Apparatus, methods, and computer programs

The proposed solution addresses the challenge of interference in CSI reconstruction by using AI/ML models and specific CSI-RS patterns to isolate and remove interference, resulting in improved CSI accuracy and channel capacity in wireless communication systems.

WO2024230967A1PCT designated stage expired Publication Date: 2024-11-14NOKIA TECHNOLOGIES OY
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
PCT/EP2024/057227
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-05-09
Filing Date
2024-03-19
Publication Date
2024-11-14

AI Technical Summary

Technical Problem

Current communication systems face challenges in accurately reconstructing channel state information (CSI) due to interference from intercarrier, inter symbol, co-channel, and cross-link interference, leading to suboptimal signal-to-noise ratio and channel capacity in wireless communication networks.

Method used

An apparatus and method that determine channel state information by removing interference components from the initial CSI value, using a combination of encoder and decoder with AI/ML models, and specific CSI-RS patterns to isolate and mitigate interference, enabling accurate CSI reconstruction and codebook selection.

Benefits of technology

This approach enhances the accuracy of CSI reconstruction, reduces feedback overhead, and improves signal-to-noise ratio, leading to increased channel capacity and efficient communication in wireless networks.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure EP2024057227_14112024_PF_FP_ABST
    Figure EP2024057227_14112024_PF_FP_ABST
Patent Text Reader

Abstract

An apparatus comprising: means for determining a first value for channel state information, said first value based on a channel between a user equipment and a base station, and on interference; means for determining, based on the first value for the channel state information, a code, said code being generated by an encoder; means for determining a second value for channel state information by removing at least a component of the interference from the first value; and means for causing one or more of the second value or the code to be provided to the base station.
Need to check novelty before this filing date? Find Prior Art

Description

[0001] APPARATUS, METHODS, AND COMPUTER PROGRAMS

[0002] Field of the disclosure

[0003] The present disclosure generally relates to apparatus, methods and computer programs in communication systems, and in particular, but not exclusively, to apparatus, methods and computer programs relating to channel state information.

[0004] Background

[0005] A communication system can be seen as a facility that enables communications between two or more communication devices, or provides communication devices access to a data network.

[0006] A communication system may be a wireless communication system. Examples of wireless communication systems comprise mobile systems operating based on radio access technology standards such as those provided by 3 GPP (Third Generation Partnership Project) or ETSI (European Telecommunications Standards Institute), satellite communication systems, and Wi-Fi communication systems. A Wireless communication system operating based on a radio access technology has a coverage are that can typically be divided into cells and are therefore often referred to as cellular systems.

[0007] A radio access technology standard sets out what the various entities of the communication system are permitted to do and how that should be achieved. For example, communication protocols and / or parameters to be used by communication devices for accessing or connecting to a radio access network are defined .

[0008] Examples of a standard are the so-called 5G (5thGeneration) standards provided by 3GPP.

[0009] Summary

[0010] According to a first aspect, there is provided an apparatus comprising: means for determining a first value for channel state information, said first value based on a channel between a user equipment and a base station, and on interference; means for determining, based on the first value for the channel state information, a code, said code being generated by an encoder; means for determining a second value for channel state information by removing at least a component of the interference from the first value; and means for causing one or more of the second value or the code to be provided to the base station.

[0011] One or more components of the interference may be a result of one or more of: intercarrier interference; inter symbol interference; co-channel interference; or cross-link interference. The apparatus may comprise means for receiving, from the base station, reference signals.

[0012] A transmitted power of reference signals, received from the base station, may be dependent on signal to interference noise ratio information associated with a channel between the user equipment and the base station.

[0013] The apparatus may comprise means for receiving from the base station a plurality of different patterns of reference signals.

[0014] The apparatus may comprise means for receiving from the base station one or more instructions associated with one or more of the different patterns for reference signals.

[0015] The apparatus may comprise means for using a first of said different patterns to determine a matrix of a plurality of first values.

[0016] The apparatus may comprise means for using one or more other of said different receive signal patterns to determine one or more interference values associated with one or more components of the interference.

[0017] Two or more different patterns may be used to determine interference values associated with different components of the interference.

[0018] The apparatus may be provided in or be a communications device.

[0019] According to another aspect, there is provided a method comprising: determining a first value for channel state information, said first value based on a channel between a user equipment and a base station, and on interference; determining, based on the first value for the channel state information, a code, said code being generated by an encoder; determining a second value for channel state information by removing at least a component of the interference from the first value; and causing one or more of the second value or the code to be provided to the base station.

[0020] One or more components of the interference may be a result of one or more of: intercarrier interference; inter symbol interference; co-channel interference; or cross-link interference.

[0021] The method may comprise receiving, from the base station, reference signals.

[0022] A transmitted power of the received reference signals may be dependent on signal to interference noise ratio information associated with a channel between the user equipment and the base station.

[0023] The method may comprise receiving from the base station a plurality of different patterns of reference signals. The method may comprise receiving from the base station one or more instructions associated with one or more of the different patterns for reference signals.

[0024] The method may comprise using a first of said different patterns to determine a matrix of a plurality of first values.

[0025] The method may comprise using one or more other of said different receive signal patterns to determine one or more interference values associated with one or more components of the interference.

[0026] Two or more different patterns may be used to determine interference values associated with different components of the interference.

[0027] The method may be performed by an apparatus. The apparatus may be provided in or be a communications device.

[0028] According to another aspect, there is provided an apparatus comprising at least one processor and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: determine a first value for channel state information, said first value based on a channel between a user equipment and a base station, and on interference; determine, based on the first value for the channel state information, a code, said code being generated by an encoder; determine a second value for channel state information by removing at least a component of the interference from the first value; and cause one or more of the second value or the code to be provided to the base station.

[0029] One or more components of the interference may be a result of one or more of: intercarrier interference; inter symbol interference; co-channel interference; or cross-link interference.

[0030] The apparatus may be caused to receive, from the base station, reference signals.

[0031] A transmitted power of reference signals, received from the base station, may be dependent on signal to interference noise ratio information associated with a channel between the user equipment and the base station.

[0032] The apparatus may be caused to receive from the base station a plurality of different patterns of reference signals.

[0033] The apparatus be caused to receive from the base station one or more instructions associated with one or more of the different patterns for reference signals.

[0034] The apparatus may be caused to use a first of said different patterns to determine a matrix of a plurality of first values. The apparatus may be caused to used one or more other of said different receive signal patterns to determine one or more interference values associated with one or more components of the interference.

[0035] Two or more different patterns may be used to determine interference values associated with different components of the interference.

[0036] The apparatus may be provided in or be a communications device.

[0037] According to another aspect, there is provided a method comprising: receiving from a user equipment one or more of: a) a code, said code being determined by an encoder based on a first value for channel state information for a channel between the user equipment and a base station, and on interference; or b) a second value for channel state information, said second value being determined by removing at least a component of the interference from the first value.

[0038] The method may comprise training a decoder such that the decoder receives said code as an input and provides said second value as an output.

[0039] One or more components of the interference may be a result of one or more of: intercarrier interference; inter symbol interference; co-channel interference; or cross-link interference.

[0040] The method may comprise transmitting reference signals.

[0041] A transmitted power of the reference signals may be dependent on signal to interference noise ratio information associated with a channel between the user equipment and the base station.

[0042] The method may comprise transmitting a plurality of different patterns of reference signals.

[0043] The method may comprise transmitting one or more instructions associated with one or more of the different patterns for reference signals.

[0044] A first of said different patterns may be used to determine a matrix of a plurality of first values.

[0045] One or more other of said different receive signal patterns may be used to determine one or more interference values associated with one or more components of the interference.

[0046] Two or more different patterns may be used to determine interference values associated with different components of the interference.

[0047] The method may be performed by an apparatus. The apparatus may be or provided in a base station. According to another aspect, there is provided an apparatus comprising: means for receiving from a user equipment one or more of: a) a code, said code being determined by an encoder based on a first value for channel state information for a channel between the user equipment and a base station, and on interference; or b) a second value for channel state information, said second value being determined by removing at least a component of the interference from the first value.

[0048] The apparatus may comprise means for training a decoder such that the when the decoder receives said code as an input, the decoder provides said second value as an output.

[0049] One or more components of the interference may be a result of one or more of: intercarrier interference; inter symbol interference; co-channel interference; or cross-link interference.

[0050] The apparatus may comprise means for transmitting reference signals.

[0051] A transmitted power of the reference signals may be dependent on signal to interference noise ratio information associated with a channel between the user equipment and the base station.

[0052] The apparatus may comprise means for transmitting a plurality of different patterns of reference signals.

[0053] The apparatus may comprise means for transmitting one or more instructions associated with one or more of the different patterns for reference signals.

[0054] A first of said different patterns may be used to determine a matrix of a plurality of first values.

[0055] One or more other of said different receive signal patterns may be used to determine one or more interference values associated with one or more components of the interference.

[0056] Two or more different patterns may be used to determine interference values associated with different components of the interference.

[0057] The apparatus may be or provided in a base station.

[0058] According to another aspect, there is provided an apparatus comprising at least one processor and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: receive from a user equipment one or more of: a) a code, said code being determined by an encoder based on a first value for channel state information for a channel between the user equipment and a base station, and on interference; or b) a second value for channel state information, said second value being determined by removing at least a component of the interference from the first value. The apparatus may be caused to train a decoder such that the when the decoder receives said code as an input, the decoder provides said second value as an output.

[0059] One or more components of the interference may be a result of one or more of: intercarrier interference; inter symbol interference; co-channel interference; or cross-link interference.

[0060] The apparatus may be caused to transmit reference signals.

[0061] A transmitted power of the reference signals may be dependent on signal to interference noise ratio information associated with a channel between the user equipment and the base station.

[0062] The apparatus may be caused to transmit a plurality of different patterns of reference signals.

[0063] The apparatus may be caused to transmit one or more instructions associated with one or more of the different patterns for reference signals.

[0064] A first of said different patterns may be used to determine a matrix of a plurality of first values.

[0065] One or more other of said different receive signal patterns may be used to determine one or more interference values associated with one or more components of the interference.

[0066] Two or more different patterns may be used to determine interference values associated with different components of the interference.

[0067] The apparatus may be or provided in a base station.

[0068] The apparatus may comprise at least one processor and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus to perform any of the previous methods.

[0069] The apparatus may comprise at circuitry to cause the apparatus to perform any of the previous methods.

[0070] According to a further aspect, there is provided a computer program comprising instructions, which when executed by an apparatus, cause the apparatus to perform any of the methods set out previously.

[0071] According to a further aspect, there is provided a computer program comprising instructions, which when executed cause any of the methods set out previously to be performed.

[0072] According to an aspect there is provided a computer program comprising computer executable code which when cause any of the methods set out previously to be performed.

[0073] According to an aspect, there is provided a computer readable medium comprising program instructions stored thereon for performing at least one of the above methods. According to an aspect, there is provided a non-transitory computer readable medium comprising program instructions which when executed by an apparatus, cause the apparatus to perform any of the methods set out previously.

[0074] According to an aspect, there is provided a non-transitory computer readable medium comprising program instructions which when executed cause any of the methods set out previously to be performed.

[0075] According to an aspect, there is provided a non-volatile tangible memory medium comprising program instructions stored thereon for performing at least one of the above methods.

[0076] In the above, many different aspects have been described. It should be appreciated that further aspects may be provided by the combination of any two or more of the aspects described above.

[0077] Various other aspects are also described in the following detailed description and in the attached claims.

[0078] Brief Description of the Figures

[0079] Some examples will now be described in further detail, by way of illustration only, with reference to the accompanying drawings, in which:

[0080] Figure 1 shows a schematic representation of a 5G system;

[0081] Figure 2 shows a schematic representation of an apparatus;

[0082] Figure 3 shows a schematic representation of a user equipment;

[0083] Figure 4 shows schematically shows the propagation of an interference effect on the user equipment side to codebook selection by the base station;

[0084] Figure 5 shows an example CSI-RS (channel state information reference signal) pattern for isolating interference from a desired channel;

[0085] Figure 6 shows schematically a de-noising autoencoder for cleaning coloured channel state information of some embodiments;

[0086] Figure 7 shows a signal flow of some embodiments;

[0087] Figure 8 shows a method of some embodiments; and

[0088] Figure 9 shows another method of some embodiments.

[0089] Detailed Description

[0090] In the following certain embodiments are explained with reference to communication devices capable of communication via a wireless cellular system and mobile communication systems serving such communication devices. Before explaining in detail, the exemplifying embodiments, certain general principles of a wireless communication system, access systems thereof, and communication devices are briefly explained with reference to Figures 1, 2 and 3 to assist in understanding the technology underlying the described examples.

[0091] Figure 1 shows a schematic representation of a communication system operating based on a 5thgeneration radio access technology (generally referred to as a 5G system (5GS)). The 5GS may comprise a (radio) access network ((R)AN), a 5G core network (5GC), one or more application functions (AF) and one or more data networks (DN). A user equipment may access or connect to the one or more DNs via the 5GS.

[0092] The 5G (R)AN may comprise one or more base stations or radio access network (RAN) nodes, such as a gNodeB (gNB). A base station or RAN node may comprise one or more distributed units connected to a central unit.

[0093] The 5GC may comprise various network functions, such as an access and mobility management function (AMF), a session management function (SMF), an authentication server function (AUSF), a user data management (UDM), a user plane function (UPF), a network data repository, a network exposure function (NEF), a service communication proxy (SCP), edge application server discovery function (EASDF), policy control function (PCF), network slice access control function (NSACF), network slice specific authentication and authorization function (NSSAAF), and / or network slicing selection function (NSSF) .

[0094] Figure 2 illustrates an example of an apparatus 200. The apparatus 200 may be provided in a user equipment and / or in a base station. The apparatus 200 may have at least one processor and at least one memory storing instructions of one or more functions that, when executed by at least one of the at least one processor cause operations or actions of one or more functions to be performed. In this example, the apparatus may comprise at least one random access memory (RAM) 211a, and / or at least one read only memory (ROM) 211b. The apparatus may comprise at least one processor 212, 213 and / or an input / output interface 214. The at least one processor 212, 213 may be coupled to the at least one memory which in this example is the RAM 211a and the ROM 211b. The at least one processor 212, 213 may be configured to execute an appropriate software code 215. The software code 215 may, for example, allow the apparatus to perform one or more steps of one or more of the present aspects.

[0095] Figure 3 illustrates an example of a communication device 300. The communication device 300 may be any device capable of or configured for sending and receiving wireless signals, including radio signals. Other non-limiting examples of a communication device 300 comprise a mobile station (MS) or mobile device such as a mobile phone or what is known as a ’smart phone’, a computer provided with a wireless interface card or other wireless interface facility (e.g., USB dongle), a personal data assistant (PDA) or a tablet, a machine-type communications (MTC) device, a Cellular Internet of things (CIoT) device or any combinations of these or the like.

[0096] The communication device 300 may be configured to send or receive wireless signals, for example, radio signals carrying communications. The communications may be one or more of voice, electronic mail (email), text message, multimedia, data, machine data and so on.

[0097] The communication device 300 may be configured to send and / or receive radio signals over an air or radio interface 307 via a transceiver apparatus 306. The transceiver apparatus 306 may comprise a radio part and associated antenna arrangement. The radio part may convert the base band signal to the radio frequency and / or vice versa. The antenna arrangement may be arranged internally or externally to the mobile device and may include a single antenna or multiple antennas. The antenna arrangement may be an antenna array comprising a plurality of antenna elements.

[0098] The communication device 300 may comprise at least one processor 301, and / or at least one memory. The at least one memory may be at least one ROM 302a, and / or at least one RAM 302b. Other possible components 303 may be provided for use in software and hardware aided execution of tasks it is designed to perform, including control of access to and communications with access networks, such as the 5G RAN and other communication devices. The at least one processor 301 is coupled to the RAM 302b and the ROM 302a. The at least one processor 301 may be configured to execute instructions of software code 308. Execution of the instructions of the software code 308 may for example allow the communication device 300 to perform one or more operations. The software code 308 may be stored in the ROM 302a. It should be appreciated that in other embodiments, any other suitable memory may be alternatively or additionally used.

[0099] The at least one processor 301, the at least one ROM 302a, and / or the at least one RAM 302b can be provided on an appropriate circuit board, in an integrated circuit, and / or in chipsets. This feature is denoted by reference 304.

[0100] The communication device 300 may optionally have a user interface such as keypad 305, touch sensitive screen or pad, combinations thereof or the like. Optionally, the communication device may have one or more of a display, a speaker and a microphone.

[0101] In the following examples, the term UE or user equipment is used. This term encompasses any of the example of communication device 300 previously discussed and / or any other communication device. The current radio access technology being standardized by 3GPP is often referred to as 5G or NR. Other radio access technologies standardized by 3GPP include long term evolution (LTE) or LTE Advanced Pro of the Universal Mobile Telecommunications System (UMTS).

[0102] Wireless communication systems generally include access networks, such as radio access networks operating based on a radio access technology that include base stations or a radio access network nodes.

[0103] Wireless communication systems may alternatively or additionally include other types of access networks, such as a wireless local area network (WLAN) and / or a WiMAX (Worldwide Interoperability for Microwave Access) network.

[0104] It should be understood that example embodiments may also be used with standards for future radio access technologies such as 6G and beyond.

[0105] With frequency division duplex (FDD) schemes, downlink channel state information (CSI) is used by base stations (BS) to obtain channel response and precoding for beamforming in a downlink of a massive multiple-input multiple-output (MIMO) system. Accurate CSI can be used by a base station (BS) to obtain higher signal-to-noise-ratio (SNR) and channel capacity. However, in some networks such as a FDD network, the UE estimates the downlink CSI. Thus, the estimated CSI needs to be shared with the BS, which introduces overhead to the network.

[0106] To reduce the overhead, several vector quantization methods have been proposed to generate a codebook that achieves a relatively high compression rate (CR), that is the ratio of compressed size to uncompressed size. CR may be a scalar in the range of (0, 1], and a lower CR means more compression. These methods may not provide enough accuracy for CSI reconstruction with a limited feedback overhead.

[0107] Compressive sensing (CS)-based methods may be used to compress the CSI based on its spatial and temporal correlation. However, channels may not be sparse, which is an assumption for the CS-based approach. Furthermore, CS-based methods use random projections, which can lead to some reconstruction loss in the BS.

[0108] As the issue relates to compression and reconstruction, the autoencoder (AE) structure from deep learning (DL) methods may be applied to the CSI-feedback application. A CsiNet structure has be proposed to do the task using an encoder and a decoder. CsiNet was proposed in Wen, C.; Shih, W; Jin, S. Deep Learning for Massive MIMO CSI Feedback. IEEE Wirel. Commun. Lett. 2018, 7, 748-751. Further work has been done on this structure by others in the field.

[0109] CSINet includes convolutional layers as well as dense layers and refine-net architectures. The encoder generates a compressed representation of the input CSI, and the decoder reconstructs the CSI from the compressed information. By joint training of the encoder and decoder, CsiNet learns the channel structures and may provide more accurate reconstruction compared to the CS-based methods.

[0110] A modified version of the CsiNet structure has been proposed and is called CsiNet+. This modifies the convolution kernel size and reconstruction blocks.

[0111] A fully convolutional neural network (FullyConv)-based CSI feedback has been proposed to enhance the quality of reconstructed CSI and decrease the number of trainable parameters and computational resources compared to the previous methods.

[0112] CsiNet, CsiNet+, and FullyConv methods are designed for a fixed CR.

[0113] To reduce the feedback payload, the output of encoder is a code which is then quantized. The UE communicates the code over the air and the gNB receives the code. The de-quantizer constructs the decoder input using the received code. Lastly, the decoder processes the compressed signal and reconstruct the full CSI.

[0114] There are various different training strategies.

[0115] In CSI compression using a two-sided model use case, the following AI / ML model training collaborations may be used:

[0116] Joint training of the two-sided model at a single side / entity, e.g., UE-sided or Networksided.

[0117] Joint training of the two-sided model at the network side and the UE side, respectively.

[0118] Separate training at the network side and the UE side, where the UE-side CSI generation part and the network-side CSI reconstruction part are trained by the UE side and the network side, respectively.

[0119] Joint training may mean that the generation model and the reconstruction model should be trained in the same loop for forward propagation and backward propagation. Joint training could be done at a single node and / or across multiple nodes. For example, in the case of multiple nodes, this may be done through gradient exchange between nodes.

[0120] Separate training may include sequential training starting with UE side training, or sequential training starting with NW side training, or parallel training at the UE side and the NW side.

[0121] There are various different possibilities for generalization of a ML model. By way of example only, some different cases are set out below. One or more of the following cases may be considered for verifying the generalization performance of an AI / ML model over various scenarios / configurations.

[0122] Case 1 : The AI / ML model is trained based on a training dataset from one Scenario#A / Configuration#A, and then the AI / ML model performs inference / test on a dataset from the same Scenario#A / Configuration#A

[0123] Case 2: The AI / ML model is trained based on training dataset from one Scenario# A / Configurati on# A, and then the AI / ML model performs inference / test on a different dataset than Scenario#A / Configuration#A, e.g., Scenario#B / Configuration#B, S cenari o# A / C onfigurati on#B

[0124] Case 3: The AI / ML model is trained based on training dataset constructed by mixing datasets from multiple scenarios / configurations including Scenario#A / Configuration#A and one or more different datasets than Scenario#A / Configuration#A, e.g., Scenario#B / Configuration#B, Scenario#A / Configuration#B, and then the AI / ML model performs inference / test on a dataset from a single Scenario / Configuration from the multiple scenarios / configurations, e.g., Scenario#A / Configuration#A, Scenario#B / Configuration#B, S cenari o# A / Configurati on#B .

[0125] Case 2A: The AI / ML model is trained based on training dataset from one Scenario#A / Configuration#A, and then the AI / ML model is updated based on a fine-tuning dataset different than Scenario#A / Configuration#A, e.g., Scenario#B / Configuration#B, Scenario#A / Configuration#B. After that, the AI / ML model is tested on a different dataset than Scenario#A / Configuration#A, e.g., subject to Scenario#B / Configuration#B, S cenari o# A / Configurati on#B .

[0126] It should be noted that these cases are by way of example only and one or more other cases may be used. Not all of the cases may be required.

[0127] For CSI enhancement evaluations, to verify the generalization performance of an AI / ML model over various scenarios, a set of scenarios may be considered focusing on one or more of the following aspects as a starting point:

[0128] Various deployment scenarios (e.g., UMa (urban macro), UMi (urban micro), and / or InH (indoor hotspot));

[0129] Various outdoor / indoor UE distributions for UMa / UMi (e.g., 10:0, 8:2, 5:5, 2:8, 0: 10); and / or

[0130] Various carrier frequencies (e.g., 2GHz, 3.5GHz).

[0131] Other aspects may be taken into account in one or more of scenarios. For example, one or more of the following may alternatively or additionally be taken into account: various antenna spacing; various antenna virtualization (TxRU mapping -TxRU is the interface between the base band unit and the radio distribution network); various ISDs (inter-site distance); various UE speeds; and / or the like. For C SI enhancement evaluations, to verify the generalization / scalability performance of an AI / ML model over various configurations (e.g., which may potentially lead to different dimensions of model input / output), the set of configurations may be considered focusing on one or more of the following aspects as a starting point:

[0132] Various bandwidths (e.g., 10MHz, 20MHz) and / or frequency granularities, (e.g., size of sub band);

[0133] Various sizes of CSI feedback payloads, and / or candidate payload number;

[0134] Various antenna port layouts, e.g., (N1 / N2 / P) and / or antenna port numbers (e.g., 32 ports, 16 ports); and / or

[0135] Other configurations such as, for example, various numerologies, various rank numbers / layers, and / or the like.

[0136] CSI is estimated using a CSI-RS. CSI describes the channel response in frequency and space domain. A channel estimator used to retrieve the response may assume that: the received subcarriers are orthogonal i.e., no intercarrier interference (ICI); the channel maximum delay spread is shorter than the duration of the CP (cyclic prefix) i.e., no inter-symbol interference (ISI); and / or

[0137] CSI-RS are not being interfered by a concurrent DL or UL transmission (no co-channel interference (CI) and no cross-link interference (CLI)).

[0138] However, in practice, ICI may occur whenever the UE moves at high speeds. ISI may be present in rural areas (see hilly terrain channel models). CI may occur when data and positioning services are triggered simultaneously and are uncoordinated (which is the default operation). CLI may appear in flexible-duplexing scenarios.

[0139] The received CSI-RS may be contaminated by self- or co- / cross-link interference and / or additive white Gaussian noise. The channel responses h estimated using an interference- unaware receiver absorb the errors caused by the various sources of interference and noise. These errors in h translate in coloured (i.e., interfered) CSI matrices which are sent to the CSI autoencoder. The decoder side of the autoencoder will reconstruct a coloured CSI which inherently degrades the codebook selection. In this regard, reference is made to Figure 4. On the UE 400, as referenced 402, the CSI-RS is corrupted by self-interference or co-channel interference. The corrupted CSI-RS is provided to an interference unaware estimator 404. As referenced 406, an erroneous channel response is estimated. As referenced 408, a CSI matrix is built. The output CSI matrix is a coloured CSI matrix, as referenced 410. The coloured matrix is encoded as referenced 412 to provide a codeword selection.

[0140] On the gNB 416, the received codeword is decoded as referenced 418. This leads to the reconstruction of the coloured CSI data set as referenced 420. The codebook selection is based on the reconstructed CSI data set, as referenced 422. This leads to an erroneous codebook selection as referenced 424.

[0141] To ensure an accurate codebook selection in the base station, it is desirable that the decoder reconstructs a clean version of the CSI.

[0142] To ensure an autoencoder architecture which is agnostic to the severity of noise and / or self- and / or co / crosslink interference, it is desirable that the decoder reconstructs a clean version of the CSI.

[0143] In some embodiments, a CSI denoising framework may be provided. In this framework, the decoder may reconstruct a clean CSI matrix. The decoder may be an AI / ML decoder. The clean CSI matrix may be reconstructed, regardless of the severity of self- and / or co-channel interference.

[0144] In some embodiments, a training CSI-RS pattern may be selected and used which enables the UE to label the coloured-CSI with both the codes generated by the encoder, but also with the clean-CSI.

[0145] To enable a clean CSI reconstruction, some embodiments may use the following training procedure.

[0146] The gNB may obtains information about the UE. The information may be any suitable information. For example the information may comprise the speed regime of the UE. The information may comprise CI and CLI conditions. The information may comprise the channel maximum excess delay.

[0147] It should be appreciated that the bases station decoder may be trained using training data which is provided by different UEs and / or simulated data.

[0148] Using the information about the UE, the gNB may design a CSI-RS pattern. The training specific CSI-RS may be provided by non-ML methods at the gNB. These are used to extract coloured and clean-CSI at the encoder.

[0149] In this regard, reference is made to Figure 5 which shows an example training specific CSI-RSI pattern to be used by the UE. The example training specific CSI-RSI pattern comprises one or more or all of: a first pattern portion 500 which contains interfered CSI-RS; a second pattern portion 502 where the CSI-RS are punctured in frequency domain to isolate the ICI effect. The puncture size may be proportional to the maximum Doppler shift. The CSI-RS may thus be muted on some resources, so that the self-interference (leakage from the active subcarriers) can be observed, and the ICI can be estimated. The UE speed may be used to configure a comb pattern in the frequency domain which the UE may use to isolate the ICI effect. This UE speed information may be acquired by the gNB using the most recent or a recent data / control signal exchange, by estimating the maximum Doppler shift associated with the signal exchange; a third pattern portion 504 where the CSI-RS are punctured in the time domain to isolate the ISI effect. The puncture size may be proportional to the duration of the channel tail outside the CP duration. Channel tail is the superimposition of all the multipath components arriving at the UE with a delay larger than the CP duration. This may be based on a channel maximum excess delay. This information may be used to configure a muting pattern in the time domain which the UE may use to isolate the ISI effect. This information may be cell-specific, and / or beam-specific; and / or a fourth pattern portion 506 where the CSI-RS are punctured in the time and frequency domain to isolate the co-channel and cross-link interference. This may use information about concurrent UL / DL transmissions. This information is used to configure a muting pattern in time-frequency to isolate the CI and CLI effects. This information may be obtained from the neighbour gNBs via an explicit request procedure. This may be via the X2 / Xn interfaces or any other gNB to gNB interface.

[0150] The gNB may indicate the selected pattern and / or the pattern effect (i.e., isolate ICI, ISI, CI, CLI) to the UE.

[0151] The gNB may instruct the UE to use the first pattern to compute the coloured CSI matrix, (referred to as colour-CSI).

[0152] The gNB may instruct the UE to use one or more of the second, third, and fourth patterns. This is to estimate ICI, ISI, CI, and / or CLI.

[0153] The gNB may instructs the UE to use the coloured CSI matrix and the estimated ICI, ISI, CI, and / or CLI to compute a clean CSI matrix, (referred to as clean-CSI).

[0154] The SNR of the received signal by UE may be determined. This information may be used to adapt the transmission power of the reference signal at the gNB. An adaptable transmission power may help to estimate the clean CSI at high SNR.

[0155] The following may provide a denoising autoencoder which uses input colour CSI and provides clean CSI as an output.

[0156] The UE may apply the instructions from the gNB. The UE may determine first a colour- CSI and from that a clean-CSI.

[0157] The UE may use the colour-CSI obtained by the UE as input to the encoder and produces code C. The UE prepares a training set to share with the gNB. The UE may generates tuples: {colour-CSI, C, clean-CSI} for all observation points. These samples may be used for further model tuning in some embodiments.

[0158] The UE transfers a training data sub-set to the gNB, where the sub-set consist of the pair: {C, clean-CSI}. In some embodiments, the UE may transfer all of the tuple. gNB uses the received pairs to train a matched decoder that receives as input the code C and outputs clean-CSI.

[0159] Thus the CSI autoencoder may be denoised. As schematically shown in Figure 6, during training, the coloured-CSI 600 obtained by the UE is used as input to the encoder 602, to produce code C as referenced 604. The clean-CSI is sent to the decoder 606 of the gNB as label to the code C. In other words, the gNB receives (code C, clean-CSI) and trains the decoder with input = C, label = clean-CSI. By doing so, the CSI autoencoder is enriched with a denoising capability as the decoder will output a clean CSI 608.

[0160] This may be advantageous during the inference phase (i.e., once deployed). When the CSI-RS are being interfered in the field, the UE may use its interference-unaware CSI estimator and compute a coloured-CSI, which is then encoded in a code that is transferred to the gNB, knowing that the gNB decoder will implicitly clean the code from all interference effects and output a clean-CSI.

[0161] A channel estimator of an NR modem may assume that no ICI, ISI, CI or CLI contaminate the CSI-RS reception. In other words, the estimator believes that the received signal y(a,j,k) at antenna a, symbol j, subcarrier k contains only the contribution of the transmit signal x(j,k) at symbol j, subcarrier k multiplied by the channel response h(a,j,k) and corrupted by AWGN (additive white Gaussian noise) n(a,j,k): y(a,j ,k)=h(a,j ,k)x(j ,k)+n(a,j ,k),

[0162] V a=l:A,j=l:J,k=l:K model (1)

[0163] The estimator may use the model (1) above to reconstruct h and build the CSI matrix.

[0164] However, there may be some situations in which the model (1) does not apply.

[0165] For example, at high speeds, the orthogonality of the subcarriers is lost. The ICI phenomenon (a first type of self-interference) appears.

[0166] Then, instead of model (1), the received signal at subcarrier k contains the contribution of the TX signal at all subcarriers i.e. k, and d k. V a = 1: A,j = l J, k = 1: K model (2)

[0167] In a second example, when the UE experiences channels with delays longer than CP (e.g., hilly terrain), the received signal at symbol j is contaminated by ISI (a second type of self-interference) i.e., the signals transmitted during symbols i<j contaminate the current symbol j reception:

[0168] In a third example, concurrent transmissions from L other cells may create CLI or CI, so that the received signal becomes a sum between the desired signal and interfering signals from other gNBs and UEs:

[0169] In another example, the UE may experience any two or more of the conditions of examples one to three.

[0170] The received CSI-RS may be contaminated by self- interference and / or co- / cross-link interference in addition to AWGN. In this case, the channel responses h estimated using the mismatched model (1) absorb the errors caused by the various sources of interference as discussed in relation to models (2-4). Erroneous h estimates lead to coloured (i.e., interfered) CSI matrices which are sent to the CSI autoencoder. The decoder side of the autoencoder will reconstruct a coloured CSI which degrades the codebook selection.

[0171] Training-specific CSI-RS may be used such as previously discussed. In some embodiments, the gNB helps the UE in isolating the various interfering signals, depending on their source, during the training phase only. Then, once each interfering signal is isolated, it may be estimated, and removed from the received CSI-RS. By doing so, the gNB may enable the UE to compute: a coloured-CSI estimate - containing both useful channel and all interferers; and a clean-CSI estimate - containing only the useful channel.

[0172] To achieve the above, the UE uses a training-specific (TS) CSI-RS pattern such as previously discussed.

[0173] Reference is made to Figure 7 which shows a signalling flow of some embodiments. As referenced 1, the gNB may do one or more of the following: determine the UE speed; determine the channel maximum excess delay; collect CI and / or CLI information from one or more neighbouring gNBs; and predict the SNR based on signals received from the UE.

[0174] As referenced 2, the gNB may evaluate to determine one or more of the ICI, ISI, CI, CLI and SNR. This may be the case where processing of the data received in 1 is needed.

[0175] As referenced, the first to fourth patterns are selected. The patterns which are used are dependent on one or more of the values determined in 2. This may be as previously described.

[0176] As referenced 4, the gNB configures the UE with the TS CSLRS and transmission power. The transmission power may be dependent on the SNR. The gNB may additionally indicate which of the TS CSI-RS patterns should be used to isolate each type of interference. This may be as previously described.

[0177] As referenced 5, the gNB transmits the TS CSI-RS.

[0178] As referenced 6, the UE uses TS CSI-RS to compute both the coloured-CSI and clean- CSI.

[0179] As referenced 7, the UE encodes the coloured-CSI to code C.

[0180] As referenced 8, the UE generates the training data set tuples (coloured-CSI, code C, clean CSI).

[0181] As referenced 9, the UE sends the data sub-set to the gNB, where the sub-set consist of the pair: {C, clean-CSI}. The coloured CSI may be sent to the gNB. This may be used by the gNB to determine how much interference the UE is experiencing. This may be used for future link configuration e.g. adapting of the MCS (modulation coding scheme.

[0182] As referenced 10, the gNB trains the decoder with the pair (clean-CSI, C) so that the decoder can implicitly learn to recover a clean CSI from an interfered code C.

[0183] Some embodiments may not increase the computational complexity of the baseband modem. The channel estimator may not need modification.

[0184] Some embodiments may compensate for self- and co-channel interference.

[0185] Some embodiments may provide accurate CSI reconstruction agnostic to interference type.

[0186] In some embodiments the TS CSI-RS may be defined and configured to be used in model updates for AI / ML CSI feedback. In inference, standard CSI-RS may be used along with the ML model trained on TS-CSI-RS.

[0187] The ML model may be any suitable model, such as previously described. Some embodiments may comprises receiving, at a user equipment (UE), a configuration from a network entity (e.g. gNB). The configuration may comprises at least one of a trainingspecific channel state indicator reference signal (TS CSI RS) configuration, a transmission power, and / or expected interference types;

[0188] In some embodiments, the TS-CSI-RS configuration may be applied to estimate coloured-CSI and clean-CSI. The coloured-CSI may comprise useful channel and interferences and the clean-CSI comprises the useful channel with at least some of the interferences removed.

[0189] In some embodiments, training dataset tuples are generated. The training dataset tuples may comprise at least one of the coloured-CSI, a code C, or the clean-CSI. The code C is encoded from the coloured-CSI.

[0190] In some embodiments, at least one of the code C or the clean-CSI is transmitted to the network entity.

[0191] It should be appreciated that reference has been made to coloured or interfered CSI. This may comprise one value or a plurality of values. Where there a plurality of values, these may comprise a coloured CSI matrix.

[0192] It should be appreciated that reference has been made to clean CSI. This may comprise one value or a plurality of values. Where there a plurality of values, these may comprise a clean CSI matrix.

[0193] The code may be provided by codeword in some embodiments.

[0194] Reference is made to Figure 8 which shows a method of some embodiments.

[0195] This method may be performed by an apparatus. The apparatus may be in or be a communications device.

[0196] The apparatus may comprise suitable means, such as circuitry for providing the method.

[0197] Alternatively or additionally, the apparatus may comprise at least one processor and at least one memory storing instructions that, when executed by the at least one processor cause the apparatus at least to provide the method below.

[0198] Alternatively or additionally, the apparatus may be such as discussed in relation to Figure 2 or 3.

[0199] The method may be provided by computer program code or computer executable instructions.

[0200] The method may comprise as referenced Al, determining a first value for channel state information, said first value based on a channel between a user equipment and a base station, and on interference. The method may comprise as referenced A2, determining, based on the first value for the channel state information, a code, said code being generated by an encoder;

[0201] The method may comprise as referenced A3, determining a second value for channel state information by removing at least a component of the interference from the first value; and

[0202] The method may comprise as referenced A4, causing one or more of the second value or the code to be provided to the base station. The first value may be provided to the base station.

[0203] It should be appreciated that the steps of Figure 8 may take place in any suitable order.

[0204] It should be appreciated that the method outlined in Figure 8 may be modified to include any of the previously described features.

[0205] Computer program code may be downloaded and stored in one or more memories of the relevant apparatus or device.

[0206] Reference is made to Figure 9 which shows a method of some embodiments.

[0207] This method may be performed by an apparatus. The apparatus may be in or be a base station.

[0208] The apparatus may comprise suitable means, such as circuitry for providing the method.

[0209] Alternatively or additionally, the apparatus may comprise at least one processor and at least one memory storing instructions that, when executed by the at least one processor cause the apparatus at least to provide the method below.

[0210] Alternatively or additionally, the apparatus may be such as discussed in relation to Figure 2.

[0211] The method may be provided by computer program code or computer executable instructions.

[0212] The method may comprise as referenced Bl, receiving from a user equipment one or more of: a) a code, said code being determined by an encoder based on a first value for channel state information for a channel between the user equipment and a base station, and on interference; or b) a second value for channel state information, said second value being determined by removing at least a component of the interference from the first value.

[0213] It should be appreciated that the method outlined in Figure 9 may be modified to include any of the previously described features.

[0214] Computer program code may be downloaded and stored in one or more memories of the relevant apparatus or device. Therefore, although certain embodiments were described above by way of example with reference to certain example architectures for wireless networks, technologies and standards, embodiments may be applied to any other suitable forms of communication systems than those illustrated and described herein. In this example, some embodiments have been described in relation to a 5G network. It should be appreciated that other embodiments may be provided in any other suitable network in which multicast services are provided by access nodes. Those multicast services may be provided to UEs which are connected to the network or which are in an inactive state. In the inactive state, the connection has not been taken down but is inactive. For example, the context of the UE may be retained.

[0215] It is also noted herein that while the above describes example embodiments, there are several variations and modifications which may be made to the disclosed solution without departing from the scope of the present invention.

[0216] As used herein, “at least one of the following: ” and “at least one of ” and similar wording, where the list of two or more elements are joined by “and” or “or”, mean at least any one of the elements, or at least any two or more of the elements, or at least all the elements.

[0217] In general, the various embodiments may be implemented in hardware or special purpose circuitry, software, logic or any combination thereof. Some aspects of the disclosure may be implemented in hardware, while other aspects may be implemented in firmware or software which may be executed by a controller, microprocessor or other computing device, although the disclosure is not limited thereto. While various aspects of the disclosure may be illustrated and described as block diagrams, flow charts, or using some other pictorial representation, it is well understood that these blocks, apparatus, systems, techniques or methods described herein may be implemented in, as non-limiting examples, hardware, software, firmware, special purpose circuits or logic, general purpose hardware or controller or other computing devices, or some combination thereof.

[0218] As used in this application, the term “circuitry” may refer to one or more or all of the following:

[0219] (a) hardware-only circuit implementations (such as implementations in only analog and / or digital circuitry) and

[0220] (b) combinations of hardware circuits and software, such as (as applicable):

[0221] (i) a combination of analog and / or digital hardware circuit(s) with software / firmware and

[0222] (ii) any portions of hardware processor(s) with software (including digital signal processor(s)), software, and memory(ies) that work together to cause an apparatus, such as a mobile phone or server, to perform various functions) and

[0223] (c) hardware circuit(s) and or processor(s), such as a microprocessor s) or a portion of a microprocessor s), that requires software (e.g., firmware) for operation, but the software may not be present when it is not needed for operation.”

[0224] This definition of circuitry applies to all uses of this term in this application, including in any claims. As a further example, as used in this application, the term circuitry also covers an implementation of merely a hardware circuit or processor (or multiple processors) or portion of a hardware circuit or processor and its (or their) accompanying software and / or firmware. The term circuitry also covers, for example and if applicable to the particular claim element, an integrated circuit such as a baseband integrated circuit or processor integrated circuit for a mobile device or a similar integrated circuit in server, a cellular network device, or other computing or network device.

[0225] The embodiments of this disclosure may be implemented by computer software executable by a data processor of the mobile device, such as in the processor entity, or by hardware, or by a combination of software and hardware. Computer software or program, also called program product, including software routines, applets and / or macros, may be stored in any apparatus-readable data storage medium and they comprise program instructions to perform particular tasks. A computer program product may comprise one or more computerexecutable components which, when the program is run, are configured to carry out embodiments. The one or more computer-executable components may be at least one software code or portions of it.

[0226] Further in this regard it should be noted that any blocks of the logic flow as in the Figures may represent program steps, or interconnected logic circuits, blocks and functions, or a combination of program steps and logic circuits, blocks and functions. The software may be stored on such physical media as memory chips, or memory blocks implemented within the processor, magnetic media such as hard disk or floppy disks, and optical media such as for example DVD and the data variants thereof, CD. The physical media is a non-transitory media.

[0227] The term “non-transitory,” as used herein, is a limitation of the medium itself (i.e., tangible, not a signal) as opposed to a limitation on data storage persistency (e.g., RAM vs. ROM).

[0228] The memory may be of any type suitable to the local technical environment and may be implemented using any suitable data storage technology, such as semiconductor-based memory devices, magnetic memory devices and systems, optical memory devices and systems, fixed memory and removable memory. The data processors may be of any type suitable to the local technical environment, and may comprise one or more of general-purpose computers, special purpose computers, microprocessors, digital signal processors (DSPs), application specific integrated circuits (ASIC), FPGA, gate level circuits and processors based on multi core processor architecture, as non-limiting examples.

[0229] Embodiments of the disclosure may be practiced in various components such as integrated circuit modules. The design of integrated circuits is by and large a highly automated process. Complex and powerful software tools are available for converting a logic level design into a semiconductor circuit design ready to be etched and formed on a semiconductor substrate.

[0230] The foregoing description has provided by way of non-limiting examples a full and informative description of the exemplary embodiments of this disclosure. However, various modifications and adaptations may become apparent to those skilled in the relevant arts in view of the foregoing description, when read in conjunction with the accompanying drawings and the appended claims. Indeed, there are further embodiments comprising a combination of one or more embodiments with any of the other embodiments previously discussed. The scope of protection sought for some embodiments of the disclosure is set out by the claims. The embodiments and features, if any, described in this specification that do not fall under the scope of the claims are to be interpreted as examples useful for understanding various embodiments of the disclosure. It should be noted that different claims with differing claim scope may be pursued in related applications such as divisional or continuation applications.

Claims

CLAIMS1. An apparatus comprising: means for determining a first value for channel state information, said first value based on a channel between a user equipment and a base station, and on interference; means for determining, based on the first value for the channel state information, a code, said code being generated by an encoder; means for determining a second value for channel state information by removing at least a component of the interference from the first value; and means for causing one or more of the second value or the code to be provided to the base station.

2. The apparatus as claimed in claim 1, wherein one or more components of the interference is a result of one or more of: intercarrier interference; inter symbol interference; co-channel interference; or cross-link interference.

3. The apparatus as claimed in claim 2, wherein a transmitted power of reference signals, received from the base station, is dependent on signal to interference noise ratio information associated with a channel between the user equipment and the base station.

4. The apparatus as claimed in any preceding claim, comprising means for receiving from the base station a plurality of different patterns of reference signals.

5. The apparatus as claimed in claim 4, comprising means for receiving from the base station one or more instructions associated with one or more of the different patterns for reference signals.

6. The apparatus as claimed 4 or 5, comprising means for using a first of said different patterns to determine a matrix of a plurality of first values.

7. The apparatus as claimed in claim 4, 5 or 6, comprising means for using one or more other of said different receive signal patterns to determine one or more interference values associated with one or more components of the interference.

8. The apparatus as claimed in claim 7, wherein two or more different patterns are used to determine interference values associated with different components of the interference.

9. A method comprising: determining a first value for channel state information, said first value based on a channel between a user equipment and a base station, and on interference; determining, based on the first value for the channel state information, a code, said code being generated by an encoder; determining a second value for channel state information by removing at least a component of the interference from the first value; and causing one or more of the second value or the code to be provided to the base station.

10. The method as claimed in claim 9, wherein one or more components of the interference is a result of one or more of: intercarrier interference; inter symbol interference; co-channel interference; or cross-link interference.

11. The method as claimed in claim 9 or 10, comprising receiving from the base station a plurality of different patterns of reference signals.

12. The method as claimed in claim 11, receiving from the base station one or more instructions associated with one or more of the different patterns for reference signals.

13. The method as claim 11 or 12, comprising using a first of said different patterns to determine a matrix of a plurality of first values.

14. The method as claimed in claim 11, 12 or 13, comprising using one or more other of said different receive signal patterns to determine one or more interference values associated with one or more components of the interference.

15. The method as claimed in claim 14, wherein two or more different patterns are used to determine interference values associated with different components of the interference.

16. A method comprising:receiving from a user equipment one or more of: a) a code, said code being determined by an encoder based on a first value for channel state information for a channel between the user equipment and a base station, and on interference; or b) a second value for channel state information, said second value being determined by removing at least a component of the interference from the first value.

17. The method as claimed in claim 16, comprising training a decoder such that the decoder receives said code as an input and provides said second value as an output.

18. An apparatus comprising: means for receiving from a user equipment one or more of: a) a code, said code being determined by an encoder based on a first value for channel state information for a channel between the user equipment and a base station, and on interference; or b) a second value for channel state information, said second value being determined by removing at least a component of the interference from the first value.

19. The apparatus as claimed in claim 18, comprising means for training a decoder such that the when the decoder receives said code as an input, the decoder provides said second value as an output.

20. A computer program comprising computer executable instructions which when run cause the method of any of claims 9 to 17 to be performed.

Citation Information

Patent Citations

  • Channel state information reporting for partially cancelled interference

    US20140003267A1

  • Signaling for a channel state information reference signal (CSI-RS)

    US20220052827A1

  • Reporting configurations for neural network-based processing at a ue

    WO2022040046A1