Electronic device and method for wireless communication, and computer readable storage medium

Abstract

The invention relates to an electronic device and method for wireless communication, and a computer readable storage medium. The electronic equipment for wireless communication comprises a processing circuit, and the processing circuit is configured to: based on channel information which is reported by at least one piece of user equipment within a service range of the electronic equipment and is related to a channel state of at least one edge link of the at least one piece of user equipment; the learning models of the user equipment related to the at least one edge link are divided into at least one group, and the learning models in the same group are jointly trained for at least a part of groups in the at least one group. (Figure 1)

Description

Electronic device and method for wireless communication, and computer-readable storage medium

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on July 11, 2022, with application number 202210809772.4 and invention name “Electronic device and method for wireless communication, computer-readable storage medium”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present disclosure relates to the field of wireless communication technology, and more particularly to an electronic device and method for wireless communication, as well as a computer-readable storage medium. More particularly, the present disclosure relates to grouping learning models of user equipment associated with edge links and jointly training the learning models in the same group. Background Art

[0003] With the development of wireless networks and artificial intelligence (AI), networks are becoming increasingly intelligent. For the future of 6G, wireless network intelligence will be a key development direction. More specifically, Federated Learning (FL), currently the most important distributed AI framework, will be integrated with wireless networks and will be a key component of future intelligent wireless network applications. Therefore, the effective joint design of FL with current 5G NR will have a significant impact on future AI applications. In particular, in highly intelligent wireless networks, the efficient use of FL to jointly train machine learning models within intelligent wireless networks, based on the characteristics of wireless communications, will garner increasing attention.

[0004] As wireless networks evolve, numerous machine learning models are being used to optimize network decision-making and operations. For example, vehicle-to-vehicle (V2V) communication in the Internet of Vehicles (IoV) is implemented via sidelinks, which can often be modeled as a Markov decision process (MDP) and addressed using deep reinforcement learning (DRP).

[0005] How to efficiently use FL for joint training of edge links is a current research hotspot.

[0006] Summary of the Invention

[0007] A brief overview of the present invention is provided below to provide a basic understanding of certain aspects of the present invention. It should be understood that this overview is not an exhaustive overview of the present invention. It is not intended to identify key or important aspects of the present invention, nor is it intended to limit the scope of the present invention. Its purpose is simply to present certain concepts in a simplified form as a prelude to the more detailed description discussed later.

[0008] According to one aspect of the present disclosure, an electronic device for wireless communication is provided, which includes a processing circuit, wherein the processing circuit is configured to: divide the learning model of the user equipment related to the at least one edge link into at least one group based on channel information reported by at least one user equipment located within the service range of the electronic device regarding the channel state of at least one edge link of the at least one user equipment, and jointly train the learning models in the same group for at least a portion of the at least one group.

[0009] In an embodiment according to the present disclosure, the electronic device solves the data heterogeneity problem of edge links caused by different environments through grouping, which can improve the efficiency of joint training and improve the quality of the learning model and the performance of the system.

[0010] According to one aspect of the present disclosure, an electronic device for wireless communication is provided, which includes a processing circuit, and the processing circuit is configured to: report channel information about the channel status of at least one edge link of the electronic device to a network-side device that provides services for the electronic device, so that the network-side device can divide the learning models of the electronic devices related to the at least one edge link and other electronic devices related to the at least one edge link and provided with services by the network-side device into at least one group based on the channel information, thereby facilitating the network-side device to jointly train the learning models within the same group for at least a portion of the at least one group.

[0011] In an embodiment according to the present disclosure, electronic devices report channel information about the channel status of edge links to network-side devices, so that the network-side devices can group learning models of electronic devices related to edge links based on the channel information. This helps the network-side devices solve the data heterogeneity problem of edge links caused by different environments through grouping, improves the efficiency of joint training, and improves the quality of the learning model and the performance of the system.

[0012] According to one aspect of the present disclosure, a method for wireless communication is provided, comprising: dividing a learning model of the user equipment related to the at least one edge link into at least one group based on channel information reported by at least one user equipment located within a service range of the electronic device regarding the channel state of at least one edge link of the at least one user equipment, and jointly training the learning models in the same group for at least a portion of the at least one group.

[0013] According to one aspect of the present disclosure, a method for wireless communication is provided, comprising: reporting channel information about the channel status of at least one edge link of the electronic device to a network-side device providing services for the electronic device, so that the network-side device can divide the learning models of the electronic devices related to the at least one edge link and other electronic devices related to the at least one edge link and provided with services by the network-side device into at least one group based on the channel information, thereby facilitating the network-side device to jointly train the learning models within the same group for at least a portion of the at least one group.

[0014] According to other aspects of the present invention, a computer program code and a computer program product for implementing the above-mentioned method for wireless communication, as well as a computer-readable storage medium having the computer program code for implementing the above-mentioned method for wireless communication recorded thereon are also provided. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to further illustrate the above and other advantages and features of the present invention, the following is a further detailed description of specific embodiments of the present invention in conjunction with the accompanying drawings. The drawings, together with the detailed description below, are included in this specification and form a part of this specification. Elements with the same function and structure are represented by the same reference numerals. It should be understood that these drawings only illustrate typical examples of the present invention and should not be regarded as limiting the scope of the present invention. In the drawings:

[0016] FIG1 shows a functional module block diagram of an electronic device for wireless communication according to an embodiment of the present disclosure;

[0017] FIG2 is a schematic diagram showing a system structure according to an embodiment of the present disclosure;

[0018] FIG3 is a schematic diagram illustrating an edge link power rate adaptive control scenario according to an embodiment of the present disclosure;

[0019] 4a and 4b are schematic diagrams illustrating division based on the similarity between probability distributions of channel energy gains of edge links according to an embodiment of the present disclosure;

[0020] FIG5 is an exemplary diagram illustrating information interaction between an electronic device and a user device according to an embodiment of the present disclosure;

[0021] FIG6 shows a functional module block diagram of an electronic device for wireless communication according to another embodiment of the present disclosure;

[0022] FIG7 shows a flowchart of a method for wireless communication according to one embodiment of the present disclosure;

[0023] FIG8 shows a flowchart of a method for wireless communication according to another embodiment of the present disclosure;

[0024] FIG9 is a block diagram showing a first example of a schematic configuration of an eNB or gNB to which the technology of the present disclosure may be applied;

[0025] FIG10 is a block diagram illustrating a second example of a schematic configuration of an eNB or gNB to which the technology of the present disclosure may be applied;

[0026] FIG11 is a block diagram showing an example of a schematic configuration of a smartphone to which the technology of the present disclosure can be applied;

[0027] FIG12 is a block diagram showing an example of a schematic configuration of a car navigation device to which the technology of the present disclosure can be applied; and

[0028] 13 is a block diagram of an exemplary structure of a general-purpose personal computer in which the method and / or apparatus and / or system according to the embodiments of the present invention may be implemented. DETAILED DESCRIPTION

[0029] Exemplary embodiments of the present invention are described below with reference to the accompanying drawings. For the sake of clarity and conciseness, not all features of an actual implementation are described in this specification. However, it should be understood that in the process of developing any such actual implementation, many implementation-specific decisions must be made in order to achieve the developer's specific goals, such as meeting system and business-related constraints, which may vary from implementation to implementation. Furthermore, it should be understood that while development work may be complex and time-consuming, it will be a routine task for those skilled in the art who benefit from this disclosure.

[0030] It is also necessary to explain here that, in order to avoid obscuring the present invention due to unnecessary details, the accompanying drawings only show the device structure and / or processing steps that are closely related to the solution according to the present invention, while other details that are not closely related to the present invention are omitted.

[0031] FIG1 shows a functional module block diagram of an electronic device 100 for wireless communication according to an embodiment of the present disclosure.

[0032] As shown in Figure 1, the electronic device 100 includes: a processing unit 101, which can divide the learning model of the user equipment related to at least one edge link into at least one group based on channel information reported by at least one user equipment located in the service range of the electronic device 100 about the channel status of at least one edge link of at least one user equipment; and a training unit 103, which can jointly train the learning models in the same group for at least a part of the at least one group.

[0033] The processing unit 101 and the training unit 103 may be implemented by one or more processing circuits, which may be implemented as a chip, for example.

[0034] The electronic device 100 can serve as a network side device in a wireless communication system, and specifically, for example, can be set on the base station side or communicatively connected to the base station. Here, it should also be pointed out that the electronic device 100 can be implemented at the chip level, or it can also be implemented at the device level. For example, the electronic device 100 can work as the base station itself, and can also include external devices such as memory, transceiver (not shown), etc. The memory can be used to store programs and related data information that need to be executed by the base station to implement various functions. The transceiver may include one or more communication interfaces to support communication with different devices (for example, user equipment (UE), other base stations, etc.), and the implementation form of the transceiver is not specifically limited here.

[0035] As an example, the base station may be, for example, an eNB or a gNB.

[0036] For example, the electronic device 100 may be connected to a core network.

[0037] The wireless communication system according to the present disclosure may be a 5G NR (New Radio) communication system. Furthermore, the wireless communication system according to the present disclosure may include a non-terrestrial network (NTN). Optionally, the wireless communication system according to the present disclosure may also include a terrestrial network (TN). In addition, those skilled in the art will appreciate that the wireless communication system according to the present disclosure may also be a 4G or 3G communication system.

[0038] For example, the user equipment may be a user equipment for sending on a sidelink (SL) (referred to as a sending user equipment) or a user equipment for receiving on a sidelink (referred to as a receiving user equipment). The user equipment can perform sidelink control.

[0039] In the electronic device 100 according to an embodiment of the present disclosure, federated learning is used for joint training of learning models under multi-user devices.

[0040] As an example, the learning model can be a traditional machine learning model or a deep reinforcement learning model. In the following, for convenience, the learning model is sometimes described as a deep reinforcement learning model.

[0041] FIG2 is a schematic diagram illustrating a system structure according to an embodiment of the present disclosure.

[0042] As shown in FIG2 , for the sake of simplicity, the user device is shown as a vehicle. Those skilled in the art will understand that the user device can be in other forms besides a vehicle. For example, the user device can be a terminal device such as a mobile phone, iPad, notebook, etc., as long as there is an edge link between the user devices. A single user device performs reinforcement learning on the learning model related to its edge link (which can be called a local model). For example, the local model is obtained based on the initial global model issued by the electronic device 100. The electronic device 100 divides the local model on the user device into different groups based on the channel information of the channel state of the edge link of the user device (for example, for the sake of simplicity, FIG2 only shows three user devices UE1, UE2 and UE3 divided into the same group). The user device uploads the parameters of its local model to the electronic device 100; for the user devices UE1, UE2 and UE3 in the same group, the electronic device 100 performs joint training of the learning model (aggregates the learning model) through federated learning to form a global model.

[0043] In existing joint training of learning models without federated learning, the number of training samples is often insufficient, making model training difficult. Compared to joint training of learning models without federated learning, joint training of multiple learning models using federated learning can overcome the problem of insufficient training samples and slow convergence of single reinforcement learning.

[0044] In the federated learning of the existing technology, different user devices have data heterogeneity problems due to their different environments. Due to the heterogeneity of the data, irrelevant samples are added during the aggregation process, causing the learning model to diverge or converge more slowly during the training process, thereby reducing the quality of the learning model and the performance of the system. In other words, the differences in the random channel environment make the data collected between different user devices heterogeneous, resulting in different degrees of differences in the learning models trained on different edge links. This situation is particularly serious in deep reinforcement learning. This difference will lead to a decline in the overall training performance of federated learning based on the existing technology. For example, in the vehicle-to-everything (V2X) network, this problem is even more serious. This is mainly due to the following two reasons: (1) Due to the movement of vehicles, the devices in V2X face more complex and diverse environments, and the heterogeneity of the data is exacerbated; (2) Reinforcement learning models are required in many places in the training of V2X. The application of reinforcement learning requires the device to continuously obtain rewards from the environment, which exacerbates the impact of diverse environments on system performance.

[0045] In the embodiment of the present disclosure, the electronic device 100 solves the data heterogeneity problem of edge links caused by different environments through grouping, which can improve the efficiency of joint training and improve the quality of the learning model and the performance of the system.

[0046] As an example, at least one user device is a device in a D2D scenario. For example, at least one user device is an on-board device in a vehicle network. However, user devices are not limited to V2X vehicle network scenarios, and any communication scenario linked by sidelink is applicable. For example, in a D2D scenario, communication between user devices can also be mutual communication between terminal devices (mobile phones, tablet computers, etc.). Communication between user devices can also be communication between XR devices in an XR (extended reality) scenario; and communication between user devices can also be communication between devices in scenarios such as the industrial Internet or smart home.

[0047] In the following, for convenience, the user equipment is described as a vehicle or vehicle-mounted device in the Internet of Vehicles. Those skilled in the art will understand that the user equipment can be in other forms besides vehicle-mounted devices, as long as there is an edge link between the user equipment.

[0048] In V2X, most problems can be modeled as Markov decision problems (MDPs). Therefore, deep reinforcement learning can be used to solve them. A specific example is adaptive power rate control for edge link information transmission. Data transmission from vehicle devices consumes battery power, but battery capacity is limited. Therefore, to achieve longer battery life, average power constraints on the transmitting device are required during edge link data transmission. However, since the wireless channel state between vehicles is random, if only low energy consumption is pursued for information transmission, and transmission is performed only when channel conditions are good (opportunistic transmission), data packets will wait in the queue for a long time, resulting in significant data queuing delays. Therefore, efficient adaptive power control is needed to achieve the optimal delay-power trade-off, minimizing data transmission delay while ensuring that average power consumption requirements are met. Such a power control problem can be modeled as an MDP problem and solved using deep reinforcement learning.

[0049] As an example, the channel information of the edge link includes the probability distribution of the channel energy gain of the edge link, the reference signal received power (RSRP), the received signal strength index (RSSI), the reference signal quality (RSRQ), the signal-to-noise ratio (SNR), information about whether the user equipment as the sender and the user equipment as the receiver of the edge link are within the line of sight, and at least one of the statistics of the interference and noise of the channel.

[0050] The channel information of the edge link is used to measure the similarity between the learning models related to the edge link. The electronic device 100 groups the learning models of the user equipment related to the edge link based on the channel information of the edge link, and can jointly train learning models with high similarity.

[0051] As an example, the processing unit 101 may be configured to perform division based on the similarity between probability distributions respectively corresponding to at least one edge link.

[0052] As an example, the channel energy gain is divided into a predetermined number of discrete levels, and the probability distribution includes the probability of the channel energy gain being in each level.

[0053] As wireless networks evolve, numerous machine learning models can be used to optimize network decision-making and operation. As mentioned above, one example is the power control problem during data transmission: the transmitting vehicle adaptively adjusts the data transmission power and the number of packets sent in real time based on the current inter-vehicle channel state and the data queue status. Because the channel state between vehicles is random, if only real-time information transmission (i.e., instant transmission) is pursued, the energy cost will be very high when encountering poor channel conditions. If only low energy consumption is pursued for information transmission, waiting for good channel conditions to transmit (i.e., opportunistic transmission) will cause packets to wait in the queue for a long time, resulting in significant data queuing delays. Therefore, efficient adaptive power control is needed to achieve the optimal delay-power trade-off, minimizing data transmission delay while ensuring average power consumption requirements.

[0054] To illustrate the basis for federated learning grouping, the following uses the example of adaptive power rate control for edge links. For example, the learning model is used to assist in determining the data transmission rate of the edge link based on the data queue length and the channel energy gain of the edge link.

[0055] Taking the user device as a vehicle as an example, as mentioned above, multiple edge links can jointly train the learning model through federated learning. However, due to the heterogeneity between different vehicles and the sensitivity of the learning model (especially the deep reinforcement learning (DRL) model) to the environment, the DRL models trained in different random environments have certain differences. In the communication problem of the edge link, the probability distribution characteristics of the wireless channel are the random environment for training. In an embodiment according to the present disclosure, by selecting user devices with similar probability distribution characteristics of the wireless channel state (for example, the probability distribution of the channel energy gain) for FL grouping, vehicles with similar random environments are selected for joint training of federated learning, which can improve the efficiency of joint training.

[0056] Figure 3 is a schematic diagram illustrating an edge link power rate adaptive control scenario according to an embodiment of the present disclosure. In Figure 3, Tx represents transmission and Rx represents reception.

[0057] In conjunction with Figure 3, the user equipment needs to determine the current data transmission rate s and the current data transmission power P (the transmission power P is determined by the transmission rate s and the channel energy gain h, and can be calculated by the channel capacity formula) based on the current data queue length q (the number of data packets waiting to be sent in the queue) and the current channel energy gain gear h (the channel energy gain is divided into w discrete gears), so as to ensure that the average queuing delay of data transmission in the edge link is minimized under the constraint of limited average power consumption. Among them, the channel energy gain of the edge link is independent and identically distributed in each transmission time slot, let P i =[pi (h1), p i (h2), ..., p i (h w )] represents the probability distribution of the channel energy gain on the i-th edge link, p i (h k ) represents the probability that the channel energy gain on the i-th edge link is in the k-th gear, where 1≤k≤w. How to select the optimal transmission power and transmission rate in real time based on the real-time dynamically changing queue length and channel energy gain can be established as a Markov decision problem. The Markov decision problem can be further solved using a deep reinforcement learning model. Specifically, the deep reinforcement learning model fits the value function in the reinforcement learning process through an artificial neural network. In Figure 3, the input of the artificial neural network is the queue length q, the gear h of the channel gain, and the transmission rate s; the output is the value function V(q,h,s) corresponding to the state (q,h,s). According to the value function V(q,h,s) provided by the artificial neural network, the user equipment can obtain the optimal transmission rate S when the queue length is q and the channel gain is in the gear h. * , where S * =argmin s V(q, h, s). Furthermore, in FIG3 , the artificial neural network models trained under different probability distributions of channel energy gains will be different.

[0058] According to the characteristics of federated learning, adding edge links with similar probability distributions of channel energy gains to the same federated learning group for training can improve the accuracy of the aggregated global model.

[0059] 4a and 4b are schematic diagrams illustrating division based on the similarity between probability distributions of channel energy gains of edge links according to an embodiment of the present disclosure.

[0060] In Figure 4a, assuming that the probability distribution P1 of the channel energy gain on edge link 1 is similar to the probability distribution P2 of the channel energy gain on edge link 2, dividing the learning model related to edge link 1 and the learning model related to edge link 1 into the same group can improve the effect of joint training.

[0061] In Figure 4b, assuming that the probability distribution P1 of the channel energy gain on edge link 1 is not similar to the probability distribution P3 of the channel energy gain on edge link 3, if the learning model related to edge link 1 and the learning model related to edge link 3 are divided into the same group, it will be detrimental to improving the effect of joint training.

[0062] As an example, the degree of similarity between the probability distributions includes the KL divergence between the probability distributions.

[0063] For two probability distributions P of a discrete random variable i and P j In terms of P i =[p i (h1), p i (h2), ..., p i (h w )] and P j =[p j (h1), p j (h2), ..., p j (h w )], KL divergence is defined as:

[0064] Due to the asymmetry of KL divergence, first for each pair of KL divergences, take the maximum value D of each pair of KL divergences ij =max{D KL (P i ||P j ), D KL (P j ||P i That is, for each pair of KL divergences expressed in Equation 1 and Equation 2, assume that the maximum value is expressed as D ij .

[0065] Then, the smallest KL divergence is selected from the maximum values ​​of the KL divergences for each pair, and the user devices with the smallest KL divergence are then grouped based on this value.

[0066] For example, there are 4 user devices and 6 edge links, and 3 user devices are selected to form a group. The corresponding KL dispersion assumption is:

[0067]

[0068] D KL (P1||P2)=0.5; D KL (P2||P1)=0.6;

[0069] D KL (P1||P3)=0.7;D KL (P3||P1)=0.6;

[0070] D KL (P1||P4)=0.5; D KL (P4||P1)=0.4;

[0071] D KL (P2||P3)=0.4;D KL (P2||P3)=0.3;

[0072] D KL (P2||P4)=1.0; D KL (P4||P2)=0.8;

[0073] D KL (P3||P4)=0.3; D KL (P4||P3)=0.2;

[0074] First, the maximum values ​​of each pair of KL divergences are: D 12 =0.6; D 13 =0.7; D 14 =0.5; D 23 =0.4; D 24 =1.0;D 34 =0.3.

[0075] Then, select the minimum value D from the above 6 maximum values 34 , which corresponds to D KL (P3||P4).

[0076] Finally, select D KL (P1||P4)=0.5,D KL (P2||P4)=0.4 and D KL The user equipment corresponding to the two smallest values ​​in (P3||P4), that is, user equipment 2 and user equipment 3, are grouped with user equipment 4.

[0077] In addition to the above examples, those skilled in the art may also conceive of other ways of grouping based on KL divergence, which will not be described here.

[0078] Among them, the smaller the KL divergence, the closer the two probability distributions are. Channel state probability distributions with high similarity indicate reinforcement learning models with high similarity. Dividing reinforcement learning models with high similarity into a group for joint training can achieve better joint training effects.

[0079] In addition to the KL divergence, those skilled in the art may also think of other examples of the degree of similarity between probability distributions, which will not be repeated here.

[0080] As an example, processing unit 101 may be configured to perform grouping based on RSRP magnitude. For example, learning models of user equipment with RSRP magnitudes greater than a predetermined threshold may be grouped together, while learning models of user equipment with RSRP magnitudes less than or equal to the predetermined threshold may be grouped together. Alternatively, learning models of user equipment may be grouped into multiple groups based on RSRP magnitudes.

[0081] As an example, the processing unit 101 may be configured to perform grouping based on the RSSI amplitude. For example, the learning models of user devices whose RSSI amplitude is greater than a predetermined threshold may be grouped together, while the learning models of user devices whose RSSI amplitude is less than or equal to the predetermined threshold may be grouped together. Alternatively, the learning models of user devices may be grouped together into multiple groups based on the RSSI amplitude.

[0082] As an example, the processing unit 101 may be configured to perform grouping based on the magnitude of the RSRQ. For example, the learning models of user equipment whose RSRQ magnitude is greater than a predetermined threshold may be grouped together, while the learning models of user equipment whose RSRQ magnitude is less than or equal to the predetermined threshold may be grouped together. Alternatively, the learning models of user equipment may be grouped together into multiple groups based on the magnitude of the RSRQ.

[0083] As an example, processing unit 101 may be configured to perform grouping based on the magnitude of the SNR. For example, learning models of user devices whose SNR magnitude is greater than a predetermined threshold may be grouped together, while learning models of user devices whose SNR magnitude is less than or equal to the predetermined threshold may be grouped together. Alternatively, learning models of user devices may be grouped together into multiple groups based on the magnitude of the SNR.

[0084] As an example, the processing unit 101 may be configured to perform grouping based on whether the user equipment serving as a transmitter and the user equipment serving as a receiver of the edge link are within line-of-sight (LOS) range. For example, if joint training is to be performed on several transmitting user equipments, the transmitting user equipments that are within line-of-sight range with the corresponding receiving user equipments are grouped into the same group, while the transmitting user equipments that are within non-line-of-sight range (NLOS) with the corresponding receiving user equipment are grouped into another group.

[0085] As an example, the processing unit 101 may be configured to perform division based on the magnitude of statistics of interference and noise of the channel.

[0086] As an example, the statistics of interference and noise of a channel include a mean and / or a variance.

[0087] The above describes how to group learning models when the channel information of the edge link includes the probability distribution of the channel energy gain of the edge link, RSRP, RSSI, RSRQ, SNR, information about whether the user equipment as the sender and the user equipment as the receiver of the edge link are within the line of sight, and an indicator of the statistics of the channel interference and noise.

[0088] The following describes how to group learning models when the channel information of the edge link includes the probability distribution of the channel energy gain of the edge link, RSRP, RSSI, RSRQ, SNR, information about whether the user equipment as the sender and the user equipment as the receiver of the edge link are within the line of sight range, and at least two indicators of the statistics of the interference and noise of the channel.

[0089] For example, the learning models may be grouped based on the priorities of the at least two indicators. For example, the priorities of the indicators may be set based on experience or application scenarios.

[0090] For example, when the at least two indicators include two indicators, the learning model is first grouped based on the indicators of the first priority to obtain the first grouping result; then, based on the first grouping result, it is grouped again based on the indicators of the second priority to obtain the final grouping result. For example, assuming that the two indicators include a first indicator RSRP and a second indicator probability distribution of the channel energy gain of the edge link, and the priority of the first indicator is higher than the priority of the second indicator, the learning models can be grouped first based on the amplitude of RSRP (for example, the learning models of user equipment whose RSRP amplitude is greater than a predetermined threshold can be divided into a first group, and the learning models of user equipment whose RSRP amplitude is less than or equal to the predetermined threshold can be divided into a second group) to obtain the first grouping result (for example, it includes the first group and the second group); then based on the similarity between the probability distributions of the channel energy gain of the edge link, the first group and the second group are grouped respectively (for example, the learning models with high similarity in the first group are divided into the first subgroup, and the other learning models in the first subgroup are divided into the second subgroup; the learning models with high similarity in the second group are divided into the third subgroup, and the other learning models in the second group are divided into the fourth subgroup), so as to obtain the final group (for example, it includes the first subgroup, the second subgroup, the third subgroup, and the fourth subgroup).

[0091] For example, when the at least two indicators include three indicators, the learning model is first grouped based on the indicator with the highest priority to obtain a first grouping result. Then, based on the first grouping result, the learning model is grouped again based on the indicator with the second priority to obtain a second grouping result. Finally, based on the second grouping result, the learning model is grouped again based on the indicator with the third priority to obtain a final grouping result. Similarly, grouping can be performed when the at least two indicators include more than four indicators, which will not be repeated here.

[0092] As an example, the processing unit 101 may be configured to receive channel information of the edge link via Radio Resource Control (RRC) signaling.

[0093] For example, the RRC signaling may be MeasResultsSL signaling.

[0094] For example, as shown above, the signaling "measResultListPDCS-NR" can be added to the MeasResultsSL signaling to transmit the probability distribution P of the channel state. i =[p i (h1), p i (h2), ..., p i (h w )], where p i (h k ) represents the probability that the channel energy gain on the i-th edge link is in the k-th level. Alternatively, the "measResultListOther-NR" signaling can be added to the MeasResultsSL signaling to transmit other channel information of the edge link, such as RSRP, RSRQ, RSSI, SNR, LOS, channel interference and noise statistics, etc. Alternatively, both the "measResultListPDCS-NR" and "measResultListOther-NR" signaling can be added to the MeasResultsSL signaling.

[0095] For details about MeasResultsSL, see "TS 38.131 Radio Resource Control (RRC) protocol specification" and are not repeated here.

[0096] As an example, the processing unit 101 may be configured to send the information about the division to at least a portion of the user equipments related to the edge link in each group through a physical downlink control channel (PDCCH).

[0097] As an example, the processing unit 101 may be configured to send parameters of the initial global learning model to at least some of the user devices in the first round of joint training, so that the user devices can perform local training based on the initial global model to obtain local models.

[0098] As an example, the processing unit 101 may be configured to receive auxiliary state information for uplink resource allocation from at least some user equipments via an uplink.

[0099] Within the same federated learning group, the status of the user equipment itself varies greatly. Therefore, after the grouping is completed, the user equipment uploads auxiliary status information to the electronic device 100 for uplink resource allocation.

[0100] As an example, the auxiliary status information includes at least one of the number of samples used by the user device to train the learning model, the location information of the user device, the moving speed of the user device, the computing power of the user device, and the CPU occupancy rate of the user device.

[0101] As an example, the processing unit 101 may be configured to allocate uplink resources to at least a portion of the user equipment based on the auxiliary state information. That is, the electronic device 100 obtains available radio resource block information to prepare for uploading the local model of the federated learning.

[0102] The electronic device 100 performs corresponding uplink resource allocation according to the auxiliary state information uploaded by the user equipment in the group, which can solve or alleviate the Straggler problem, thereby accelerating the FL process and improving system performance.

[0103] The main manifestations of straggering are that the user device has: 1) a large amount of data: which has a larger weight in the aggregation process; 2) a higher priority; 3) poor computing power or a higher CPU occupancy rate; and 4) a long distance from the electronic device 100 or poor channel quality, resulting in a longer transmission time or a lower transmission rate.

[0104] The electronic device 100 can reduce transmission delay and accelerate the learning model convergence process by allocating more frequency resources to user equipment with the Straggler problem.

[0105] For example, the number of samples used by the user device to train the learning model is the number of samples used by the user device to train the local model in each iteration of the federated learning training process. Based on the number of samples used by the user device to train the local model, the importance of the local model trained by the user device is determined and used to determine uplink radio resource allocation during the federated learning process.

[0106] As an example, the computing power of the user device used for local model training is the computing speed of the CPU, and the CPU occupancy of the user device is the CPU occupancy rate during the local model training process. For example, the CPU occupancy rate information used for local model training is used to estimate the computing power of the user device during the federated learning process, thereby determining the Straggler.

[0107] Compared with the case where the location information of the user device is not considered (i.e., the distance information between the user device and the electronic device 100 is not used) and the CPU usage for training the local model is not considered, the present disclosure considers such information to determine the Straggler in the federated learning process, which can reduce the time required for one round of iteration.

[0108] As an example, the processing unit 101 may be configured to send information about uplink resource allocation to at least some user equipments via a downlink.

[0109] As an example, the training unit 103 can be configured to receive parameters related to the local learning model uploaded by at least a portion of user equipment based on information about uplink resource allocation, wherein the local learning model is trained based on the initial global learning model sent down by the electronic device 100.

[0110] As an example, joint training includes aggregating local learning models related to edge links in the same group as an updated global learning model, thereby obtaining an aggregated learning model. For example, aggregation is a weighted average of the parameters of the local learning models related to the edge links in the same group. For example, the base station of the electronic device 100 judges the importance of the uploaded reinforcement learning model based on the number of training samples used when training the local reinforcement learning model for each edge link, and uses it to determine the weight coefficient of the local model during aggregation, thereby aggregating a more accurate global model during this round of iteration. That is, the electronic device 100 can determine the weight of the local model based on the number of samples used by the user device to train the local model, thereby minimizing the error of the global model trained by federated learning.

[0111] As an example, the training unit 103 may be configured to broadcast parameters of the aggregated learning model (also referred to as an updated global model) of each group to the user equipments in the group.

[0112] As an example, the training unit 103 may be configured to repeatedly perform division and joint training until a predetermined condition is met, such as reaching a predetermined number of iterations, or the error of the aggregated learning model being less than a predetermined error, etc.

[0113] Figure 5 is an example diagram illustrating information interaction between the electronic device 100 and the user equipment UE according to an embodiment of the present disclosure. In Figure 5 , the channel information of the edge link is taken as the probability distribution of the channel energy gain of the edge link for illustration.

[0114] The probability distribution P of the UE collected channel energy gain i =[p i (h1), p i (h2), ..., p i (h w )]. In S51, the UE uploads the collected probability distribution to the electronic device 100.

[0115] The electronic device 100 determines the similarity of the learning models of the user equipment based on the probability distribution of the channel energy gain of the edge link, and divides the learning models with higher similarity into the same group. In S52, the electronic device 100 sends the grouping information and the initial global model to the UE.

[0116] In S53 , the UE uploads the assistance status information to the electronic device 100 .

[0117] The electronic device 100 allocates uplink resources to the user equipment based on the assistance status information. For example, the electronic device 100 finds the user equipment with the Straggler problem and allocates more resources to such user equipment.

[0118] In S54 , the electronic device 100 sends the uplink resource allocation information to the UE.

[0119] The UE performs local training based on the initial global model according to local sample data to obtain a local model.

[0120] In S55 , the UE uploads the parameters of the local model to the electronic device 100 via the allocated uplink resources.

[0121] The electronic device 100 aggregates the local models of the user devices in the same group to obtain an updated global model. The updated global model represents the final model of the federated learning in this round of training, and its model error represents the effect of this round of federated learning training.

[0122] The electronic device 100 broadcasts the updated global model to all user devices participating in federated learning.

[0123] The training of federated learning requires the UE and the electronic device 100 to perform several rounds of iteration and aggregation of the learning model, that is, repeatedly perform division and joint training, that is, repeatedly execute the processing of S51-S55 until a predetermined condition is met.

[0124] The present disclosure further provides an electronic device for wireless communication according to another embodiment. FIG6 shows a functional module block diagram of an electronic device 600 for wireless communication according to yet another embodiment of the present disclosure.

[0125] As shown in Figure 6, the electronic device 600 includes: a communication unit 601, which can report channel information about the channel status of at least one edge link of the electronic device 600 to the network side device that provides services for the electronic device 600, so that the network side device can divide the learning models of the electronic device 600 related to the at least one edge link and other electronic devices related to the at least one edge link and provided with services by the network side device into at least one group based on the channel information, thereby facilitating the network side device to jointly train the learning models in the same group for at least a part of the at least one group.

[0126] The communication unit 601 may be implemented by one or more processing circuits, which may be implemented as a chip, for example.

[0127] The electronic device 600 can be, for example, arranged on the user equipment (UE) side or communicatively connected to the user equipment. In the case where the electronic device 600 is arranged on the user equipment side or communicatively connected to the user equipment, the device related to the electronic device 600 can be a user equipment. It should also be noted here that the electronic device 600 can be implemented at the chip level, or it can also be implemented at the device level. For example, the electronic device 600 can work as the user equipment itself, and can also include external devices such as memory, transceiver (not shown in the figure), etc. The memory can be used to store programs and related data information that the user equipment needs to execute to implement various functions. The transceiver may include one or more communication interfaces to support communication with different devices (for example, base stations, other user equipment, etc.), and the implementation form of the transceiver is not specifically limited here.

[0128] As an example, the network side device may be the electronic device 100 mentioned above. As an example, the electronic device 600 may be the user equipment involved in the embodiment of the electronic device 100 mentioned above.

[0129] The wireless communication system according to the present disclosure may be a 5G NR communication system. Furthermore, the wireless communication system according to the present disclosure may include a non-terrestrial network. Alternatively, the wireless communication system according to the present disclosure may also include a terrestrial network. Furthermore, those skilled in the art will appreciate that the wireless communication system according to the present disclosure may also be a 4G or 3G communication system.

[0130] In an embodiment according to the present disclosure, the electronic device 600 reports channel information about the channel status of the edge link to the network side device, so that the network side device can group the learning model of the electronic device 600 related to the edge link based on the channel information. This helps the network side device to solve the data heterogeneity problem of the edge link caused by different environments through grouping, improves the efficiency of joint training, and improves the quality of the learning model and the performance of the system.

[0131] As an example, the channel information of the edge link includes the probability distribution of the channel energy gain of the edge link, the reference signal received power (RSRP), the received signal strength index (RSSI), the reference signal quality (RSRQ), the signal-to-noise ratio (SNR), information about whether the user equipment as the sender and the user equipment as the receiver of the edge link are within the line of sight, and at least one of the statistics of the interference and noise of the channel.

[0132] As an example, the network-side device performs division based on the similarity between the probability distributions corresponding to at least one edge link. For an example of division based on the similarity between the probability distributions of the channel energy gains of the edge links, see the description in conjunction with FIG. 3 in the embodiment of electronic device 100, which is not repeated here.

[0133] As an example, the degree of similarity between the probability distributions includes the KL divergence between the probability distributions.

[0134] As an example, the channel energy gain is divided into a predetermined number of discrete gears, and the probability distribution includes the probability of the channel energy gain being in each gear. For the probability of the channel energy gain being in each gear, see P in the embodiment of the electronic device 100. i , I will not repeat it here.

[0135] As an example, the network-side device performs division based on the magnitude of RSRP.

[0136] As an example, the network-side devices are divided based on the RSSI amplitude.

[0137] As an example, the network-side device performs division based on the magnitude of RSRQ.

[0138] As an example, the network-side device performs division based on the magnitude of the SNR.

[0139] As an example, the network-side device is divided according to whether the electronic device as a sender and the electronic device as a receiver of the edge link are within the line of sight.

[0140] As an example, the network-side device performs division based on the size of the statistics of the channel interference and noise.

[0141] As an example, the statistics of interference and noise of a channel include a mean and / or a variance.

[0142] As an example, the communication unit 601 may be configured to report the channel information via radio resource control (RRC) signaling. For example, the RRC signaling may be MeasResultsSL signaling. For an example of MeasResultsSL, please refer to the description in the embodiment of the electronic device 100, which will not be repeated here.

[0143] As an example, the communication unit 601 may be configured to receive information about the partitioning from the network side device via a physical downlink control channel (PDCCH).

[0144] As an example, the communication unit 601 may be configured to receive parameters related to the initial global learning model in a first round of joint training.

[0145] As an example, the communication unit 601 may be configured to send auxiliary state information for uplink resource allocation to the network side device via an uplink.

[0146] As an example, the auxiliary status information includes at least one of the number of samples used by the electronic device 600 to train the learning model, the location information of the electronic device 600, the moving speed of the electronic device 600, the computing power of the electronic device 600, and the CPU occupancy rate of the electronic device 600. For examples of the auxiliary status information, please refer to the description of the embodiment of the electronic device 100, which will not be repeated here.

[0147] As an example, the communication unit 601 may be configured to receive information on uplink resource allocation from a network-side device via a downlink.

[0148] As an example, the communication unit 601 can be configured to send parameters of a local learning model to the network side device based on information about uplink resource allocation, where the local learning model is trained based on an initial global learning model sent by the network side device.

[0149] As an example, joint training includes aggregating local learning models related to edge links within the same group as an updated global learning model to obtain an aggregated learning model, and the communication unit 601 can be configured to receive parameters about the aggregated learning model from the network side device.

[0150] As an example, the network-side device repeatedly performs division and joint training until a predetermined condition is met.

[0151] As an example, the above learning model is used to assist in determining the data transmission rate of the edge link based on the data queue length and the channel energy gain of the edge link. For example, the learning model can be the deep reinforcement learning model involved in Figure 3.

[0152] As an example, the electronic device 600 is a device in a D2D scenario, for example, the electronic device 600 is a vehicle-mounted device in an Internet of Vehicles (IoV).

[0153] In the process of describing the electronic device for wireless communication in the above embodiments, it is obvious that some processes or methods are also disclosed. Below, an overview of these methods is given without repeating some of the details discussed above, but it should be noted that although these methods are disclosed in the process of describing the electronic device for wireless communication, these methods do not necessarily use the components described or are not necessarily performed by those components. For example, the embodiments of the electronic device for wireless communication can be partially or completely implemented using hardware and / or firmware, and the methods for wireless communication discussed below can be completely implemented by computer-executable programs, although these methods can also use the hardware and / or firmware of the electronic device for wireless communication.

[0154] FIG7 illustrates a flowchart of a method S700 for wireless communication according to an embodiment of the present disclosure. Method S700 begins at step S702. In step S704, based on channel information regarding the channel state of at least one edge link of at least one user device within the service range of the electronic device, the learning models of the user devices associated with the at least one edge link are divided into at least one group. In step S706, for at least a portion of the at least one group, joint training is performed on the learning models within the same group. Method S700 ends at step S708.

[0155] The method may be executed, for example, by the electronic device 100 described above. For specific details, please refer to the description of the related processing of the electronic device 100, which will not be repeated here.

[0156] FIG8 illustrates a flowchart of a method S800 for wireless communication according to an embodiment of the present disclosure. Method S800 begins at step S802. At step S804, channel information regarding the channel state of at least one edge link of the electronic device is reported to a network device providing services for the electronic device. The network device then divides the learning models of the electronic devices associated with the at least one edge link into at least one group based on the channel information, thereby facilitating joint training of the learning models within the same group for at least a portion of the at least one group. Method S800 concludes at step S806.

[0157] The method may be executed, for example, by the electronic device 600 described above. For specific details, please refer to the description of the related processing of the electronic device 600, which will not be repeated here.

[0158] The technology of the present disclosure can be applied to various products.

[0159] The electronic device 100 can be implemented as various network-side devices such as a base station. The base station can be implemented as any type of evolved Node B (eNB) or gNB (5G base station). eNBs include, for example, macro eNBs and small eNBs. Small eNBs can be eNBs that cover cells smaller than macro cells, such as pico eNBs, micro eNBs, and home (femto) eNBs. Similar situations can also apply to gNBs. Alternatively, the base station can be implemented as any other type of base station, such as a NodeB and a base transceiver station (BTS). The base station may include: a main body (also referred to as a base station device) configured to control wireless communications; and one or more remote radio heads (RRHs) located at a different location from the main body. In addition, various types of electronic devices can work as base stations by temporarily or semi-permanently performing base station functions.

[0160] The electronic device 600 can be implemented as various user devices. The user device can be implemented as a mobile terminal (such as a smartphone, a tablet personal computer (PC), a notebook PC, a portable game terminal, a portable / dongle-type mobile router, and a digital camera) or an in-vehicle terminal (such as a car navigation device). The user device can also be implemented as a terminal that performs machine-to-machine (M2M) communication (also known as a machine type communication (MTC) terminal). In addition, the user device can be a wireless communication module (such as an integrated circuit module including a single chip) installed on each of the above terminals.

[0161] [Application examples for base stations]

[0162] (First application example)

[0163] FIG9 is a block diagram illustrating a first example of a schematic configuration of an eNB or gNB to which the techniques of this disclosure can be applied. Note that the following description uses an eNB as an example, but is equally applicable to a gNB. An eNB 800 includes one or more antennas 810 and a base station device 820. The base station device 820 and each antenna 810 can be connected to each other via an RF cable.

[0164] Each of the antennas 810 includes a single or multiple antenna elements (such as multiple antenna elements included in a multiple-input multiple-output (MIMO) antenna) and is used for base station device 820 to transmit and receive wireless signals. As shown in FIG9 , eNB 800 may include multiple antennas 810. For example, multiple antennas 810 may be compatible with multiple frequency bands used by eNB 800. Although FIG9 shows an example in which eNB 800 includes multiple antennas 810, eNB 800 may also include a single antenna 810.

[0165] The base station device 820 includes a controller 821 , a memory 822 , a network interface 823 , and a wireless communication interface 825 .

[0166] The controller 821 may be, for example, a CPU or a DSP, and operates various functions of the higher layers of the base station device 820. For example, the controller 821 generates data packets based on the data in the signal processed by the wireless communication interface 825, and transmits the generated packets via the network interface 823. The controller 821 may bundle data from multiple baseband processors to generate bundled packets, and transmit the generated bundled packets. The controller 821 may have logic functions for performing the following controls: the control may be radio resource control, radio bearer control, mobility management, admission control, and scheduling. The control may be performed in conjunction with a nearby eNB or core network node. The memory 822 includes RAM and ROM, and stores programs executed by the controller 821 and various types of control data (such as a terminal list, transmission power data, and scheduling data).

[0167] The network interface 823 is a communication interface for connecting the base station device 820 to the core network 824. The controller 821 can communicate with the core network node or another eNB via the network interface 823. In this case, the eNB 800 and the core network node or other eNBs can be connected to each other through a logical interface (such as an S1 interface and an X2 interface). The network interface 823 can also be a wired communication interface or a wireless communication interface for a wireless backhaul line. If the network interface 823 is a wireless communication interface, the network interface 823 can use a higher frequency band for wireless communication than the frequency band used by the wireless communication interface 825.

[0168] The wireless communication interface 825 supports any cellular communication scheme, such as Long Term Evolution (LTE) and LTE-Advanced, and provides wireless connectivity to terminals located in the cell of the eNB 800 via the antenna 810. The wireless communication interface 825 may typically include, for example, a baseband (BB) processor 826 and RF circuitry 87. The BB processor 826 can perform various signal processing functions, such as encoding / decoding, modulation / demodulation, and multiplexing / demultiplexing, and performs various types of signal processing for layers such as Layer 1, Medium Access Control (MAC), Radio Link Control (RLC), and Packet Data Convergence Protocol (PDCP). In place of the controller 821, the BB processor 826 may have some or all of the aforementioned logical functions. The BB processor 826 may be a memory that stores communication control programs, or a module including a processor configured to execute programs and associated circuitry. Program updates can modify the functionality of the BB processor 826. This module may be a card or blade inserted into a slot in the base station device 820. Alternatively, the module may be a chip mounted on the card or blade. Meanwhile, the RF circuit 87 may include, for example, a mixer, a filter, and an amplifier, and transmits and receives wireless signals via the antenna 810 .

[0169] As shown in FIG9 , the wireless communication interface 825 may include multiple BB processors 826. For example, multiple BB processors 826 may be compatible with multiple frequency bands used by the eNB 800. As shown in FIG9 , the wireless communication interface 825 may include multiple RF circuits 87. For example, multiple RF circuits 87 may be compatible with multiple antenna elements. Although FIG9 illustrates an example in which the wireless communication interface 825 includes multiple BB processors 826 and multiple RF circuits 87, the wireless communication interface 825 may also include a single BB processor 826 or a single RF circuit 87.

[0170] In the eNB 800 shown in FIG9 , when the electronic device 100 is implemented as a base station, its transceiver may be implemented by the wireless communication interface 825. At least part of the functions may also be implemented by the controller 821. For example, the controller 821 may perform grouping and joint training by executing the functions of the units in the electronic device 100.

[0171] (Second application example)

[0172] FIG10 is a block diagram illustrating a second example of a schematic configuration of an eNB or gNB to which the techniques of this disclosure can be applied. Note that similarly, the following description uses an eNB as an example, but is equally applicable to a gNB. An eNB 830 includes one or more antennas 840, a base station device 850, and an RRH 860. The RRH 860 and each antenna 840 can be connected to each other via an RF cable. The base station device 850 and the RRH 860 can be connected to each other via a high-speed line such as a fiber optic cable.

[0173] Each of the antennas 840 includes a single or multiple antenna elements (such as multiple antenna elements included in a MIMO antenna) and is used for RRH 860 to transmit and receive wireless signals. As shown in FIG10 , eNB 830 may include multiple antennas 840. For example, multiple antennas 840 may be compatible with multiple frequency bands used by eNB 830. Although FIG10 shows an example in which eNB 830 includes multiple antennas 840, eNB 830 may also include a single antenna 840.

[0174] Base station device 850 includes a controller 851, a memory 852, a network interface 853, a wireless communication interface 855, and a connection interface 857. Controller 851, memory 852, and network interface 853 are the same as controller 821, memory 822, and network interface 823 described with reference to FIG.

[0175] The wireless communication interface 855 supports any cellular communication scheme (such as LTE and LTE-Advanced) and provides wireless communication to terminals located in the sector corresponding to the RRH 860 via the RRH 860 and the antenna 840. The wireless communication interface 855 may generally include, for example, a BB processor 856. The BB processor 856 is the same as the BB processor 826 described with reference to FIG. 9, except that the BB processor 856 is connected to the RF circuit 864 of the RRH 860 via the connection interface 857. As shown in FIG. 10, the wireless communication interface 855 may include multiple BB processors 856. For example, the multiple BB processors 856 may be compatible with multiple frequency bands used by the eNB 830. Although FIG. 10 shows an example in which the wireless communication interface 855 includes multiple BB processors 856, the wireless communication interface 855 may also include a single BB processor 856.

[0176] The connection interface 857 is an interface for connecting the base station device 850 (wireless communication interface 855) to the RRH 860. The connection interface 857 may also be a communication module for connecting the base station device 850 (wireless communication interface 855) to the RRH 860 for communication in the high-speed line.

[0177] The RRH 860 includes a connection interface 861 and a wireless communication interface 863 .

[0178] The connection interface 861 is an interface for connecting the RRH 860 (wireless communication interface 863) to the base station device 850. The connection interface 861 may also be a communication module for communication in the above-mentioned high-speed line.

[0179] The wireless communication interface 863 transmits and receives wireless signals via the antenna 840. The wireless communication interface 863 may generally include, for example, an RF circuit 864. The RF circuit 864 may include, for example, a mixer, a filter, and an amplifier, and transmits and receives wireless signals via the antenna 840. As shown in FIG10 , the wireless communication interface 863 may include multiple RF circuits 864. For example, the multiple RF circuits 864 may support multiple antenna elements. Although FIG10 shows an example in which the wireless communication interface 863 includes multiple RF circuits 864, the wireless communication interface 863 may also include a single RF circuit 864.

[0180] In the eNB 830 shown in FIG10 , when the electronic device 100 is implemented as a base station, its transceiver may be implemented by the wireless communication interface 855. At least part of the functions may also be implemented by the controller 851. For example, the controller 851 may perform grouping and joint training by executing the functions of the units in the electronic device 100.

[0181] [Application examples on user devices]

[0182] (First application example)

[0183] 11 is a block diagram showing an example of a schematic configuration of a smartphone 900 to which the technology of the present disclosure can be applied. The smartphone 900 includes a processor 901, a memory 902, a storage device 903, an external connection interface 904, a camera 906, a sensor 907, a microphone 908, an input device 909, a display device 910, a speaker 911, a wireless communication interface 912, one or more antenna switches 915, one or more antennas 916, a bus 917, a battery 918, and an auxiliary controller 919.

[0184] The processor 901 may be, for example, a CPU or a system on a chip (SoC), and controls the functions of the application layer and other layers of the smartphone 900. The memory 902 includes RAM and ROM, and stores data and programs executed by the processor 901. The storage device 903 may include storage media such as semiconductor memories and hard disks. The external connection interface 904 is an interface for connecting external devices (such as memory cards and universal serial bus (USB) devices) to the smartphone 900.

[0185] The camera 906 includes an image sensor such as a charge coupled device (CCD) and a complementary metal oxide semiconductor (CMOS) and generates a captured image. The sensor 907 may include a group of sensors such as a measurement sensor, a gyroscope sensor, a geomagnetic sensor, and an acceleration sensor. The microphone 908 converts the sound input to the smartphone 900 into an audio signal. The input device 909 includes, for example, a touch sensor, a keypad, a keyboard, a button, or a switch configured to detect a touch on the screen of the display device 910, and receives an operation or information input from the user. The display device 910 includes a screen such as a liquid crystal display (LCD) and an organic light emitting diode (OLED) display and displays an output image of the smartphone 900. The speaker 911 converts the audio signal output from the smartphone 900 into sound.

[0186] The wireless communication interface 912 supports any cellular communication scheme (such as LTE and LTE-Advanced) and performs wireless communications. The wireless communication interface 912 may typically include, for example, a BB processor 913 and an RF circuit 914. The BB processor 913 may perform, for example, encoding / decoding, modulation / demodulation, and multiplexing / demultiplexing, and may also perform various types of signal processing for wireless communications. Meanwhile, the RF circuit 914 may include, for example, mixers, filters, and amplifiers, and transmit and receive wireless signals via an antenna 916. Note that while the figure shows a scenario where one RF link is connected to one antenna, this is merely illustrative, and also encompasses scenarios where one RF link is connected to multiple antennas via multiple phase shifters. The wireless communication interface 912 may be a chip module on which the BB processor 913 and the RF circuit 914 are integrated. As shown in FIG11 , the wireless communication interface 912 may include multiple BB processors 913 and multiple RF circuits 914. While FIG11 illustrates an example in which the wireless communication interface 912 includes multiple BB processors 913 and multiple RF circuits 914, the wireless communication interface 912 may also include a single BB processor 913 or a single RF circuit 914.

[0187] In addition, in addition to the cellular communication scheme, the wireless communication interface 912 can support other types of wireless communication schemes, such as a short-range wireless communication scheme, a near-field communication scheme, and a wireless local area network (LAN) scheme. In this case, the wireless communication interface 912 may include a BB processor 913 and an RF circuit 914 for each wireless communication scheme.

[0188] Each of the antenna switches 915 switches a connection destination of the antenna 916 between a plurality of circuits (eg, circuits for different wireless communication schemes) included in the wireless communication interface 912 .

[0189] Each of the antennas 916 includes a single or multiple antenna elements (such as multiple antenna elements included in a MIMO antenna) and is used for transmitting and receiving wireless signals via the wireless communication interface 912. As shown in FIG11 , the smartphone 900 may include multiple antennas 916. Although FIG11 shows an example in which the smartphone 900 includes multiple antennas 916, the smartphone 900 may also include a single antenna 916.

[0190] In addition, the smartphone 900 may include an antenna 916 for each wireless communication scheme. In this case, the antenna switch 915 may be omitted from the configuration of the smartphone 900.

[0191] The bus 917 connects the processor 901, the memory 902, the storage device 903, the external connection interface 904, the camera 906, the sensor 907, the microphone 908, the input device 909, the display device 910, the speaker 911, the wireless communication interface 912, and the auxiliary controller 919. The battery 918 supplies power to the various blocks of the smartphone 900 shown in FIG11 via feeders, which are partially shown as dotted lines in the figure. The auxiliary controller 919 operates the minimum necessary functions of the smartphone 900, for example, in sleep mode.

[0192] In the smartphone 900 shown in FIG11 , when the electronic device 600 is implemented as a smartphone serving as a user device, for example, the transceiver of the electronic device 600 may be implemented by the wireless communication interface 912. At least a portion of the functionality may also be implemented by the processor 901 or the auxiliary controller 919. For example, the processor 901 or the auxiliary controller 919 may report channel information of the edge link by executing the functionality of the aforementioned units in the electronic device 600.

[0193] (Second application example)

[0194] 12 is a block diagram showing an example of a schematic configuration of a car navigation device 920 to which the technology of the present disclosure can be applied. The car navigation device 920 includes a processor 921, a memory 922, a global positioning system (GPS) module 924, a sensor 925, a data interface 926, a content player 97, a storage medium interface 928, an input device 99, a display device 930, a speaker 931, a wireless communication interface 913, one or more antenna switches 936, one or more antennas 937, and a battery 938.

[0195] The processor 921 may be, for example, a CPU or an SoC, and controls a navigation function and other functions of the car navigation apparatus 920. The memory 922 includes a RAM and a ROM, and stores data and programs executed by the processor 921.

[0196] The GPS module 924 measures the position (such as latitude, longitude, and altitude) of the car navigation device 920 using GPS signals received from GPS satellites. The sensor 925 may include a group of sensors such as a gyroscope sensor, a geomagnetic sensor, and an air pressure sensor. The data interface 926 is connected to, for example, the in-vehicle network 941 via an unillustrated terminal and acquires data generated by the vehicle (such as vehicle speed data).

[0197] The content player 97 reproduces content stored in a storage medium (such as a CD or DVD) inserted into the storage medium interface 928. The input device 99 includes, for example, a touch sensor, button, or switch configured to detect a touch on the screen of the display device 930, and receives operations or information input from the user. The display device 930 includes a screen such as an LCD or OLED display and displays images of the navigation function or reproduced content. The speaker 931 outputs sounds of the navigation function or reproduced content.

[0198] The wireless communication interface 913 supports any cellular communication scheme (such as LTE and LTE-Advanced) and performs wireless communication. The wireless communication interface 913 may generally include, for example, a BB processor 934 and an RF circuit 935. The BB processor 934 may perform, for example, encoding / decoding, modulation / demodulation, and multiplexing / demultiplexing, and perform various types of signal processing for wireless communication. Meanwhile, the RF circuit 935 may include, for example, a mixer, a filter, and an amplifier, and transmit and receive wireless signals via an antenna 937. The wireless communication interface 913 may also be a chip module on which the BB processor 934 and the RF circuit 935 are integrated. As shown in Figure 12, the wireless communication interface 913 may include multiple BB processors 934 and multiple RF circuits 935. Although Figure 12 shows an example in which the wireless communication interface 913 includes multiple BB processors 934 and multiple RF circuits 935, the wireless communication interface 913 may also include a single BB processor 934 or a single RF circuit 935.

[0199] In addition, in addition to the cellular communication scheme, the wireless communication interface 913 can support other types of wireless communication schemes, such as a short-range wireless communication scheme, a near field communication scheme, and a wireless LAN scheme. In this case, for each wireless communication scheme, the wireless communication interface 913 can include a BB processor 934 and an RF circuit 935.

[0200] Each of the antenna switches 936 switches a connection destination of the antenna 937 between a plurality of circuits included in the wireless communication interface 913 , such as circuits for different wireless communication schemes.

[0201] Each of the antennas 937 includes a single or multiple antenna elements (such as multiple antenna elements included in a MIMO antenna) and is used for transmitting and receiving wireless signals via the wireless communication interface 913. As shown in FIG12, the car navigation device 920 may include multiple antennas 937. Although FIG12 shows an example in which the car navigation device 920 includes multiple antennas 937, the car navigation device 920 may also include a single antenna 937.

[0202] Furthermore, the car navigation device 920 may include an antenna 937 for each wireless communication scheme. In this case, the antenna switch 936 may be omitted from the configuration of the car navigation device 920.

[0203] The battery 938 supplies power to the respective blocks of the car navigation device 920 shown in Fig. 12 via a feeder line, which is partially shown as a dotted line in the figure. The battery 938 accumulates the power supplied from the vehicle.

[0204] In the car navigation device 920 shown in FIG12 , when the electronic device 600 is implemented as a car navigation device serving as a user equipment, for example, the transceiver of the electronic device 600 may be implemented by the wireless communication interface 933. At least a portion of the functions may also be implemented by the processor 921. For example, the processor 921 may report channel information of the edge link by executing the functions of the units in the electronic device 600 described above.

[0205] The technology of the present disclosure can also be implemented as an in-vehicle system (or vehicle) 940 including a car navigation device 920, an in-vehicle network 941, and one or more blocks of a vehicle module 942. The vehicle module 942 generates vehicle data (such as vehicle speed, engine speed, and fault information) and outputs the generated data to the in-vehicle network 941.

[0206] The basic principles of the present invention are described above in conjunction with specific embodiments. However, it should be pointed out that those skilled in the art will understand that all or any steps or components of the methods and devices of the present invention can be implemented in any computing device (including a processor, storage medium, etc.) or a network of computing devices in the form of hardware, firmware, software, or a combination thereof. This can be achieved by those skilled in the art using their basic circuit design knowledge or basic programming skills after reading the description of the present invention.

[0207] Furthermore, the present invention also provides a program product storing machine-readable instruction codes. When the instruction codes are read and executed by a machine, the method according to the embodiment of the present invention can be executed.

[0208] Accordingly, the storage medium for carrying the program product storing the machine-readable instruction code is also included in the disclosure of the present invention. The storage medium includes but is not limited to a floppy disk, an optical disk, a magneto-optical disk, a memory card, a memory stick, and the like.

[0209] When the present invention is implemented through software or firmware, the programs constituting the software are installed from a storage medium or a network to a computer with a dedicated hardware structure (such as the general-purpose computer 1300 shown in Figure 13). When various programs are installed on the computer, it can perform various functions, etc.

[0210] In FIG13 , a central processing unit (CPU) 1301 executes various processes according to a program stored in a read-only memory (ROM) 1302 or a program loaded from a storage section 1308 to a random access memory (RAM) 1303. In the RAM 1303, data required when the CPU 1301 executes various processes, etc., is also stored as needed. The CPU 1301, the ROM 1302, and the RAM 1303 are connected to each other via a bus 1304. An input / output interface 1305 is also connected to the bus 1304.

[0211] The following components are connected to the input / output interface 1305: an input section 1306 (including a keyboard, a mouse, etc.), an output section 1307 (including a display such as a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and speakers, etc.), a storage section 1308 (including a hard disk, etc.), and a communication section 1309 (including a network interface card such as a LAN card, a modem, etc.). The communication section 1309 performs communication processing via a network such as the Internet. A drive 1310 may also be connected to the input / output interface 1305 as needed. A removable medium 1311 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is installed in the drive 1310 as needed, so that a computer program read therefrom is installed in the storage section 1308 as needed.

[0212] In the case of realizing the above-described series of processing by software, a program constituting the software is installed from a network such as the Internet or a storage medium such as the removable medium 1311 .

[0213] It should be understood by those skilled in the art that such storage media is not limited to the removable medium 1311 shown in FIG. 13 , which stores the program and is distributed separately from the device to provide the program to the user. Examples of the removable medium 1311 include magnetic disks (including floppy disks (registered trademark)), optical disks (including compact disk read-only memories (CD-ROMs) and digital versatile disks (DVDs)), magneto-optical disks (including minidiscs (MDs) (registered trademark)), and semiconductor memories. Alternatively, the storage medium may be the ROM 1302, a hard disk included in the storage section 1308, or the like, in which the program is stored and distributed to the user together with the device containing the program.

[0214] It should also be noted that in the apparatus, method, and system of the present invention, each component or step can be decomposed and / or recombined. Such decomposition and / or recombination should be considered equivalent solutions of the present invention. Furthermore, the steps of performing the above series of processes can naturally be performed in chronological order according to the order described, but do not necessarily need to be performed in chronological order. Certain steps can be performed in parallel or independently of each other.

[0215] Finally, it should be noted that the terms "comprises," "comprising," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Furthermore, in the absence of further limitations, an element defined by the phrase "comprising a..." does not preclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0216] Although the embodiments of the present invention have been described in detail above with reference to the accompanying drawings, it should be understood that the embodiments described above are merely illustrative of the present invention and are not intended to limit the present invention. It will be apparent to those skilled in the art that various modifications and variations may be made to the embodiments described above without departing from the spirit and scope of the present invention. Therefore, the scope of the present invention is limited solely by the appended claims and their equivalents.

[0217] The present technology can also be implemented as follows.

[0218] Solution 1. An electronic device for wireless communication, comprising:

[0219] The processing circuit is configured to:

[0220] dividing the learning model of the user equipment related to the at least one edge link into at least one group based on channel information about the channel state of at least one edge link of the at least one user equipment reported by the at least one user equipment located within the service range of the electronic device, and

[0221] For at least a part of the at least one group, the learning models in the same group are jointly trained.

[0222] Solution 2. The electronic device according to Solution 1, wherein:

[0223] The channel information of the edge link includes the probability distribution of the channel energy gain of the edge link, the reference signal received power RSRP, the received signal strength indicator RSSI, the reference signal quality RSRQ, the signal-to-noise ratio SNR, information about whether the user equipment as the sender and the user equipment as the receiver of the edge link are within the line of sight range, and at least one of the statistics of the channel interference and noise.

[0224] Solution 3. The electronic device according to Solution 2, wherein:

[0225] The processing circuit is configured to perform the division based on a degree of similarity between probability distributions respectively corresponding to the at least one edge link.

[0226] Solution 4. The electronic device according to Solution 3, wherein:

[0227] The degree of similarity includes the KL divergence between the probability distributions.

[0228] Solution 5. The electronic device according to any one of Solution 2 to Solution 4, wherein:

[0229] The channel energy gain is divided into a predetermined number of discrete levels, and the probability distribution includes a probability of the channel energy gain being in each level.

[0230] Solution 6. The electronic device according to Solution 2, wherein:

[0231] The processing circuit is configured to perform the division based on a magnitude of the RSRP.

[0232] Solution 7. The electronic device according to Solution 2, wherein:

[0233] The processing circuit is configured to perform the division based on a magnitude of the RSSI.

[0234] Solution 8. The electronic device according to Solution 2, wherein:

[0235] The processing circuit is configured to perform the partitioning based on a magnitude of the RSRQ.

[0236] Solution 9. The electronic device according to Solution 2, wherein:

[0237] The processing circuit is configured to perform the division based on a magnitude of the SNR.

[0238] Solution 10. The electronic device according to Solution 2, wherein:

[0239] The processing circuit is configured to perform the division according to whether the user equipment serving as a sender and the user equipment serving as a receiver of the edge link are within a line of sight range.

[0240] Solution 11. The electronic device according to Solution 2, wherein:

[0241] The processing circuit is configured to perform the division based on the magnitude of statistics of interference and noise of the channel.

[0242] Solution 12. The electronic device according to Solution 11, wherein:

[0243] The statistics of interference and noise of the channel include mean and / or variance.

[0244] Solution 13. The electronic device according to any one of Solutions 1 to 12, wherein:

[0245] The processing circuit is configured to receive the channel information via Radio Resource Control (RRC) signaling.

[0246] Solution 14. The electronic device according to any one of Solutions 1 to 13, wherein:

[0247] The processing circuit is configured to send information about the division to at least a portion of the user equipments related to the edge link in each group through a physical downlink control channel (PDCCH).

[0248] Solution 15. The electronic device according to Solution 14, wherein:

[0249] The processing circuit is configured to send parameters related to the initial global learning model to the at least part of the user equipment in a first round of the joint training.

[0250] Solution 16. The electronic device according to Solution 15, wherein:

[0251] The processing circuit is configured to receive auxiliary state information for uplink resource allocation from the at least part of the user equipments via an uplink.

[0252] Solution 17. The electronic device according to Solution 16, wherein:

[0253] The auxiliary status information includes at least one of the number of samples used by the user equipment to train the learning model, the location information of the user equipment, the moving speed of the user equipment, the computing power of the user equipment, and the CPU occupancy rate of the user equipment.

[0254] Solution 18. The electronic device according to Solution 16 or 17, wherein the processing circuit is configured to allocate uplink resources to the at least part of the user equipment based on the auxiliary status information.

[0255] Solution 19. The electronic device according to Solution 18, wherein the processing circuit is configured to send information about uplink resource allocation to the at least part of the user equipment via a downlink.

[0256] Scheme 20. An electronic device according to Scheme 18 or 19, wherein the processing circuit is configured to receive parameters related to the local learning model uploaded by at least a portion of the user equipment based on the information about uplink resource allocation, wherein the local learning model is trained based on the initial global learning model sent down by the electronic device.

[0257] Solution 21. The electronic device according to Solution 20, wherein:

[0258] The joint training includes aggregating local learning models related to edge links in the same group, thereby obtaining the aggregated learning model as an updated global learning model, and

[0259] The processing circuit is configured to broadcast the parameters of the aggregated learning model of each group to the user equipments in the group.

[0260] Solution 22. The electronic device according to any one of Solutions 1 to 21, wherein the processing circuit is configured to repeatedly perform the dividing and the joint training until a predetermined condition is met.

[0261] Solution 23. The electronic device according to any one of Solutions 1 to 22, wherein:

[0262] The learning model is used to assist in determining the data transmission rate of the edge link according to the data queue length and the channel energy gain of the edge link.

[0263] Solution 24. The electronic device according to any one of Solutions 1 to 23, wherein:

[0264] The at least one user equipment is a device in a D2D scenario.

[0265] Solution 25. An electronic device for wireless communication, comprising:

[0266] The processing circuit is configured to:

[0267] Channel information about the channel status of at least one edge link of the electronic device is reported to a network-side device that provides services for the electronic device, so that the network-side device can divide the learning models of the electronic devices related to the at least one edge link and other electronic devices related to the at least one edge link and provided with services by the network-side device into at least one group based on the channel information, thereby facilitating the network-side device to jointly train the learning models in the same group for at least a part of the at least one group.

[0268] Solution 26. The electronic device according to Solution 25, wherein:

[0269] The channel information of the edge link includes the probability distribution of the channel energy gain of the edge link, the reference signal received power RSRP, the received signal strength indicator RSSI, the reference signal quality RSRQ, the signal-to-noise ratio SNR, information about whether the user equipment as the sender and the user equipment as the receiver of the edge link are within the line of sight range, and at least one of the statistics of the channel interference and noise.

[0270] Solution 27. The electronic device according to Solution 26, wherein:

[0271] The network-side device performs the division based on the similarity between the probability distributions respectively corresponding to the at least one edge link.

[0272] Solution 28. The electronic device according to Solution 27, wherein:

[0273] The degree of similarity includes the KL divergence between the probability distributions.

[0274] Solution 29. The electronic device according to any one of Solution 26 to Solution 28, wherein:

[0275] The channel energy gain is divided into a predetermined number of discrete levels, and the probability distribution includes a probability of the channel energy gain being in each level.

[0276] Solution 30. The electronic device according to Solution 26, wherein:

[0277] The network-side device performs the division based on the magnitude of the RSRP.

[0278] Solution 31. The electronic device according to Solution 26, wherein:

[0279] The network-side device performs the division based on the amplitude of the RSSI.

[0280] Solution 32. The electronic device according to Solution 26, wherein:

[0281] The network side device performs the division based on the magnitude of the RSRQ.

[0282] Solution 33. The electronic device according to Solution 26, wherein:

[0283] The network-side device performs the division based on the magnitude of the SNR.

[0284] Solution 34. The electronic device according to Solution 26, wherein:

[0285] The network-side device performs the division according to whether the electronic device serving as a sender and the electronic device serving as a receiver of the edge link are within a line-of-sight range.

[0286] Option 35. The electronic device according to Option 26, wherein:

[0287] The network side device performs the division based on the size of the statistics of the interference and noise of the channel.

[0288] Solution 36. The electronic device according to Solution 35, wherein:

[0289] The statistics of interference and noise of the channel include mean and / or variance.

[0290] Solution 37. The electronic device according to any one of Solution 25 to Solution 36, wherein:

[0291] The processing circuit is configured to report the channel information via radio resource control (RRC) signaling.

[0292] Solution 38. The electronic device according to any one of Solutions 25 to 37, wherein:

[0293] The processing circuit is configured to receive information about the division from the network side device via a physical downlink control channel (PDCCH).

[0294] Solution 39. The electronic device according to Solution 38, wherein:

[0295] The processing circuit is configured to receive parameters related to an initial global learning model in a first round of joint training.

[0296] Solution 40. The electronic device according to Solution 39, wherein:

[0297] The processing circuit is configured to send auxiliary state information for uplink resource allocation to the network side device via an uplink.

[0298] Solution 41. The electronic device according to Solution 40, wherein:

[0299] The auxiliary status information includes at least one of the number of samples used to train the learning model of the electronic device, the location information of the electronic device, the moving speed of the electronic device, the computing power of the electronic device, and the CPU occupancy rate of the electronic device.

[0300] Solution 42. The electronic device according to Solution 40 or 41, wherein the processing circuit is configured to receive information about uplink resource allocation from the network-side device via a downlink.

[0301] Scheme 43. An electronic device according to Scheme 42, wherein the processing circuit is configured to send parameters related to the local learning model to the network side device based on the information about uplink resource allocation, wherein the local learning model is trained based on the initial global learning model sent down by the network side device.

[0302] Solution 44. The electronic device according to Solution 43, wherein:

[0303] The joint training includes aggregating local learning models related to edge links in the same group as an updated global learning model, thereby obtaining an aggregated learning model, and

[0304] The processing circuit is configured to receive parameters related to the aggregated learning model from the network-side device.

[0305] Solution 45. The electronic device according to any one of Solutions 25 to 44, wherein the network-side device repeatedly performs the division and the joint training until a predetermined condition is met.

[0306] Solution 46. The electronic device according to any one of Solution 25 to Solution 45, wherein:

[0307] The learning model is used to assist in determining the data transmission rate of the edge link according to the data queue length and the channel energy gain of the edge link.

[0308] Solution 47. The electronic device according to any one of Solutions 25 to 46, wherein:

[0309] The electronic device is a device in a D2D scenario.

[0310] Solution 48. A method for wireless communication, comprising:

[0311] dividing the learning model of the user equipment related to the at least one edge link into at least one group based on channel information about the channel state of at least one edge link of the at least one user equipment reported by the at least one user equipment located within the service range of the electronic device, and

[0312] For at least a part of the at least one group, the learning models in the same group are jointly trained.

[0313] Solution 49. A method for wireless communication, comprising:

[0314] Channel information about the channel status of at least one edge link of the electronic device is reported to a network-side device that provides services for the electronic device, so that the network-side device can divide the learning models of the electronic devices related to the at least one edge link and other electronic devices related to the at least one edge link and provided with services by the network-side device into at least one group based on the channel information, thereby facilitating the network-side device to jointly train the learning models in the same group for at least a part of the at least one group.

[0315] Embodiment 50: A computer-readable storage medium having computer-executable instructions stored thereon. When the computer-executable instructions are executed, the method for wireless communication according to embodiment 48 or 49 is performed.

Claims

1. An electronic device for wireless communication, comprising: The processing circuit is configured to: dividing the learning model of the user equipment related to the at least one edge link into at least one group based on channel information about the channel state of at least one edge link of the at least one user equipment reported by the at least one user equipment located within the service range of the electronic device, and For at least a part of the at least one group, the learning models in the same group are jointly trained.

2. The electronic device according to claim 1, wherein The channel information of the edge link includes the probability distribution of the channel energy gain of the edge link, the reference signal received power RSRP, the received signal strength indicator RSSI, the reference signal quality RSRQ, the signal-to-noise ratio SNR, information about whether the user equipment as the sender and the user equipment as the receiver of the edge link are within the line of sight range, and at least one of the statistics of the channel interference and noise.

3. The electronic device according to claim 2, wherein The processing circuit is configured to perform the division based on a degree of similarity between probability distributions respectively corresponding to the at least one edge link.

4. The electronic device according to claim 3, wherein The degree of similarity includes the KL divergence between the probability distributions.

5. The electronic device according to any one of claims 2 to 4, wherein: The channel energy gain is divided into a predetermined number of discrete levels, and the probability distribution includes a probability of the channel energy gain being in each level.

6. The electronic device according to claim 2, wherein The processing circuit is configured to perform the division based on a magnitude of the RSRP.

7. The electronic device according to claim 2, wherein: The processing circuit is configured to perform the division based on a magnitude of the RSSI.

8. The electronic device according to claim 2, wherein: The processing circuit is configured to perform the partitioning based on a magnitude of the RSRQ.

9. The electronic device according to claim 2, wherein: The processing circuit is configured to perform the division based on a magnitude of the SNR.

10. The electronic device according to claim 2, wherein The processing circuit is configured to perform the division according to whether the user equipment serving as a sender and the user equipment serving as a receiver of the edge link are within a line of sight range.

11. The electronic device according to claim 2, wherein: The processing circuit is configured to perform the division based on the magnitude of statistics of interference and noise of the channel.

12. The electronic device according to claim 11, wherein The statistics of interference and noise of the channel include mean and / or variance.

13. The electronic device according to any one of claims 1 to 12, wherein: The processing circuit is configured to receive the channel information via Radio Resource Control (RRC) signaling.

14. The electronic device according to any one of claims 1 to 13, wherein: The processing circuit is configured to send information about the division to at least a portion of the user equipments related to the edge link in each group through a physical downlink control channel (PDCCH).

15. The electronic device according to claim 14, wherein The processing circuit is configured to send parameters related to the initial global learning model to the at least part of the user equipment in a first round of the joint training.

16. The electronic device according to claim 15, wherein The processing circuit is configured to receive auxiliary state information for uplink resource allocation from the at least part of the user equipments via an uplink.

17. The electronic device according to claim 16, wherein: The auxiliary state information includes the number of samples used by the user equipment to train the learning model, At least one of the following: location information of the user equipment, moving speed of the user equipment, computing power of the user equipment, and CPU occupancy rate of the user equipment.

18. The electronic device according to claim 16 or 17, wherein: The processing circuit is configured to perform uplink resource allocation for the at least part of the user equipment based on the auxiliary state information.

19. The electronic device according to claim 18, wherein The processing circuit is configured to send information on uplink resource allocation to the at least part of the user equipment via a downlink.

20. The electronic device according to claim 18 or 19, wherein: The processing circuit is configured to receive parameters related to a local learning model uploaded by at least a portion of the user equipment based on the information about uplink resource allocation, wherein the local learning model is trained based on an initial global learning model sent down by the electronic device.

21. The electronic device according to claim 20, wherein The joint training includes aggregating local learning models related to edge links in the same group, thereby obtaining the aggregated learning model as an updated global learning model, and The processing circuit is configured to broadcast the parameters of the aggregated learning model of each group to the user equipments in the group.

22. The electronic device according to any one of claims 1 to 21, wherein: The processing circuit is configured to repeatedly perform the dividing and the joint training until a predetermined condition is met.

23. The electronic device according to any one of claims 1 to 22, wherein: The learning model is used to assist in determining the data transmission rate of the edge link according to the data queue length and the channel energy gain of the edge link.

24. The electronic device according to any one of claims 1 to 23, wherein: The at least one user equipment is a device in a D2D scenario.

25. An electronic device for wireless communication, comprising: The processing circuit is configured to: Report information about the electronic device to the network side device that provides services for the electronic device The channel information of the channel state of at least one edge link is provided so that the network side device can divide the learning models of the electronic devices related to the at least one edge link and other electronic devices related to the at least one edge link and served by the network side device into at least one group based on the channel information, thereby facilitating the network side device to jointly train the learning models in the same group for at least a part of the at least one group.

26. The electronic device according to claim 25, wherein The channel information of the edge link includes the probability distribution of the channel energy gain of the edge link, the reference signal received power RSRP, the received signal strength indicator RSSI, the reference signal quality RSRQ, the signal-to-noise ratio SNR, information about whether the user equipment as the sender and the user equipment as the receiver of the edge link are within the line of sight range, and at least one of the statistics of the channel interference and noise.

27. The electronic device according to claim 26, wherein The network-side device performs the division based on the similarity between the probability distributions respectively corresponding to the at least one edge link.

28. The electronic device according to claim 27, wherein The degree of similarity includes the KL divergence between the probability distributions.

29. The electronic device according to any one of claims 26 to 28, wherein: The channel energy gain is divided into a predetermined number of discrete levels, and the probability distribution includes a probability of the channel energy gain being in each level.

30. The electronic device according to claim 26, wherein The network-side device performs the division based on the magnitude of the RSRP.

31. The electronic device according to claim 26, wherein The network-side device performs the division based on the amplitude of the RSSI.

32. The electronic device according to claim 26, wherein The network side device performs the division based on the magnitude of the RSRQ.

33. The electronic device according to claim 26, wherein The network-side device performs the division based on the magnitude of the SNR.

34. The electronic device according to claim 26, wherein The network-side device performs the division according to whether the electronic device serving as a sender and the electronic device serving as a receiver of the edge link are within a line-of-sight range.

35. The electronic device according to claim 26, wherein The network side device performs the division based on the size of the statistics of the interference and noise of the channel.

36. The electronic device according to claim 35, wherein The statistics of interference and noise of the channel include mean and / or variance.

37. The electronic device according to any one of claims 25 to 36, wherein: The processing circuit is configured to report the channel information via radio resource control (RRC) signaling.

38. The electronic device according to any one of claims 25 to 37, wherein: The processing circuit is configured to receive information about the division from the network side device via a physical downlink control channel (PDCCH).

39. The electronic device according to claim 38, wherein The processing circuit is configured to receive parameters related to an initial global learning model in a first round of joint training.

40. The electronic device according to claim 39, wherein The processing circuit is configured to send auxiliary state information for uplink resource allocation to the network side device via an uplink.

41. The electronic device according to claim 40, wherein The auxiliary status information includes at least one of the number of samples used to train the learning model of the electronic device, the location information of the electronic device, the moving speed of the electronic device, the computing power of the electronic device, and the CPU occupancy rate of the electronic device.

42. The electronic device according to claim 40 or 41, wherein: The processing circuit is configured to receive information about uplink resource allocation from the network-side device via a downlink.

43. The electronic device according to claim 42, wherein The processing circuit is configured to send parameters related to a local learning model to the network side device based on the information related to uplink resource allocation, wherein the local learning model is trained based on an initial global learning model sent down by the network side device.

44. The electronic device according to claim 43, wherein The joint training includes aggregating local learning models related to edge links in the same group as an updated global learning model, thereby obtaining an aggregated learning model, and The processing circuit is configured to receive parameters related to the aggregated learning model from the network-side device.

45. The electronic device according to any one of claims 25 to 44, wherein The network-side device repeatedly performs the division and the joint training until a predetermined condition is met.

46. ​​The electronic device according to any one of claims 25 to 45, wherein: The learning model is used to assist in determining the data transmission rate of the edge link according to the data queue length and the channel energy gain of the edge link.

47. The electronic device according to any one of claims 25 to 46, wherein: The electronic device is a device in a D2D scenario.

48. A method for wireless communication, comprising: dividing the learning model of the user equipment related to the at least one edge link into at least one group based on channel information about the channel state of at least one edge link of the at least one user equipment reported by the at least one user equipment located within the service range of the electronic device, and For at least a part of the at least one group, the learning models in the same group are jointly trained.

49. A method for wireless communication, comprising: Channel information about the channel status of at least one edge link of the electronic device is reported to a network-side device that provides services for the electronic device, so that the network-side device can divide the learning models of the electronic devices related to the at least one edge link and other electronic devices related to the at least one edge link and provided with services by the network-side device into at least one group based on the channel information, thereby facilitating the network-side device to jointly train the learning models in the same group for at least a part of the at least one group.

50. A computer-readable storage medium having computer-executable instructions stored thereon, which, when executed, perform the method for wireless communication according to claim 48 or 49.

Images