Artificial intelligence native radio resource management inspired by large language models

Abstract

Embodiments of a scheduler for generating radio resource management, RRM, decisions in a radio network. The scheduler comprises: a preprocessing block configured to receive input signals and generate corresponding tokens; and an Artificial Intelligence, AI, agent configured to receive the tokens from the preprocessing block, and generate RRM decisions based on the tokens using one or more Transformers.

Description

P112240W001Artificial Intelligence Native Radio Resource Management Inspired by Large Language ModelsTechnical Field

[0001] This application is based on, and claims benefit of US provisional patent application No. 63 / 713653 filed October 30, 2024, the entire content of which is incorporated herein by reference.Technical Field

[0002] The present disclosure relates to Radio Resource Management (RRM) and in particular to Artificial Intelligence (Al) native RRM inspired by large language models.Background

[0003] Artificial Intelligence (Al) is expected to play a crucial role in nextgeneration wireless systems, i.e. 6G, by either enhancing or replacing current technologies used in 4G and 5G systems. This is caused by the need for more efficient and adaptive solutions to manage complex communication environments. For instance, Al is shown to improve energy efficiency, spectrum sensing, and latency in various scenarios.

[0004] Radio Resource Management (RRM) and its scheduling mechanisms are a significant area of impact for Al. This is because RRM includes various multi-objective optimization problems and classification tasks which, unlike traditional approaches, Al is able to address efficiently. For instance, recent studies show Al’s potential to improve resource allocation while adapting to various dynamic conditions.

[0005] The known prior art presents a transformer-based deep reinforcement learning (TDRL) approach that optimizes resource allocation in multi-user cellular networks, improving spectral efficiency and fairness. Likewise, the decision transformer framework enhances adaptability and efficiency in resource management. In addition, the prior art proposes a deep reinforcement learning (DRL) model for loadP112240W001 balancing in 6G networks, which improves throughput and latency by adapting to realtime network conditions and sudden traffic changes. Such models based on reinforcement learning techniques often rely on user-defined reward functions that could be potentially far from the real-world requirements needed by the operators.

[0006] The prior art demonstrates the use of Transformers in Massive MIMO processing and semantic communication, improving both physical layer and higher- level communication in 6G networks. Transformer models are also applied in channel state information (CSI) prediction for V2X communication, enhancing interference management through accurate CSI predictions. Other prior art explore transformerbased methods for optimizing resource allocation in multicarrier NOMA systems, focusing on channel assignment and power allocation. Finally, the SURE model as used in the prior art uses Transformers for uplink radio resource prediction in 5G dual connectivity, improving throughput through joint 4G and 5G training.

[0007] While the above-described methods provide insights into various aspects of RRM and transformers, most of them do not specifically address the challenges associated with scheduling tasks, which are essential for resource management optimization in multi-user environments or even practical implementation strategies in dynamic real-world scenarios.

[0008] As previously mentioned, RRM includes various multi-objective optimization problems and classification tasks. Many of such problems either don’t have an optimal solution or their optimal solution is extremely complex to implement. Hence, various suboptimal or heuristic algorithms are used which achieve subpar performance. Additionally, a lot of input grouping, filtering and preprocessing are required to address various tasks within RRM, e.g. in scheduling, which increases the latency of decision making or packet processing.Summary

[0009] Certain aspects of the disclosure and their embodiments may provide solutions to these or other challenges. Currently, many isolated suboptimal algorithmsP112240W001 are used within RRM scheduling procedure to allocate resources to different UEs. In certain aspects, a main objective is to replace all (or most of) such algorithms with a single Al agent that allocates resources in a more efficient, adaptive and context-aware manner. Here, the auto-regressive nature of Transformer models is leveraged within an Al agent that navigates through heterogeneous and massive information used by an rule-based scheduler, filters them, and uses the appropriate information to allocate resources to different users. More specifically, an Al agent is shown that can effectively address some specific subtasks within each of the four main scheduling tasks, i.e. Physical Downlink Control Channel (PDCCH), Physical Downlink Shared Channel (PDSCH), Physical Uplink Shared Channel (PUSCH), Physical Uplink Control Channel (PUCCH) allocation, while effectively handling real-time changes in network conditions, without any feature engineering or input filtering.

[0010] Accordingly, aspects of the present disclosure provide a scheduler for generating radio resource management, RRM, decisions in a radio network. The scheduler comprises: a preprocessing block configured to receive input signals and generate corresponding tokens; and an Artificial Intelligence, Al, agent configured to receive the tokens from the preprocessing block, and generate RRM decisions based on the tokens using one or more Transformers.

[0011] In some embodiments, the input signals comprise: initial configuration, IC, signals comprising a number of downlink CSI-reference signal, RS, ports; and an indication of frequency division multiplexing, FDD, or time division multiplexing, TDD; and external input, El, signals comprising user downlink buffer status and power headroom.

[0012] In some embodiments, the preprocessing block comprises: a breaker configured partition each input signal into respective tokens; and a mapper configured to receive the tokens from the breaker, and map the received tokens to an identifier.

[0013] In some embodiments, the breaker is configured partition each input signal in accordance with one or more of:P112240W001• Naive Tokenization, wherein an input signal value is prefixed with a signal name and is used as token;• Offset-based Tokenization, wherein where an offset from a current slot is the token;• Integers, wherein El signals that are integers are split into multiple tokens, each representing two digits, starting from the least significant digit; and• floating points, wherein El signals that are floating point values are split into five tokens: a first token indicating the sign, a second token for digits before the decimal, and three tokens for digits after the decimal, with two digits per token up to the sixth decimal place.

[0014] In some embodiments, the Al agent comprises a respective functional block configured to generate RRM decisions related to each scheduler task, wherein each functional block comprises a one or more Transformer models.

[0015] In some embodiments, scheduler tasks comprise one or more of:• Physical Downlink Control Channel, PDCCH, scheduling;• Physical Downlink Shared Channel, PDSCH, scheduling;• Physical Uplink Control Channel, PUCCH, scheduling; and• Physical Uplink Shared Channel, PUSCH, scheduling.

[0016] In certain aspects, includes the system architecture of the Al agent, tokenization block used for training and prediction, and the leveraging LLM to mimic a rule-based scheduler.

[0017] Certain embodiments may provide one or more of the following technical advantage(s). In certain embodiments, the legacy algorithms used in RRM are replaced with an Al agent which benefits from a constant running time, constant memory usage, easier fine-tuning, and the ability to efficiently run on commodity accelerators. As a concrete example, as several RAN vendors embark on their journey towards cloud- RAN implementation, they are incurring high development cost to port their rule-based scheduler implementation from their proprietary hardware to an off-the-shelf computing platform, such as x86-based platforms; however, if their rule-basedP112240W001 scheduler were an Al-based scheduler instead, then porting the implementation would be much simpler due to the proliferation of matrix multiplication accelerators.Additionally, such an Al agent removes the need for feature engineering, input filtering and input grouping which in turn could potentially reduce the latency for resource allocation.

[0018] Embodiments of a base station, communication system, and a method in a communication system are also disclosed.Brief Description of the Drawings

[0019] The accompanying drawing figures incorporated in and forming a part of this specification illustrate several aspects of the disclosure, and together with the description serve to explain principles of the disclosure.

[0020] FIG. 1 is a block diagram illustrating a high-level overview of an architecture in accordance with embodiments of the present disclosure;

[0021] FIG. 2 is a block diagram illustrating a preprocessing block of FIG. 1 in accordance with embodiments of the present disclosure;

[0022] FIG. 3 is a block diagram illustrating an Al agent of FIG. 1 in accordance with embodiments of the present disclosure;

[0023] Fig.4. is a chart illustrating an example training loss for user priority prediction in PDCCH scheduling in accordance with embodiments of the present disclosure;

[0024] FIG. 5 is a chart illustrating an example validation loss for user priority prediction in PDCCH scheduling in accordance with embodiments of the present disclosure;

[0025] FIG. 6 is a chart illustrating an example training loss for number of allocated CCEs in PDCCH scheduling in accordance with embodiments of the present disclosure;P112240W001

[0026] FIG. 7 is a chart illustrating an example validation loss for number of allocated CCEs prediction in PDCCH scheduling in accordance with embodiments of the present disclosure;

[0027] FIG. 8 is a chart illustrating an example Confusion matrix for number of allocated CCEs prediction in PDCCH scheduling in accordance with embodiments of the present disclosure;

[0028] FIG. 9 is a chart illustrating an example Attention for number of allocated CCEs prediction in PDCCH scheduling in accordance with embodiments of the present disclosure;

[0029] FIG. 10 is a chart illustrating an example Training loss for user start CCE prediction in PDCCH scheduling in accordance with embodiments of the present disclosure;

[0030] FIG. 11 is a chart illustrating an example Validation loss for start cce prediction in PDCCH scheduling in accordance with embodiments of the present disclosure;

[0031] FIG. 12 shows an example of a communication system in accordance with some embodiments;

[0032] FIG. 13 shows another example of a communication system according to some embodiments;

[0033] FIG. 14 shows a wireless device according to some embodiments;

[0034] FIG. 15 shows a network node in accordance with some embodiments; and

[0035] FIG. 16 is a block diagram illustrating a virtualization environment in which functions implemented by some embodiments may be virtualized.Detailed Description

[0036] The embodiments set forth below represent information to enable those skilled in the art to practice the embodiments and illustrate the best mode of practicing the embodiments. Upon reading the following description in light of the accompanyingP112240W001 drawing figures, those skilled in the art will understand the concepts of the disclosure and will recognize applications of these concepts not particularly addressed herein. It should be understood that these concepts and applications fall within the scope of the disclosure.

[0037] At least some of the following abbreviations and terms may be used in this disclosure.2D Two Dimensional3 GPP Third Generation Partnership Project5G Fifth GenerationAAS Antenna Array SystemAoA Angle of ArrivalAoD Angle of DepartureASIC Application Specific Integrated CircuitBF BeamformingBLER Block Error RateBW BeamwidthCPU Central Processing UnitCSI Channel State Information dB DecibelDCI Downlink Control InformationDFT Discrete Fourier TransformDSP Digital Signal Processor eNB Enhanced or Evolved Node BFIR Finite Impulse ResponseFPGA Field Programmable Gate Array gNB New Radio Base StationICC Information Carrying CapacityHR Infinite Impulse ResponseP112240W001LTE Long Term EvolutionMIMO Multiple Input Multiple OutputMME Mobility Management EntityMMSE Minimum Mean Square ErrorMTC Machine Type CommunicationNR New RadioOTT Over-the-TopPBCH Physical Broadcast ChannelPDCCH Physical Downlink Control ChannelPDSCH Physical Downlink Shared ChannelP-GW Packet Data Network GatewayRAM Random Access MemoryROM Read Only MemoryRRC Radio Resource ControlRRH Remote Radio HeadSCEF Service Capability Exposure FunctionSINR Signal to Interference plus Noise RatioTBS Transmission Block SizeUE User EquipmentULA Uniform Linear ArrayURA Uniform Rectangular Array

[0038] Radio Node: As used herein, a “radio node” is either a radio access node or a wireless device.

[0039] Radio Access Node: As used herein, a “radio access node” or “radio network node” is any node in a radio access network of a cellular communications network that operates to wirelessly transmit and / or receive signals. Some examples of a radio access node include, but are not limited to, a base station (e.g., a New Radio (NR) base station (gNB) in a Third Generation Partnership Project (3GPP) FifthP112240W001Generation (5G) NR network or an enhanced or evolved Node B (eNB) in a 3GPP Long Term Evolution (LTE) network), a high-power or macro base station, a low-power base station (e.g., a micro base station, a pico base station, a home eNB, or the like), and a relay node.

[0040] Core Network Node: As used herein, a “core network node” is any type of node in a core network. Some examples of a core network node include, e.g., a Mobility Management Entity (MME), a Packet Data Network Gateway (P-GW), a Service Capability Exposure Function (SCEF), or the like.

[0041] Wireless Device: As used herein, a “wireless device” is any type of device that has access to (i.e., is served by) a cellular communications network by wirelessly transmitting (and / or receiving) signals to (and / or from) a radio access node. Some examples of a wireless device include, but are not limited to, a User Equipment device (UE) in a 3 GPP network and a Machine Type Communication (MTC) device.

[0042] Network Node: As used herein, a “network node” is any node that is either part of the radio access network or the core network of a cellular communications network / system.

[0043] Cell: As used herein, a “cell” is a combination of radio resources (such as, for example, antenna port allocation, time and frequency) that a wireless device may use to exchange radio signals with a radio access node, which may be referred to as a host node or a serving node of the cell. However, it is important to note that beams may be used instead of cells, particularly with respect to 5G NR. As such, it should be appreciated that the techniques described herein are equally applicable to both cells and beams.

[0044] Note that references in this disclosure to various technical standards (such as 3GPP TS 38.211 V15.1.0 (2018-03) and 3GPP TS 38.214 V15.1.0 (2018-03), for example) should be understood to refer to the specific version(s) of such standard(s) that is(were) current at the time the present application was filed.P112240W001

[0045] The description herein focuses on a 3GPP cellular communications system and, as such, 3 GPP terminology or terminology similar to 3 GPP terminology is oftentimes used. However, the concepts disclosed herein are not limited to a 3 GPP system.

[0046] Systems and methods are disclosed herein that provide present disclosure provide a scheduler for generating radio resource management, RRM, decisions in a radio network. The scheduler comprises: a preprocessing block configured to receive input signals and generate corresponding tokens; and an Artificial Intelligence, Al, agent configured to receive the tokens from the preprocessing block, and generate RRM decisions based on the tokens using one or more Transformers.

[0047] In some embodiments, the input signals comprise: initial configuration, IC, signals comprising a number of downlink CSI-reference signal, RS, ports; and an indication of frequency division multiplexing, FDD, or time division multiplexing, TDD; and external input, El, signals comprising user downlink buffer status and power headroom.

[0048] In some embodiments, the preprocessing block comprises: a breaker configured partition each input signal into respective tokens; and a mapper configured to receive the tokens from the breaker, and map the received tokens to an identifier.

[0049] In some embodiments, the breaker is configured partition each input signal in accordance with one or more of:• Naive Tokenization, wherein an input signal value is prefixed with a signal name and is used as token;• Offset-based Tokenization, wherein where an offset from a current slot is the token;• Integers, wherein El signals that are integers are split into multiple tokens, each representing two digits, starting from the least significant digit; and• floating points, wherein El signals that are floating point values are split into five tokens: a first token indicating the sign, a second token for digits before the decimal,P112240W001 and three tokens for digits after the decimal, with two digits per token up to the sixth decimal place.

[0050] In some embodiments, the Al agent comprises a respective functional block configured to generate RRM decisions related to each scheduler task, wherein each functional block comprises a one or more Transformer models.

[0051] In some embodiments, scheduler tasks comprise one or more of:• Physical Downlink Control Channel, PDCCH, scheduling;• Physical Downlink Shared Channel, PDSCH, scheduling;• Physical Uplink Control Channel, PUCCH, scheduling; and• Physical Uplink Shared Channel, PUSCH, scheduling.

[0052] Radio Resource Management (RRM) and its scheduling mechanisms are a significant area of impact for Al. This is because RRM includes various multi-objective optimization problems and classification tasks which, unlike traditional approaches, Al can address efficiently. Within RRM, the scheduler performs four main allocation tasks:• Physical Downlink Control Channel (PDCCH): This channel is responsible for transmitting control information in the downlink direction, including scheduling commands that allocate resources for other downlink channels.• Physical Downlink Shared Channel (PDSCH): The PDSCH is used for transmitting user data from the base station to the user equipment.• Physical Uplink Shared Channel (PUSCH): The PUSCH facilitates the transmission of user data from the user equipment to the base station.• Physical Uplink Control Channel (PUCCH): The PUCCH carries uplink control signals such as Hybrid Automatic Repeat reQuest (HARQ) acknowledgments, scheduling requests, and channel quality indicators.

[0053] Each of these tasks are then divided into subtasks. For example, PDCCH scheduling consists of various subtasks such as user selection, and Control ChannelP112240W001Element (CCE) (group of resources) allocation via number of CCE (nCCE) and the starting CCE (startCCE) assignments.

[0054] Recent advancements demonstrate that Large Language Models (LLMs) and specifically Transformer models can effectively manage complex sequential data and provide relevant outputs, making them suitable for improving resource allocation and network management. Thus, RRM scheduling can benefit from LLMs, which are characterized by their auto-regressive nature, allowing them to generate predictions based on sequential data inputs. This principle echoes the process used in traditional scheduling methods such as PDCCH allocation, where decisions are made sequentially and adaptively in response to network conditions. In other words, as LLM predicts the next word or token in a sequence based on prior context, this can be used to predict and allocate resources in a dynamic and context-aware manner.

[0055] In this disclosure, the auto-regressive nature of Transformer models is leveraged within an Al agent that navigates through heterogeneous and massive information used by a traditional scheduler, filters them, and uses the appropriate information to allocate resources to different users. More specifically, there is disclosed an Al agent that can effectively address subtasks within each of the four main scheduling tasks while effectively handling real-time changes in network conditions, without any feature engineering or input filtering.High-level Svstem Overview

[0056] A high-level overview of the proposed scheduler architecture including the Al agent is shown within the dashed line in PIG. 1. In the example of FIG. 1, the scheduler 100 comprises a preprocessing block 102, the Al agent 104 and a postprocessing block 106. The preprocessing block 102 generally includes a Rulebased mapping block 108, a Tokenizer 110 and a States block 112.

[0057] Each unit of information used or generated by the scheduler is referred to as a signal. Each signal is then represented by one or more tokens depending on theP112240W001 tokenization process which is described in next section. The inputs of the model are divided into two categories. The first category is called initial configuration (IC) signals, and includes signals such as the number of downlink CSI-reference signal (RS) ports and the choice between frequency division multiplexing (FDD) and time division multiplexing (TDD). The second category is called external input (El) signals which includes information such as the user downlink buffer and power headroom. IC signals remain constant during the simulation, whereas new El signals are constantly being generated and used by the scheduler. Due to memory limitations, feeding every El signal to the model is not feasible, as this would result in an unmanageable number of tokens being fed to the model. Hence, a window called maximum sequence length (MSL) is used to limit the number of signals and therefore tokens fed to the model. In some embodiments, MSL is set to 1000. As the input to the model, for every prediction, the constant IC signals appended with the most recent El signals are passed until the MSL is reached. The output signals generated by the model depend on the sub-task. For instance, for user priority prediction, the output signal consists of only the user ID. On the other hand, the output signal for nCCE prediction includes the number of allocated CCEs as well as the ID of the user CCEs are allocated to. A similar approach is used for startCCE prediction. The predictions are then performed every transmission time interval (TTI) when the scheduler makes a scheduling decision.

[0058] The internals of the preprocessing block 102 are shown in FIG. 2. The postprocessing block 106 performs the preprocessing steps in reverse.A. Tokenization

[0059] An embodiment of the tokenization as implemented within the Tokenizer block 110 is illustrated in FIG. 2. In the illustrated embodiment, the tokenizer 110 includes a breaker block 200 and a mapper 202.

[0060] Tokenization is the process of converting the raw information, that is used by the scheduler 100 in this case, to a data format that is used by an Al model.P112240W001Transformer models that are used within the Al agent 104, discussed in next section, rely on tokenizing the dataset for training and prediction. Thus, IC, El, and output signals need to be tokenized for model training and prediction. These signals contain integer, boolean, and floating-point values which are different from the words typically used in LLMs where a single tokenization method is used for every word. Therefore, different tokenization methods are needed for handling various data types. It should be noted that different tokenization methods even for the same data type will impact the performance differently and will produce different results. Additionally, naive tokenization can lead to dictionary size explosion (DSE) problem. Hence, effective tokenization plays a key role in training such models. Therefore, several tokenization methods are disclosed as follows:

[0061] Naive Tokenization: This method is used for many of the El and output signals, where the signal value is prefixed with the signal name and is used as token. However, for some cases, this approach is not feasible due to DSE problem.

[0062] Offset-based Tokenization: Naively tokenizing many of the slot- related signals, e.g., PUCCHSlot, leads to DSE problem and makes predictions harder for the model. Instead, for many of the slot-related signals, an offset-based tokenization is used, where the offset from the current slot is the token. This reduces the number of tokens, keeping the dictionary smaller and making predictions easier for the model.

[0063] Integers: Signals such as nrofbits, size, and nrofucibits are integers that can take values in a large range. To this end, El signals that are integers are split into multiple tokens 1, each representing two digits, starting from the least significant digit. Output integers remain as single tokens for efficiency.

[0064] Floating points: For floating point values, tokenization is implemented by splitting them into five tokens: one for the sign, one for digits before the decimal, and three for digits after the decimal, with two digits per token up to the sixth decimal place. Digits after the sixth decimal place are ignored.P112240W001

[0065] After this step, which is done within the Breaker block 200, each token is then mapped to an ID, within the Mapper block 202, before feeding them to the Al agent 104.Al agent

[0066] The block diagram of an embodiment of the Al agent 104 that mimics a rule-based scheduler is given in FIG. 3. The Al agent 104 comprises a set of function blocks 300a-d, each of which is trained to generate scheduling decisions for PDCCH, PUCCH, PDCCH and PUS CH, respectively, corresponding to the four scheduling tasks performed by the scheduler 100. Each functional block 300 further comprises smaller blocks 302a-n, where each block 302 is an encoder-decoder Transformer model. Example training parameters are given in Table 1 below.Model Training

[0067] Following the tokenization process, each Transformer model 302 requires a carefully designed training strategy to handle the complexity of scheduling tasks and token generation. The training, validation, and test datasets may be generated using simulation environment that replicates a cell with a number of users, each having a given speed to provide varied channel conditions. For example, a simulation environment containing e.g. 120,000 examples, with e.g. 15,000 examples each for validation and testing may be used to replicate a 1 km radius cell with two users moving at high speeds to experience varied channel conditions. This approach ensures that the model encounters a diverse range of input and output tokens, allowing it to learn a more comprehensive data distribution.

[0068] To keep the resource usage under control, a batch size may be set to a suitably small number, such as 16. Since the batch size is low, a low learning rate may be considered as well, such as, for example, le-6. The Adam optimizer may be used to train the model. The training process may be carried out over e.g. about 50 epochs, while some predictions require multi-step training with more epochs, e.g., about 90 epochs. A resampling technique may be used to mitigate data bias and significantlyP112240W001 improve the model performance for some predictions. A complete list of example parameters used for training is given in Table 1.

[0069] Table 1. Training ParametersEvaluation

[0070] In this section, an example performance evaluation of the Transformer models in FIG. 3 is provided for several key subtasks in PDCCH scheduling, starting with user priority prediction, followed by the number of CCEs, and finally the starting CCE. The models are evaluated using accuracy, as well as multi-class precision and recall for various output tokens. A prediction may be considered to be correct when the token generated by the model matches the scheduler’s token. Mispredictions include skipped or repeated tokens which are common in transformer models. Thus, a confusion matrix may be used to analyze such errors and investigate the prediction bias.P112240W001

[0071] User Priority Prediction: the initial subtask is to predict which user should be scheduled next. A three-user scenario is considered for this subtask. This prediction is crucial for efficient scheduling since many other subtasks are dependent on the correct prediction of this subtask. Example training and validation losses for this subtask are illustrated in FIG. 4 and FIG. 5, respectively. The results illustrate that the losses decrease with increasing the number of training steps and epochs. The example model achieves an accuracy of 94.8%, indicating its effectiveness in predicting the user priority.

[0072] Number of CCEs (nCCEs): following user priority prediction, this subtask focuses on predicting the nCCEs allocated to the scheduled user. In this subtask, the model is expected to output two tokens, one for the nCCEs allocated and one for the user ID. Therefore, not only does the model need to predict how many nCCEs are allocated but also to whom they are assigned. Example training and validation losses for this subtask are shown in FIG. 6 and FIG. 7, respectively. The model is able to achieve an accuracy of 96.25%.

[0073] FIG. 8 shows the confusion matrix for user ID and nCCE prediction. The matrix shows high probabilities on the diagonal, indicating high recall (sensitivity), while off-diagonal elements are significantly smaller. The first row shows that the model produces some repeated tokens although with very small probability. The second and third rows show that the model does not confuse the token related to user priority with the token related to the number of allocated CCEs. A slight bias towards the allocation of only one CCE is observed by focusing on the remaining rows.

[0074] Table 2. Multi-class precision and recall for userid and nCCE prediction.P112240W001

[0075] Table 3. Multi-class precision and recall for nCCE prediction when userid is predicted correctly.

[0076] Multi-class precision and recall are presented in Table 2. Due to fewer training examples, ncce4 indicates lower values relative to other values. Furthermore, Table 3 demonstrates improved, on average, precision and recall when the user ID is correctly predicted. One can take advantage of this in order to enhance the performance. For instance, a two-step approach can be used where one model first predicts the user ID with very high accuracy and then a second model uses this prediction to perform nCCE prediction. The attention heads formed in nCCE prediction are visualized in FIG. 9. The index of the input tokens, instead of the actual tokens, are used on the x-axis for brevity. The goal of this investigation is twofold: to potentially reduce the MSL if the model focuses only on the most recent tokens, and ensuring that the model is attending to the relevant information for nCCE prediction. Although the model focuses primarily on the most recent tokens, i.e. tokens on the right, it still uses some information from the middle portion which prevents us from using a potentially smaller MSL. Moreover, the model shows significant attention to power-related tokens while also relying on a range of non-power-related tokens.

[0077] Table 4. MULTI-class precision and recall for starting CCE prediction.P112240W001

[0078] Table 5. MULTI-class precision and recall for starting CCE prediction when user id is predicted correctly.P112240W001

[0079] Starting CCE (startCCE): The final subtask involves predicting the starting CCE for a specific user to receive PDCCH. The model is trained to identify the user and the starting CCE. Performance improvements were achieved through multi- step training, resampling, and multi-initialization techniques. The accuracy for this subtask is 87.45%, indicating a reasonable performance. Training and validation losses for this subtask are shown in FIG. 10 and FIG. 11, respectively. Multi-class precision and recall metrics are presented in Table 4 and Table 5. A similar phenomenon to nCCE prediction is seen here where the average performance in terms of precision and recall improves when the user ID is predicted correctly.

[0080] FIG. 12 shows an example of a communication system 1200 in accordance with some embodiments.

[0081] In the example, the communication system 1200 includes a telecommunications network 1202 that includes an access network 1204, such as a radio access network (RAN), and a core network 1206, which includes one or moreP112240W001 core network nodes 1208. The access network 1204 includes one or more access network nodes or base stations of various types, access network nodes 1210A and 121 OB are depicted (which may be collectively referred to as network nodes 1210), or any other similar 3rdGeneration Partnership Project (3GPP) access nodes or non-3GPP access points (APs). Some embodiments of the access network 1204 may include more than one access network technology. The network nodes 1210 of access network 1204 facilitate direct or indirect connection of wireless devices, also referred to as user equipment (UEs), such as by connecting UEs 1212A, 1212B, 1212C, and 1212D (one or more of which may be generally referred to as UEs 1212) to the core network 1206 over one or more wireless connections.

[0082] 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 1202 includes one or more Open-RAN (ORAN) network nodes. An ORAN network node is a network node in the telecommunications network 1202 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 1202, including one or more access network nodes 1210 and / or core network nodes 1208.

[0083] Examples of an ORAN network node include an open radio unit (O-RU), an open distributed unit (O-DU), 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). An ORAN network node may support a specification by, for example, supporting an interface defined by the ORAN specification, such as an Al,P112240W001Fl, Wl, El, 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 0-2 interface defined by the 0-RAN Alliance or comparable technologies.

[0084] The network nodes 1210 facilitate direct or indirect connection of one or more UEs 1212 to the core network 1206 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 1200 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 1200 may include and / or interface with any type of communication, telecommunication, data, cellular, radio network, and / or other similar type of system.

[0085] The UEs 1212 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 1210 and other communication devices. Similarly, the network nodes 1208, 1210 are arranged, capable, configured, and / or operable to communicate directly or indirectly (e.g., via other devices of telecommunications network 1202) with the UEs 1212 and / or with other network nodes or equipment in the telecommunications network 1202 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 1202. More specifically, UEs 1212 may sendP112240W001 messages, data, and / or other signals to network nodes 1208, 1210 or other elements of the telecommunications network 1202 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 1208, 1210 may send messages, data, and other signals to UEs 1212, other network nodes 1208, 1210, and other devices in telecommunications network 1202 directly or indirectly. As one specific example, a core network node 1208 may transmit a particular message to a UE 1212 by transmitting the message to an access network node 1210 that will then transmit the message to the intended UE 1212. Similarly, a core network node 1208 may receive a particular message from a UE 1212 by receiving the message from an access network node 1210 that itself received the message from the UE 1212.

[0086] In the depicted example, the core network 1206 connects elements of the access network 1204 (e.g., one or more of the network nodes 1210) to one or more host computing systems, such as host 1216. 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 1206 includes one or more core network nodes (e.g., core network node 1208) of various types, one or more of which may be generally referred to as network nodes 1208. Network nodes 1208 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 1208. 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 De-concealing function (SIDF), Unified DataP112240W001Management (UDM), Security Edge Protection Proxy (SEPP), Network Exposure Function (NEF), and / or a User Plane Function (UPF).

[0087] The host 1216 may be under the ownership or control of a service provider other than an operator or provider of the access network 1204 and / or the telecommunications network 1202. The host 1216 may be operated by the service provider or on behalf of the service provider. The host 1216 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.

[0088] As a whole, the communication system 1200 of FIG. 12 enables connectivity between the UEs, network nodes, and hosts. In that sense, the communication system 1200 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 1200 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 1200 supporting different standards, protocols, or rule sets.P112240W001

[0089] As one example, in certain embodiments, access network 1204 may contain some access network nodes 1210 that support 3GPP radio access technologies (RAT), such as LTE or NR, while other access network nodes 1210 support (or the same access network nodes 1210 additionally support) non-3GPP RATs, such as Wi-Fi or a proprietary RAT. As another example, telecommunications network 1202 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 1204 and / or a core network 1206 that supports multiple different standard generations or may include multiple access networks 1204 and / or multiple core networks 1206 with individual networks 1204, 1206 supporting different standard generations.

[0090] Telecommunications network 1202 may support network slicing to provide different logical networks to different devices that are connected to the telecommunications network 1202. For example, the telecommunications network 1202 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)ZMassive loT services to yet further UEs.

[0091] In some examples, one or more of the UEs 1212 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 1204 on a predetermined schedule, when triggered by an internal or external event, or in response to requests from the access network 1204. 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).

[0092] In the example, the hub 1214 communicates with the access network 1204 to facilitate indirect communication between one or more UEs (e.g., UE 1212C and / or 1212D) and network nodes (e.g., network node 1210B). In some examples, the hubP112240W0011214 may be a controller, router, content source and analytics, or any of the other communication devices described herein regarding UEs. For example, the hub 1214 may be a broadband router enabling access to the core network 1206 for the UEs. As another example, the hub 1214 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 1210, or by executable code, script, process, or other instructions in the hub 1214.

[0093] As another example, the hub 1214 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 1214 may be a content source. For example, for a UE that is a VR headset, display, loudspeaker or other media delivery device, the hub 1214 may retrieve VR assets, video, audio, or other media or data related to sensory information via a network node, which the hub 1214 then provides to the UE either directly, after performing local processing, and / or after adding additional local content. In still another example, the hub 1214 acts as a proxy server or orchestrator for the UEs, in particular if one or more of the UEs are low energy loT devices.

[0094] The hub 1214 may have a constant / persistent or intermittent connection to the network node 1210B. The hub 1214 may also allow for a different communication scheme and / or schedule between the hub 1214 and UEs (e.g., UE 1212C and / or 1212D), and between the hub 1214 and the core network 1206. In other examples, the hub 1214 is connected to the core network 1206 and / or one or more UEs via a wired connection. Moreover, the hub 1214 may be configured to connect to an M2M service provider over the access network 1204 and / or to another UE over a direct connection. In some scenarios, UEs may establish a wireless connection with the network nodes 1210 while still connected via the hub 1214 via a wired or wireless connection. In some embodiments, the hub 1214 may be a dedicated hub - that is, a hub whose primary function is to route communications to / from the UEs from / to the network node 1210B. In other embodiments, the hub 1214 may be a non-dedicated hub - that is, a deviceP112240W001 which is capable of operating to route communications between the UEs and network node 121 OB, but which is additionally capable of operating as a communication start and / or end point for certain data channels.

[0095] FIG. 13 is another example of a communication system 1300 according to some embodiments. As used herein, the communication system 1300 includes multiple access points (APs) 1310 (with four example APs 1310A, 1310B, 1310C, and 1310D being depicted) and multiple wireless devices, referred to in the context of communication system 1300 as stations (STAs) 1312 (referred to individually as STA 1312A, STA 1312B, STA 1312C, STA 1312D, and STA 1312E). STA 1312A is served by AP 1310A in a first basic service set (BSS) 1320A. STA 1310B and STA 1310C are served by AP 1310B in a second BSS, BSS 1320B. STA 1312D 1S served by AP 1310C in a third BSS, BSS 1320C. STA 1312E is served by AP 1310D in a fourth BSS, BSS 1320D. Stations 1312 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 1312 could, for example, correspond to other kinds of equipment like smart home devices, printers, multimedia devices, data storage devices, or the like.

[0096] Each of STAs 1312 may connect through a radio link to one of APs 1310. For example, depending on location or channel conditions experienced by a given STA 1312, 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.

[0097] Each AP 1310 may provide data connectivity to STAs 1312 connected to a particular AP 1310. As illustrated, APs 1310 may be connected to a data network 1330.P112240W001In this way, APs 1310 may also provide data connectivity between STAs 1312 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 1312 and its serving AP 1310 may be used for providing various kinds of services to STA 1312, e.g., a voice service, a multimedia service, or other data service. Such services may be based on applications that are executed on STA 1312 and / or on a device linked to STA 1312. By way of example, FIG. 13 illustrates an application service platform 1332 provided in data network 1330. The application(s) executed on STA 1312 and / or on one or more other devices linked to STA 1312 may use the radio link for data communication with one or more other STA 1312 and / or the application service platform 1332, thereby enabling utilization of the corresponding service(s) at STA 1312.

[0098] FIG. 14 shows a wireless device 1400, which may be configured to operate in communication system 1200 of FIG. 12 or in communication system 1300 of FIG.13. The wireless device 1400 may be alternatively referred to as a UE, like a UE 1212 within the context of communication system 1200, or as a station (STA) 1400 or as a non-access-point station (non-AP STA), like a STA 1312 within the context of the communication system 1300, 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), laptopmounted 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 GenerationP112240W001Partnership Project (3 GPP), including a narrow band internet of things (NB-IoT) UE, a machine type communication (MTC) UE, and / or an enhanced MTC (eMTC) UE.

[0099] A wireless device 1400 may support device-to-device (D2D) communication, for example by implementing a 3 GPP 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 1400 may not necessarily have a user in the sense of a human user who owns and / or operates the relevant device. Instead, wireless device 1400 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 1400 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).

[0100] In particular embodiments, wireless device 1400 includes processing circuitry 1402 that is operatively coupled via a bus 1404 to an input / output interface 1406, a power source 1408, a memory 1410, a communication interface 1412, and / or any other component, or any combination thereof. Certain embodiments of wireless device 1400 may include all or a subset of the components shown in FIG. 14. The level of integration between the components may vary from one embodiment of wireless device 1400 to another. In general, in a particular embodiment of wireless device 1400, processing circuitry 1402, input / output interface 1406, power source 1408, memory 1410, and communication interface 1412 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 1400. Further, certain embodiments of wireless devices 1400 may contain multiple instances of a component, such as multiple processors, memories, transceivers, transmitters, receivers, etc.

[0101] The processing circuitry 1402 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 1410. TheP112240W001 processing circuitry 1402 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 1402 may include multiple central processing units (CPUs).

[0102] In the example, the input / output interface 1406 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 1400. 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 presence-sensitive 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.

[0103] In some embodiments, the power source 1408 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 1408 may further include power circuitry for delivering power from the power source 1408 itself, and / or an external power source, to the various parts of wireless device 1400 via input circuitry or an interface such as an electrical power cable. Power source 1408 may perform anyP112240W001 formatting, converting, or other modification to make accessible power suitable for the respective components of the wireless device 1400 to which power is supplied.

[0104] The memory 1410 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 1410 includes one or more programs 1414, such as an operating system, web browser application, a widget, gadget engine, or other application, and corresponding data 1416. The memory 1410 may store, for use by wireless device 1400, any of a variety of various operating systems or combinations of operating systems.

[0105] The memory 1410 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 minidual 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 (eUICC), integrated UICC (iUICC) or a removable UICC commonly known as ‘ SIM card. ’ The memory 1410 may allow wireless device 1400 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 1410, which may be or comprise a device- readable storage medium.

[0106] The processing circuitry 1402 may be configured to communicate with an access network or other network via or using the communication interface 1412. TheP112240W001 communication interface 1412 may comprise one or more communication subsystems and may include or be communicatively coupled to an antenna 1422. The communication interface 1412 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 1418 and / or a receiver 1420 appropriate to provide network communications (e.g., optical, electrical, frequency allocations, and so forth). Moreover, the transmitter 1418 and receiver 1420 may be coupled to one or more antennas (e.g., antenna 1422) and may share circuit components, software or firmware, or alternatively be implemented separately.

[0107] In the illustrated embodiment, communication functions of the communication interface 1412 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- field communication, 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.

[0108] In particular embodiments, wireless device 1400 may provide an output of data captured via a sensor, through its communication interface 1412, via a wireless connection to a network node, and / or in any appropriate manner. Data captured by sensors of a wireless device 1400 can be communicated through a wireless connectionP112240W001 to a network node via another wireless device 1400. 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).

[0109] As another example, wireless device 1400 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 1400 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.

[0110] Wireless device 1400, 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 1400 represents an loT device that comprises circuitry and / or software in dependence of the intendedP112240W001 application of the loT device in addition to other components as described in relation to the example embodiment of wireless device 1400 shown in FIG. 14.

[0111] As yet another specific example, in an loT scenario, wireless device 1400 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 1400 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 1400 may implement the 3 GPP NB-IoT standard. In other scenarios, wireless device 1400 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.

[0112] In practice, any number of wireless devices 1400 may be used together with respect to a single use case. For example, a first wireless device 1400 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 1400 that is a remote controller operating the drone. When a user makes changes from the remote controller, the first wireless device 1400 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 1400 can also include more than one of the functionalities described above. For example, wireless device 1400 might comprise the sensor and the actuator, and handle communication of data for both the speed sensor and the actuators.

[0113] FIG. 15 shows a network node 1500 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 1500 may be configured to operate in communication system 1200 of FIG. 12, like network nodes 1208 or 1210, or in communication system 1300 of FIG. 13, like an AP 1310 or a station 1312. Examples of network nodesP112240W001 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).

[0114] Network nodes 1500 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 1500 may be a relay node or a relay donor node controlling a relay. Network nodes 1500 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).

[0115] Other examples of network nodes 1500 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).

[0116] In particular embodiments, network node 1500 includes a processing circuitry 1502, a memory 15015, a communication interface 1506, and a power source 1508. In general, in a particular embodiment of network node 1500, processing circuitry 1502, memory 1504, communication interface 1506, and power source 1508 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 1500.P112240W001

[0117] The network node 1500 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 1500 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 1500 may be configured to support multiple radio access technologies (RATs). In such embodiments, some components may be duplicated (e.g., separate memories 1504 or portions of memory 1504 for different RATs) and some components may be reused (e.g., a same antenna 1510 may be shared by different RATs). The network node 1500 may also include multiple sets of the various illustrated components for different wireless technologies integrated into network node 1500, 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 1500.

[0118] The processing circuitry 1502 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 operable to provide, either alone or in conjunction with other components, such as the memory 1504, to provide network node 1500 functionality.

[0119] In some embodiments, the processing circuitry 1502 includes a system on a chip (SOC). In some embodiments, the processing circuitry 1502 includes one or more of radio frequency (RF) transceiver circuitry 1512 and baseband processing circuitry 1514. In some embodiments, the RF transceiver circuitry 1512 and the baseband processing circuitry 1514 may be on separate chips (or sets of chips), boards, or units,P112240W001 such as radio units and digital units. In alternative embodiments, part or all of RF transceiver circuitry 1512 and baseband processing circuitry 1514 may be on the same chip or set of chips, boards, or units.

[0120] The memory 1504 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 1502. The memory 1504 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 1502 and utilized by the network node 1500. The memory 1504 may be used to store any calculations made by the processing circuitry 1502 and / or any data received via the communication interface 1506. In some embodiments, the processing circuitry 1502 and memory 1504 is integrated.

[0121] The communication interface 1506 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 1506 comprises port(s) / terminal(s) 1516 to send and receive data, for example to and from a network over a wired connection. In particular embodiments, network node 300 may be capable of wireless communication and communication interface 1506 may also include radio front-end circuitry 1518 that may be coupled to, or in certain embodiments a part of, an antenna 1510. Particular embodiments of radio front-end circuitry 1518 include filter(s) 1520 and amplifier(s) 1522. The radio front-end circuitry 1518 may be connected to an antenna 1510 and processing circuitry 1502. The radio front-end circuitry may be configured to condition signals communicated betweenP112240W001 antenna 1510 and processing circuitry 1502. The radio front-end circuitry 1518 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 1518 may convert the digital data into a radio signal(s) having the appropriate channel and bandwidth parameters using a combination of filters 1520 and / or amplifiers 1522. The radio signal(s) may then be transmitted via the antenna 1510. Similarly, when receiving data, the antenna 1510 may collect radio signals which are then converted into digital data by the radio front-end circuitry 1518. The digital data may be passed to the processing circuitry 1502. In other embodiments, the communication interface may comprise different components and / or different combinations of components.

[0122] In certain alternative embodiments, network node 1500 may be capable of wireless communication but does not include separate radio front-end circuitry 1518, instead, the processing circuitry 1502 includes radio front-end circuitry and is connected to the antenna 1510. Similarly, in some embodiments, all or some of the RF transceiver circuitry 1512 is part of the communication interface 1506. In still other embodiments, the communication interface 1506 includes one or more ports or terminals 1516, the radio front-end circuitry 1518, and the RF transceiver circuitry 1512, as part of a radio unit (not shown), and the communication interface 1506 communicates with the baseband processing circuitry 1514, which is part of a digital unit (not shown).

[0123] The antenna 1510 may include one or more antennas, or antenna arrays, configured to send and / or receive wireless signals. The antenna 1510 may be coupled to the radio front-end circuitry 1518 and may be any type of antenna capable of transmitting and receiving data and / or signals wirelessly. In certain embodiments, the antenna 1510 is separate from the network node 1500 and connectable to the network node 1500 through one or more interfaces or ports.

[0124] The antenna 1510, communication interface 1506, and / or the processing circuitry 1502 may be configured to perform some or all of the receiving operations and / or obtaining operations described herein as being performed by the network nodeP112240W0011500. Any information, data and / or signals may be received from a UE, another network node and / or any other network equipment. Similarly, the antenna 1510, the communication interface 1506, and / or the processing circuitry 1502 may be configured to perform some or all of the transmitting or sending operations described herein as being performed by the network node 1500. Any information, data and / or signals may be transmitted to a UE, another network node and / or any other network equipment.

[0125] The power source 1508 provides power to the various components of network node 1500 in a form suitable for the respective components (e.g., at a voltage and current level needed for each respective component). The power source 1508 may further comprise, or be coupled to, power management circuitry to supply the components of the network node 1500 with power for performing the functionality described herein. For example, the network node 1500 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 1508. As a further example, the power source 1508 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.

[0126] Embodiments of the network node 1500 may include additional components beyond those shown in FIG. 15 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 1500 may include user interface equipment to allow input of information into the network node 1500 and to allow output of information from the network node 1500. This may allow a user to perform diagnostic, maintenance, repair, and other administrative functions for the network node 1500.

[0127] FIG. 16 is a block diagram illustrating a virtualization environment 1600 in which functions implemented by some embodiments may be virtualized. In the present context, virtualizing means creating virtual versions of apparatuses or devices whichP112240W001 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 1600 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 1600 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.

[0128] Applications 1602 (which may alternatively be called software instances, virtual appliances, network functions, virtual nodes, virtual network functions, etc.) are run in the virtualization environment 1600 to implement some of the features, functions, and / or benefits of some of the embodiments disclosed herein.

[0129] Hardware 1604 includes processing circuitry, memory that stores software and / or instructions executable by hardware processing circuitry, and / or other hardware devices as described herein, such as a network interface, input / output interface, and so forth. Software may be executed by the processing circuitry to instantiate one or more virtualization layers 1606 (also referred to as hypervisors or virtual machine monitors (VMMs)), provide VM 1608 A and VM 1608B (which may be collectively referred to as VMs 1608), and / or perform any of the functions, features and / or benefits described in relation with some embodiments described herein. The virtualization layer 1606 may present a virtual operating platform that appears like networking hardware to one or more of the VMs 1608.

[0130] The VMs 1608 comprise virtual processing, virtual memory, virtual networking or interface and virtual storage, and may be run by virtualization layerP112240W0011606. Different embodiments of the instance of a virtual appliance 1602 may be implemented on one or more of VMs 1608, and the implementations may be made in different ways. Virtualization of the hardware is in some contexts referred to as network function virtualization (NFV). NFV may be used to consolidate many network equipment types onto industry standard high volume server hardware, physical switches, and physical storage, which can be located in data centers, and customer premise equipment.

[0131] In the context of NFV, each of the VMs 1608 may be a software implementation of a physical machine that runs programs as if they were executing on a physical, non- virtualized machine. Each of the VMs 1608, and that part of hardware 1604 that executes that VM, be it hardware dedicated to that VM and / or hardware shared by that VM with others of the VMs, forms separate virtual network elements. Still in the context of NFV, a virtual network function is responsible for handling specific network functions that run in one or more of the VMs 1608 on top of the hardware 1604 and corresponds to an application 1602.

[0132] Hardware 1604 may be implemented in a standalone network node with generic or specific components. Hardware 1604 may implement some functions via virtualization. Alternatively, hardware 1604 may be part of a larger cluster of hardware (e.g. such as in a data center or CPE) where many hardware nodes work together and are managed via management and orchestration 1610, which, among others, oversees lifecycle management of applications 1602. In some embodiments, hardware 1604 is coupled to one or more radio units that each include one or more transmitters and one or more receivers that may be coupled to one or more antennas. Radio units may communicate directly with other hardware nodes via one or more appropriate network interfaces and may be used in combination with the virtual components to provide a virtual node with radio capabilities, such as a radio access node or a base station. In some embodiments, some signaling can be provided with the use of a control system 1612 which may alternatively be used for communication between hardware nodes and radio units.P112240W001

[0133] Although the computing devices described herein (e.g., UEs, network nodes, hosts) may include the illustrated combination of hardware components, other embodiments may comprise computing devices with different combinations of components. It is to be understood that these computing devices may comprise any suitable combination of hardware and / or software needed to perform the tasks, features, functions and methods disclosed herein. Determining, calculating, obtaining or similar operations described herein may be performed by processing circuitry, which may process information by, for example, converting the obtained information into other information, comparing the obtained information or converted information to information stored in the network node, and / or performing one or more operations based on the obtained information or converted information, and as a result of said processing making a determination. Moreover, while components are depicted as single boxes located within a larger box, or nested within multiple boxes, in practice, computing devices may comprise multiple different physical components that make up a single illustrated component, and functionality may be partitioned between separate components. For example, a communication interface may be configured to include any of the components described herein, and / or the functionality of the components may be partitioned between the processing circuitry and the communication interface. In another example, non-computationally intensive functions of any of such components may be implemented in software or firmware and computationally intensive functions may be implemented in hardware.

[0134] In certain embodiments, some or all of the functionality described herein may be provided by processing circuitry executing instructions stored on in memory, which in certain embodiments may be a computer program product in the form of a non-transitory computer-readable storage medium. In alternative embodiments, some or all of the functionality may be provided by the processing circuitry without executing instructions stored on a separate or discrete device-readable storage medium, such as in a hard-wired manner. In any of those particular embodiments, whether executing instructions stored on a non-transitory computer-readable storage medium or not, theP112240W001 processing circuitry can be configured to perform the described functionality. The benefits provided by such functionality are not limited to the processing circuitry alone or to other components of the computing device, but are enjoyed by the computing device as a whole, and / or by end users and a wireless network generally.

[0135]

[0136] While processes in the figures may show a particular order of operations performed by certain embodiments of the present disclosure, it should be understood that such order is representative, and that alternative embodiments may perform the operations in a different order, combine certain operations, overlap certain operations, etc.

[0137] Those skilled in the art will recognize improvements and modifications to the embodiments of the present disclosure. All such improvements and modifications are considered within the scope of the concepts disclosed herein.

Claims

P112240W001ClaimsWhat is claimed is:

1. A scheduler (100) for generating radio resource management, RRM, decisions in a radio network, the scheduler comprising: a preprocessing block (102) configured to receive input signals and generate corresponding tokens; an Artificial Intelligence, Al, agent (104) configured to receive the tokens from the preprocessing block, and generate RRM decisions based on the tokens using one or more Transformers (302)2. The scheduler as claimed in claim 1, wherein the input signals comprise: initial configuration (IC) signals comprising a number of downlink CSI-reference signal (RS) ports; and an indication of frequency division multiplexing (FDD) or time division multiplexing (TDD); and external input (El) signals comprising user downlink buffer status and power headroom.

3. The scheduler as claimed in claim 2, wherein the preprocessing block (102) comprises: a breaker (200) configured partition each input signal into respective tokens; and a mapper (202) configured to receive the tokens from the breaker, and map the received tokens to an identifier.

4. The scheduler as claimed in claim 3, wherein the breaker (200) is configured partition each input signal in accordance with one or more of:Naive Tokenization, wherein an input signal value is prefixed with a signal name and is used as token;Offset-based Tokenization, wherein where an offset from a current slot is the token;Integers, wherein El signals that are integers are split into multiple tokens, each representing two digits, starting from the least significant digit; andP112240W001 floating points, wherein El signals that are floating point values are split into five tokens: a first token indicating the sign, a second token for digits before the decimal, and three tokens for digits after the decimal, with two digits per token up to the sixth decimal place.

5. The scheduler as claimed in claim 1, wherein the Al agent (104) comprises a respective functional block configured to generate RRM decisions related to each scheduler task, wherein each functional block comprises a one or more Transformer models.

6. The scheduler as claimed in claim 5, wherein scheduler tasks comprise:Physical Downlink Control Channel (PDCCH) scheduling;Physical Downlink Shared Channel (PDSCH) scheduling;Physical Uplink Control Channel (PUCCH) scheduling; andPhysical Uplink Shared Channel (PUSCH) scheduling.

Images