 , e.g. by means of the processing circuitry 1501 within the second network node 112 configured to, obtain the second information to assist the second network node 112 in training the MLM. The training of the MLM may be configured to be performed based on the second information configured to be obtained.

[0543] In some embodiments, the second information may be configured to comprise one or more of: a) the one or more codebooks the second device 132 may have to assume during the inference phase of the MLM, b) the fifth indication of the one or more configurations of the report of the DL RSs that the second device 132 may have to assume during the inference phase, configured to be selected from: i) subbands the second device 132 may have to report CSI for, ii) subband size of the report, iii) subband PM I reporting, iv) subband CQI reporting, v) wideband PMI reporting, and vi) wideband CQI reporting, c) the third information configured to be about how one or more beams of the one or more frequency resources for reception of the DL RSs may be configured to be spatially related to each other, and d) the sixth indication of the one or more conditions configured to correspond to the transmission of the DL RSs the second device 132 may have to assume during the inference phase upon receipt of the sixth indication.

[0544] In some embodiments, one or more of the following may apply: i) the RSs may be configured to be CSI RSs, ii) the second set of frequency resources may be configured to be a subset of the first set of frequency resources, and iii) the communications system 100 may be configured to be a wireless communications system 100.

[0545] The embodiments herein in the second network node 112 may be implemented through one or more processors, such as a processing circuitry 1601 in the second network node 112 depicted in Figure 16, together with computer program code for performing the functions and actions of the embodiments herein. A processor, as used herein, may be understood to be a hardware component. The program code mentioned above may also be provided as a computerprogram product, for instance in the form of a data carrier carrying computer program code for performing the embodiments herein when being loaded into the second network node 112. One such carrier may be in the form of a CD ROM disc. It is however feasible with other data carriers such as a memory stick. The computer program code may furthermore be provided as pure program code on a server and downloaded to the second network node 112.

[0546] The second network node 112 may further comprise a memory 1602 comprising one or more memory units. The memory 1602 is arranged to be used to store obtained information, store data, configurations, schedulings, and applications etc. to perform the methods herein when being executed in the second network node 112.

[0547] In some embodiments, the second network node 112 may receive information from, e.g., the first network node 111, the third network node 113, the first device 131, the second device 132, or another structure in the communications system 100, through a receiving port 1603. In some embodiments, the receiving port 1603 may be, for example, connected to one or more antennas in the second network node 112. In other embodiments, the second network node 112 may receive information from another structure in the communications system 100 through the receiving port 1603. Since the receiving port 1603 may be in communication with the processing circuitry 1601, the receiving port 1603 may then send the received information to the processing circuitry 1601. The receiving port 1603 may also be configured to receive other information.

[0548] The processing circuitry 1601 in the second network node 112 may be further configured to transmit or send information to e.g., the first network node 111, the third network node 113, the first device 131, the second device 132, or another structure in the communications system 100, through a sending port 1604, which may be in communication with the processing circuitry 1601, and the memory 1602.

[0549] Those skilled in the art will also appreciate that the processing circuitry 1601 described above may comprise a combination of analog and digital modules, and / or one or more processors configured with software and / or firmware, e.g., stored in memory, that, when executed by the one or more processors such as the processing circuitry 1601, perform as described above. One or more of these processors, as well as the other digital hardware, may be included in a single Application-Specific Integrated Circuit (ASIC), or several processors and various digital hardware may be distributed among several separate components, whether individually packaged or assembled into a System-on-a-Chip (SoC).

[0550] The processing circuitry 1601 may be configured to, or operable to, perform the method actions according to Figure 10 and / or any of Figures 11-12.

[0551] Also, in some embodiments, the second network node 112 may be configured to perform the actions of Figure 10 and / or any of Figures 11-12 with respective units or modules that may be implemented as one or more applications running on one or more processors such as the processing circuitry 1601.Thus, the methods according to the embodiments described herein for the second network node 112 may be respectively implemented by means of a computer program 1605 product, comprising instructions, i.e., software code portions, which, when executed on at least one processing circuitry 1601 , cause the at least one processing circuitry 1601 to carry out the actions described herein, as performed by the second network node 112. The computer program 1605 product may be stored on a computer-readable storage medium 1606. The computer-readable storage medium 1606, having stored thereon the computer program 1605, may comprise instructions which, when executed on at least one processing circuitry 1601, cause the at least one processing circuitry 1601 to carry out the actions described herein, as performed by the second network node 112. In some embodiments, the computer-readable storage medium 1606 may be a non-transitory computer-readable storage medium, such as a CD ROM disc, or a memory stick. In other embodiments, the computer program 1605 product may be stored on a carrier containing the computer program 1605 just described, wherein the carrier is one of an electronic signal, optical signal, radio signal, or the computer-readable storage medium 1606, as described above.

[0552] The second network node 112 may comprise a communication interface configured to facilitate communications between the second network node 112 and other nodes or devices, e.g., the first network node 111, the third network node 113, the first device 131, the second device 132, or another structure in the communications system 100. The interface may, for example, include a transceiver configured to transmit and receive radio signals over an air interface in accordance with a suitable standard.

[0553] In other embodiments, the second network node 112 may also comprise a radio circuitry 1607, which may comprise e.g., the receiving port 1603 and the sending port 1604. The radio circuitry 1607 may be configured to set up and maintain at least a wireless connection with the first network node 111, the third network node 113, the first device 131, the second device 132, or another structure in the communications system 100. Circuitry may be understood herein as a hardware component.

[0554] Hence, embodiments herein also relate to the second network node 112 comprising the processing circuitry 1601 and the memory 1602, said memory 1602 containing instructions executable by said processing circuitry 1601, whereby the second network node 112 is operative to perform the actions described herein in relation to the second network node 112, e.g., in Figure 10 and / or any of Figures 11-12.

[0555] Generally, all terms used herein are to be interpreted according to their ordinary meaning in the relevant technical field, unless a different meaning is clearly given and / or is implied from the context in which it is used. All references to a / an / the element, apparatus, component, means, step, etc. are to be interpreted openly as referring to at least one instance of the element,apparatus, component, means, step, etc., unless explicitly stated otherwise. The steps of any methods disclosed herein do not have to be performed in the exact order disclosed, unless a step is explicitly described as following or preceding another step and / or where it is implicit that a step must follow or precede another step. Any feature of any of the embodiments disclosed herein may be applied to any other embodiment, wherever appropriate. Likewise, any advantage of any of the embodiments may apply to any other embodiments, and vice versa. Other objectives, features and advantages of the enclosed embodiments will be apparent from the following description.

[0556] As used herein, the expression “at least one of:” followed by a list of alternatives separated by commas, and wherein the last alternative is preceded by the “and” term, may be understood to mean that only one of the list of alternatives may apply, more than one of the list of alternatives may apply or all of the list of alternatives may apply. This expression may be understood to be equivalent to the expression “at least one of:” followed by a list of alternatives separated by commas, and wherein the last alternative is preceded by the “or” term.

[0557] EXAMPLES related to embodiments herein

[0558] The following are examples related to embodiments herein. Any of the features described in relation to Figures 16-19 may be combined with the actions of the examples related to embodiments herein, described in relation to 1-15.

[0559] The first device 131 embodiments relate to Figure 7, any of Figures 11-13, and Figures 21-23.

[0560] A computer-implemented method, performed by a device, such as the first device 131 is described herein. The method may be understood to be for handling information pertaining to Reference Signals (RSs). The first device 131 may operate in a communications system, such as the communications system 100.

[0561] In some embodiments, the communications system 100 may support New Radio (NR). The method may comprise one or more of the following actions. In some embodiments, all the actions may be performed. In some examples, Action 704, Action 705 and Action 706 may be performed. One or more embodiments may be combined, where applicable.

[0562] Components from one embodiment may be tacitly assumed to be present in another embodiment and it will be obvious to a person skilled in the art how those components may be used in the other exemplary embodiments. All possible combinations are not described to simplify the description. A non-limiting example of the method performed by the first device 131 is depicted in Figure 7. In Figure 7, optional actions in some embodiments may be represented with dashed lines. In some embodiments, the actions may be performed in a different order than that depicted Figure 7.o Obtaining 704 a first indication and a second indication. The first device 131 may be configured to perform the obtaining in this Action 704.

[0563] The first indication may indicate a first set of frequency resources out of one or more frequency resources configured for reception of downlink (DL) RSs. The one or more frequency resources may be configured for reception of the DL RSs at the first device 131. The first set of frequency resources may be also referred to in this document as “set A of frequency resources”, or first frequency domain resource mapping pattern.

[0564] The second indication may indicate a second set of frequency resources out of the one or more frequency resources. The second set of frequency resources may be also referred to in this document as “set B of frequency resources”, or second frequency domain resource mapping pattern.

[0565] In some examples, the obtaining in this Action 704 may optionally comprise obtaining a third indication. The third indication may indicate a correspondence between the first set of frequency resources and the second set of frequency resources.

[0566] The RSs may be CSI-RSs.

[0567] The second set of frequency resources may be a subset of the first set of frequency resources.

[0568] The second set of frequency resources may be different than the first set of frequency resources.

[0569] Obtaining in this Action 704 may comprise receiving, retrieving, fetching or deriving. o Performing 705 one or more first measurements and one or more second measurements. The first device 131 may be configured to perform the performing in this Action 705.

[0570] The first device 131, in this Action 705, may perform, on the DL RSs, as transmitted by the first network node 111 operating in a communications system 100:

[0571] i. the one or more first measurements on the first set of frequency resources, and ii. the one or more second measurements on the second set of frequency resources. The one or more first measurements and the one or more second measurements may be performed within a time period, e.g., close in time.

[0572] o Outputting 706 first information. The first device 131 may be configured to perform the outputting in this Action 706.

[0573] The first information may indicate:

[0574] i. the one or more first measurements,

[0575] ii. the one or more second measurements, and

[0576] iii. optionally, the correspondence.

[0577] Outputting may comprise, in some examples, sending, e.g., to the first network node 111.In some embodiments, the method may be iterated for a plurality of respective second sets of frequency resources and, optionally, a corresponding plurality of correspondences between the respective second set of frequency resources and the first set of frequency resources.

[0578] The iteration of the method may comprise the iteration of the actions described this far, 704, 705, 706.

[0579] In some embodiments, the method may further comprise one or more of the following two actions:

[0580] o Initiating 707 training of a machine learning model, MLM. The first device 131 may be configured to perform the initiating in this Action 707.

[0581] Initiating may comprise starting itself, or triggering or enabling that another entity, e.g., the first network node 111 or the second network node 112 may perform the training of the MLM.

[0582] The MLM may be any of, e.g., a Neural Network, a Convolutional Neural Network, a Federated Learning MLM, an Autoencoder, Decision Tree, etc.

[0583] The training of the MLM may be with the output first information for each respective iteration.

[0584] The MLM may be to predict CSI of a channel, e.g., between the first device 131 and the first network node 111. The prediction may be for the first set of frequency resources, based on the respective one or more second measurements on the second set of frequency resources.

[0585] During a training phase of the MLM, the one or more second measurements on the second set of frequency resources may be used as input to the MLM, and the one or more first measurements may be used as output labels of the MLM.

[0586] o Initiating 708 outputting a fourth indication. The first device 131 may be configured to perform the initiating in this Action 708.

[0587] The fourth indication may be of the trained MLM.

[0588] In some embodiments, the method may further comprise the following action:

[0589] o Using 709 the trained MLM. The first device 131 may be configured to perform the using in this Action 709.

[0590] The using in this Action 709 may be, e.g., to predict CSI, of the channel between the first device 131 and the first network node 111 , or a second channel between the first device 131 and third network node 113.

[0591] In some embodiments, the method may further comprise one or more of the following three actions:

[0592] o Providing 701 a previous indication. The first device 131 may be configured to perform the providing in this Action 701.

[0593] The providing in this Action 701 may be to the first network node 111. The previous indication may indicate a capability for the performance of measurements on the DL RSs.o Obtaining 702 one or more configurations. The first device 131 may be configured to perform the obtaining in this Action 702.

[0594] The obtaining in this Action 702 may be from the first network node 111.

[0595] The one or more configurations may be of the one or more frequency resources for reception of the DL RSs.

[0596] The obtaining in this Action 702 of the one or more configurations may be based on the provided previous indication

[0597] In some embodiments, e.g., the first set of frequency resources may be identical to a frequency resource configuration of the DL RSs comprised in the one or more configurations.

[0598] o Obtaining 703 second information. The first device 131 may be configured to perform the obtaining in this Action 703.

[0599] The obtaining in this Action 703 may be from the first network node 111.

[0600] The second information may be to assist the first device 131 in training the MLM. The training of the MLM may be performed based on the obtained second information.

[0601] The second information may comprise one or more of:

[0602] - one or more codebooks a second device 132 may have to assume during an inference phase of the MLM,

[0603] - a fifth indication of one or more configurations of a report of the DL RSs that the second device 132 may have to assume during the inference phase, selected from:

[0604] i. subbands the second device 132 may have to report CSI for,

[0605] ii. subband size of the report,

[0606] iii. subband Precoder Matrix Indicator (PMI) reporting,

[0607] iv. subband Channel Quality Information (CQI) reporting, v. wideband PMI reporting,

[0608] vi. wideband CQI reporting

[0609] - third information about how one or more beams of the one or more frequency resources for reception of the DL RSs may be spatially related to each other, and - a sixth indication of one or more conditions corresponding to the transmission of the DL RSs the second device 132 may have to assume during the inference phase upon receipt of the sixth indication.

[0610] In some embodiments, one or more of the following may apply:

[0611] i. the RSs may be CSI-RSs,

[0612] ii. the first set of frequency resources may be larger than the second set of frequency resources,

[0613] iii. the second set of frequency resources may be a subset of the first set of frequency resources,iv. the first information may be output to the second network node 112 operating in the communications system 100,

[0614] v. the obtaining in Action 704 of the first indication and the second indication, may be based on obtaining, from the first network node 111, a respective second indication of the respective second sets of frequency resources, and

[0615] vi. the communications system 100 may be a wireless communications system 100.

[0616] The first device 131 may be a device that may collect data to use as input to the MLM during a training phase of the MLM. In some examples, the first device 131 may train the MLM itself.

[0617] In Figure 13, optional units are indicated with dashed boxes.

[0618] The first device 131 may comprise an arrangement as shown in Figure 13 or in Figure 23.

[0619] The second device 132 embodiments relate to Figure 8, any of Figures 11-13, Figure 14 and Figures 21-23.

[0620] A computer-implemented method, performed by a device, such as the second device 132 is described herein. The method may be understood to be for handling information pertaining to RSs. The second device 132 may operate in a communications system, such as the communications system 100.

[0621] In some embodiments, the communications system 100 may support New Radio (NR). The method may comprise one or more of the following actions. In some embodiments, all the actions may be performed. In some examples, Action 805, Action 806, Action 807, and Action 808 may be performed. One or more embodiments may be combined, where applicable. Components from one embodiment may be tacitly assumed to be present in another embodiment and it will be obvious to a person skilled in the art how those components may be used in the other exemplary embodiments. All possible combinations are not described to simplify the description. A non-limiting example of the method performed by the second device 132 is depicted in Figure 8. In Figure 8, optional actions in some embodiments may be represented with dashed lines. In some embodiments, the actions may be performed in a different order than that depicted Figure 8.

[0622] The detailed description of some of the following corresponds to the same references provided above, in relation to the actions described for the first device 131 and will thus not be repeated here to simplify the description. For example, the MLM may be any of, e.g., a Neural Network, a Convolutional Neural Network, a Federated Learning MLM, an Autoencoder, Decision Tree, etc.The second device 132 may be a device that may perform inference with the MLM, once trained. The second device 132 may use similar input data to the MLM as the first measurements, using new or fresh data or measurements.

[0623] o Obtaining 805 a first first indication and a first second indication. The second device 132 may be configured to perform the obtaining in this Action 805.

[0624] The first first indication may indicate a first first set of frequency resources out of one or more first frequency resources configured for reception of downlink (DL) RSs. The one or more frequency resources may be configured for reception of the DL RSs at the second device 132. The first first set of frequency resources may be also referred to in this document as “set A of frequency resources”, or first frequency domain resource mapping pattern.

[0625] The first second indication may indicate a first second set of frequency resources out of the one or more first frequency resources. The second set of frequency resources may be also referred to in this document as “set B of frequency resources”, or second frequency domain resource mapping pattern.

[0626] The RSs may be CSI-RSs.

[0627] The first first set of frequency resources may be larger than the first second set of frequency resources,

[0628] The first second set of frequency resources may be a subset of the first set of frequency resources.

[0629] The second set of frequency resources may be different than the first set of frequency resources.

[0630] Obtaining in this Action 704 may comprise receiving, retrieving, fetching or deriving. o Obtaining 806 one or more first second measurements. The second device 132 may be configured to perform the obtaining in this Action 806.

[0631] The second device 132, in this Action 806, may obtain, e.g., perform, the one or more first second measurements on the first second set of frequency resources on the DL RSs, as transmitted, e.g., by the first network node 111 operating in a communications system 100. o Predicting 807 CSI. The second device 132 may be configured to perform the predicting in this Action 807.

[0632] The CSI may be of a first channel between the second device 132 and, e.g., the first network node 111, or another network node.

[0633] The predicting in this Action 807 may be using first first information.

[0634] The first first information may indicate the one or more first second measurements as input to the trained MLM,

[0635] The prediction may be for the first first set of frequency resources.

[0636] The prediction may be based on the respective one or more first second measurements on the first second set of frequency resources.The prediction may be further based on a first correspondence between the first first set of frequency resources and the first second set of frequency resources.

[0637] o Initiating 808 outputting a seventh indication. The second device 132 may be configured to perform the initiating in this Action 808.

[0638] Initiating may comprise starting or triggering. Outputting may comprise, e.g., sending, the seventh indication.

[0639] The seventh indication may be of the predicted CSI. The seventh indication may be a result of the inference using the MLM.

[0640] In some embodiments, the method may further comprise one or more of the following actions:

[0641] o Obtaining 801 the trained MLM. The second device 132 may be configured to perform the obtaining in this Action 801.

[0642] The obtaining in this Action 801 may be, e.g., from the first device 131 or the second network node 112 operating in the communications network 100.

[0643] In some embodiments, the method may further comprise one or more of the following three actions:

[0644] o Providing 802 a first previous indication. The second device 132 may be configured to perform the providing in this Action 802.

[0645] The providing in this Action 802 of the first previous indication may be to the first network node 111.

[0646] The first previous indication may indicate a first capability for the performance of measurements on the DL RSs.

[0647] o Obtaining 803 one or more first configurations. The second device 132 may be configured to perform the obtaining in this Action 803.

[0648] The obtaining in this Action 803 may be from the first network node 111.

[0649] The one or more first configurations may be of the one or more frequency resources for reception of the DL RSs.

[0650] The obtaining in this Action 803 of the one or more first configurations may be based on the provided first previous indication.

[0651] In some embodiments, e.g., the first first set of frequency resources may be identical to a frequency resource first configuration of the DL RSs comprised in the one or more first configurations.

[0652] o Obtaining 804 first second information. The second device 132 may be configured to perform the obtaining in this Action 804.

[0653] The obtaining in this Action 804 may be from the first network node 111.

[0654] The first second information may be to be input by the second node 132 to the MLM for the predicting in Action 805 of the CSI.The first second information may comprise one or more of:

[0655] - the one or more codebooks the second device 132 may have to assume for the predicting in Action 805 of the CSI,

[0656] - the fifth indication of the one or more configurations of the report of the DL RSs that the second device 132 may have to assume for the predicting in Action 805 of the CSI, selected from:

[0657] i. the subbands the second device 132 may have to report CSI for, ii. the subband size of the report,

[0658] iii. the subband PMI reporting,

[0659] iv. the subband CQI reporting,

[0660] v. the wideband PMI reporting,

[0661] vi. the wideband CQI reporting

[0662] - the third information about how the one or more beams of the one or more frequency resources for reception of the DL RSs may be spatially related to each other, and

[0663] - the sixth indication of the one or more conditions corresponding to the transmission of the DL RSs the second device 132 may have to assume for the predicting in Action 805 of the CSI based on the receipt of the sixth indication. In some embodiments, one or more of the following may apply:

[0664] i. the RSs may be CSI-RSs,

[0665] ii. the first first set of frequency resources may be larger than the first second set of frequency resources,

[0666] iii. the first second set of frequency resources may be a subset of the first first set of frequency resources,

[0667] iv. the obtaining in Action 805 of the first first indication and the first second indication, may be based on obtaining, from the first network node 111, a respective first second indication of the first second set of frequency resources, and

[0668] v. the communications system 100 may be a wireless communications system 100.

[0669] In Figure 14, optional units are indicated with dashed boxes.

[0670] The second device 132 may comprise an arrangement as shown in Figure 14 or in Figure

[0671] The first network node 111 embodiments relate to Figure 9, any of Figures 11-12, Figure and Figures 21-22, and Figures 24-25.A computer-implemented method, performed by a network node, such as the first network node 111 is described herein. The method may be understood to be for handling information pertaining to RSs. The first network node 111 may operate in a communications system, such as the communications system 100.

[0672] In some embodiments, the communications system 100 may support New Radio (NR). The method may comprise one or more of the following actions. In some embodiments, all the actions may be performed. In some examples, Action 910, Action 911 and Action 912 may be performed. One or more embodiments may be combined, where applicable.

[0673] Components from one embodiment may be tacitly assumed to be present in another embodiment and it will be obvious to a person skilled in the art how those components may be used in the other exemplary embodiments. All possible combinations are not described to simplify the description. A non-limiting example of the method performed by the first network node 111 is depicted in Figure 9. In Figure 9, optional actions in some embodiments may be represented with dashed lines. In some embodiments, the actions may be performed in a different order than that depicted Figure 9.

[0674] The detailed description of some of the following corresponds to the same references provided above, in relation to the actions described for the first device 131 and will thus not be repeated here to simplify the description. For example, the MLM may be any of, e.g., a Neural Network, a Convolutional Neural Network, a Federated Learning MLM, an Autoencoder, Decision Tree, etc.

[0675] The first network node 111 may be a network node that may receive an indication, e.g., a report, from the second device 132 based on predicted CSI.

[0676] In some examples, the first network node 111 may be a network node that may configure the first device 131 to collect data to use as input to the MLM during a training phase of the MLM. In some examples, the first network node 111 may train the MLM itself.

[0677] o Providing 910 the first first indication and the first second indication. The first network node 111 may be configured to perform the providing in this Action 910.

[0678] The first first indication may indicate the first first set of frequency resources out of the one or more first frequency resources configured for reception of DL RSs, at the second device 132 operating in the communications system 100.

[0679] The first second indication may indicate the first second set of frequency resources resources out of the one or more first frequency resources.

[0680] The providing, e.g., sending in this Action 910 may be to the second device 132 operating in the communication system 100.

[0681] o Transmitting 911 the DL RSs. The first network node 111 may be configured to perform the transmitting in this Action 911.The transmitting in this Action 911 of the DL RSs may be on the first second set of frequency resources to the second device 132.

[0682] o Receiving 912 the seventh indication. The first network node 111 may be configured to perform the receiving in this Action 912.

[0683] The receiving in this Action 912 may be from the second device 132.

[0684] The seventh indication may be of the predicted CSI of the first channel between the second device 132 and the first network node 111.

[0685] The prediction may be for the first first set of frequency resources, and based on the respective one or more first second measurements performed by the second device 132 on the first second set of frequency resources.

[0686] The prediction may be optionally further based on the first correspondence between the first first set of frequency resources and the first second set of frequency resources.

[0687] In some embodiments, the method may further comprise one or more of the following two actions:

[0688] o Providing 904 the first indication and the second indication. The first network node 111 may be configured to perform the providing in this Action 904.

[0689] The providing, e.g., sending, in this Action 904 may be to the first device 131 operating in the communication system 100.

[0690] The first indication may indicate the first set of frequency resources out of the one or more frequency resources configured for reception of the DL RSs. The one or more frequency resources may be configured for reception of the DL RSs at the first device 131.

[0691] The second indication may indicate the second set of frequency resources out of the one or more frequency resources.

[0692] In some examples, the providing in this Action 904 may optionally comprise providing the third indication. The third indication may indicate the correspondence between the first set of frequency resources and the second set of frequency resources.

[0693] The RSs may be CSI-RSs.

[0694] The second set of frequency resources may be a subset of the first set of frequency resources.

[0695] The second set of frequency resources may be different than the first set of frequency resources.

[0696] o Transmitting 905 the DL RSs. The first network node 111 may be configured to perform the transmitting in this Action 905.

[0697] The transmitting in this Action 905 may be to the first device 131.

[0698] The transmitting in this Action 905 may be:

[0699] i. on the first set of frequency resources, and

[0700] ii. on the second set of frequency resources.In some embodiments, the method may further comprise the following action:

[0701] o Receiving 906 the first information. The first network node 111 may be configured to perform the receiving in this Action 906.

[0702] The receiving in this Action 906 may be from the first device 131.

[0703] The first information may indicate:

[0704] i. the one or more first measurements,

[0705] ii. the one or more second measurements, and

[0706] iii. the correspondence.

[0707] In some embodiments, the providing 904 of the first indication, the second indication and the third indication, the transmitting 905 of the DL RSs, and the receiving 906 of the first information may be iterated for the plurality of respective second sets of frequency resources and, optionally, the corresponding plurality of correspondences between the respective second set of frequency resources and the first set of frequency resources.

[0708] In some embodiments, the method may further comprise one or more of the following two actions:

[0709] o Initiating 907 training the MLM. The first network node 111 may be configured to perform the initiating in this Action 907.

[0710] The training of the MLM may be with the received first information for each respective iteration. The MLM may be to predict the CSI of the channel between the first device 131 and the first network node 111. The prediction may be for the first set of frequency resources, based on the respective one or more second measurements on the second set of frequency resources.

[0711] o Initiating 908 outputting the fourth indication. The first network node 111 may be configured to perform the initiating in this Action 908.

[0712] Initiating may comprise starting or triggering.

[0713] The fourth indication may be of the trained MLM.

[0714] In some embodiments, the method may further comprise the following action:

[0715] o Using 909 the trained MLM. The first network node 111 may be configured to perform the using in this Action 909.

[0716] The using in this Action 909 may be, e.g., to predict CSI, of the channel between the first device 131 and the first network node 111 , or the second channel between the first device 131 and third network node 113.

[0717] During the training phase of the MLM, the one or more second measurements on the second set of frequency resources may be used as input to the MLM, and the one or more first measurements may be used as output labels of the MLM.

[0718] In some embodiments, the method may further comprise one or more of the following three actions:o Obtaining 901 the previous indication. The first network node 111 may be configured to perform the obtaining in this Action 901.

[0719] The obtaining in this Action 901 may be from the first device 131.

[0720] The previous indication may indicate the capability for the performance of measurements on the DL RSs.

[0721] o Providing 902 the one or more configurations. The first network node 111 may be configured to perform the providing in this Action 902.

[0722] The providing in this Action 902 may be to the first device 131.

[0723] The one or more configurations may be of the one or more frequency resources for reception of the DL RSs.

[0724] The providing in this Action 902 of the one or more configurations may be based on the provided previous indication.

[0725] In some embodiments, e.g., the first set of frequency resources may be identical to a frequency resource configuration of the DL RSs comprised in the one or more configurations.

[0726] o Providing 903 the second information. The first network node 111 may be configured to perform the providing in this Action 903.

[0727] The providing in this Action 902 may be to the first device 131.

[0728] The second information may be to assist the first device 131 in training a respective MLM. That is, its own MLM, if trained by the first device 131. The respective MLM may be to predict CSI of the channel between the first device 131 and the first network node 111. The prediction may be for the first set of frequency resources, based on respective one or more second measurements on the second set of frequency resources.

[0729] The training of the respective MLM may be performed based on the obtained second information.

[0730] The second information may comprise one or more of:

[0731] - one or more codebooks the second device 132 may have to assume during the inference phase of the MLM or of the respective MLM,

[0732] - the fifth indication of one or more configurations of the report of the DL RSs that the second device 132 may have to assume during the inference phase, selected from:

[0733] i. the subbands the second device 132 may have to report CSI for, ii. the subband size of the report,

[0734] iii. the subband PMI reporting,

[0735] iv. the subband CQI reporting,

[0736] v. the wideband PMI reporting,

[0737] vi. the wideband CQI reporting- the third information about how the one or more beams of the one or more frequency resources for reception of the DL RSs may be spatially related to each other, and

[0738] - the sixth indication of the one or more conditions corresponding to the transmission of the DL RSs the second device 132 may have to assume during the inference phase upon receipt of the sixth indication.

[0739] In some embodiments, one or more of the following may apply:

[0740] i. the RSs may be CSI-RSs,

[0741] ii. the first set of frequency resources may be larger than the second set of frequency resources,

[0742] iii. the second set of frequency resources may be the subset of the first set of frequency resources, and

[0743] iv. the communications system 100 may be a wireless communications system 100.

[0744] In Figure 15, optional units are indicated with dashed boxes.

[0745] The first network node 111 may comprise an arrangement as shown in Figure 15 or in any of Figures 24-25.

[0746] The second network node 112 embodiments relate to Figure 10, any of Figures 11-13, Figure 17 and Figures 21-22, and Figures 24-25.

[0747] A computer-implemented method, performed by a network node, such as the second network node 112 is described herein. The method may be understood to be handling information pertaining to RSs. The second network node 112 may operate in a communications system, such as the communications system 100.

[0748] In some embodiments, the communications system 100 may support New Radio (NR). The method may comprise one or more of the following actions. In some embodiments, all the actions may be performed. In some examples, Action 1002 may be performed. One or more embodiments may be combined, where applicable. Components from one embodiment may be tacitly assumed to be present in another embodiment and it will be obvious to a person skilled in the art how those components may be used in the other exemplary embodiments. All possible combinations are not described to simplify the description. A non-limiting example of the method performed by the second network node 112 is depicted in Figure 10. In Figure 10, optional actions in some embodiments may be represented with dashed lines. In some embodiments, the actions may be performed in a different order than that depicted Figure 10.

[0749] The detailed description of some of the following corresponds to the same references provided above, in relation to the actions described for the first device 131 and will thus not be repeated here to simplify the description. For example, the MLM may be any of, e.g., a NeuralNetwork, a Convolutional Neural Network, a Federated Learning MLM, an Autoencoder, Decision Tree, etc.

[0750] The second network node 112 may be a network node 112 that may collect data to use as input to the MLM during a training phase of the MLM and train the MLM.

[0751] o Obtaining 1002 the first information. The second network node 112 may be configured to perform the obtaining in this Action 1002.

[0752] The obtaining in this Action 1001 may be at least from the first device 131. That is, the second network node 112 may receive a respective first information from every first device.

[0753] The first information may be of the first set of measurements.2

[0754] The first information may indicate:

[0755] i. the one or more first measurements on the DL RSs transmitted by the first network node 111 operating in the communications system 100, on the first set of frequency resources out of the one or more frequency resources configured for reception of the DL RSs, at the first device 131, and

[0756] ii. the one or more second measurements of the DL RSs, on the second set of frequency resources, out of the one or more frequency resources, and iii. optionally, the correspondence between the first set of frequency resources and the second set of frequency resources.

[0757] In some embodiments, the method may be iterated for the plurality of respective second sets of frequency resources and, optionally, the corresponding plurality of correspondences between the respective second set of frequency resources and the first set of frequency resources.

[0758] In some embodiments, the method may further comprise one or more of the following two actions:

[0759] o Initiating 1003 training of the machine learning model, MLM. The fi second network node 112 may be configured to perform the initiating in this Action 1003.

[0760] Initiating may comprise starting itself, or triggering or enabling that another entity.

[0761] The training of the MLM may be with the obtained first information for each respective iteration.

[0762] The MLM may be to predict the CSI of the channel, e.g., between the first device 131 and the first network node 111. The prediction may be for the first set of frequency resources, based on the respective one or more second measurements on the second set of frequency resources.

[0763] During the training phase of the MLM, the one or more second measurements on the second set of frequency resources may be used as input to the MLM, and the one or more first measurements may be used as output labels of the MLM.o Initiating 1004 outputting the fourth indication. The second network node 112 may be configured to perform the initiating in this Action 1004.

[0764] The fourth indication may be of the trained MLM.

[0765] In some embodiments, the method may further comprise the following action:

[0766] o Using 1005 the trained MLM. The second network node 112 may be configured to perform the using in this Action 1005.

[0767] The using in this Action 1005 may be, e.g., to predict CSI, of the channel between the first device 131 and the first network node 111 , or the second channel between the first device 131 and third network node 113.

[0768] o Obtaining 1001 the second information. The second network node 112 may be configured to perform the obtaining in this Action 1001.

[0769] The obtaining in this Action 1001 may be from the first network node 111.

[0770] The second information may be to assist the second network node 112 in training the MLM. The training of the MLM may be performed based on the obtained second information.

[0771] The second information may comprise one or more of:

[0772] - the one or more codebooks the second device 132 may have to assume during the inference phase of the MLM,

[0773] - the fifth indication of one or more configurations of the report of the DL RSs that the second device 132 may have to assume during the inference phase, selected from:

[0774] i. the subbands the second device 132 may have to report CSI for, ii. the subband size of the report,

[0775] iii. the subband Precoder Matrix Indicator (PMI) reporting, iv. the subband Channel Quality Information (CQI) reporting, v. the wideband PMI reporting,

[0776] vi. the wideband CQI reporting

[0777] - the third information about how one or more beams of the one or more frequency resources for reception of the DL RSs may be spatially related to each other, and - the sixth indication of one or more conditions corresponding to the transmission of the DL RSs the second device 132 may have to assume during the inference phase based on the receipt of the sixth indication.

[0778] In some embodiments, one or more of the following may apply:

[0779] i. the RSs may be CSI-RSs,

[0780] ii. the first set of frequency resources may be larger than the second set of frequency resources,

[0781] iii. the second set of frequency resources may be a subset of the first set of frequency resources, andiv. the communications system 100 may be a wireless communications system 100.

[0782] In Figure 16, optional units are indicated with dashed boxes.

[0783] The second network node 112 may comprise an arrangement as shown in Figure 16 or in any of Figures 24-25.

[0784] Selected examples of embodiments herein may be as follows.

[0785] EXAMPLES:

[0786] EXAMPLE 1. A computer-implemented method performed by a first device (131), the method being for handling information pertaining to Reference Signals, RSs, the first device (131) operating in a communications system (100), the method comprising:

[0787] - obtaining (704) a first indication indicating a first set of frequency resources out of one or more frequency resources configured for reception of downlink, DL, RSs, and a second indication indicating a second set of frequency resources out of the one or more frequency resources, and, e.g., optionally, a third indication indicating a correspondence between the first set of frequency resources and the second set of frequency resources,

[0788] - performing (705), on the DL RSs, as transmitted by a first network node (111) operating in a communications system (100),

[0789] i. one or more first measurements on the first set of frequency resources, and

[0790] ii. one or more second measurements on the second set of frequency resources, and

[0791] - outputting (706) first information indicating:

[0792] i. the one or more first measurements,

[0793] ii. the one or more second measurements, and

[0794] iii. e.g., optionally, the correspondence.

[0795] EXAMPLE 2. The method according to example 1, wherein the method is iterated for a plurality of respective second sets of frequency resources and, optionally, a corresponding plurality of correspondences between the respective second set of frequency resources and the first set of frequency resources.

[0796] EXAMPLE 3. The method according to example 2, wherein the method further comprises one or more of:

[0797] initiating (707) training of a machine learning model, MLM, with the output first information for each respective iteration, the MLM being to predict Channel StateInformation, CSI, of a channel between the first device (131) and the first network node (111), the prediction being for the first set of frequency resources, based on the respective one or more second measurements on the second set of frequency resources, and

[0798] - initiating (708) outputting a fourth indication of the trained MLM.

[0799] EXAMPLE 4. The method according to example 3, further comprising:

[0800] - using (709) the trained MLM, e.g., to predict CSI, of the channel between the first device (131) and the first network node (111), or a second channel between the first device (131) and third network node (113).

[0801] EXAMPLE 5. The method according to any of examples 3-4 wherein, during the training phase of the MLM, the one or more second measurements on the second set of frequency resources are used as input to the MLM, and the one or more first measurements are used as output labels of the MLM.

[0802] EXAMPLE 6. The method according to any of examples 2-5, further comprising one or more of:

[0803] - providing (701), to the first network node (111), a previous indication indicating a capability for the performance of measurements on the DL RSs, and - obtaining (702), from the first network node (111), one or more configurations of the one or more frequency resources for reception of the DL RSs, wherein the obtaining (702) of the one or more configurations is based on the provided previous indication, e.g., the first set of frequency resources is identical to a frequency resource configuration of the DL RSs comprised in the one or more configurations, and

[0804] - obtaining (703), e.g., from the first network node (111), second information to assist the first device (131) in training the MLM, and wherein the training of the MLM is performed based on the obtained second information.

[0805] EXAMPLE 7. The method according to example 6, wherein the second information comprises one or more of:

[0806] - one or more codebooks a second device (132) is to assume during an inference phase of the MLM or the respective MLM,

[0807] - a fifth indication of one or more configurations of a report of the DL RSs that the second device (132) is to assume during the inference phase, selected from: i. subbands the second device (132) is to report CSI for, ii. subband size of the report,iii. subband Precoder Matrix Indicator, PMI, reporting,

[0808] iv. subband Channel Quality Information, CQI, reporting, v. wideband PMI reporting,

[0809] vi. wideband CQI reporting

[0810] - third information about how one or more beams of the one or more frequency resources for reception of the DL RSs are spatially related to each other, and - a sixth indication of one or more conditions corresponding to the transmission of the DL RSs the second device (132) is to assume during the inference phase upon receipt of the sixth indication.

[0811] EXAMPLE 8. The method according to any of examples 2-7, wherein one or more of:

[0812] i. the RSs are Channel State Information, CSI, RSs,

[0813] ii. the first set of frequency resources is larger than the second set of frequency resources,

[0814] iii. the second set of frequency resources is a subset of the first set of frequency resources,

[0815] iv. the first information is output to a second network node (112) operating in the communications system (100),

[0816] v. the obtaining (704) of the first indication and the second indication, is based on obtaining, from the first network node (111), a respective second indication of the respective second sets of frequency resources, and

[0817] vi. the communications system (100) is a wireless communications system (100).

[0818] EXAMPLE 9. A computer-implemented method performed by a second device (132), the method being for handling information pertaining to Reference Signals, RSs, the second device (132) operating in a communications system (100), the method comprising:

[0819] - obtaining (805) a first first indication indicating a first first set of frequency resources out of one or more first frequency resources configured for reception of downlink, DL, RSs, and a first second indication indicating a first second set of frequency resources out of the one or more first frequency resources,

[0820] - obtaining (806) one or more first second measurements on the first second set of frequency resources on the DL RSs, as transmitted by a first network node (111) operating in a communications system (100),

[0821] - predicting (807), using first first information indicating the one or more first second measurements as input to a trained machine learning model, MLM,Channel State Information, CSI, of a first channel between the second device (132) and the first network node (111), the prediction being for the first first set of frequency resources, and based on the respective one or more first second measurements on the first second set of frequency resources, and, optionally, further based on a first correspondence between the first first set of frequency resources and the first second set of frequency resources, and

[0822] - initiating (808) outputting a seventh indication of the predicted CSI.

[0823] EXAMPLE 10. The method according to example 9, wherein the method further comprises:

[0824] - obtaining (801) the trained MLM, e.g., from a first device (131) or a second network node (112) operating in the communications system (100).

[0825] EXAMPLE 11. The method according to any of examples 9-10, further comprising one or more of:

[0826] - providing (802), to the first network node (111), a first previous indication indicating a first capability for the performance of measurements on the DL RSs, and

[0827] - obtaining (803), from the first network node (111), one or more first configurations of the one or more frequency resources for reception of the DL RSs, wherein the obtaining (803) of the one or more first configurations is based on the provided first previous indication, e.g., the first first set of frequency resources is identical to a frequency resource first configuration of the DL RSs comprised in the one or more first configurations, and

[0828] - obtaining (804), e.g., from the first network node (111), first second information to be input by the second node (132) to the MLM for the predicting (805) of the CSI.

[0829] EXAMPLE 12. The method according to example 11, wherein the first second information comprises one or more of:

[0830] - one or more codebooks the second device (132) is to assume for the predicting (805) of the CSI,

[0831] - a fifth indication of one or more configurations of a report of the DL RSs that the second device (132) is to assume for the predicting (805) of the CSI, selected from:

[0832] i. subbands the second device (132) is to report CSI for, ii. subband size of the report,

[0833] iii. subband Precoder Matrix Indicator, PMI, reporting,

[0834] iv. subband Channel Quality Information, CQI, reporting,v. wideband PMI reporting, and

[0835] vi. wideband CQI reporting,

[0836] - third information about how one or more beams of the one or more frequency resources for reception of the DL RSs are spatially related to each other, and - a sixth indication of one or more conditions corresponding to the transmission of the DL RSs the second device (132) is to assume during for the predicting (805) of the CSI based on the receipt of the sixth indication.

[0837] EXAMPLE 13. The method according to any of examples 9-12, wherein one or more of:

[0838] i. the RSs are Channel State Information, CSI, RSs,

[0839] ii. the first first set of frequency resources is larger than the first second set of frequency resources,

[0840] iii. the first second set of frequency resources is a subset of the first first set of frequency resources,

[0841] iv. the obtaining (805) of the first first indication and the first second indication, is based on obtaining, from the first network node (111), a respective first second indication of the first second set of frequency resources, and

[0842] v. the communications system (100) is a wireless communications system (100).

[0843] EXAMPLE 14. A computer-implemented method performed by a first network node (111), the method being for handling information pertaining to Reference Signals, RSs, the first network node (111) operating in a communications system (100), the method comprising:

[0844] - providing (910) a first first indication indicating a first first set of frequency resources out of one or more first frequency resources configured for reception of downlink, DL, RSs, at a second device (132) operating in the communications system (100), and a first second indication indicating a first second set of frequency resources out of the one or more first frequency resources,

[0845] - transmitting (911) the DL RSs on the first second set of frequency resources to the second device (132), and

[0846] - receiving (912), from the second device (132), a seventh indication of a predicted Channel State Information, CSI, of a first channel between the second device (132) and the first network node (111), the prediction being for the first first set of frequency resources, and based on respective one or more first second measurements performed by the second device (132) on the first second set of frequency resources, and, optionally further based on a first correspondencebetween the first first set of frequency resources and the first second set of frequency resources.

[0847] EXAMPLE 15. The method according to example 14, further comprising:

[0848] - providing (904), to a first device (131) operating in the communications system (100), of the downlink, DL, RSs, a first indication indicating a first set of frequency resources out of one or more frequency resources configured for reception, by the first device (131), and a second indication indicating a second set of frequency resources out of the one or more frequency resources, and, optionally, a third indication indicating a correspondence between the first set of frequency resources and the second set of frequency resources, and

[0849] - transmitting (905) the DL RSs to the first device (131),

[0850] i. on the first set of frequency resources, and

[0851] ii. on the second set of frequency resources.

[0852] EXAMPLE 16. The method of claim 15, further comprising:

[0853] - receiving (906), from the first device (131), first information indicating:

[0854] i. one or more first measurements on the first set of frequency resources, ii. one or more second measurements on the second set of frequency resources, and

[0855] iii. optionally, the correspondence.

[0856] EXAMPLE 17. The method according to example 16, wherein the providing (904) of the first indication, the second indication and the third indication, the transmitting (905) of the DL RSs, and the receiving (906) of the first information is iterated for a plurality of respective second sets of frequency resources and, optionally, a corresponding plurality of correspondences between the respective second set of frequency resources and the first set of frequency resources.

[0857] EXAMPLE 18. The method according to example 17, wherein the method further comprises one or more of:

[0858] - initiating (907) training of a machine learning model, MLM, with the received first information for each respective iteration, the MLM being to predict Channel State Information, CSI, of a channel between the first device (131) and the first network node (111), the prediction being for the first set of frequency resources, based on the respective one or more second measurements on the second set of frequency resources, and

[0859] - initiating (908) outputting a fourth indication of the trained MLM.EXAMPLE 19. The method according to example 18, further comprising:

[0860] - using (909) the trained MLM, e.g., to predict CSI, of the channel between the first device (131) and the first network node (111), or a second channel between the first device (131) and third network node (113).

[0861] EXAMPLE 20. The method according to any of examples 18-19 wherein, during the training phase of the MLM, the one or more second measurements on the second set of frequency resources are used as input to the MLM, and the one or more first measurements are used as output labels of the MLM.

[0862] EXAMPLE 21. The method according to any of examples 15-20, further comprising one or more of:

[0863] - obtaining (901), from the first device (131), a previous indication indicating a capability for the performance of measurements on the DL RSs, and - providing (902), to the first device (131), one or more configurations of the one or more frequency resources for reception of the DL RSs, wherein the providing (902) of the one or more configurations is based on the obtained previous indication, e.g., optionally, in some examples, the first set of frequency resources is identical to a frequency resource configuration of the DL RSs comprised in the one or more configurations, and

[0864] - providing (903), e.g., to the first device (131), second information to assist the first device (131) in training a respective MLM, to predict Channel State Information, CSI, of a channel between the first device (131) and the first network node (111), the prediction being for the first set of frequency resources, based on respective one or more second measurements on the second set of frequency resources, and wherein the training of the respective MLM is performed based on the provided second information.

[0865] EXAMPLE 22. The method according to example 21, wherein the second information comprises one or more of:

[0866] - one or more codebooks a second device (132) is to assume during an inference phase of the respective MLM,

[0867] - a fifth indication of one or more configurations of a report of the DL RSs that the second device (132) is to assume during the inference phase, selected from: i. subbands the second device (132) is to report CSI for, ii. subband size of the report,iii. subband Precoder Matrix Indicator, PMI, reporting,

[0868] iv. subband Channel Quality Information, CQI, reporting, v. wideband PMI reporting, and

[0869] vi. wideband CQI reporting

[0870] - third information about how one or more beams of the one or more frequency resources for reception of the DL RSs are spatially related to each other, and - a sixth indication of one or more conditions corresponding to the transmission of the DL RSs the second device (132) is to assume during the inference phase upon receipt of the sixth indication.

[0871] EXAMPLE 23. The method according to any of examples 14-22, wherein one or more of:

[0872] i. the RSs are Channel State Information, CSI, RSs,

[0873] ii. the first first set of frequency resources is larger than the second set of frequency resources,

[0874] iii. the first second set of frequency resources is a subset of the first set of frequency resources, and

[0875] iv. the communications system (100) is a wireless communications system (100).

[0876] EXAMPLE 24. A computer-implemented method performed by a second network node (112), the method being for handling information pertaining to Reference Signals, RSs, the second network node (112) operating in a communications system (100), the method comprising:

[0877] - obtaining (1002) first information from a first device (131) indicating:

[0878] i. one or more first measurements on downlink, DL, RSs transmitted by a first network node (111) operating in a communications system (100), on a first set of frequency resources out of one or more frequency resources configured for reception of the DL RSs, at the first device (131), and ii. one or more second measurements of the DL RSs, on a second set of frequency resources, out of the one or more frequency resources, and iii. optionally, a correspondence between the first set of frequency resources and the second set of frequency resources.

[0879] EXAMPLE 25. The method according to example 24, wherein the method is iterated for a plurality of respective second sets of frequency resources and, optionally, a corresponding plurality of correspondences between the respective second set of frequency resources and the first set of frequency resources.EXAMPLE 26. The method according to example 25, further comprising one or more of:

[0880] - initiating (1003) training of a machine learning model, MLM, with the obtained first information for each respective iteration, the MLM being to predict Channel State Information, CSI, of a channel between the first device (131) and the first network node (111), the prediction being for the first set of frequency resources, based on the respective one or more second measurements on the second set of frequency resources, and

[0881] - initiating (1004) outputting a fourth indication of the trained MLM.

[0882] EXAMPLE 27. The method according to example 26, further comprising:

[0883] - using (1005) the trained MLM, e.g., to predict CSI, of the channel between the first device (131) and the first network node (111), or a second channel between the first device (131) and third network node (113).

[0884] EXAMPLE 28. The method according to any of examples 26-27 wherein, during the training phase of the MLM, the one or more second measurements on the second set of frequency resources are used as input to the MLM, and the one or more first measurements are used as output labels of the MLM.

[0885] EXAMPLE 29. The method according to any of examples 25-28, further comprising one or more of:

[0886] - obtaining (1001), e.g., from the first network node (111), second information to assist the second network node (112) in training the MLM, and wherein the training of the MLM is performed based on the obtained second information.

[0887] EXAMPLE 30. The method according to example 29, wherein the second information comprises one or more of:

[0888] - one or more codebooks a second device (132) is to assume during an inference phase of the MLM,

[0889] - a fifth indication of one or more configurations of a report of the DL RSs that the second device (132) is to assume during the inference phase, selected from: i. subbands the second device (132) is to report CSI for, ii. subband size of the report,

[0890] iii. subband Precoder Matrix Indicator, PMI, reporting,

[0891] iv. subband Channel Quality Information, CQI, reporting, v. wideband PMI reporting, and

[0892] vi. wideband CQI reporting- third information about how one or more beams of the one or more frequency resources for reception of the DL RSs are spatially related to each other, and - a sixth indication of one or more conditions corresponding to the transmission of the DL RSs the second device (132) is to assume during the inference phase upon receipt of the sixth indication.

[0893] EXAMPLE 31. The method according to any of examples 23-30, wherein one or more of:

[0894] i. the RSs are Channel State Information, CSI, RSs,

[0895] ii. the first set of frequency resources is larger than the second set of frequency resources,

[0896] iii. the second set of frequency resources is a subset of the first set of frequency resources, and

[0897] iv. the communications system (100) is a wireless communications system (100).

[0898] Further Extensions And Variations

[0899] Figure 21 shows an example of a communication system 2100 in accordance with some embodiments.

[0900] In the example, the communication system 2100, such as the communications system 100, includes a telecommunications network 2102 that includes an access network 2104, such as a radio access network (RAN), and a core network 2106, which includes one or more core network nodes 2108, such as the second network node 112, in some examples. The access network 2104 includes one or more access network nodes or base stations of various types, such as any of the first network node 111, the second network node 112 and the third network node 113 in some examples. For example, access network nodes 2110A and 2110B are depicted (which may be collectively referred to as network nodes 2110), or any other similar 3rdGeneration Partnership Project (3GPP) access nodes or non-3GPP access points (APs). Some embodiments of the access network 2104 may include more than one access network technology. The network nodes 2110 of access network 2104 facilitate direct or indirect connection of wireless devices, also referred to as user equipments (UEs), e.g., any of the first device 131 and the second device 132, such as by connecting UEs 2112A, 2112B, 2112C, and 2112D (one or more of which may be generally referred to as UEs 2112) to the core network 2106 over one or more wireless connections. Any of the UEs 2112A, 2112B, 2112C, and 2112D are examples of any of the first device 131 and the second device 132.Moreover, a network node is not necessarily limited to an implementation in which a radio portion and a baseband portion are supplied and integrated by a single vendor. Thus, it will be understood that network nodes include disaggregated implementations or portions thereof. For example, in some embodiments, the telecommunications network 2102 includes one or more Open-RAN (ORAN) network nodes. An ORAN network node is a network node in the telecommunications network 2102 that supports an ORAN specification (e.g., a specification published by the O-RAN Alliance, or any similar organization) and may operate alone or together with other network nodes to implement one or more functionalities of any network node in the telecommunications network 2102, including one or more access network nodes 2110 and / or core network nodes 2108.

[0901] Examples of an ORAN network node include an open radio unit (0-Rll), an open distributed unit (O-DU), an open central unit (O-CU), including an O-CU control plane (O-CU-CP) or an O-Cll user plane (O-CU-UP), a RAN intelligent controller (near-real time or non-real time) hosting software or software plug-ins, such as a near-real time control application (e.g., xApp) or a non-real time control application (e.g., rApp), or any combination thereof (the adjective “open” designating support of an ORAN specification). An ORAN network node may support a specification by, for example, supporting an interface defined by the ORAN specification, such as an A1, F1, W1, E1, E2, X2, Xn interface, an open fronthaul user plane interface, or an open fronthaul management plane interface. Moreover, an ORAN network node may be a logical node in a physical node. Furthermore, an ORAN network node may be implemented in a virtualization environment (described further below) in which one or more network functions are virtualized. For example, the virtualization environment may include an O-Cloud computing platform orchestrated by a Service Management and Orchestration Framework via an O-2 interface defined by the O-RAN Alliance or comparable technologies.

[0902] The network nodes 2110, e.g., any of the first network node 111, the second network node 112 and the third network node 113, facilitate direct or indirect connection of one or more UEs 2112, e.g., any of the first device 131 and the second device 132, to the core network 2106 over one or more wireless connections. Example wireless communications over a wireless connection include transmitting and / or receiving wireless signals using electromagnetic waves, radio waves, infrared waves, and / or other types of signals suitable for conveying information without the use of wires, cables, or other material conductors. Moreover, in different embodiments, the communication system 2100 may include any number of wired or wireless networks, network nodes, UEs, and / or any other components or systems that may facilitate or participate in the communication of data and / or signals whether via wired or wireless connections. The communication system 2100 may include and / or interface with any type of communication, telecommunication, data, cellular, radio network, and / or other similar type of system.The UEs 2112, e.g., any of the first device 131 and the second device 132, may be any of a wide variety of communication devices, including wireless devices arranged, configured, and / or operable to communicate wirelessly with the network nodes 2110 and other communication devices. Similarly, the network nodes 2108, 2110, e.g., any of the first network node 111, the second network node 112 and the third network node 113, are arranged, capable, configured, and / or operable to communicate directly or indirectly (e.g., via other devices of telecommunications network 2102) with the UEs 2112 and / or with other network nodes or equipment in the telecommunications network 2102 to enable and / or provide network access, such as wireless network access, and / or to perform other functions, such as administration in the telecommunications network 2102. More specifically, UEs 2112 may send messages, data, and / or other signals to network nodes 2108, 2110 or other elements of the telecommunications network 2102 by transmitting such signals to the relevant device directly without the signals passing through any intervening devices or by transmitting such signals to the relevant device indirectly through an intervening device (or multiple intervening devices) that then transmit the signal to the relevant device. Similarly, network nodes 2108, 2110 may send messages, data, and other signals to UEs 21122, other network nodes 2108, 2110, and other devices in telecommunications network 2102 directly or indirectly. As one specific example, a core network node 108 may transmit a particular message to a UE 2112 by transmitting the message to an access network node 2110 that will then transmit the message to the intended UE2112. Similarly, a core network node 108 may receive a particular message from a UE 2112 by receiving the message from an access network node 2110 that itself received the message from the UE 2112.

[0903] In the depicted example, the core network 2106 connects elements of the access network 2104 (e.g., one or more of the network nodes 2110) to one or more host computing systems, such as host 2116. These connections may be direct or indirect via one or more intermediary networks or devices. In other examples, network nodes may be directly coupled to hosts. The core network 2106 includes one or more core network nodes (e.g., core network node 2108) of various types, one or more of which may be generally referred to as network nodes 2108. Network nodes 2108 are structured with hardware and software components. Features of these components may be substantially similar to those described with respect to the UEs, access network nodes, and / or hosts, such that the descriptions thereof are generally applicable to the corresponding components of the core network node 2108. Example core network nodes provide functions of one or more of a Mobile Switching Center (MSC), Mobility Management Entity (MME), Home Subscriber Server (HSS), Access and Mobility Management Function (AMF), Session Management Function (SMF), Authentication Server Function (AUSF), Subscription Identifier Deconcealing function (SIDF), Unified Data Management (UDM), Security Edge Protection Proxy (SEPP), Network Exposure Function (NEF), and / or a User Plane Function (UPF).The host 2116 may be under the ownership or control of a service provider other than an operator or provider of the access network 2104 and / or the telecommunications network 2102. The host 2116 may be operated by the service provider or on behalf of the service provider. The host 2116 may host a variety of applications to provide one or more service. Examples of such applications include live and pre-recorded audio / video content, data collection services such as retrieving and compiling data on various ambient conditions detected by a plurality of UEs, analytics functionality, social media, functions for controlling or otherwise interacting with remote devices, functions for an alarm and surveillance center, or any other such function performed by a server.

[0904] As a whole, the communication system 2100 of Figure 21 enables connectivity between the UEs, network nodes, and hosts. In that sense, the communication system 2100 may be configured to operate according to predefined rules or procedures, such as specific standards that include, but are not limited to: Global System for Mobile Communications (GSM); Universal Mobile Telecommunications System (UMTS); Long Term Evolution (LTE), and / or other suitable 2G, 3G, 4G, 5G standards, or any applicable future generation standard (e.g., 6G); wireless local area network (WLAN) standards, such as the Institute of Electrical and Electronics Engineers (IEEE) 802.11 standards (Wi-Fi); and / or any other appropriate wireless communication standard, such as the Worldwide Interoperability for Microwave Access (Wi-Max), Bluetooth, Z-Wave, Near Field Communication (NFC) ZigBee, Li-Fi, and / or any low-power wide-area network (LPWAN) standards such as LoRa and Sigfox. Moreover, the communication system 2100 may be configured to support multiple different standards, protocols, or other rule sets, with individual components supporting all of the relevant rule sets or with different components or sub-systems within the communication system 2100 supporting different standards, protocols, or rule sets.

[0905] As one example, in certain embodiments, access network 2104 may contain some access network nodes 2110 that support 3GPP radio access technologies (RAT), such as LTE or NR, while other access network nodes 2110 support (or the same access network nodes 2110 additionally support) non-3GPP RATs, such as Wi-Fi or a proprietary RAT. As another example, telecommunications network 2102 may support multiple generations of related communication standards (e.g., 4G and 5G 3GPP communication standards) and, as a result, may include an access network 104 and / or a core network 106 that supports multiple different standard generations or may include multiple access networks 104 and / or multiple core networks 106 with individual networks 104, 106 supporting different standard generations.

[0906] Telecommunications network 2102 may support network slicing to provide different logical networks to different devices that are connected to the telecommunications network 2102. For example, the telecommunications network 2102 may provide Ultra Reliable Low Latency Communication (URLLC) services to some UEs, while providing Enhanced Mobile Broadband(eMBB) services to other UEs, and / or Massive Machine Type Communication (mMTC) / Massive loT services to yet further UEs.

[0907] In some examples, one or more of the UEs 2112 are configured to transmit and / or receive information without direct human interaction. For instance, a UE may be designed to transmit information to the access network 2104 on a predetermined schedule, when triggered by an internal or external event, or in response to requests from the access network 2104. Additionally, a UE may be configured for operating in single- or multi-RAT or multi-standard mode. For example, a UE may operate with any one or combination of Wi-Fi, NR (New Radio) and LTE, i.e. being configured for multi-radio dual connectivity (MR-DC), such as E-UTRAN (Evolved-UMTS Terrestrial Radio Access Network) New Radio - Dual Connectivity (EN-DC).

[0908] In the example, the hub 2114 communicates with the access network 2104 to facilitate indirect communication between one or more UEs (e.g., UE 2112C and / or 2112D) and network nodes (e.g., network node 2110B). In some examples, the hub 2114 may be a controller, router, content source and analytics, or any of the other communication devices described herein regarding UEs. For example, the hub 2114 may be a broadband router enabling access to the core network 2106 for the UEs. As another example, the hub 2114 may be a controller that sends commands or instructions to one or more actuators in the UEs. Commands or instructions may be received from the UEs, network nodes 2110, or by executable code, script, process, or other instructions in the hub 2114.

[0909] As another example, the hub 2114 may be a data collector that acts as temporary storage for UE data and, in some embodiments, may perform analysis or other processing of the data. As another example, the hub 2114 may be a content source. For example, for a UE that is a VR headset, display, loudspeaker or other media delivery device, the hub 2114 may retrieve VR assets, video, audio, or other media or data related to sensory information via a network node, which the hub 2114 then provides to the UE either directly, after performing local processing, and / or after adding additional local content. In still another example, the hub 2114 acts as a proxy server or orchestrator for the UEs, in particular if one or more of the UEs are low energy loT devices.

[0910] The hub 2114 may have a constant / persistent or intermittent connection to the network node 2110B. The hub 2114 may also allow for a different communication scheme and / or schedule between the hub 2114 and UEs (e.g., UE 2112C and / or 2112D), and between the hub 2114 and the core network 2106. In other examples, the hub 2114 is connected to the core network 2106 and / or one or more UEs via a wired connection. Moreover, the hub 2114 may be configured to connect to an M2M service provider over the access network 2104 and / or to another UE over a direct connection. In some scenarios, UEs may establish a wireless connection with the network nodes 2110 while still connected via the hub 2114 via a wired or wireless connection. In some embodiments, the hub 2114 may be a dedicated hub - that is, a hub whose primary function is toroute communications to / from the UEs from / to the network node 2110B. In other embodiments, the hub 2114 may be a non-dedicated hub - that is, a device which is capable of operating to route communications between the UEs and network node 2110B, but which is additionally capable of operating as a communication start and / or end point for certain data channels.

[0911] Figure 22 is another example of a communication system 2200, such as the wireless communications network 100, according to some embodiments. As used herein, the communication system 2200 includes multiple access points (APs) 2210 (with four exemplary APs 2210A, 2210B, 2210C, and 2210D being depicted), such as any of the first network node 111 , the second network node 112 and the third network node 113, and multiple wireless devices, referred to in the context of communication system 2200 as stations (STAs) 2212 (referred to individually as STA 2212A, STA 2212B, STA 2212C, STA 2212D, and STA 2212E), such as e.g., any of the first device 131 and the second device 132. STA 2212A is served by AP 2210A in a first basic service set (BSS) 2220A. STA 2210B and STA 2210C are served by AP 2210B in a second BSS, BSS 2220B. STA 2212D is served by AP 2210C in a third BSS, BSS 2220C. STA 2212E is served by AP 2210D in a fourth BSS, BSS 2220D. Stations 2212 may be non-AP STAs and correspond to various kinds of wireless devices, for example, user terminals, such as mobile or stationary computing devices like smartphones, laptop computers, desktop computers, tablet computers, gaming devices, head-mounted displays (HMDs) for Augmented Reality (AR) or Virtual Reality (VR), or the like. Further, stations 2212 could, for example, correspond to other kinds of equipment like smart home devices, printers, multimedia devices, data storage devices, or the like.

[0912] Each of STAs 2212 may connect through a radio link to one of APs 2210. For example, depending on location or channel conditions experienced by a given STA 2212, the STA may select an appropriate AP and BSS for establishing the radio link. The radio link may be based on one or more orthogonal frequency-division multiplexing (OFDM) carriers from a frequency spectrum that is shared on the basis of a contention-based mechanism, e.g., an unlicensed or license exempt band like 2.4 GHz Industrial, Scientific, and Medical (ISM) band, the 5 GHz band, the 6 GHz band, or the 60 GHz band.

[0913] Each AP 2210 may provide data connectivity to STAs 2212 connected to a particular AP 2210. As illustrated, APs 2210 may be connected to a data network 2230. In this way, APs 2210 may also provide data connectivity between STAs 2212 and other entities, e.g., to one or more servers, service providers, data sources, data sinks, user terminals, or the like. Accordingly, the radio link established between a given STA 2212 and its serving AP 2210 may be used for providing various kinds of services to STA 2212, e.g., a voice service, a multimedia service, or other data service. Such services may be based on applications that are executed on STA 2212 and / or on a device linked to STA 2212. By way of example, Figure 22 illustrates an application service platform 2232 provided in data network 2230. The application(s) executed on STA 2212and / or on one or more other devices linked to STA 2212 may use the radio link for data communication with one or more other STA 2212 and / or the application service platform 2232, thereby enabling utilization of the corresponding service(s) at STA 2212.

[0914] Figure 23 shows a wireless device 2300, such as any of the first device 131 and the second device 132, which may be configured to operate in communication system 2100 of Figure 21 or in communication system 2200 of Figure 220. The wireless device 2300 may be alternatively referred to as a UE 2300, like a UE 2112 within the context of communication system 2100, or as a station (STA) 2300 or as a non-access-point station (non-AP STA) 2300, like a STA 2212 within the context of the communication system 2200, in accordance with respective embodiments. As used herein, a wireless device refers to a device capable, configured, arranged and / or operable to communicate wirelessly with network nodes and / or other wireless devices. Examples of a wireless device include, but are not limited to, a smart phone, mobile phone, cell phone, voice over IP (VoIP) phone, wireless local loop phone, desktop computer, personal digital assistant (PDA), wireless cameras, gaming console or device, music storage device, playback appliance, wearable terminal device, wireless endpoint, mobile station, tablet, laptop, laptop-embedded equipment (LEE), laptop-mounted equipment (LME), smart device, wireless customer-premise equipment (CPE), vehicle, vehicle-mounted or vehicle embedded / integrated wireless device, and wireless terminal. Other examples include any type of UE identified by the 3rd Generation Partnership Project (3GPP), including a narrow band internet of things (NB-loT) UE, a machine type communication (MTC) UE, and / or an enhanced MTC (eMTC) UE.

[0915] A wireless device 2300 may support device-to-device (D2D) communication, for example by implementing a 3GPP standard for sidelink communication, Dedicated Short-Range Communication (DSRC), vehicle-to-vehicle (V2V), vehicle-to-infrastructure (V2I), or vehicle-to-everything (V2X). In other examples, wireless device 2300 may not necessarily have a user in the sense of a human user who owns and / or operates the relevant device. Instead, wireless device 2300 may represent a device that is intended for sale to, or operation by, a human user but which may not, or which may not initially, be associated with a specific human user (e.g., a smart sprinkler controller). Alternatively, wireless device 2300 may represent a device that is not intended for sale to, or operation by, an end user but which may be associated with or operated for the benefit of a user (e.g., a smart power meter).

[0916] In particular embodiments, wireless device 2300 includes processing circuitry 2302 that is operatively coupled via a bus 2304 to an input / output interface 2306, a power source 2308, a memory 2310, a communication interface 2312, and / or any other component, or any combination thereof. Certain embodiments of wireless device 2300 may include all or a subset of the components shown in Figure 23. The level of integration between the components may vary from one embodiment of wireless device 2300 to another. In general, in a particular embodiment of wireless device 2300, processing circuitry 2302, input / output interface 2306, power source 2308,memory 2310, and communication interface 2312 may, in whole or in part, represent or include physical components common to or shared by one or more of the other elements of wireless device 2300. Further, certain embodiments of wireless devices 2300 may contain multiple instances of a component, such as multiple processors, memories, transceivers, transmitters, receivers, etc.

[0917] The processing circuitry 2302 is configured to process instructions and data and may be configured to implement any sequential state machine operative to execute instructions stored as machine-readable computer programs in the memory 2310. The processing circuitry 2302 may be implemented as one or more hardware-implemented state machines (e.g., in discrete logic, field-programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), etc.); programmable logic together with appropriate firmware; one or more stored computer programs, general-purpose processors, such as a microprocessor or digital signal processor (DSP), together with appropriate software; or any combination of the above. For example, the processing circuitry 2302 may include multiple central processing units (CPUs).

[0918] In the example, the input / output interface 2306 may be configured to provide an interface or interfaces to an input device, output device, or one or more input and / or output devices. Examples of an output device include a speaker, a sound card, a video card, a display, a monitor, a printer, an actuator, an emitter, a smartcard, another output device, or any combination thereof. An input device may allow a user to capture information into wireless device 2300. Examples of an input device include a touch-sensitive or presence-sensitive display, a camera (e.g., a digital camera, a digital video camera, a web camera, etc.), a microphone, a sensor, a mouse, a trackball, a directional pad, a trackpad, a scroll wheel, a smartcard, and the like. The presencesensitive display may include a capacitive or resistive touch sensor to sense input from a user. A sensor may be, for instance, an accelerometer, a gyroscope, a tilt sensor, a force sensor, a magnetometer, an optical sensor, a proximity sensor, a biometric sensor, etc., or any combination thereof. An output device may use the same type of interface port as an input device. For example, a Universal Serial Bus (USB) port may be used to provide an input device and an output device.

[0919] In some embodiments, the power source 2308 is structured as a battery or battery pack. Other types of power sources, such as an external power source (e.g., an electricity outlet), photovoltaic device, or power cell, may be used to supply power to circuitry or to charge an associated battery. The power source 2308 may further include power circuitry for delivering power from the power source 2308 itself, and / or an external power source, to the various parts of wireless device 2300 via input circuitry or an interface such as an electrical power cable. Power source 2308 may perform any formatting, converting, or other modification to make accessible power suitable for the respective components of the wireless device 2300 to which power is supplied.The memory 2310 may be or be configured to include memory such as random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic disks, optical disks, hard disks, removable cartridges, flash drives, and so forth. In one example, the memory 2310 includes one or more programs 2314, such as an operating system, web browser application, a widget, gadget engine, or other application, and corresponding data 2316. The memory 2310 may store, for use by wireless device 2300, any of a variety of various operating systems or combinations of operating systems.

[0920] The memory 2310 may be configured to include a number of physical drive units, such as redundant array of independent disks (RAID), flash memory, USB flash drive, external hard disk drive, thumb drive, pen drive, key drive, high-density digital versatile disc (HD-DVD) optical disc drive, internal hard disk drive, Blu-Ray optical disc drive, holographic digital data storage (HDDS) optical disc drive, external mini-dual in-line memory module (DIMM), synchronous dynamic random access memory (SDRAM), external micro-DIMM SDRAM, smartcard memory such as tamper resistant module in the form of a universal integrated circuit card (UICC) including one or more subscriber identity modules (SIMs), such as a USIM and / or ISIM, other memory, or any combination thereof. The UICC may for example be an embedded UICC (eUlCC), integrated UICC (iUICC) or a removable UICC commonly known as ‘SIM card.’ The memory 2310 may allow wireless device 2300 to access instructions, programs and the like, stored on transitory or non-transitory memory media, to off-load data, or to upload data. An article of manufacture, such as one utilizing a communication system may be tangibly embodied as or in the memory 2310, which may be or comprise a device-readable storage medium.

[0921] The processing circuitry 2302 may be configured to communicate with an access network or other network via or using the communication interface 2312. The communication interface 2312 may comprise one or more communication subsystems and may include or be communicatively coupled to an antenna 2322. The communication interface 2312 may include one or more transceivers used to communicate, such as by communicating with one or more remote transceivers of another device capable of wireless communication (e.g., another wireless device or a network node in an access network). Each transceiver may include a transmitter 2318 and / or a receiver 2320 appropriate to provide network communications (e.g., optical, electrical, frequency allocations, and so forth). Moreover, the transmitter 2318 and receiver 2320 may be coupled to one or more antennas (e.g., antenna 2322) and may share circuit components, software or firmware, or alternatively be implemented separately.

[0922] In the illustrated embodiment, communication functions of the communication interface 2312 may include cellular communication, Wi-Fi communication (e.g., according to an IEEE 802.11 family standard), LPWAN communication, data communication, voice communication, multimedia communication, short-range communications such as Bluetooth, near-fieldcommunication, location-based communication such as the use of the global positioning system (GPS) to determine a location, another like communication function, or any combination thereof. Communications may be implemented according to one or more communication protocols and / or standards, such as IEEE 802.11, Code Division Multiplexing Access (CDMA), Wideband Code Division Multiple Access (WCDMA), GSM, LTE, New Radio (NR), UMTS, WiMax, Ethernet, transmission control protocol / internet protocol (TCP / IP), synchronous optical networking (SONET), Asynchronous Transfer Mode (ATM), QUIC, Hypertext Transfer Protocol (HTTP), and so forth.

[0923] In particular embodiments, wireless device 2300 may provide an output of data captured via a sensor, through its communication interface 2312, via a wireless connection to a network node, and / or in any appropriate manner. Data captured by sensors of a wireless device 2300 can be communicated through a wireless connection to a network node via another wireless device 2300. In particular embodiments, such output may be periodic (e.g., once every 15 minutes if it reports the sensed temperature), random (e.g., to even out the load from reporting from several sensors), in response to a triggering event (e.g., when moisture is detected an alert is sent), in response to a request (e.g., a user initiated request), or a continuous stream (e.g., a live video feed of a patient).

[0924] As another example, wireless device 2300 comprises an actuator, a motor, or a switch, related to a communication interface configured to receive wireless input from a network node via a wireless connection. In response to the received wireless input the states of the actuator, the motor, or the switch may change. For example, wireless device 2300 may comprise a motor that adjusts the control surfaces or rotors of a drone in flight according to the received input or to a robotic arm performing a medical procedure according to the received input.

[0925] Wireless device 2300, when in the form of an Internet of Things (loT) device, may be a device for use in one or more application domains, these domains comprising, but not limited to, wearable technology, extended industrial application and healthcare. Non-limiting examples of such an loT device are a device which is or which is embedded in: a connected refrigerator or freezer, a TV, a connected lighting device, an electricity meter, a robot vacuum cleaner, a voice controlled smart speaker, a home security camera, a motion detector, a thermostat, a smoke detector, a door / window sensor, a flood / moisture sensor, an electrical door lock, a connected doorbell, an air conditioning system like a heat pump, an autonomous vehicle, a surveillance system, a weather monitoring device, a vehicle parking monitoring device, an electric vehicle charging station, a smart watch, a fitness tracker, a wearable for tactile augmentation or sensory enhancement, a water sprinkler, an animal- or item-tracking device, a sensor for monitoring a plant or animal, an industrial robot, an Unmanned Aerial Vehicle (UAV), and any kind of medical device, like a heart rate monitor or a remote controlled surgical robot. In particular embodiments, wireless device 2300 represents an loT device that comprises circuitry and / or software independence of the intended application of the loT device in addition to other components as described in relation to the example embodiment of wireless device 2300 shown in Figure 23.

[0926] As yet another specific example, in an loT scenario, wireless device 2300 may represent a machine or other device that performs monitoring and / or measurements and transmits the results of such monitoring and / or measurements to another wireless device and / or a network node. Wireless device 2300 may in this case be an M2M device, which may in a 3GPP context be referred to as an MTC device. As one particular example, wireless device 2300 may implement the 3GPP NB-loT standard. In other scenarios, wireless device 2300 may represent a vehicle, such as a car, a bus, a truck, a ship and an airplane, or other equipment that is capable of monitoring and / or reporting on its operational status or other functions associated with its operation.

[0927] In practice, any number of wireless devices 2300 may be used together with respect to a single use case. For example, a first wireless device 2300 might be or be integrated in a drone and provide the drone’s speed information (obtained through a speed sensor) to a second wireless device 2300 that is a remote controller operating the drone. When a user makes changes from the remote controller, the first wireless device 2300 may adjust the throttle on the drone (e.g. by controlling an actuator) to increase or decrease the drone’s speed. The first and / or the second wireless device 2300 can also include more than one of the functionalities described above. For example, wireless device 2300 might comprise the sensor and the actuator, and handle communication of data for both the speed sensor and the actuators.

[0928] Figure 24 shows a network node 2400, such as any of the first network node 111, the second network node 112 and the third network node 113, in accordance with some embodiments. As used herein, network node refers to equipment capable, configured, arranged and / or operable to communicate directly or indirectly with a UE and / or with other network nodes or equipment, in a telecommunications network. In accordance with respective embodiments, network node 2400 may be configured to operate in communication system 2100 of Figure 21, like network nodes 2108 or 2110, or in communication system 2200 of Figure 22, like an AP 2210 or a station 2212. Examples of network nodes include, but are not limited to, access points (APs) (e.g., radio access points), base stations (BSs) (e.g., radio base stations, Node Bs, evolved Node Bs (eNBs) and NR NodeBs (gNBs)), O-RAN nodes or components of an O-RAN node (e.g., O-RU, O-DU, O-CU).

[0929] Network nodes 2400 may be categorized based on the amount of coverage they provide (or, stated differently, their transmit power level) and so, depending on the provided amount of coverage, may be referred to as femto base stations, pico base stations, micro base stations, or macro base stations. Network node 2400 may be a relay node or a relay donor node controlling a relay. Network nodes 2400 may also include one or more (or all) parts of a distributed radio base station such as centralized digital units, distributed units (e.g., in an O-RAN access node)and / or remote radio units (RRUs), sometimes referred to as Remote Radio Heads (RRHs). Such remote radio units may or may not be integrated with an antenna as an antenna integrated radio. Parts of a distributed radio base station may also be referred to as nodes in a distributed antenna system (DAS).

[0930] Other examples of network nodes 2400 include multiple transmission point (multi-TRP) 5G access nodes, multi-standard radio (MSR) equipment such as MSR BSs, network controllers such as radio network controllers (RNCs) or base station controllers (BSCs), base transceiver stations (BTSs), transmission points, transmission nodes, multi-cell / multicast coordination entities (MCEs), Operation and Maintenance (O&M) nodes, Operations Support System (OSS) nodes, Self-Organizing Network (SON) nodes, positioning nodes (e.g., Evolved Serving Mobile Location Centers (E-SMLCs)), and / or Minimization of Drive Tests (MDTs).

[0931] In particular embodiments, network node 2400 includes a processing circuitry 2402, a memory 2404, a communication interface 2406, and a power source 2408. In general, in a particular embodiment of network node 2400, processing circuitry 2402, memory 2404, communication interface 2406, and power source 2408 may, in whole or in part, represent or include physical components common to or shared by one or more of the other elements of network node 2400.

[0932] The network node 2400 may be composed of multiple distinct network entities (e.g., a NodeB entity and a RNC entity, or a BTS entity and a BSC entity, etc.), which may each have or utilize their own respective physical components. In certain scenarios in which the network node 2400 comprises multiple such entities (e.g., BTS and BSC), one or more of the separate entities may be shared among several network nodes. For example, a single RNC may control multiple NodeBs. In such a scenario, each unique NodeB and RNC pair, may in some instances be considered a single separate network node. In some embodiments, the network node 2400 may be configured to support multiple radio access technologies (RATs). In such embodiments, some components may be duplicated (e.g., separate memories 2404 or portions of memory 2404 for different RATs) and some components may be reused (e.g., a same antenna 2410 may be shared by different RATs). The network node 2400 may also include multiple sets of the various illustrated components for different wireless technologies integrated into network node 2400, for example GSM, WCDMA, LTE, NR, Wi-Fi (e.g., according to an IEEE 802.11 family standard), Zigbee, Z-wave, LoRaWAN, Radio Frequency Identification (RFID) or Bluetooth wireless technologies. These wireless technologies may be integrated into the same or different chip or set of chips and other components within network node 2400.

[0933] The processing circuitry 2402 may comprise a combination of one or more of a microprocessor, controller, microcontroller, central processing unit, digital signal processor, application-specific integrated circuit, field programmable gate array, or any other suitable computing device, resource, or combination of hardware, software and / or encoded logic operableto provide, either alone or in conjunction with other components, such as the memory 2404, to provide network node 2400 functionality.

[0934] In some embodiments, the processing circuitry 2402 includes a system on a chip (SOC). In some embodiments, the processing circuitry 2402 includes one or more of radio frequency (RF) transceiver circuitry 2412 and baseband processing circuitry 2414. In some embodiments, the RF transceiver circuitry 2412 and the baseband processing circuitry 2414 may be on separate chips (or sets of chips), boards, or units, such as radio units and digital units. In alternative embodiments, part or all of RF transceiver circuitry 2412 and baseband processing circuitry 2414 may be on the same chip or set of chips, boards, or units.

[0935] The memory 2404 may comprise any form of volatile or non-volatile computer-readable memory including, without limitation, persistent storage, solid-state memory, remotely mounted memory, magnetic media, optical media, random access memory (RAM), read-only memory (ROM), mass storage media (for example, a hard disk), removable storage media (for example, a flash drive, a Compact Disk (CD) or a Digital Video Disk (DVD)), and / or any other volatile or non-volatile, non-transitory device-readable and / or computer-executable memory devices that store information, data, and / or instructions that may be used by the processing circuitry 2402. The memory 2404 may store any suitable instructions, data, or information, including a computer program, software, an application including one or more of logic, rules, code, tables, and / or other instructions capable of being executed by the processing circuitry 2402 and utilized by the network node 2400. The memory 2404 may be used to store any calculations made by the processing circuitry 2402 and / or any data received via the communication interface 2406. In some embodiments, the processing circuitry 2402 and memory 2404 is integrated.

[0936] The communication interface 2406 is used in wired or wireless communication of signaling and / or data with UEs, other network nodes, and / or any other network equipment. In the illustrated embodiment, communication interface 2406 comprises port(s) / terminal(s) 2416 to send and receive data, for example to and from a network over a wired connection. In particular embodiments, network node 2300 may be capable of wireless communication and communication interface 2406 may also include radio front-end circuitry 2418 that may be coupled to, or in certain embodiments a part of, an antenna 2410. Particular embodiments of radio frontend circuitry 2418 include filter(s) 2420 and amplifier(s) 2422. The radio front-end circuitry 2418 may be connected to an antenna 2410 and processing circuitry 2402. The radio front-end circuitry may be configured to condition signals communicated between antenna 2410 and processing circuitry 2402. The radio front-end circuitry 2418 may receive digital data that is to be sent out to other network nodes or UEs via a wireless connection. The radio front-end circuitry 2418 may convert the digital data into a radio signal(s) having the appropriate channel and bandwidth parameters using a combination of filters 2420 and / or amplifiers 2422. The radio signal(s) may then be transmitted via the antenna 2410. Similarly, when receiving data, the antenna 2410 maycollect radio signals which are then converted into digital data by the radio front-end circuitry 2418. The digital data may be passed to the processing circuitry 2402. In other embodiments, the communication interface may comprise different components and / or different combinations of components.

[0937] In certain alternative embodiments, network node 2400 may be capable of wireless communication but does not include separate radio front-end circuitry 2418, instead, the processing circuitry 2402 includes radio front-end circuitry and is connected to the antenna 2410. Similarly, in some embodiments, all or some of the RF transceiver circuitry 2412 is part of the communication interface 2406. In still other embodiments, the communication interface 2406 includes one or more ports or terminals 2416, the radio front-end circuitry 2418, and the RF transceiver circuitry 2412, as part of a radio unit (not shown), and the communication interface 2406 communicates with the baseband processing circuitry 2414, which is part of a digital unit (not shown).

[0938] The antenna 2410 may include one or more antennas, or antenna arrays, configured to send and / or receive wireless signals. The antenna 2410 may be coupled to the radio front-end circuitry 2418 and may be any type of antenna capable of transmitting and receiving data and / or signals wirelessly. In certain embodiments, the antenna 2410 is separate from the network node 2400 and connectable to the network node 2400 through one or more interfaces or ports.

[0939] The antenna 2410, communication interface 2406, and / or the processing circuitry 2402 may be configured to perform some or all of the receiving operations and / or obtaining operations described herein as being performed by the network node 2400. Any information, data and / or signals may be received from a UE, another network node and / or any other network equipment. Similarly, the antenna 2410, the communication interface 2406, and / or the processing circuitry 2402 may be configured to perform some or all of the transmitting or sending operations described herein as being performed by the network node 2400. Any information, data and / or signals may be transmitted to a UE, another network node and / or any other network equipment.

[0940] The power source 2408 provides power to the various components of network node 2400 in a form suitable for the respective components (e.g., at a voltage and current level needed for each respective component). The power source 2408 may further comprise, or be coupled to, power management circuitry to supply the components of the network node 2400 with power for performing the functionality described herein. For example, the network node 2400 may be connectable to an external power source (e.g., the power grid, an electricity outlet) via an input circuitry or interface such as an electrical cable, whereby the external power source supplies power to power circuitry of the power source 2408. As a further example, the power source 2408 may comprise a source of power in the form of a battery or battery pack which is connected to, or integrated in, power circuitry. The battery may provide backup power should the external power source fail.Embodiments of the network node 2400 may include additional components beyond those shown in Figure 24 for providing certain aspects of the network node’s functionality, including any of the functionality described herein and / or any functionality necessary to support the subject matter described herein. For example, the network node 2400 may include user interface equipment to allow input of information into the network node 2400 and to allow output of information from the network node 2400. This may allow a user to perform diagnostic, maintenance, repair, and other administrative functions for the network node 2400.

[0941] Figure 25 is a block diagram illustrating a virtualization environment 2500 in which functions implemented by some embodiments may be virtualized. In the present context, virtualizing means creating virtual versions of apparatuses or devices which may include virtualizing hardware platforms, storage devices and networking resources. As used herein, virtualization can be applied to any device described herein, or components thereof, and relates to an implementation in which at least a portion of the functionality is implemented as one or more virtual components. Some or all of the functions described herein may be implemented as virtual components executed by one or more virtual machines (VMs) implemented in one or more virtual environments 2500 hosted by one or more of hardware nodes, such as a hardware computing device that operates as an access network node, UE, core network node, or host. Further, in embodiments in which a virtual node does not require radio connectivity (e.g., a core network node or host), then the node may be entirely virtualized. In some embodiments, the virtualization environment 2500 includes components defined by the O-RAN Alliance, such as an O-Cloud environment orchestrated by a Service Management and Orchestration Framework via an O-2 interface.

[0942] Applications 2502 (which may alternatively be called software instances, virtual appliances, network functions, virtual nodes, virtual network functions, etc.) are run in the virtualization environment Q400 to implement some of the features, functions, and / or benefits of some of the embodiments disclosed herein.

[0943] Hardware 2504 includes processing circuitry, memory that stores software and / or instructions exe...

Claims

1. CLAIMS:

1. A computer-implemented method performed by a first device (131), the method being for handling information pertaining to Reference Signals, RSs, the first device (131) operating in a communications system (100), the method comprising:- obtaining (704) a first indication indicating a first set of frequency resources out of one or more frequency resources configured for reception of downlink, DL, RSs, and a second indication indicating a second set of frequency resources out of the one or more frequency resources, and a third indication indicating a correspondence between the first set of frequency resources and the second set of frequency resources, wherein the first set of frequency resources is larger than the second set of frequency resources, and- performing (705), on the DL RSs, as transmitted by a first network node (111) operating in the communications system (100),i. one or more first measurements on the first set of frequency resources, andii. one or more second measurements on the second set of frequency resources.

2. The method according to claim 1 , further comprising:- outputting (706) first information indicating:i. the one or more first measurements,ii. the one or more second measurements, andiii. the correspondence.

3. The method according to any of claims 1-2, wherein the method is iterated for a plurality of respective second sets of frequency resources and, optionally, a corresponding plurality of correspondences between the respective second set of frequency resources and the first set of frequency resources.

4. The method according to claim 3, wherein the method further comprises one or more of:- initiating (707) training of a machine learning model, MLM, with the output first information for each respective iteration, the MLM being to predict Channel State Information, CSI, of a channel between the first device (131) and the first network node (111), the prediction being for the first set of frequency resources, based on the respective one or more second measurements on the second set of frequency resources, andinitiating (708) outputting a fourth indication of the trained MLM.

5. The method according to claim 4, further comprising:- using (709) the trained MLM to predict CSI of the channel between the first device (131) and the first network node (111), or a second channel between the first device (131) and a third network node (113).

6. The method according to any of claims 4-5 wherein, during the training phase of the MLM, the one or more second measurements on the second set of frequency resources are used as input to the MLM, and the one or more first measurements are used as output labels of the MLM.

7. The method according to any of claims 3-6, further comprising one or more of:- providing (701), to the first network node (111), a previous indication indicating a capability for the performance of measurements on the DL RSs,- obtaining (702), from the first network node (111), one or more configurations of the one or more frequency resources for reception of the DL RSs, wherein the obtaining (702) of the one or more configurations is based on the provided previous indication, and- obtaining (703) second information to assist the first device (131) in training the MLM, and wherein the training of the MLM is performed based on the obtained second information.

8. The method according to claim 7, wherein the second information comprises one or more of:- one or more codebooks a second device (132) is to assume during an inference phase of the MLM or a respective MLM,- a fifth indication of one or more configurations of a report of the DL RSs that the second device (132) is to assume during the inference phase, selected from: i. subbands the second device (132) is to report CSI for,ii. subband size of the report,iii. subband Precoder Matrix Indicator, PMI, reporting,iv. subband Channel Quality Information, CQI, reporting,v. wideband PMI reporting, andvi. wideband CQI reporting- third information about how one or more beams of the one or more frequency resources for reception of the DL RSs are spatially related to each other, anda sixth indication of one or more conditions corresponding to the transmission of the DL RSs the second device (132) is to assume during the inference phase upon receipt of the sixth indication.

9. The method according to any of claims 3-8, wherein one or more of:i. the RSs are Channel State Information, CSI, RSs,ii. the second set of frequency resources is a subset of the first set of frequency resources,iii. the first information is output to a second network node (112) operating in the communications system (100),iv. the obtaining (704) of the first indication and the second indication, is based on obtaining, from the first network node (111), a respective second indication of the respective second sets of frequency resources, andv. the communications system (100) is a wireless communications system (100).

10. A computer-implemented method performed by a second device (132), the method being for handling information pertaining to Reference Signals, RSs, the second device (132) operating in a communications system (100), the method comprising:- obtaining (805) a first first indication indicating a first first set of frequency resources out of one or more first frequency resources configured for reception of downlink, DL, RSs, and a first second indication indicating a first second set of frequency resources out of the one or more first frequency resources, - obtaining (806) one or more first second measurements on the first second set of frequency resources on the DL RSs, as transmitted by a first network node (111) operating in the communications system (100), wherein the first first set of frequency resources is larger than the first second set of frequency resources, and- predicting (807), using first first information indicating the one or more first second measurements as input to a trained machine learning model, MLM, Channel State Information, CSI, of a first channel between the second device (132) and the first network node (111), the prediction being for the first first set of frequency resources, and based on the respective one or more first second measurements on the first second set of frequency resources.

11. The method according to claim 10, further comprising:initiating (808) outputting a seventh indication of the predicted CSI.

12. The method according to any of claims 10-11, wherein the method further comprises:- obtaining (801) the trained MLM, from a first device (131) or a second network node (112) operating in the communications system (100).

13. The method according to any of claims 10-12, further comprising one or more of:- providing (802), to the first network node (111), a first previous indication indicating a first capability for the performance of measurements on the DL RSs, - obtaining (803), from the first network node (111), one or more first configurations of the one or more first frequency resources for reception of the DL RSs, wherein the obtaining (803) of the one or more first configurations is based on the provided first previous indication, and- obtaining (804) first second information to be input by the second device (132) to the MLM for the predicting (805) of the CSI.

14. The method according to claim 13, wherein the first second information comprises one or more of:- one or more codebooks the second device (132) is to assume for the predicting (805) of the CSI,- a fifth indication of one or more configurations of a report of the DL RSs that the second device (132) is to assume for the predicting (805) of the CSI, selected from:i. subbands the second device (132) is to report CSI for,ii. subband size of the report,iii. subband Precoder Matrix Indicator, PMI, reporting,iv. subband Channel Quality Information, CQI, reporting,v. wideband PMI reporting, andvi. wideband CQI reporting,- third information about how one or more beams of the one or more first frequency resources for reception of the DL RSs are spatially related to each other, and- a sixth indication of one or more conditions corresponding to the transmission of the DL RSs the second device (132) is to assume for the predicting (805) of the CSI based on the receipt of the sixth indication.

15. The method according to any of claims 10-14, wherein one or more of:i. the RSs are Channel State Information, CSI, RSs,ii. the first second set of frequency resources is a subset of the first first set of frequency resources,iii. the obtaining (805) of the first first indication and the first second indication, is based on obtaining, from the first network node (111), a respective first second indication of the first second set of frequency resources,iv. the predicting (807) is further based on a first correspondence between the first first set of frequency resources and the first second set of frequency resources, andv. the communications system (100) is a wireless communications system (100).

16. A computer-implemented method performed by a first network node (111), the method being for handling information pertaining to Reference Signals, RSs, the first network node (111) operating in a communications system (100), the method comprising:- providing (910) a first first indication indicating a first first set of frequency resources out of one or more first frequency resources configured for reception of downlink, DL, RSs, at a second device (132) operating in the communications system (100), and a first second indication indicating a first second set of frequency resources out of the one or more first frequency resources, wherein the first first set of frequency resources is larger than the first second set of frequency resources, and- transmitting (911) the DL RSs on the first second set of frequency resources to the second device (132).

17. The method according to claim 16, further comprising:- receiving (912), from the second device (132), a seventh indication of a predicted Channel State Information, CSI, of a first channel between the second device (132) and the first network node (111), the prediction being for the first first set of frequency resources, and based on respective one or more first second measurements performed by the second device (132) on the first second set of frequency resources, and, optionally further based on a first correspondence between the first first set of frequency resources and the first second set of frequency resources.

18. The method according to any of claims 16-17, further comprising:- providing (904), to a first device (131) operating in the communications system (100), a first indication indicating a first set of frequency resources out of one or more frequency resources configured for reception of the downlink, DL, RSs, by the first device (131), and a second indication indicating a second set of frequency resources out of the one or more frequency resources, and, optionally, a third indication indicating a correspondence between the first set of frequency resources and the second set of frequency resources, and- transmitting (905) the DL RSs to the first device (131),i. on the first set of frequency resources, andii. on the second set of frequency resources.

19. The method of claim 18, further comprising:- receiving (906), from the first device (131), first information indicating:i. one or more first measurements on the first set of frequency resources, ii. one or more second measurements on the second set of frequency resources, andiii. optionally, the correspondence.

20. The method according to claim 19, wherein the providing (904) of the first indication, the second indication and the third indication, the transmitting (905) of the DL RSs, and the receiving (906) of the first information is iterated for a plurality of respective second sets of frequency resources and, optionally, a corresponding plurality of correspondences between the respective second set of frequency resources and the first set of frequency resources.

21. The method according to claim 20, wherein the method further comprises one or more of:- initiating (907) training of a machine learning model, MLM, with the received first information for each respective iteration, the MLM being to predict Channel State Information, CSI, of a channel between the first device (131) and the first network node (111), the prediction being for the first set of frequency resources, based on the respective one or more second measurements on the second set of frequency resources, and- initiating (908) outputting a fourth indication of the trained MLM.

22. The method according to claim 21, further comprising:using (909) the trained MLM to predict CSI of the channel between the first device (131) and the first network node (111), or a second channel between the first device (131) and a third network node (113).

23. The method according to any of claims 21-22, wherein during the training phase of the MLM, the one or more second measurements on the second set of frequency resources are used as input to the MLM, and the one or more first measurements are used as output labels of the MLM.

24. The method according to any of claims 18-23, further comprising one or more of:- obtaining (901), from the first device (131), a previous indication indicating a capability for the performance of measurements on the DL RSs,- providing (902), to the first device (131), one or more configurations of the one or more frequency resources for reception of the DL RSs, wherein the providing (902) of the one or more configurations is based on the obtained previous indication, and- providing (903), to the first device (131), second information to assist the first device (131) in training a respective MLM, to predict Channel State Information, CSI, of a channel between the first device (131) and the first network node (111), the prediction being for the first set of frequency resources, based on respective one or more second measurements on the second set of frequency resources, and wherein the training of the respective MLM is performed based on the provided second information.

25. The method according to claim 24, wherein the second information comprises one or more of:- one or more codebooks a second device (132) is to assume during an inference phase of the respective MLM,- a fifth indication of one or more configurations of a report of the DL RSs that the second device (132) is to assume during the inference phase, selected from: i. subbands the second device (132) is to report CSI for,ii. subband size of the report,iii. subband Precoder Matrix Indicator, PMI, reporting,iv. subband Channel Quality Information, CQI, reporting,v. wideband PMI reporting, andvi. wideband CQI reporting,- third information about how one or more beams of the one or more frequency resources for reception of the DL RSs are spatially related to each other, and - a sixth indication of one or more conditions corresponding to the transmission of the DL RSs the second device (132) is to assume during the inference phase upon receipt of the sixth indication.

26. The method according to any of claims 17-25, wherein one or more of:i. the RSs are Channel State Information, CSI, RSs,ii. the first second set of frequency resources is a subset of the first set of frequency resources, andiii. the communications system (100) is a wireless communications system (100).

27. A computer-implemented method performed by a second network node (112), the method being for handling information pertaining to Reference Signals, RSs, the second network node (112) operating in a communications system (100), the method comprising:- obtaining (1002) first information from a first device (131) indicating:i. one or more first measurements on downlink, DL, RSs transmitted by a first network node (111) operating in a communications system (100), on a first set of frequency resources out of one or more frequency resources configured for reception of the DL RSs, at the first device (131), ii. one or more second measurements of the DL RSs, on a second set of frequency resources, out of the one or more frequency resources, wherein the first set of frequency resources is larger than the second set of frequency resources, andiii. a correspondence between the first set of frequency resources and the second set of frequency resources.

28. The method according to claim 27, wherein the method is iterated for a plurality of respective second sets of frequency resources and, optionally, a corresponding plurality of correspondences between the respective second set of frequency resources and the first set of frequency resources.

29. The method according to claim 28, further comprising one or more of:- initiating (1003) training of a machine learning model, MLM, with the obtained first information for each respective iteration, the MLM being to predict ChannelState Information, CSI, of a channel between the first device (131) and the first network node (111), the prediction being for the first set of frequency resources, based on the respective one or more second measurements on the second set of frequency resources, and- initiating (1004) outputting a fourth indication of the trained MLM.

30. The method according to claim 29, further comprising:- using (1005) the trained MLM to predict CSI of the channel between the first device (131) and the first network node (111), or a second channel between the first device (131) and a third network node (113).

31. The method according to any of claims 29-30 wherein, during the training phase of the MLM, the one or more second measurements on the second set of frequency resources are used as input to the MLM, and the one or more first measurements are used as output labels of the MLM.

32. The method according to any of claims 28-31, further comprising one or more of:- obtaining (1001) second information to assist the second network node (112) in training the MLM, and wherein the training of the MLM is performed based on the obtained second information.

33. The method according to claim 32, wherein the second information comprises one or more of:- one or more codebooks a second device (132) is to assume during an inference phase of the MLM,- a fifth indication of one or more configurations of a report of the DL RSs that the second device (132) is to assume during the inference phase, selected from: i. subbands the second device (132) is to report CSI for,ii. subband size of the report,iii. subband Precoder Matrix Indicator, PMI, reporting,iv. subband Channel Quality Information, CQI, reporting,v. wideband PMI reporting, andvi. wideband CQI reporting,- third information about how one or more beams of the one or more frequency resources for reception of the DL RSs are spatially related to each other, and- a sixth indication of one or more conditions corresponding to the transmission of the DL RSs the second device (132) is to assume during the inference phase upon receipt of the sixth indication.

34. The method according to any of claims 27-33, wherein one or more of:i. the RSs are Channel State Information, CSI, RSs,ii. the second set of frequency resources is a subset of the first set of frequency resources, andiii. the communications system (100) is a wireless communications system (100).

35. A first device (131), for handling information pertaining to Reference Signals, RSs, the first device (131) being configured to operate in a communications system (100), the first device (131) being further configured to:- obtain a first indication configured to indicate a first set of frequency resources out of one or more frequency resources configured for reception of downlink, DL, RSs, a second indication configured to indicate a second set of frequency resources out of the one or more frequency resources, and a third indication configured to indicate a correspondence between the first set of frequency resources and the second set of frequency resources, wherein the first set of frequency resources is configured to be larger than the second set of frequency resources, and- perform, on the DL RSs, as configured to be transmitted by a first network node (111) configured to operate in the communications system (100),i. one or more first measurements on the first set of frequency resources, andii. one or more second measurements on the second set of frequency resources.

36. The first device (131) according to claim 35, being further configured to:- output first information configured to indicate:i. the one or more first measurements,ii. the one or more second measurements, andiii. the correspondence.

37. The first device (131) according to any of claims 35-36, wherein the first device (131) is configured to iterate the obtaining, the performing and the outputting for a plurality ofrespective second sets of frequency resources and, optionally, a corresponding plurality of correspondences between the respective second set of frequency resources and the first set of frequency resources.

38. The first device (131) according to claim 37, wherein the first device (131) is further configured to one or more of:- initiate training of a machine learning model, MLM, with the first information configured to be output for each respective iteration, the MLM being configured to predict Channel State Information, CSI, of a channel between the first device (131) and the first network node (111), the prediction being configured to be for the first set of frequency resources, based on the respective one or more second measurements on the second set of frequency resources, and- initiate outputting a fourth indication of the trained MLM.

39. The first device (131) according to claim 38, being further configured to:- use the trained MLM to predict CSI of the channel between the first device (131) and the first network node (111), or a second channel between the first device (131) and a third network node (113).

40. The first device (131) according to any of claims 38-39 wherein, during the training phase of the MLM, the one or more second measurements on the second set of frequency resources are used as input to the MLM, and the one or more first measurements are used as output labels of the MLM.

41. The first device (131) according to any of claims 38-40, being further configured to one or more of:- provide, to the first network node (111), a previous indication configured to indicate a capability for the performance of measurements on the DL RSs, - obtain, from the first network node (111), one or more configurations of the one or more frequency resources for reception of the DL RSs, wherein the obtaining of the one or more configurations is configured to be based on the previous indication configured to be provided, and- obtain second information to assist the first device (131) in training the MLM, and wherein the training of the MLM is configured to be performed based on the second information configured to be obtained.

42. The first device (131) according to claim 41, wherein the second information is configured to comprise one or more of:- one or more codebooks a second device (132) is to assume during an inference phase of the MLM or a respective MLM,- a fifth indication of one or more configurations of a report of the DL RSs that the second device (132) is to assume during the inference phase, selected from: i. subbands the second device (132) is to report CSI for,ii. subband size of the report,iii. subband Precoder Matrix Indicator, PMI, reporting,iv. subband Channel Quality Information, CQI, reporting,v. wideband PMI reporting, andvi. wideband CQI reporting,- third information about how one or more beams of the one or more frequency resources for reception of the DL RSs are spatially related to each other, and - a sixth indication of one or more conditions corresponding to the transmission of the DL RSs the second device (132) is to assume during the inference phase upon receipt of the sixth indication.

43. The first device (131) according to any of claims 37-42, wherein one or more of:i. the RSs are configured to be Channel State Information, CSI, RSs, ii. the second set of frequency resources is configured to be a subset of the first set of frequency resources,iii. the first information is configured to be output to a second network node (112) configured to operate in the communications system (100), iv. the obtaining of the first indication and the second indication, is configured to be based on obtaining, from the first network node (111), a respective second indication of the respective second sets of frequency resources, andv. the communications system (100) is configured to be a wireless communications system (100).

44. A second device (132), for handling information pertaining to Reference Signals, RSs, the second device (132) being configured to operate in a communications system (100), the second device (132) being further configured to:- obtain a first first indication configured to indicate a first first set of frequency resources out of one or more first frequency resources configured for reception of downlink, DL, RSs, and a first second indication configured to indicate a firstsecond set of frequency resources out of the one or more first frequency resources,- obtain one or more first second measurements on the first second set of frequency resources on the DL RSs, as configured to be transmitted by a first network node (111) configured to operate in the communications system (100), wherein the first first set of frequency resources is configured to be larger than the first second set of frequency resources, and- predict, using first first information configured to indicate the one or more first second measurements as input to a trained machine learning model, MLM, Channel State Information, CSI, of a first channel between the second device (132) and the first network node (111), the prediction being configured to be for the first first set of frequency resources, and based on the respective one or more first second measurements on the first second set of frequency resources.

45. The second device (132) according to claim 44, being further configured to:- initiate outputting a seventh indication of the predicted CSI.

46. The second device (132) according to any of claims 44-45, wherein the second device (132) is further configured to:- obtain the trained MLM, from a first device (131) or a second network node (112) configured to operate in the communications system (100).

47. The second device (132) according to any of claims 44-46, being further configured to one or more of:- provide, to the first network node (111), a first previous indication configured to indicate a first capability for the performance of measurements on the DL RSs, - obtain, from the first network node (111), one or more first configurations of the one or more first frequency resources for reception of the DL RSs, wherein the obtaining of the one or more first configurations is configured to be based on the first previous indication configured to be provided, and- obtain first second information to be input by the second device (132) to the MLM for the predicting of the CSI.

48. The second device (132) according to claim 47, wherein the first second information is configured to comprise one or more of:- one or more codebooks the second device (132) is to assume for the predicting of the CSI,a fifth indication of one or more configurations of a report of the DL RSs that the second device (132) is to assume for the predicting of the CSI, configured to be selected from:i. subbands the second device (132) is to report CSI for,ii. subband size of the report,iii. subband Precoder Matrix Indicator, PMI, reporting,iv. subband Channel Quality Information, CQI, reporting,v. wideband PMI reporting, andvi. wideband CQI reporting,- third information configured to be about how one or more beams of the one or more first frequency resources for reception of the DL RSs are spatially related to each other, and- a sixth indication of one or more conditions corresponding to the transmission of the DL RSs the second device (132) is to assume for the predicting of the CSI based on the receipt of the sixth indication.

49. The second device (132) according to any of claims 44-48, wherein one or more of:i. the RSs are configured to be Channel State Information, CSI, RSs, ii. the first second set of frequency resources is configured to be a subset of the first first set of frequency resources,iii. the obtaining of the first first indication and the first second indication, is configured to be based on obtaining, from the first network node (111), a respective first second indication of the first second set of frequency resources,iv. wherein the predicting is configured to be further based on a first correspondence between the first first set of frequency resources and the first second set of frequency resources, andv. the communications system (100) is configured to be a wireless communications system (100).

50. A first network node (111), for handling information pertaining to Reference Signals, RSs, the first network node (111) being configured to operate in a communications system (100), the first network node (111) being further configured to:- provide a first first indication configured to indicate a first first set of frequency resources out of one or more first frequency resources configured for reception of downlink, DL, RSs, at a second device (132) configured to operate in the communications system (100), and a first second indication configured toindicate a first second set of frequency resources out of the one or more first frequency resources, wherein the first first set of frequency resources is configured to be larger than the first second set of frequency resources, and - transmit the DL RSs on the first second set of frequency resources to the second device (132).

51. The first network node (111) according to claim 50, being further configured to:- receive, from the second device (132), a seventh indication of a predicted Channel State Information, CSI, of a first channel between the second device (132) and the first network node (111), the prediction being configured to be for the first first set of frequency resources, and based on respective one or more first second measurements configured to be performed by the second device (132) on the first second set of frequency resources, and, optionally further configured to be based on a first correspondence between the first first set of frequency resources and the first second set of frequency resources.

52. The first network node (111) according to any of claims 50-51, further comprising:- provide, to a first device (131) configured to operate in the communications system (100), a first indication configured to indicate a first set of frequency resources out of one or more frequency resources configured for reception of the downlink, DL, RSs, by the first device (131), and a second indication configured to indicate a second set of frequency resources out of the one or more frequency resources, and, optionally, a third indication configured to indicate a correspondence between the first set of frequency resources and the second set of frequency resources, and- transmit the DL RSs to the first device (131),i. on the first set of frequency resources, andii. on the second set of frequency resources.

53. The first network node (111) of claim 52, being further configured to:- receive, from the first device (131), first information configured to indicate:i. one or more first measurements on the first set of frequency resources, ii. one or more second measurements on the second set of frequency resources, andiii. optionally, the correspondence.

54. The first network node (111) according to claim 53, wherein the providing of the first indication, the second indication and the third indication, the transmitting of the DL RSs, and the receiving of the first information is configured to be iterated for a plurality of respective second sets of frequency resources and, optionally, a corresponding plurality of correspondences between the respective second set of frequency resources and the first set of frequency resources.

55. The first network node (111) according to claim 54, wherein the first network node (111) is further configured to one or more of:- initiate training of a machine learning model, MLM, with the first information configured to be received for each respective iteration, the MLM being configured to be to predict Channel State Information, CSI, of a channel between the first device (131) and the first network node (111), the prediction being configured to be for the first set of frequency resources, based on the respective one or more second measurements on the second set of frequency resources, and - initiate outputting a fourth indication of the trained MLM.

56. The first network node (111) according to claim 55, being further configured to:- use the trained MLM to predict CSI of the channel between the first device (131) and the first network node (111), or a second channel between the first device (131) and a third network node (113).

57. The first network node (111) according to any of claims 55-56 wherein, during the training phase of the MLM, the one or more second measurements on the second set of frequency resources are configured to be used as input to the MLM, and the one or more first measurements are configured to be used as output labels of the MLM.

58. The first network node (111) according to any of claims 52-57, being further configured to one or more of:- obtain, from the first device (131), a previous indication configured to indicate a capability for the performance of measurements on the DL RSs,- provide, to the first device (131), one or more configurations of the one or more frequency resources for reception of the DL RSs, wherein the providing of the one or more configurations is configured to be based on the previous indication configured to be obtained, and- provide, to the first device (131), second information configured to assist the first device (131) in training a respective MLM, to predict Channel State Information,CSI, of a channel between the first device (131) and the first network node (111), the prediction being for the first set of frequency resources, based on respective one or more second measurements on the second set of frequency resources, and wherein the training of the respective MLM is configured to be performed based on the second information configured to be provided.

59. The first network node (111) according to claim 58, wherein the second information is configured to comprise one or more of:- one or more codebooks a second device (132) is to assume during an inference phase of the respective MLM,- a fifth indication of one or more configurations of a report of the DL RSs that the second device (132) is to assume during the inference phase, selected from: i. subbands the second device (132) is to report CSI for,ii. subband size of the report,iii. subband Precoder Matrix Indicator, PMI, reporting,iv. subband Channel Quality Information, CQI, reporting,v. wideband PMI reporting, andvi. wideband CQI reporting,- third information configured to be about how one or more beams of the one or more frequency resources for reception of the DL RSs are configured to be spatially related to each other, and- a sixth indication of one or more conditions configured to correspond to the transmission of the DL RSs the second device (132) is to assume during the inference phase upon receipt of the sixth indication.

60. The first network node (111) according to any of claims 51-59, wherein one or more of:i. the RSs are configured to be Channel State Information, CSI, RSs, ii. the first second set of frequency resources is configured to be a subset of the first set of frequency resources, andiii. the communications system (100) is configured to be a wireless communications system (100).

61. A second network node (112), for handling information pertaining to Reference Signals, RSs, the second network node (112) being configured to operate in a communications system (100), the second network node (112) being further configured to:- obtain first information from a first device (131) configured to indicate:i. one or more first measurements on downlink, DL, RSs configured to be transmitted by a first network node (111) configured to operate in a communications system (100), on a first set of frequency resources out of one or more frequency resources configured for reception of the DL RSs, at the first device (131),ii. one or more second measurements of the DL RSs, on a second set of frequency resources, out of the one or more frequency resources, wherein the first set of frequency resources is configured to be larger than the second set of frequency resources, andiii. a correspondence between the first set of frequency resources and the second set of frequency resources.

62. The second network node (112) according to claim 61, wherein the second network node (112) is configured to iterate the obtaining for a plurality of respective second sets of frequency resources and, optionally, a corresponding plurality of correspondences between the respective second set of frequency resources and the first set of frequency resources.

63. The second network node (112) according to claim 62, further configured to one or more of:- initiate training of a machine learning model, MLM, with the first information configured to be obtained for each respective iteration, the MLM being configured to predict Channel State Information, CSI, of a channel between the first device (131) and the first network node (111), the prediction being configured to be for the first set of frequency resources, based on the respective one or more second measurements on the second set of frequency resources, and- initiate outputting a fourth indication of the trained MLM.

64. The second network node (112) according to claim 63, being further configured to:- use the trained MLM to predict CSI of the channel between the first device (131) and the first network node (111), or a second channel between the first device (131) and a third network node (113).

65. The second network node (112) according to any of claims 63-64 wherein, during the training phase of the MLM, the one or more second measurements on the second set of frequency resources are configured to be used as input to the MLM, and the one or more first measurements are configured to be used as output labels of the MLM.

66. The second network node (112) according to any of claims 62-65, being further configured to:- obtain second information to assist the second network node (112) in training the MLM, and wherein the training of the MLM is configured to be performed based on the second information configured to be obtained.

67. The second network node (112) according to claim 66, wherein the second information is configured to comprise one or more of:- one or more codebooks a second device (132) is to assume during an inference phase of the MLM,- a fifth indication of one or more configurations of a report of the DL RSs that the second device (132) is to assume during the inference phase, configured to be selected from:i. subbands the second device (132) is to report CSI for,ii. subband size of the report,iii. subband Precoder Matrix Indicator, PMI, reporting,iv. subband Channel Quality Information, CQI, reporting,v. wideband PMI reporting, andvi. wideband CQI reporting,- third information configured to be about how one or more beams of the one or more frequency resources for reception of the DL RSs are configured to be spatially related to each other, and- a sixth indication of one or more conditions configured to correspond to the transmission of the DL RSs the second device (132) is to assume during the inference phase upon receipt of the sixth indication.

68. The second network node (112) according to any of claims 61-67, wherein one or more of:i. the RSs are configured to be Channel State Information, CSI, RSs, ii. the second set of frequency resources is configured to be a subset of the first set of frequency resources, andiii. the communications system (100) is configured to be a wireless communications system (100).

Images