Electronic device and method for spectrum management apparatus

Abstract

The present application relates to an electronic device and method for a spectrum management apparatus. The electronic device for the spectrum management apparatus comprises a processing circuit. The processing circuit is configured to, with respect to at least one federated prediction area in a plurality of federated prediction areas constructed based on a secondary system, obtain a primary system behavior model configured for predicting the behavior of a primary system using spectrum resources by means of federated learning.

Description

Electronic device and method for spectrum management device

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on May 9, 2023, with application number 202310519954.2 and invention name “Electronic device and method for spectrum management device”, 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 a spectrum management device, and more particularly to more effectively predicting the received power of a primary system in different areas for spectrum resource sensing. Background Art

[0003] Existing spectrum sharing technologies rely on federated learning to predict the occupancy of available spectrum resources. In large-scale network scenarios, global federated learning leads to high communication latency and high model complexity.

[0004] Summary of the Invention

[0005] 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.

[0006] According to one aspect of the present disclosure, an electronic device for a spectrum management device is provided, which includes a processing circuit, and the processing circuit is configured to: obtain a main system behavior model for predicting the behavior of the main system in using spectrum resources through federated learning for at least one federal prediction area among multiple federal prediction areas constructed based on the secondary system.

[0007] In the embodiments of the present disclosure, the received power of the primary system in different areas can be predicted more effectively for spectrum resource sensing.

[0008] According to one aspect of the present disclosure, an electronic device for a spectrum management device is provided, which includes a processing circuit, and the processing circuit is configured to: for one federal prediction area among multiple federal prediction areas constructed based on a secondary system, assist in obtaining a main system behavior model for predicting the behavior of the main system in using spectrum resources through federated learning.

[0009] In the embodiments according to the present disclosure, it is possible to assist in more effectively predicting the received power of the primary system in different areas for spectrum resource sensing.

[0010] According to one aspect of the present disclosure, a method for a spectrum management device is provided, comprising: for at least one federal prediction area among multiple federal prediction areas constructed based on a secondary system, the spectrum management device obtains a main system behavior model for predicting the behavior of the main system in using spectrum resources through federated learning.

[0011] According to one aspect of the present disclosure, a method for a spectrum management device is provided, including: for one federal prediction area among multiple federal prediction areas constructed based on a secondary system, assisting in obtaining a main system behavior model for predicting the behavior of the main system in using spectrum resources through federated learning.

[0012] According to other aspects of the present invention, a computer program code and a computer program product for implementing the above-mentioned method for a spectrum management apparatus are also provided, as well as a computer-readable storage medium having the computer program code for implementing the above-mentioned method for a spectrum management apparatus recorded thereon. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] 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 accompanying 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 depict typical examples of the present invention and should not be regarded as limiting the scope of the present invention. In the drawings:

[0014] FIG1 shows a functional module block diagram of an electronic device used in a spectrum management apparatus according to an embodiment of the present disclosure;

[0015] FIG. 2( a ) shows one example of a system structure according to an embodiment of the present disclosure, and FIG. 2( b ) shows another example of a system structure according to an embodiment of the present disclosure;

[0016] FIG3 is a diagram illustrating an example of dividing a network according to an embodiment of the present disclosure;

[0017] FIG4 is an example of a pseudo code illustrating a K-DBSCAN algorithm according to an embodiment of the present disclosure;

[0018] 5( a ) and 5 ( b ) are examples showing the effect of using the K-DBSCAN algorithm to determine the federated prediction area according to an embodiment of the present disclosure;

[0019] FIG6 is an example of a process for constructing a federated prediction region according to an embodiment of the present disclosure;

[0020] FIG7 is a schematic diagram illustrating information interaction for constructing a federated learning group according to an embodiment of the present disclosure;

[0021] FIG8 shows an example of selecting a federation aggregation point for performing local model aggregation according to an embodiment of the present disclosure;

[0022] FIG9 is an example showing the structure of an LSTM network model according to an embodiment of the present disclosure;

[0023] FIG10 is an example flow chart illustrating obtaining a primary system behavior model through federated learning based on a federated prediction region according to an embodiment of the present disclosure;

[0024] Figure 11(a) shows the actual received power of the primary system and the predicted received power of the primary system predicted using the existing technology. Figure 11(b) shows the actual received power of the primary system and the predicted received power of the primary system predicted using quantity-weighted aggregation. Figure 11(c) shows the error of the predicted received power of the primary system predicted using the existing technology and the error of the predicted received power of the primary system predicted using quantity-weighted aggregation.

[0025] FIG12 shows a functional module block diagram of an electronic device used in a spectrum management apparatus according to another embodiment of the present disclosure;

[0026] FIG13 shows a flowchart of a method for a spectrum management apparatus according to an embodiment of the present disclosure;

[0027] FIG14 shows a flowchart of a method for a spectrum management apparatus according to another embodiment of the present disclosure;

[0028] FIG15 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;

[0029] FIG16 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;

[0030] FIG17 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;

[0031] FIG18 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

[0032] 19 is a block diagram of an exemplary structure of a general-purpose personal computer in which methods and / or apparatuses and / or systems according to embodiments of the present invention may be implemented. DETAILED DESCRIPTION

[0033] 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.

[0034] 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.

[0035] Fig. 1 shows a functional block diagram of an electronic device 100 used as a spectrum management device according to an embodiment of the present disclosure. The electronic device 100 can serve as a spectrum management device.

[0036] As shown in Figure 1, the electronic device 100 includes: a federal prediction area obtaining unit 101, which can be configured to obtain at least one federal prediction area among multiple federal prediction areas constructed based on a secondary system (also referred to as a secondary user or SU (Secondary User)); and a main system behavior model obtaining unit 103, which can be configured to obtain a main system behavior model (hereinafter sometimes referred to as a global model) for predicting the behavior of a main system (also referred to as a primary user or PU (Primary User)) in using spectrum resources. The main system behavior model is obtained through federated learning.

[0037] The federated prediction region obtaining unit 101 and the main system behavior model obtaining unit 103 can be implemented by one or more processing circuits, such as chips or processors. Furthermore, it should be understood that the various functional units in the electronic device shown in FIG1 are merely logical modules divided according to the specific functions they implement, and are not intended to limit specific implementations.

[0038] 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 electronic device to implement various functions. The transceiver may include one or more communication interfaces to support communication with different devices (for example, servers, base stations, etc.), and the implementation form of the transceiver is not specifically limited here.

[0039] As an example, the base station may be, for example, an eNB or a gNB.

[0040] 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.

[0041] The primary system (which includes base stations and user equipment) has priority access to spectrum resources, while the secondary systems (which also include base stations and user equipment) do not have legal spectrum access rights. The spectrum sharing technical requirements stipulate that as long as the aggregate interference intensity generated by all secondary systems at the primary system receiver is below the primary system's interference protection threshold, the secondary systems can still use spectrum resources.

[0042] For example, in centralized federated learning, the electronic device 100, i.e., the spectrum management device, can act as a federated learning server and obtain the main system behavior model through federated learning, or can obtain the main system behavior model from a federated learning server (e.g., NWDAF) without participating in federated learning; in addition, for example, in distributed federated learning, the spectrum management device can act as a federated learning client and obtain the local main system behavior model through federated learning.

[0043] In an embodiment of the present disclosure, the network is divided into multiple federated prediction regions based on the secondary system. Instead of performing federated learning on the entire network, federated learning is performed on each of at least one of the multiple federated prediction regions to obtain a corresponding primary system behavior model. This federated learning, performed separately in each of these federated prediction regions, yields a corresponding primary system behavior model, which can be applied to spectrum sharing scenarios in wireless communications. The primary system behavior model can, for example, be a deep learning model, which can be used for primary system power prediction.

[0044] In large-scale network scenarios, global federated learning will lead to high communication delays and high model complexity.

[0045] By dividing the federated prediction regions, at least one of the following technical benefits can be achieved: it can reduce communication costs and constrain the scope of local model data analysis in federated learning by reducing the size of the federated prediction regions, thereby reducing model complexity. All base stations within the federated prediction region will participate in federated learning, thereby making better use of the base station's local training data, which improves model accuracy while reducing overhead. In addition, the network is divided into multiple federated prediction regions, and the network's spectrum prediction tasks are divided into multiple federated prediction regions. If a single point of failure occurs at the center used for model aggregation in a single federated prediction region, the other federated prediction regions can still complete federated learning. Compared to other spectrum sensing technologies, this technology can predict the future received power of the main system signal in a specific area rather than simply determine the shutdown status of the main system. It can more accurately discover the availability of spectrum resources in spatial and temporal dimensions, thereby more effectively predicting the received power of the main system in different areas for spectrum resource sensing.

[0046] As an example, the spectrum management device, i.e., the electronic device 100, can use the final global model obtained from the federated learning server as the main system behavior model, wherein the federated learning server aggregates the local main system behavior models (hereinafter sometimes referred to as local models) trained by each federated learning client participating in the federated learning to obtain the final global model.

[0047] Hereinafter, the federated learning client is sometimes referred to as FL-Client or FL Client, and the federated learning server is sometimes referred to as FL-Sever. Federated learning that includes the federated learning server and the federated learning client is called centralized federated learning.

[0048] As an example, the federated learning server can be implemented by the NWDAF (Network Data Analytics Function) of the 5G core network.

[0049] As an example, the federated learning server sends a federated learning request to other devices within the federated prediction area associated with it, and receives a federated learning response from other devices that agree to participate in the federated learning.

[0050] As an example, the federated learning response includes the number of geographical units occupied by user devices in the secondary system associated with the federated learning client.

[0051] As an example, in each round of federated learning training, the federated learning server aggregates the local main system behavior models trained by each federated learning client based on weights to obtain a global model, and sends the global model to each federated learning client so that each federated learning client can perform the next round of training based on the global model. The federated learning server stops federated learning and obtains a final global model until predetermined conditions are met. For example, the predetermined conditions include the final global model reaching a predetermined accuracy (e.g., the final global model converges) and / or a predetermined number of training rounds have been performed.

[0052] FIG. 2( a ) shows an example of a system structure according to an embodiment of the present disclosure.

[0053] Figure 2(a) relies on the federated learning framework in the 3GPP TS23.288 standard. The base stations in the secondary system upload the collected data to the corresponding NWDAF.

[0054] In Figure 2(a), the primary system is represented by the PU, and the secondary system is represented by the SU. The SU senses the PU's signals and uploads the collected information to the devices or functions it accesses. The system consists of an access layer and a data layer. The bottom layer is the access layer, representing the access relationship between user equipment and base stations. The upper layer of the system structure in Figure 2(a) is the abstract data layer. The data layer in Figure 2(a) consists of the core network NWDAF and the NRF (Network Repository Function). In Figure 2(a), there is one PU and multiple SUs. The base station in the PU is represented by BS, and the base station set of multiple SUs is {BS1, BS2, BS3, BS4, BS5, BS6, BS7, BS8}. For example and not limitation, the base station set is divided into two federated prediction zones (FPZs): federated prediction zone 1, namely FPZ_1, and federated prediction zone 2, namely FPZ_2, where FPZ_1 = {BS1, BS2, BS3, BS4} and FPZ_2 = {BS5, BS6, BS7, BS8}.

[0055] As shown in Figure 2(a), for example, FPZ_1 includes NWDAF_1 and NWDAF_2. Base station BS1 uploads the collected data Dataset 1 to the corresponding NWDAF_1, base station BS2 uploads the collected data Dataset 2 to the corresponding NWDAF_1, base station BS3 uploads the collected data Dataset 3 to the corresponding NWDAF_2, and base station BS4 uploads the collected data Dataset 4 to the corresponding NWDAF_2; NWDAF_1 and NWDAF_2 act as federated learning clients (for example, marked as FPZ_1Client: {1,2} in the figure) and use the collected data to train the local main system behavior model, and NWDAF_0 acts as a federated learning server (for example, marked as FL-Sever: {0} in the figure) to globally aggregate the local models to obtain the final global model (for example, global model 1). For FPZ_2, base station BS5 uploads Dataset 5 to the corresponding NWDAF_3, base station BS6 uploads Dataset 6 to the corresponding NWDAF_3, base station BS7 uploads Dataset 7 to the corresponding NWDAF_4, and base station BS8 uploads Dataset 8 to the corresponding NWDAF_4. NWDAF_3 and NWDAF_4 act as federated learning clients (e.g., labeled FPZ_2Client: {3,4} in the figure) and use the collected data to train local models. NWDAF_0, acting as the federated learning server, globally aggregates the local models to obtain the final global model (e.g., global model 2).

[0056] The electronic device 100 may obtain the global model 1 for FPZ_1 from NWDAF_0 as the main system behavior model for FPZ_1 , and may obtain the global model 2 for FPZ_2 from NWDAF_0 as the main system behavior model for FPZ_2 .

[0057] That is, the electronic device 100 implements primary system power prediction for at least one area in FPZ_1 and FPZ_2 through federated learning, thereby providing reliable primary system behavior data for spectrum sharing.

[0058] As an example, the spectrum management device, i.e., the electronic device 100, can serve as a federated learning server, and the main system behavior model obtaining unit 103 can be configured to aggregate the local main system behavior models trained by one or more other spectrum management devices as various federated learning clients participating in the federated learning to obtain the final global model as the main system behavior model. In this example, the spectrum management device, i.e., the electronic device 100, can itself participate in the federated learning as a federated learning server to obtain the main system behavior model. For example, the electronic device 100 can replace NWDAF_0 shown in FIG. 2( a) as the federated learning server, and one or more other spectrum management devices can replace NWDAF_1 to NWDAF_4 shown in FIG. 2( a) as the federated learning clients, which will not be repeated here.

[0059] As an example, the primary system behavior model obtaining unit 103 may be configured to send a federated learning request to other spectrum management devices within the associated federated prediction area, and receive a federated learning response from the other spectrum management devices that agree to participate in the federated learning. As an example, the federated learning response includes the number of geographical cells occupied by user devices in the secondary system associated with the federated learning client.

[0060] As an example, the main system behavior model obtaining unit 103 may be configured to: in each round of federated learning training, aggregate the local main system behavior models trained by each federated learning client based on weights to obtain a global model, and send the global model to each federated learning client so that each federated learning client performs the next round of training based on the global model; and, until a predetermined condition is met, terminate federated learning and use the final global model obtained as the main system behavior model. As an example, the predetermined condition includes that the final global model reaches a predetermined accuracy and / or has been trained for a predetermined number of rounds.

[0061] As an example, the spectrum management device, i.e., the electronic device 100, can function as a federated learning client. The primary system behavior model obtaining unit 103 can be configured to perform federated learning with one or more other spectrum management devices, also serving as federated learning clients, and to aggregate the local primary system behavior models trained by each federated learning client to obtain a global model as the primary system behavior model. For example, the spectrum management device, i.e., the electronic device 100, can function as a federated learning client in distributed federated learning.

[0062] As an example, the spectrum management apparatus, ie, the electronic device 100 , is implemented by a base station in the secondary system or an edge server (edge ​​computing node) associated with the secondary system.

[0063] Figure 2(b) shows another example of the system structure according to the embodiment of the present disclosure. It should be noted that the system structure according to the embodiment of the present disclosure is not limited to Figures 2(a) and 2(b), but there are various other variations.

[0064] Figure 2(b) shows a distributed federated learning solution based on edge computing, in which the local training and model aggregation of federated learning are undertaken by base stations or edge servers.

[0065] The system in Figure 2(b) consists of an access layer and a data layer. The bottom layer is the access layer, which represents the access relationship between user equipment and base stations. The upper layer in the system structure is the abstract data layer, which is composed of, for example, the edge server of the base station. In Figure 2(b), there is one user-controlled unit (PU) and multiple user-controlled units (SUs). The base station in the PU is represented by a BS. The set of base stations for the multiple SUs is N = {BS1, BS2, BS3, BS4, BS5, BS6, BS7, BS8}. For example and not limitation, the set of base stations is divided into two federated prediction zones (FPZs): Federated Prediction Zone 1, or FPZ_1, and Federated Prediction Zone 2, or FPZ_2. FPZ_1 = {BS1, BS2, BS3, BS4}, and FPZ_2 = {BS5, BS6, BS7, BS8}.

[0066] As shown in Figure 2(b), eight edge computing nodes, Edge_1 to Edge_8, are associated with BS1 to BS8, respectively. For example, FPZ_1 includes Edge_1, Edge_2, Edge_3, and Edge_4. Each edge computing node acts as a federated learning client to train a local model using data obtained from the associated base station. One edge computing node (e.g., Edge_2) among Edge_1, Edge_2, Edge_3, and Edge_4 acts as a federated learning server to globally aggregate the local models to obtain the final global model (e.g., global model a). For example, FPZ_2 includes Edge_5, Edge_6, Edge_7, and Edge_8. Each edge computing node acts as a federated learning client to train a local model using data obtained from the associated base station. One edge computing node (e.g., Edge_6) among Edge_5, Edge_6, Edge_7, and Edge_8 acts as a federated learning server to globally aggregate the local model to obtain the final global model (e.g., global model b).

[0067] Electronic device 100 may be Edge_2, i.e., electronic device 100 obtains global model a for FPZ_1 as the primary system behavior model for FPZ_1; or electronic device 100 may be Edge_6, i.e., electronic device 100 obtains global model b for FPZ_2 as the primary system behavior model for FPZ_2. For ease of description, the edge server is also referred to as a spectrum management device. However, electronic devices 100 such as Edge_2 or Edge_6 may not have functions such as spectrum allocation and / or interference analysis.

[0068] As an example, when the spectrum management device, i.e., the electronic device 100, serves as a federated learning client in distributed federated learning, the primary system behavior model obtaining unit 103 may be configured to send the number of geographical units occupied by user devices in the secondary system associated with the spectrum management device to other federated learning clients. For example, Edge_2 shown in FIG2(b) may send the number of geographical units occupied by user devices in the secondary system associated with Edge_2 to Edge_1, Edge_3, and Edge_4.

[0069] As an example, the main system behavior model obtaining unit 103 can be configured to, in each round of federated learning training, aggregate the local main system behavior model trained by the spectrum management device and the local main system behavior models received through broadcast from other federated learning clients based on weights to obtain a global model (for example, Edge_2 shown in FIG2( b) aggregates the local main system behavior model of Edge_2 and the local main system behavior models received through broadcast from Edge_1, Edge_3, and Edge_4 based on weights to obtain a global model), and use the global model as the new local main system behavior model for the next round of training; and until a predetermined condition is met, stop federated learning, and use the final global model obtained as the main system behavior model. As an example, the predetermined condition includes that the final global model reaches a predetermined accuracy and / or a predetermined number of rounds of training have been performed.

[0070] As an example, a plurality of federated prediction areas are constructed based on the geographical locations of base stations in the secondary system, and the size of the federated prediction area is reflected by the number of geographical units having a predetermined geographical size.

[0071] FIG3 shows an example of dividing a network according to an embodiment of the present disclosure.

[0072] As shown in Figure 3, the network is divided into geographic units (also called minimum units or cells). By way of example and not limitation, a geographic unit can be a 100m x 100m square cell. The cells are numbered, as shown in Figure 3, to form a minimum unit set U = {0, 1, 2, ..., 63}.

[0073] For example, as shown in FIG3 , the PU is located in the cell numbered 22 , and the federal prediction zone FPZ1 is a 3×3 cell, including cells numbered 0 , 1 , 2 , 8 , 9 , 10 , 16 , 17 , and 18 .

[0074] As an example, the number and locations of the plurality of federated prediction regions are determined by using a k-means algorithm and a density-based spatial clustering algorithm DBSCAN for noisy applications. The above combination of the k-means algorithm and DBSCAN may be referred to as a K-DBSCAN algorithm.

[0075] As an example, the k-means algorithm is used to cluster base stations in a secondary system, delete clusters that do not contain any base stations without changing the position of the cluster center, and set the position of a specific base station in a cluster as a new cluster center when the distance between the center of the cluster to which it belongs exceeds a first predetermined distance threshold. The DBSCAN algorithm uses the position of the cluster center determined by the k-means algorithm as input to obtain a new cluster center, merges the cluster centers among the new cluster centers whose distance is less than a second predetermined distance threshold, and repeats the k-means algorithm and the DBSCAN algorithm until the number of cluster centers no longer changes, wherein the cluster center serves as the center of the federal prediction area and the number of cluster centers corresponds to the number of multiple federal prediction areas.

[0076] FIG4 is an example of a pseudo code illustrating a K-DBSCAN algorithm according to an embodiment of the present disclosure.

[0077] As an example, the K-DBSCAN algorithm first sets the initial clustering K value of the network. The initial K value should be set to the square of an integer to facilitate the determination of the location of the K cluster centers. Since this value is not the number of the final federal prediction areas, a larger value can be set at the beginning. The initial K cluster centers are evenly distributed in the network. First, the k-means algorithm is run to perform the initial clustering of the base stations. When the location of the cluster center does not change, the cluster that does not contain the base station is deleted. Secondly, when the distance between a base station in the cluster and its cluster center exceeds the predetermined value D, the cluster center is deleted. max After that, the base station location is set as the new cluster center. At this point, the DBSCAN algorithm is run with the cluster center location as input to obtain a new cluster. Finally, the new cluster centers are traversed and the cluster centers with similar distances are merged to form the new cluster center. The distance is, for example, the Euclidean distance.

[0078] The pseudo code of Figure 4 is described in conjunction with NWDAF. More specifically, in the pseudo code of Figure 4:

[0079] Input: Coordinates (x, y) of N base stations in the secondary system: N = {(x1, y1), ..., (x i ,y i ),...,(x N ,y N )};

[0080] Output: cluster centers K and their associated base stations;

[0081] 1: Initialization: Set the maximum radius D of the cluster max . Set the initial value of K and initialize K cluster centers to be evenly distributed in the network. K={(X1,Y1),...,(X i ,Y i ),...,(X K ,Y K )};

[0082] 2: Repeat steps 3-11 below

[0083] 3: Run the k-means algorithm with the input of the preset K cluster centers K and the location of the base station N

[0084] 4: Delete empty cluster centers in K

[0085] 5: For all (x in (for) N n ,y n )conduct

[0086] 6: if(x n ,y n ) and its cluster center has a Euclidean distance greater than or equal to D max ,So

[0087] 7: Add new cluster centers (x n ,y n );

[0088] 8: End if

[0089] 9: End for

[0090] 10: Run the DBSCAN algorithm with the input as the cluster center K

[0091] 11: Merge cluster centers in K if their distance is close to 0

[0092] 12: Until the number of clusters remains unchanged

[0093] Traditional clustering algorithms, such as k-means, are limited by the initial K value. Once K is determined, the number of clusters remains constant, making it incapable of adaptively adjusting the number of federated prediction regions. Furthermore, the k-means clustering algorithm can only handle spherical clusters—that is, clusters with a solid center (due to limitations in the algorithm's calculation of average distance). However, reality often presents a variety of shapes, such as rings and irregular shapes. In these cases, clustering algorithms based on high sample density are more suitable. The DBSCAN density-based clustering algorithm, which lacks a cluster center, results in irregular cluster shapes. This can lead to large distances between base stations located at the edge of a cluster, and when base station density is high, invalid clusters may be generated or the number of clusters may be too low. The K-DBSCAN algorithm retains the regular clustering properties of the k-means algorithm while avoiding the limitations of the initial K value setting, allowing for adaptive adjustment of the number of clusters. Its goal is to ensure that the federated prediction region formed after clustering is composed of base stations centered around the cluster center, allowing the primary system received signal strength information provided by the base stations to be fully fed into the learning model. Therefore, the K-DBSCAN algorithm can optimize the number of clusters and thus reduce the number of federated prediction regions.

[0094] Figures 5(a) and 5(b) are examples showing the effect of using the K-DBSCAN algorithm to determine the federal prediction area according to an embodiment of the present disclosure. As shown in Figure 5(a), the network size is set to 3km×3km, the number of base stations is 300, and the dots in Figure 5(a) represent the distribution of base stations. Figure 5(b) shows the effect after clustering using the K-DBSCAN algorithm, where the asterisks represent the positions of the centers of the 82 federal prediction areas (marked as Centers in the figure), and the dots represent the distribution of base stations (marked as Base Stations in the figure). As can be seen from Figure 5(b), the two-layer clustering algorithm (K-DBSCAN algorithm) can minimize the number of federal prediction areas, so that local data can be fully utilized in federated learning.

[0095] The way of obtaining the federal prediction area in the embodiments of the present disclosure is different from the user clustering in the existing federated learning. The user clustering in the existing federated learning is to cluster and group users with similar data, select representative user data from the group for training, and then realize the sampling processing of the data. The key point is that the clustering of users in the existing federated learning technology does not affect the structure of the learning model in the federated learning, but is only a screening of the training data. In the embodiments of the present disclosure, for example, clustering is performed based on the geographical distribution of base stations, and the size and location of the clustered federal prediction area will determine the input and output targets of the model in the federated learning. The federal prediction area decouples the main system signal prediction problem in a large-scale network into prediction problems of multiple sub-areas. On the one hand, it reduces the communication overhead of centralized prediction data collection, and on the other hand, it also reduces the computational complexity of model training.

[0096] Figure 6 illustrates an example of a process for constructing a federated prediction region according to an embodiment of the present disclosure. In Figure 6 , taking the system structure of Figure 2(a) as an example, the process for constructing a federated prediction region is as follows. The federated learning in Figure 2(a) is centralized federated learning.

[0097] In A1, the network is divided into geographical units as shown in Figure 3. In A2, the electronic device 100 collects the geographical location information of the base station, and determines the number and location of the federal prediction areas based on the location information uploaded by the base station, for example, by running the K-DBSCAN dual clustering algorithm (it should be added here that when the electronic device 100 directly participates in federated learning as a federated learning server, the electronic device 100 also collects the geographical location information of the base station, and determines the number and location of the federal prediction areas based on the location information uploaded by the base station, for example, by running the K-DBSCAN dual clustering algorithm). In A3, after determining the division of the federal prediction areas, NWDAF needs to register the federal learning information in the network. As shown in the example of Figure 2(a), the network is divided into two federal prediction areas, FPZ_1 and FPZ_2. When the base station associated with the NWDAF is divided into a federal prediction area, the NWDAF will register with the NRF as a federal learning client of the federal prediction area. The NWDAF that undertakes the federated learning model aggregation task is registered as a federated learning server. As shown in Figure 2(a), federated prediction zone 1, or FPZ_1, contains {NWDAF_1, NWDAF_2}, federated prediction zone 2, or FPZ_2, contains {NWDAF_3, NWDAF_4}, and NWDAF_0 is registered as the FL-Server. In A4, after the federated learning information is registered, the NWDAF corresponding to the federated prediction zone constructs the federated prediction zone members (forming a federated learning group).

[0098] FIG7 is a schematic diagram showing the information interaction for constructing a federated learning group according to an embodiment of the present disclosure. This is described in conjunction with FIG2( a). First, the NRF notifies the NWDAF (for example, NWDAF_0 in FIG2( a) ) serving as the federated learning aggregation point to become the FL-Server of the federated prediction area through FL_Zone Notify. This information will also include the identity information of other FL-Clients (for example, NWDAF_1 to NWDAF_4 in FIG2( a) ) in the current federated prediction area. The FL-Server requests the FL-Client to participate in the federated prediction area through NWDAF_FL_Zone Request. If the FL-Client confirms to participate in federated learning, the FL-Client sends an NWDAF_FL_Zone Response to the FL-Server for confirmation. The NWDAF_FL_Zone Response information can also include the number of geographical units occupied by user devices in the subsystem corresponding to each FL-Client. The purpose is to provide guidance for the subsequent federated learning model aggregation, for example, to calculate the aggregation weight of the local model based on this number.

[0099] Taking the system structure of Figure 2(b) as an example, the process of constructing a federal prediction area is as follows. B1. Divide the geographical units. B2. For example, run the K-DBSCAN algorithm to cluster the base stations and divide the federal prediction area. In the distributed federated learning network shown in Figure 2(b), the federal prediction area can be divided by the network management OAM (Orchestration and management) or another centralized spectrum management device. B3. After the federal prediction area is divided, the base stations or edge servers in the same federal prediction area form a federated learning group. As shown in Figure 2(b), federal prediction area 1, namely FPZ_1, contains: {Edge_1, Edge_2, Edge_3, Edge_4}, and federal prediction area 2, namely FPZ_2, contains: {Edge_5, Edge_6, Edge_7, Edge_8}.

[0100] To optimize computational and communication energy consumption in federated learning models, the overall energy consumption of the model is minimized while still meeting accuracy requirements, based on the model accuracy requirements of different scenarios. Computational energy consumption comes from local model training, while communication energy consumption comes from model parameter aggregation. Since these two energy consumption components are relatively independent within the entire model training environment, they can be optimized separately, thereby reducing the difficulty of solving the optimization problem. For optimizing computational energy consumption in federated learning, an optimal range (e.g., a rectangle with the smallest grid cell as the unit) can be determined for each federated prediction region to achieve optimal energy efficiency (accuracy / energy consumption) when federated learning converges. For optimizing communication energy consumption in distributed federated learning, the location of the federated aggregation point for local model aggregation (also referred to as model aggregation) can be selected based on real-time channel conditions (i.e., a federated learning client (hereinafter referred to as an access point (AP)) for local model aggregation) to minimize overall communication energy consumption, thereby improving the overall energy efficiency of federated learning.

[0101] An example of determining a preferred range for each federal forecast region is described below.

[0102] As an example, lower bound values ​​of the sizes of the plurality of federated prediction regions are determined based on the distance between the center of the federated prediction region and the secondary system, and each federated prediction region is updated based on the accuracy and / or energy consumption when the primary system behavior model converges.

[0103] Accuracy and / or energy consumption can be collectively referred to as energy efficiency.

[0104] The method steps for determining the federal forecast area are as follows.

[0105] 1.1 Use geometric methods to determine the lower bound of the size of each federated prediction region.

[0106] 1.1.1 Obtain the center of each federated prediction area and the locations of the base stations it contains using the K-DBSCAN algorithm or the k-means clustering algorithm.

[0107] 1.1.2 Using the horizontal and vertical coordinates as references, calculate the maximum distance from the center point among all base stations, denoted as Δx and Δy.

[0108] 1.1.3 Take the maximum value of Δx and Δy, round it up, and multiply it by 2 to use it as the minimum radius of the federal prediction area.

[0109] 1.2 For each federated prediction region, based on its lower bound value, the three-point method in calculus is used to find the function extreme value. Three federated learning models (local models) are trained in parallel. The energy efficiency of the three models is evaluated after convergence. The parameters are then updated using the "three-point method" to determine the learning models of three different dimensions. The main steps of the three-point method are as follows:

[0110] 1.2.1 Based on the minimum radius r0, take r1 = r0 + s and r2 = r0 + 2*s, and use r0, r1, and r2 as the radii corresponding to the federated learning models in three input dimensions (where s is the step factor).

[0111] 1.2.2 Train the three models separately under the same environment, and calculate the energy efficiency when the three models converge, corresponding to E0, E1, and E2 respectively.

[0112] 1.2.3 Update r0, r1, and r2 according to different situations, and the updates are as follows:

[0113] (1) E0 < E1 < E2, r0 = r1, r1 = r2, r2 = r2 + s<着

[0114] (2) E0 > E1 > E2, and r0 - s > the minimum radius, r0 = r0 - s, r1 = r0, r2 = r1

[0115] (3) E0 > E1 > E2, and r0 - s < the minimum radius, and s ≤ 1, the optimal radius = r0,

[0116] (4) E0 < E2 < E1, and s ≥ 2, s = s / 2, r0 = r1, r1 = r0 + s

[0117] (5) E2 < E1 < E1, and s ≥ 2, s = s / 2, r0 = r1, r1 = r2 - s, r2 = r1

[0118] (6) For the relationships of E0, E1, and E2 in (4) and (5), if s < 2, output the radius corresponding to the maximum energy efficiency.

[0119] 1.2.4 Repeat 1.2.2 - 1.2.3 several times until the predetermined conditions are met.

[0120] 1.3 Output the optimal radius of each federated prediction area.

[0121] It should be noted that the optimal area may not necessarily be a circular area.

[0122] Examples of selecting federated aggregation points (which can also be called model aggregation points or aggregation points) for local model aggregation in distributed federated learning are described below.

[0123] As an example, when the spectrum management device, i.e., the electronic device 100, serves as a federated learning client in distributed federated learning, the spectrum management device, i.e., the electronic device 100, is selected for aggregation under the following predetermined conditions: based on the channel information between the spectrum management device and one or more other spectrum management devices, the sum of the transmission energy consumption of the transmission path between the spectrum management device and one or more other spectrum management devices is calculated when the spectrum management device serves as an aggregation device for aggregating the local main user behavior model within the federated prediction area associated with it, wherein the sum of the transmission energy consumption when the spectrum management device serves as an aggregation device is less than the sum of the transmission energy consumption when any other spectrum management device of the one or more other spectrum management devices serves as an aggregation device.

[0124] As an example, the unit for obtaining the primary system behavior model 103 may be configured to exchange channel information with one or more other spectrum management devices through broadcasting.

[0125] As an example, the transmission energy consumption of the transmission path is calculated based on the transmission rate and transmission power of the transmission path.

[0126] Here, the spectrum management device and one or more other spectrum management devices are collectively referred to as APs for explanation. For all APs in each federal prediction area (cluster), the channel state information is shared. Each AP is selected in turn, and the AP calculates the communication energy consumption of other APs when the model is aggregated on the AP, and the AP records the result. After all APs have calculated the aggregated energy consumption when they are used as aggregation points (aggregation devices, aggregation centers), all APs share energy consumption information with each other, and then select the AP with the minimum energy consumption as the model aggregation point. In other words, when determining the aggregation center, APs exchange channel information with each other by broadcasting, calculate the overall communication energy consumption of different APs as aggregation centers based on the channel information, and select the AP corresponding to the minimum communication energy consumption as the federated learning aggregation center.

[0127] FIG8 shows an example of selecting a federation aggregation point for performing local model aggregation according to an embodiment of the present disclosure.

[0128] As shown in Figure 8, if AP1 is selected as the aggregation point, there are three wireless transmission paths between AP1 and the other APs, AP2-AP4. The transmission rates corresponding to these three wireless transmission paths can be calculated based on the free-space loss model and the Rayleigh fading model. The transmission energy consumption is then calculated based on the transmission power. The sum of the transmission energy consumption corresponding to these three wireless transmission paths is less than the sum of the corresponding transmission energy consumption when any one of AP2-AP4 is used as the aggregation device.

[0129] Consider a time-slotted system. At the beginning of each time slot, the terminals (user equipment) of the secondary system report the received PU signal power to their base station. The goal of using the primary system behavior model is to predict the future signal reception strength based on the historical PU received signal strength.

[0130] As an example, the main system behavior model is a multi-input and multi-output long short-term memory neural network model (LSTM model for short).

[0131] Using a single-input, single-output LSTM increases the number of models in the system, leading to increased communication overhead. This application uses a multi-input, multi-output LSTM. During the federated aggregation process, the federated learning client (aggregation client) only needs to transmit a single local model, eliminating the need to establish multiple communication connections with the devices or functions used for model aggregation, thereby reducing communication overhead.

[0132] As an example, the dimensions of the input and output of the MIMO LSTM neural network model are determined by the size of the federated prediction region.

[0133] As an example, for each federal prediction area, the input of the multi-input multi-output long-term and short-term neural network model is the main system signal reception power information of all geographical units included in the federal prediction area in a predetermined number of historical time slots, and the output is the predicted value of the main system signal reception power of each geographical unit in the next time slot.

[0134] Although the main system signal receiving power varies between geographical units at different locations, the main system signal change trend is consistent. Therefore, using the main system signal receiving power information of multiple geographical units as input to the LSTM model can better learn the power changes of the main system.

[0135] As an example, the main system behavior model is obtained by aggregating local main system behavior models obtained from federated learning clients participating in federated learning.

[0136] For example, the federated learning client trains local data to obtain a local main system behavior model. The local main system behavior model is aggregated to obtain the main system behavior model.

[0137] As an example, the local primary system behavior model corresponding to the federated learning client may be aggregated by calculating a weight based on the number of geographical units occupied by user devices in the secondary system associated with the federated learning client.

[0138] Assume that the federated prediction area contains N FL-Clients, and the number set of SU-related FL-Clients in the federated prediction area is S = {S1, S2, ..., S n,...,S N}, where S n It represents the number of geographical units occupied by the user equipment in the secondary system associated with the nth FL-Client. Assume that the local model parameter set of FL-Client is in, Represents the local model parameters of the nth FL-Client. Assume that the number of geographical units in the federated prediction area is M.

[0139] The weight value set of the model can be calculated by formula (1) A = [α1, α2, ..., α n ,...,α N}:

[0140] Among them, S n / M normalizes the number of geographical units occupied by the user devices in the FL-Client and its associated secondary system. After normalization, the exponential function is used to protect the local primary system behavior model with sparse SU distribution, avoiding its weight value being too low in the aggregation. After calculating the weight value, the local model can be aggregated based on the weight value. For example, the local model parameters are multiplied by the weight value and then summed to obtain the parameters of the global model.

[0141] As an example, when the federated learning client transmits a local model to a device for model aggregation (for example, a federated learning server, or a federated learning client for model aggregation in distributed federated learning), the number of geographical units occupied by user devices in the associated subsystem is transmitted, rather than the specific location of the user devices in the associated subsystem. Location information is private information, and leaking the location may lead to the risk of attack or eavesdropping. In an embodiment according to the present disclosure, providing the specific location of the user device in the SU is avoided, thereby protecting user privacy. That is, during the model aggregation process, the FL Client will not disclose the location information of the user device in the current SU, but only transmits the number of geographical units occupied by the user devices in the associated subsystem, thereby ensuring the security of the SU's location privacy information.

[0142] As an example, the local primary system behavior models corresponding to the federated learning client can be aggregated by calculating weights based on the distribution of user devices in the secondary system associated with the federated learning client. This weighted aggregation approach according to embodiments of the present disclosure can effectively filter local models, thereby improving the accuracy of the federated learning model.

[0143] For example, the aggregation weight of the FL client can be calculated based on the distribution of user devices in the secondary system. When user devices are geographically concentrated (because users are concentrated in a few locations and there are no users elsewhere, only the power information of the primary user in a few locations can be perceived), the FL client can only provide accurate power predictions for the primary user in a local area, and the aggregation weight is low. When user devices are more evenly distributed (because users are evenly distributed in different locations, the power information of the primary user in more locations can be perceived, and the signal strength of the primary user in more locations can be obtained, thus providing higher-quality training data for local model training), the FL client has a higher aggregation weight.

[0144] In other words, the federated learning solution uses weighted model aggregation, where the weights are calculated based on the distribution of users served by base stations in the secondary system. When a base station's users are evenly distributed within the federated prediction area, the local model provided by that base station has a higher weight. This is because base stations with evenly distributed users can obtain signal strength from primary users in more locations, providing higher-quality training data for local model training. During global model aggregation, the network parameters of the local models are weighted to form the network parameters of the global model.

[0145] As an example, the local main system behavior models may be aggregated by calculating weights based on the model accuracy of the local main system behavior models corresponding to the federated learning clients.

[0146] For all federated learning clients (APs) within a federated prediction region, each AP may possess different user data. Therefore, when performing federated aggregation, it is necessary to assign different weights to the models trained by different APs. The weight assignment scheme can adopt a distribution method based on model accuracy, using direct or indirect accuracy expressions to determine the weight of each model.

[0147] For example, the model accuracy of the local main system behavior model increases as the amount of user data involved in the local main system behavior model increases, and decreases as the loss of the local main system behavior model increases. Based on the aggregation method of weighting based on model accuracy according to the embodiments of the present disclosure, the model training speed is improved and the energy consumption overhead of achieving model convergence is reduced.

[0148] For example, the accuracy of a deep learning model, which serves as the primary system behavior model, can be defined as the ratio of the number of correct data points to the total number of data points. However, this definition is not applicable in practice, so an expression that indirectly represents model accuracy is needed. For example, a function of the amount of user data and model loss can be designed, whose value increases with the amount of user data and decreases with the model loss. Compared with the general average weight distribution method, this aggregation weight determination method assigns higher weights to local models with higher model accuracy during aggregation. This aggregation allows the federated learning model to converge faster, reduces the number of aggregation communication rounds at the communication level, and thus reduces communication energy consumption.

[0149] For example, the weight calculation for each local model is designed as follows: a fraction with the logarithmic value of the user data volume as the numerator and the model loss as the denominator. Using the logarithmic function of the user data volume as the numerator ensures monotonically increasing performance while also reasonably reflecting the impact of user data volume on model accuracy. Using the model loss as the denominator, while ensuring monotonically decreasing performance, fully reflects the significant impact of the local model's fitting performance on the overall performance of the federated learning model.

[0150] As an example, when determining the aggregation weight, the following formula (2) may be used:

[0151] Among them, Indicator(n)=log2(1+d n ) / η n

[0152] In the above two equations, ω n represents the weight of the local model of the nth AP in the federated prediction area, |C i | represents the number of APs in the federated prediction area, d n represents the amount of user data owned by the nth AP, η n represents the loss of the local model of the nth AP.

[0153] For the same model, a larger federation aggregation period (model aggregation period) results in faster convergence, but higher losses upon convergence. A smaller federation aggregation period results in slower convergence, but lower losses upon convergence. Based on this, to optimize overall energy consumption in federated learning, a function related to the federation aggregation period can be designed to calculate and determine the period of each aggregation round. For example, by calculating the communication computing energy consumption under different aggregation periods, the aggregation period that minimizes energy consumption can be determined.

[0154] In an embodiment of the present disclosure, a function related to the federation aggregation period is designed that decreases monotonically over time. By continuously adjusting the aggregation period based on this function, a compromise is achieved between federated learning model accuracy and convergence speed. While maintaining a certain level of model accuracy, the number of parameter aggregation communication rounds is reduced, thereby reducing the communication energy consumption of model training.

[0155] As an example, as the loss of the primary system behavior model decreases monotonically, the period of the aggregation also decreases monotonically.

[0156] As an example, if the loss of the local primary system behavior model is not monotonically decreasing, the period of aggregation is reduced by a predetermined ratio.

[0157] When determining the aggregation period, each federated prediction region records the aggregation period of the previous time slot and the loss at the current moment. Taking into account the potential fluctuations in loss during model training, a designed monotonically decreasing function is used to update the model aggregation period when the loss shows a monotonically decreasing trend. In other cases, the model aggregation period is reduced by a fixed ratio.

[0158] Among them, F(x) in formula (3) represents the average loss of the federated model, f(x; s i ) is the loss of each local model in federated learning, x is the local model parameter, and s is the training dataset.

[0159] Formula (4) represents the update iteration of model parameters, where the upper branch in formula (4) represents the update of the federated aggregation mode, k mod τ = 0 means that the federated aggregation time node has been reached, so all local models need to be aggregated and the aggregation results are sent to each local model to complete the parameter update, where τ represents the federated aggregation period; the lower branch in formula (4) represents the independent update of the local model, k mod τ ≠ 0 means that the federated aggregation time node has not been reached, and each local model only updates its parameters based on its own training results, where g() represents the stochastic gradient, η k It is a preset parameter.

[0160] Formula (5) represents the update iteration of the federated aggregation period, where T0 is the preset time parameter, τ0 is the initial federated aggregation period, and l represents a positive integer greater than 1. The two parts of Formula (5) represent the update rules of the federated aggregation period under different conditions: the upper branch represents the general case, which assumes that the federated learning model will be trained in an overall positive trend, that is, the model loss will gradually decrease, and the federated aggregation period will also continue to decrease; the lower branch represents the special case, which takes into account the fluctuations that may occur during the training of the federated learning model, that is, a certain update may cause the federated learning model to move in a bad direction, but in order to ensure the final effect of the model, it is still necessary to reduce the federated aggregation period. It should be noted that for special cases, 1 / 2 is only a reference value. In theory, any value set between (0, 1) is acceptable.

[0161] The LSTM model network parameters are set so that the model input is T×M dimensional, where T is the predetermined number of historical time slots and M is the number of all geographic units included in the corresponding federal forecast area.

[0162] When the model training and aggregation functions of federated learning are located in the core network (e.g., NWDAF) (as shown in Figure 2(a)), since the core network has sufficient computing power, the computational overhead of federated learning does not need to be considered when training the federated learning model. Therefore, no upper limit is set for the input T (predetermined number of historical time slots) of the LSTM model.

[0163] In contrast, when the model training and aggregation functions of federated learning are implemented by the edge computing nodes (edge ​​servers) of the base station (for example, as shown in Figure 2(b)), the edge servers generally have limited computing power and have to handle computing tasks in the access network at the same time. Therefore, their computing overhead needs to be considered in federated learning.

[0164] When considering the computational overhead, the primary user received power prediction under the system structure shown in FIG2( b ) mainly includes the following steps T1 to T5 .

[0165] Let's first describe step T1. The LSTM model input and output dimensions are determined based on the size of the federated prediction region. In the example shown in Figure 3, federated prediction region 1 consists of a 3×3 minimum cell area. In this case, the LSTM model input must include PU signal received power information for nine minimum cells. The FL-Client's computing power must be considered when determining the model's input and output dimensions. Let C be the average computing power of the FL-Client, expressed in cycles / second, i.e., the number of CPU cycles that can be executed per second. Let τ be the user's local training time in each time slot, and γ be the number of local training iterations.

[0166] Figure 9 illustrates an example of the structure of an LSTM network model according to an embodiment of the present disclosure. In Figure 9, T represents the number of historical time slots input, S represents the size of the federated prediction region (in the example shown in Figure 3, S = 9), and none is an intermediate parameter during model operation. hidden_size1 and hidden_size2 represent the number of hidden nodes in the two-layer LSTM, and pred_time represents the number of future time slots predicted.

[0167] The computational complexity of the LSTM layer is analyzed. LSTM mainly consists of input gate, forget gate, output gate and cell state update. Taking time t as an example, the input gate input t Calculate as input t =σ(W ii x t +b ii +W hi h t-1 +b hi ). Where σ is the Sigmoid activation function, W ii is the input gate network weight value, the dimension is (H,,T×S), where H is the number of hidden nodes. t is the input, the dimension is T×S. ii is the bias value, and the dimension is H. W hi To retain the network weight value of the hidden state input at the previous moment, the dimension is (H,,T×S). t-1 is the hidden state at the previous moment, with a dimension of H. b hi is the bias value, and the dimension is H. The matrix multiplication and addition operations inside the activation function can be calculated to have a complexity of O(H×T×S+2H+H 2 ), when using the Relu activation function, the input gate calculation complexity is O(4(H×T×S+2H+H 2 )). Similarly, calculate the forget gate forget t =σ(W if x t +b if +W hf h t-1 +b hf ) and output gate out t =σ(W io x t +b io +W ho h t-1 +b ho ), cell state update g t =tanh(W ig x t +b ig +W hg h t-1 +bhg ) The final LSTM output hidden state h t =out t ⊙c t-1 , cell state c t =forget t ⊙c t-1 +input t ⊙g t The computational complexity of a single-layer LSTM is O(4(H×T×S+3H+H 2 )). Similarly, the second layer LSTM, LSTM2, uses the input of the first layer LSTM, LSTM1, as the output for operation. The computational complexity of the two layers of LSTM is O(4(H1×T×S+3H1+H1 2 )+4(H2×H1+3H2+H2 2 )), where H1 and H2 are hidden_size1 and hidden_size2, i.e. the number of hidden layer nodes. Finally, a fully connected layer (Dense) is added. Therefore, the complexity of the network's forward propagation is O f =O(4(H1×T×S+3H1+H1 2 )+4(H2×H1+3H2+H2 2 )+H2(T pred ×S+1)). The network has the same complexity when it is back-propagated as when it is forward-propagated, so the final complexity is O train =2O f According to the calculated complexity, the input history time slot length of the current FL-Client that meets the time limit requirement can be obtained, that is, Where α is the computational density, that is, the number of CPU cycles required to perform one operation. When the maximum delay is used as the training time, the input historical time slot length can be calculated

[0168] Next, step T2 is described. A Tensorflow-based LSTM deep neural network is constructed based on the parameters calculated in the previous step T1. For example, a deep neural network constructed with T=10 can be used, that is, 10 historical time slots are used to predict the PU received power of the next time slot. Combined with the example of S=9 shown in Figure 3, the input dimension of the LSTM deep neural network is 10×9=90, and the output dimension is 9. The input and output dimensions in this embodiment are just an example of a case. When the federal prediction area changes, the input and output dimensions should also be adjusted accordingly. For example, when the federal prediction area contains a minimum number of cells of M and the predicted time slot length is pred_time, the input dimension is T×M and the output dimension is M×pred_time.

[0169] Assume that the network structure and parameters of LSTM are as follows:

[0170] The first layer is a standard LSTM layer implemented in Keras (an open source artificial neural network library), with an input data dimension of (9,10), 128 hidden nodes, and a Sigmoid activation function;

[0171] The second layer is a standard LSTM layer implemented in Keras, with 64 hidden nodes and a Sigmoid activation function.

[0172] The third layer is the fully connected layer.

[0173] Next, let's describe step T3. After the LSTM deep neural network is constructed, the FL-Client trains the model based on local data. For example, the loss function for model training is defined as the mean squared error between the PU's predicted received power and the actual received power. When local training converges or reaches the number of iterations, the FL-Client broadcasts the model parameters within the federated prediction area. For example, as shown in Figure 2(b), Edge_1 in FPZ_1 will pass the trained local model parameters to {Edge_2, Edge_3, Edge_4}. Similarly, other edge computing nodes will also pass the model parameters to Edge_1.

[0174] Next, step T4 is described. After receiving the local model parameters for all federated prediction regions, the FL-Client performs weighted aggregation on the model parameters. The weights can be determined based on at least one of formula (1), formula (2), or the distribution of user devices in the secondary system associated with the federated learning client.

[0175] Finally, step T5 is described. FL-Client uses the aggregated global model as the local model for a new round of training based on local data, repeating steps T3-T5 until a predetermined condition is met, where the predetermined condition includes the global model reaching a predetermined accuracy or having undergone a predetermined number of training rounds.

[0176] The primary user received power prediction under the system structure shown in FIG2( a ) mainly includes the following steps S1 to S5 .

[0177] First, we describe step S1. The LSTM model network parameters are set. The model input is T × M dimensional, where T is the number of historical time slots. Due to the sufficient computing power of the core network server, no upper limit is set for the T value. M is the minimum number of cells corresponding to the federated prediction area.

[0178] Next, step S2 is described. Similar to step T2 described above in conjunction with FIG2( b ), an LSTM deep neural network is constructed.

[0179] Let's describe step S3. The NWDAF acting as the FL-Client collects data uploaded by the base stations within its jurisdiction. As shown in Figure 2(a), there are four base stations in the federal prediction zone 1, FPZ_1, and the data sets collected by the base stations are {Dataset 1, Dataset 2, Dataset 3, Dataset 4}. For example, the base stations under the jurisdiction of NWDAF_1 include {BS1, BS2}, so the collected data is {Dataset 1, Dataset 2}. Since base stations may have overlapping coverage areas, the FL-Client needs to preprocess the collected data sets. The specific preprocessing method is to take the average of the received powers of the multiple main system signals when there are multiple received powers of the main system signals corresponding to the same minimum cell in the data set.

[0180] Next, we'll describe step S4. After the FL-Client's trained model converges or reaches the aggregation period, the FL-Client uploads the model parameters to the NWDAF acting as the FL-Server. As shown in Figure 2(a), NWDAF_0 collects the local model parameters uploaded by NWDAF_1 and NWDAF_2 in FPZ_1, and also collects the local model parameters uploaded by NWDAF_3 and NWDAF_4 in FPZ_2. The FL-Server calculates the model aggregation weights for FPZ_1 and FPZ_2, using the same method as step T4 described in conjunction with Figure 2(b).

[0181] Finally, step S5 is described. The FL-Server sends the aggregated global model to the FL-Client. The FL-Client uses the global model as the new local model for a new round of training, repeating steps S3-S5 until a predetermined condition is met, where the predetermined condition includes the global model reaching a predetermined accuracy or having undergone a predetermined number of training rounds.

[0182] FIG10 is a flowchart illustrating an example of obtaining a main system behavior model through federated learning based on a federated prediction region according to an embodiment of the present disclosure.

[0183] The process begins in step S101. In step S102, a federated prediction region is constructed. In step S103, an LSTM model is constructed based on the federated prediction region. In step S104, the federated learning client trains a local LSTM model based on local data. In step S105, a determination is made as to whether the aggregation period has been reached or whether the model has converged. If the determination in step S105 is negative, the process returns to step S104. If the determination in step S105 is positive, the process proceeds to step S106. In step S106, if this is centralized federated learning, the federated learning client uploads its local model to the federated learning server. If this is distributed federated learning, the federated learning client performing model aggregation collects local models from other federated learning clients. In step S107, a determination is made as to whether local model collection is complete. If the determination in step S107 is negative, the process returns to step S106. If the determination in step S107 is positive, the process proceeds to step S108. In step S108, the model aggregation weight is calculated and the local model is aggregated, with the global model being used as the new local model. In step S109, a determination is made as to whether the federation aggregation count has been reached. If the determination in step S109 is negative, the process returns to step S104. If the determination in step S109 is positive, the process proceeds to step S110. In step S110, the process ends.

[0184] Using weights calculated based on the number of geographical units occupied by user devices in the secondary system associated with the federated learning client (for example, weights calculated according to formula (1)) to aggregate the federated learning model (referred to as quantity-weighted aggregation) can improve the average prediction accuracy of the aggregation model. Figure 11 (a) shows the actual received power of the main system and the predicted received power of the main system predicted using the existing technology, Figure 11 (b) shows the actual received power of the main system and the predicted received power of the main system predicted using quantity-weighted aggregation, and Figure 11 (c) shows the error of the predicted received power of the main system predicted using the existing technology and the error of the predicted received power of the main system predicted using quantity-weighted aggregation. To demonstrate the performance in terms of prediction accuracy, Figure 11 (b) shows the predicted power when the input of the LSTM model is the received power of the PU signal containing 9 minimum cells. In Figures 11 (a) to 11 (c), 9 areas, namely Area 0 to Area 8, are involved respectively. In Figures 11(a) and 11(b), the horizontal axis is time, the vertical axis is the predicted received power of the main system and the actual received power of the main system, the unit of power is mW, the solid line is the actual received power (marked with real in the figure), and the dotted line is the predicted received power (marked with prediction in the figure). Figure 11(a) shows the prediction effect of the traditional average weighted federated learning algorithm, and Figure 11(b) shows the prediction effect of the prediction using quantity weighted aggregation. It can be seen that Figure 11(b) shows a better prediction effect, that is, in Figure 11(b), the predicted received power of the main system is closer to the actual received power of the main system. In Figure 11(c), the vertical axis is mW, the solid line is the error curve of the prediction using quantity weighted aggregation (marked with weight in the figure), and the dotted line is the error curve of the traditional average weighted federated learning algorithm (marked with avg in the figure). It can be seen that the error of the prediction using quantity weighted aggregation according to the embodiment of the present disclosure is smaller.

[0185] The present disclosure further provides an electronic device for spectrum management according to another embodiment. FIG12 shows a functional module block diagram of an electronic device 1200 for spectrum management according to another embodiment of the present disclosure.

[0186] As shown in FIG12 , electronic device 1200 includes: an area acquisition unit 1201 , which may be configured to acquire one of multiple federated prediction areas constructed based on a secondary system; and an assisting processing unit 1203 , which may be configured to assist in acquiring a primary system behavior model for predicting the primary system's behavior in using spectrum resources through federated learning. Furthermore, it should be understood that the various functional units in the electronic device shown in FIG12 are merely logical modules divided according to the specific functions they implement, and are not intended to limit specific implementations.

[0187] The obtaining federated prediction area unit 1201 and the assisting processing unit 1203 may be implemented by one or more processing circuits, which may be implemented as a chip, for example.

[0188] The electronic device 1200 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 noted that the electronic device 1200 can be implemented at the chip level, or it can also be implemented at the device level. For example, the electronic device 1200 can work as the base station itself, and can also include external devices such as memory and transceiver (not shown). The memory can be used to store programs and related data information that need to be executed by the electronic device to implement various functions. The transceiver may include one or more communication interfaces to support communication with different devices (for example, servers, base stations, etc.), and the implementation form of the transceiver is not specifically limited here.

[0189] 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.

[0190] The electronic device 1200 according to an embodiment of the present disclosure can help to more effectively predict the received power of the primary system in different areas for spectrum resource sensing.

[0191] As an example, the spectrum management device, i.e., the electronic device 1200, can obtain a trained local main system behavior model from a corresponding federated learning client corresponding to it that participates in federated learning. The corresponding federated learning client preprocesses the data set uploaded from the secondary system associated with the spectrum management device, and trains the local main system behavior model based on the preprocessed data set.

[0192] As an example, the corresponding federated learning client is implemented by NWDAF.

[0193] As an example, the corresponding federated learning client may be one of NWDAF_1 to NWDAF_4 in FIG. 2( a ).

[0194] As an example, the pre-processing includes: when there are multiple primary system signal received powers corresponding to the same geographical unit in the data set, averaging the multiple primary system signal received powers, wherein the geographical unit has a predetermined geographical size.

[0195] For the description of the preprocessing, please refer to the description in conjunction with FIG2( a ), which will not be repeated here.

[0196] As an example, the corresponding federated learning client sends the trained local main system behavior model to the federated learning server participating in the federated learning, so that the federated learning server aggregates the local main system behavior model to obtain the main system behavior model.

[0197] As an example, the spectrum management device, i.e., the electronic device 1200, can act as a federated learning client participating in federated learning. The auxiliary processing unit 1203 can be configured to pre-process a data set uploaded from a secondary system associated with the spectrum management device and train a local primary system behavior model based on the pre-processed data set. In this example, the electronic device 1200 can directly participate in federated learning as a federated learning client. For example, the electronic device 1200 can directly participate in federated learning instead of the corresponding NWDAF (e.g., one of NWDAF_1 to NWDAF_4) in Figure 2(a).

[0198] As an example, the pre-processing includes: when there are multiple primary system signal received powers corresponding to the same geographical unit in the data set, averaging the multiple primary system signal received powers, wherein the geographical unit has a predetermined geographical size.

[0199] For the description of the preprocessing, please refer to the description in conjunction with FIG2( a ), which will not be repeated here.

[0200] As an example, the assisting processing unit 1203 may be configured to send the trained local main system behavior model to a federated learning server participating in federated learning, so that the federated learning server may aggregate the trained local main system behavior model to obtain the main system behavior model.

[0201] While the above embodiments describe the electronic device used in a spectrum management apparatus, it is apparent that certain processes or methods are also disclosed. Below, an overview of these methods is provided without repeating some of the details discussed above. However, it should be noted that while these methods are disclosed in the description of the electronic device used in a spectrum management apparatus, these methods do not necessarily employ or are not necessarily executed by the components described. For example, the embodiments of the electronic device used in a spectrum management apparatus may be partially or completely implemented using hardware and / or firmware, while the methods used in a spectrum management apparatus discussed below may be completely implemented using computer-executable programs, although these methods may also employ the hardware and / or firmware of the electronic device used in a spectrum management apparatus.

[0202] Figure 13 shows a flowchart of method S1300 for a spectrum management device according to an embodiment of the present disclosure. Method S1300 begins at step S1302. At step S1304, the spectrum management device uses federated learning to obtain a primary system behavior model for predicting the primary system's spectrum resource usage behavior, for at least one of the multiple federated prediction regions constructed based on the secondary system. Method S1300 concludes at step S1306.

[0203] 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.

[0204] Figure 14 shows a flowchart of method S1400 for a spectrum management apparatus according to another embodiment of the present disclosure. Method S1400 begins at step S1402. At step S1404, federated learning is used to assist in obtaining a primary system behavior model for predicting the primary system's spectrum resource usage behavior for one of the multiple federated prediction regions constructed based on the secondary system. Method S1400 ends at step S1406.

[0205] The method may be executed, for example, by the electronic device 1200 described above. For specific details, please refer to the description of the related processing of the electronic device 1200, which will not be repeated here.

[0206] The technology of the present disclosure can be applied to various products.

[0207] The electronic devices 100 and 1200 can be implemented as various network-side devices. The network-side device can be set on the base station side or connected to the base station. The base station can be implemented as any type of evolved Node B (eNB) or gNB (5G base station). eNB includes, for example, macro eNB and small eNB. Small eNB can be an eNB that covers a cell smaller than a macro cell, such as a pico eNB, micro eNB, and home (femto) eNB. Similar situations can also be encountered for gNB. 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 called a base station device) configured to control wireless communications; and one or more remote radio heads (RRHs) set at a location different from the main body. In addition, various types of electronic devices can work as a base station by temporarily or semi-permanently performing base station functions.

[0208] [Application examples for base stations]

[0209] (First application example)

[0210] FIG15 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.

[0211] 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 FIG15 , eNB 800 may include multiple antennas 810. For example, multiple antennas 810 may be compatible with multiple frequency bands used by eNB 800. Although FIG15 shows an example in which eNB 800 includes multiple antennas 810, eNB 800 may also include a single antenna 810.

[0212] The base station device 820 includes a controller 821 , a memory 822 , a network interface 823 , and a wireless communication interface 825 .

[0213] 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).

[0214] 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.

[0215] 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 827. 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 827 may include, for example, a mixer, a filter, and an amplifier, and transmit and receive wireless signals via the antenna 810 .

[0216] As shown in FIG15 , 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 FIG15 , the wireless communication interface 825 may include multiple RF circuits 827. For example, multiple RF circuits 827 may be compatible with multiple antenna elements. Although FIG15 illustrates an example in which the wireless communication interface 825 includes multiple BB processors 826 and multiple RF circuits 827, the wireless communication interface 825 may also include a single BB processor 826 or a single RF circuit 827.

[0217] In the eNB 800 shown in FIG15 , when the electronic devices 100 and 1200 are implemented as base stations, their transceivers may be implemented by the wireless communication interface 825. At least a portion of the functions may also be implemented by the controller 821. For example, the controller 821 may execute the functions of the units in the electronic devices 100 and 1200 to more effectively predict the received power of the primary system in different areas for spectrum resource sensing.

[0218] (Second application example)

[0219] FIG16 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 an optical fiber cable.

[0220] 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 FIG16 , eNB 830 may include multiple antennas 840. For example, multiple antennas 840 may be compatible with multiple frequency bands used by eNB 830. Although FIG16 shows an example in which eNB 830 includes multiple antennas 840, eNB 830 may also include a single antenna 840.

[0221] 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.

[0222] 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. 15, 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. 16, 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. 16 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.

[0223] 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.

[0224] The RRH 860 includes a connection interface 861 and a wireless communication interface 863 .

[0225] 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.

[0226] 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 FIG16 , the wireless communication interface 863 may include multiple RF circuits 864. For example, multiple RF circuits 864 may support multiple antenna elements. Although FIG16 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.

[0227] In the eNB 830 shown in FIG16 , when the electronic devices 100 and 1200 are implemented as base stations, their transceivers may be implemented by the wireless communication interface 855. At least a portion of the functions may also be implemented by the controller 851. For example, the controller 851 may execute the functions of the units in the electronic devices 100 and 1200 to more effectively predict the received power of the primary system in different areas for spectrum resource sensing.

[0228] [Application examples on user devices]

[0229] (First application example)

[0230] 17 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.

[0231] 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.

[0232] 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.

[0233] 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 RF circuit 914 are integrated. As shown in FIG17 , the wireless communication interface 912 may include multiple BB processors 913 and multiple RF circuits 914. While FIG17 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.

[0234] 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.

[0235] 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 .

[0236] 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 FIG17 , the smartphone 900 may include multiple antennas 916. Although FIG17 shows an example in which the smartphone 900 includes multiple antennas 916, the smartphone 900 may also include a single antenna 916.

[0237] 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.

[0238] 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 FIG17 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.

[0239] 17 , the transceiver may be implemented by the wireless communication interface 912 . At least part of the functions may also be implemented by the processor 901 or the auxiliary controller 919 .

[0240] (Second application example)

[0241] 18 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 927, a storage medium interface 928, an input device 929, a display device 930, a speaker 931, a wireless communication interface 933, one or more antenna switches 936, one or more antennas 937, and a battery 938.

[0242] 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.

[0243] 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).

[0244] The content player 927 reproduces content stored in a storage medium (such as a CD or DVD) inserted into the storage medium interface 928. The input device 929 includes, for example, a touch sensor, button, or switch configured to detect a touch on the screen of the display device 930, and receives an operation or information input from the user. The display device 930 includes a screen such as an LCD or OLED display and displays an image of a navigation function or reproduced content. The speaker 931 outputs the sound of the navigation function or the reproduced content.

[0245] The wireless communication interface 933 supports any cellular communication scheme (such as LTE and LTE-Advanced) and performs wireless communication. The wireless communication interface 933 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 933 may also be a chip module on which the BB processor 934 and the RF circuit 935 are integrated. As shown in Figure 18, the wireless communication interface 933 may include multiple BB processors 934 and multiple RF circuits 935. Although Figure 18 shows an example in which the wireless communication interface 933 includes multiple BB processors 934 and multiple RF circuits 935, the wireless communication interface 933 may also include a single BB processor 934 or a single RF circuit 935.

[0246] In addition, in addition to the cellular communication scheme, the wireless communication interface 933 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 933 can include a BB processor 934 and an RF circuit 935.

[0247] 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 933 , such as circuits for different wireless communication schemes.

[0248] 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 933. As shown in FIG18, the car navigation device 920 may include multiple antennas 937. Although FIG18 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.

[0249] 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.

[0250] The battery 938 supplies power to the respective blocks of the car navigation device 920 shown in Fig. 18 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.

[0251] In the car navigation device 920 shown in FIG18 , the transceiver may be implemented by the wireless communication interface 933. At least part of the functions may also be implemented by the processor 921.

[0252] 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.

[0253] 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.

[0254] 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.

[0255] 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.

[0256] 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 1900 shown in Figure 19). When various programs are installed on the computer, it can perform various functions, etc.

[0257] In FIG19 , a central processing unit (CPU) 1901 executes various processes according to a program stored in a read-only memory (ROM) 1902 or a program loaded from a storage section 1908 to a random access memory (RAM) 1903. In the RAM 1903, data required when the CPU 1901 executes various processes, etc., is also stored as needed. The CPU 1901, the ROM 1902, and the RAM 1903 are connected to each other via a bus 1904. An input / output interface 1905 is also connected to the bus 1904.

[0258] The following components are connected to the input / output interface 1905: an input section 1906 (including a keyboard, a mouse, etc.), an output section 1907 (including a display such as a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and speakers, etc.), a storage section 1908 (including a hard disk, etc.), and a communication section 1909 (including a network interface card such as a LAN card, a modem, etc.). The communication section 1909 performs communication processing via a network such as the Internet. A drive 1910 may also be connected to the input / output interface 1905 as needed. Removable media 1911 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. are installed in the drive 1910 as needed, so that computer programs read therefrom are installed in the storage section 1908 as needed.

[0259] 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 1911 .

[0260] It should be understood by those skilled in the art that such storage media is not limited to the removable medium 1911 shown in FIG. 19 , which stores the program and is distributed separately from the device to provide the program to the user. Examples of the removable medium 1911 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 1902, a hard disk included in the storage section 1908, or the like, in which the program is stored and distributed to the user together with the device containing the program.

[0261] 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.

[0262] 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 explicitly 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.

[0263] 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.

[0264] The present technology can also be implemented as follows.

[0265] Solution 1. An electronic device for a spectrum management device, comprising:

[0266] The processing circuit is configured to:

[0267] For at least one of the multiple federated prediction areas constructed based on the secondary system, a primary system behavior model for predicting the behavior of the primary system in using spectrum resources is obtained through federated learning.

[0268] Solution 2. The electronic device according to Solution 1, wherein the plurality of federated prediction areas are constructed based on the geographical location of the subsystem, and the size of the federated prediction area is reflected by the number of geographical units having a predetermined geographical size.

[0269] Solution 3. The electronic device according to Solution 2, wherein the number and positions of the plurality of federated prediction regions are determined by a k-means algorithm and a density-based spatial clustering algorithm (DBSCAN) for noisy applications.

[0270] Solution 4. The electronic device according to Solution 3, wherein:

[0271] The k-means algorithm is used to cluster the base stations in the secondary system, delete the cluster that does not contain any base stations when the position of the cluster center does not change, and set the position of a specific base station in the cluster as the new cluster center when the distance between the specific base station and the center of the cluster to which it belongs exceeds a first predetermined distance threshold.

[0272] The DBSCAN algorithm uses the positions of the cluster centers determined by the k-means algorithm as input to obtain new cluster centers, and merges the cluster centers whose distances are less than a second predetermined distance threshold among the new cluster centers, and

[0273] The k-means algorithm and the DBSCAN algorithm are repeated until the number of cluster centers no longer changes, wherein the cluster centers serve as the centers of the federated prediction regions and the number of the cluster centers corresponds to the number of the plurality of federated prediction regions.

[0274] Option 5. An electronic device according to any one of Options 2 to 4, wherein the lower limit value of the size of the multiple federal prediction areas is determined based on the distance between the center of the federal prediction area and the secondary system, and each federal prediction area is updated based on the accuracy and / or energy consumption when the main system behavior model converges.

[0275] Solution 6. An electronic device according to any one of Solutions 1 to 5, wherein the main system behavior model is a multi-input multi-output long short-term memory neural network model.

[0276] Option 7. An electronic device according to Option 6, wherein the dimensions of the input and output of the multi-input multi-output long short-term memory neural network model are determined by the size of the federated prediction area.

[0277] Solution 8. An electronic device according to Solution 7, wherein, for each federal prediction area, the input of the multi-input multi-output long-term and short-term neural network model is the main system signal reception power information of all geographical units included in the federal prediction area in a predetermined number of historical time slots, and the output is the predicted value of the main system signal reception power of each geographical unit in the next time slot.

[0278] Solution 9. An electronic device according to any one of Solutions 1 to 8, wherein the main system behavior model is obtained by aggregating local main system behavior models obtained from federated learning clients participating in the federated learning.

[0279] Solution 10. An electronic device according to Solution 9, wherein the local main system behavior model corresponding to the federated learning client is aggregated by calculating the weight based on the number of geographical units occupied by user devices in the sub-system associated with the federated learning client.

[0280] Solution 11. An electronic device according to Solution 9, wherein the local main system behavior model corresponding to the federated learning client is aggregated by calculating weights based on the distribution status of user devices in the sub-system associated with the federated learning client.

[0281] Solution 12. The electronic device according to Solution 9, wherein the local main system behavior model is aggregated by calculating a weight based on the model accuracy of the local main system behavior model corresponding to the federated learning client.

[0282] Solution 13. The electronic device according to Solution 12, wherein the model accuracy of the local main system behavior model increases as the amount of user data involved in the local main system behavior model increases, and decreases as the loss of the local main system behavior model increases.

[0283] Solution 14: The electronic device according to any one of solutions 9 to 13, wherein as the loss of the local main system behavior model decreases monotonically, the aggregated period also decreases monotonically.

[0284] Solution 15. The electronic device according to Solution 14, wherein if the loss of the local main system behavior model is not monotonically decreasing, the aggregated period is reduced according to a predetermined ratio.

[0285] Scheme 16. An electronic device according to any one of Schemes 1 to 15, wherein the spectrum management device acts as a federated learning server, and the processing circuit is configured to use a final global model obtained by aggregating local main system behavior models trained by one or more other spectrum management devices that act as federated learning clients participating in the federated learning as the main system behavior model.

[0286] Option 17. An electronic device according to Option 16, wherein the processing circuit is configured to send a federated learning request to other spectrum management devices within a federated prediction area associated with it, and receive a federated learning response from other spectrum management devices that agree to participate in the federated learning.

[0287] Solution 18. The electronic device according to Solution 17, wherein the federated learning response includes the number of geographical units occupied by user devices in the secondary system associated with the federated learning client.

[0288] Solution 19. The electronic device according to any one of Solution 16 to Solution 18, wherein the processing circuit is configured to:

[0289] In each round of training of the federated learning, aggregating the local main system behavior models trained by each federated learning client based on the weights to obtain a global model, and sending the global model to each federated learning client, so that each federated learning client performs the next round of training based on the global model; and

[0290] Until a predetermined condition is met, the federated learning is stopped, and the final global model obtained is used as the main system behavior model.

[0291] Solution 20. An electronic device according to Solution 19, wherein the predetermined condition includes that the final global model reaches a predetermined accuracy and / or has been trained for a predetermined number of rounds.

[0292] Scheme 21. An electronic device according to any one of Schemes 1 to 15, wherein the spectrum management device uses the final global model obtained from the federated learning server as the main system behavior model, wherein the federated learning server aggregates the local main system behavior models trained by each federated learning client participating in the federated learning to obtain the final global model.

[0293] Solution 22. An electronic device according to Solution 21, wherein the federated learning server sends a federated learning request to other devices within a federated prediction area associated with it, and receives a federated learning response from other devices that agree to participate in the federated learning.

[0294] Solution 23. The electronic device according to Solution 22, wherein the federated learning response includes the number of geographical units occupied by user devices in the secondary system associated with the federated learning client.

[0295] Solution 24. The electronic device according to any one of Solutions 21 to 23, wherein the federated learning server:

[0296] In each round of training of the federated learning, aggregating the local main system behavior models trained by each federated learning client based on the weights to obtain a global model, and sending the global model to each federated learning client, so that each federated learning client performs the next round of training based on the global model; and

[0297] Once a predetermined condition is met, the federated learning is stopped and the final global model is obtained.

[0298] Solution 25. An electronic device according to Solution 24, wherein the predetermined condition includes that the final global model reaches a predetermined accuracy and / or has been trained for a predetermined number of rounds.

[0299] Solution 26. The electronic device according to any one of Solutions 21 to 25, wherein the federated learning server is implemented by a network data analysis function NWDAF.

[0300] Scheme 27. An electronic device according to any one of Schemes 1 to 15, wherein the spectrum management device serves as a federated learning client, and the processing circuit is configured to perform federated learning together with one or more other spectrum management devices serving as federated learning clients, and use the global model obtained by aggregating the local main system behavior models trained by each federated learning client as the main system behavior model.

[0301] Solution 28. The electronic device according to Solution 27, wherein the processing circuit is configured to send the number of geographical units occupied by user equipment in the secondary system associated with the spectrum management device to other federated learning clients.

[0302] Solution 29. The electronic device according to Solution 27 or 28, wherein the processing circuit is configured to, in each round of training of the federated learning, aggregate the local primary system behavior model trained by the spectrum management device and the local primary system behavior models received via broadcast from other federated learning clients based on weights to obtain a global model, and use the global model as the new local primary system behavior model for the next round of training;

[0303] Until a predetermined condition is met, the federated learning is stopped, and the final global model obtained is used as the main system behavior model.

[0304] Solution 30. The electronic device according to Solution 27 or 28, wherein the spectrum management device is selected to perform the aggregation when the following predetermined conditions are met:

[0305] calculating, based on channel information between the spectrum management device and the one or more other spectrum management devices, a sum of transmission energy consumptions of transmission paths between the spectrum management device and the one or more other spectrum management devices when the spectrum management device serves as an aggregating device for aggregating local primary user behavior models within a federated prediction area associated with the spectrum management device;

[0306] The sum of transmission energy consumption when the spectrum management device functions as the aggregation device is less than the sum of transmission energy consumption when any other spectrum management device of the one or more other spectrum management devices functions as the aggregation device.

[0307] Embodiment 31. The electronic device according to embodiment 30, wherein the processing circuit is configured to exchange the channel information with the one or more other spectrum management devices via broadcasting.

[0308] Solution 32. The electronic device according to Solution 30 or 31, wherein the transmission energy consumption of the transmission path is calculated based on the transmission rate and transmission power of the transmission path.

[0309] Solution 33. The electronic device according to any one of Solutions 27 to 33, wherein the spectrum management device is implemented by a base station in the secondary system or an edge server associated with the secondary system.

[0310] Solution 34. An electronic device for a spectrum management device, comprising:

[0311] The processing circuit is configured to:

[0312] For one of the multiple federated prediction areas constructed based on the secondary system, a primary system behavior model for predicting the behavior of the primary system in using spectrum resources is obtained through federated learning.

[0313] Solution 35. The electronic device according to Solution 34, wherein:

[0314] The spectrum management device acts as a federated learning client participating in the federated learning,

[0315] The processing circuit is configured to pre-process a data set uploaded from a secondary system associated with the spectrum management apparatus, and train a local primary system behavior model based on the pre-processed data set.

[0316] Option 36. An electronic device according to Option 35, wherein the preprocessing includes: averaging the multiple main system signal reception powers when there are multiple main system signal reception powers corresponding to the same geographical unit in the data set, wherein the geographical unit has a predetermined geographical size.

[0317] Option 37. An electronic device according to Option 35 or 36, wherein the processing circuit is configured to send the trained local main system behavior model to a federated learning server participating in the federated learning, so that the federated learning server can aggregate the trained local main system behavior model to obtain the main system behavior model.

[0318] Solution 38. The electronic device according to Solution 34, wherein:

[0319] The spectrum management device obtains a trained local primary system behavior model from a corresponding federated learning client that participates in the federated learning.

[0320] The corresponding federated learning client preprocesses a data set uploaded from a secondary system associated with the spectrum management device, and trains a local primary system behavior model based on the preprocessed data set.

[0321] Option 39. An electronic device according to Option 38, wherein the preprocessing includes: averaging the multiple main system signal reception powers when there are multiple main system signal reception powers corresponding to the same geographical unit in the data set, wherein the geographical unit has a predetermined geographical size.

[0322] Solution 40. An electronic device according to Solution 38 or 39, wherein the corresponding federated learning client sends the trained local main system behavior model to a federated learning server participating in the federated learning, so that the federated learning server aggregates the local main system behavior model to obtain the main system behavior model.

[0323] Solution 41. An electronic device according to any one of Solutions 38 to 40, wherein the corresponding federated learning client is implemented by a network data analysis function NWDAF.

[0324] Scheme 42. A method for a spectrum management device, comprising: for at least one federal prediction area among multiple federal prediction areas constructed based on a secondary system, the spectrum management device obtains a main system behavior model for predicting the behavior of the main system in using spectrum resources through federated learning.

[0325] Scheme 43. A method for a spectrum management device, comprising: for one federal prediction area among multiple federal prediction areas constructed based on a secondary system, assisting in obtaining a main system behavior model for predicting the behavior of the main system in using spectrum resources through federated learning.

[0326] Solution 44. A computer-readable storage medium having computer-executable instructions stored thereon. When the computer-executable instructions are executed by a processor, the processor executes the method for a spectrum management device according to any one of Solutions 42 to 43.

Claims

1. An electronic device for a spectrum management apparatus, comprising: A processing circuit configured to: For at least one of a plurality of federated prediction regions constructed based on subsystems, obtain a primary system behavior model for predicting the behavior of the primary system using spectrum resources through federated learning.

2. The electronic device according to claim 1, wherein, The plurality of federated prediction regions are constructed based on the geographical locations of the subsystems, and the size of a federated prediction region is represented by the number of geographical units having a predetermined geographical size.

3. The electronic device according to claim 2, wherein, The number and locations of the plurality of federated prediction regions are determined by the k-means algorithm and the density-based spatial clustering of applications with noise (DBSCAN) algorithm.

4. The electronic device according to claim 3, wherein The k-means algorithm is used to cluster base stations in the subsystem, delete clusters that do not contain any base stations without changing the locations of the cluster centers, and when the distance between a specific base station and the center of its affiliated cluster in a cluster exceeds a first predetermined distance threshold, set the location of the specific base station as a new cluster center. The DBSCAN algorithm takes the locations of the cluster centers determined by the k-means algorithm as input to obtain new cluster centers, and merges cluster centers among the new cluster centers whose distances are less than a second predetermined distance threshold, and Repeat the k-means algorithm and the DBSCAN algorithm until the number of cluster centers no longer changes, wherein the cluster centers serve as the centers of the federated prediction regions and the number of the cluster centers corresponds to the number of the plurality of federated prediction regions.

5. The electronic device according to any one of claims 2 to 4, wherein, The lower bound value of the size of the plurality of federated prediction regions is determined based on the distance between the center of the federated prediction region and the subsystem, and each federated prediction region is updated and thus determined based on the accuracy and / or energy consumption when the primary system behavior model converges.

6. The electronic device according to any one of claims 1 to 5, wherein, The primary system behavior model is a multi-input multi-output long short-term memory neural network model.

7. The electronic device according to claim 6, wherein, The dimensions of the input and output of the multi-input multi-output long short-term memory neural network model are determined by the size of the federated prediction region.

8. The electronic device according to claim 7, wherein, For each federated prediction region, the input of the multi-input multi-output long short-term neural network model is the primary system signal reception power information of all geographical units included in the federated prediction region in a predetermined number of historical time slots, and the output is the predicted value of the primary system signal reception power of each geographical unit in the next time slot.

9. The electronic device according to any one of claims 1 to 8, wherein, The primary system behavior model is obtained by aggregating local primary system behavior models obtained from federated learning clients participating in the federated learning.

10. The electronic device according to claim 9, wherein, Aggregate the local primary system behavior model corresponding to the federated learning client by calculating weights based on the number of geographical units occupied by user equipment in the subsystem associated with the federated learning client.

11. The electronic device according to claim 9, wherein, Aggregate the local primary system behavior model corresponding to the federated learning client by calculating weights based on the distribution state of user equipment in the subsystem associated with the federated learning client.

12. The electronic device according to claim 9, wherein, Aggregate the local master system behavior model by calculating weights based on the model accuracy of the local master system behavior model corresponding to the federated learning client.

13. The electronic device according to claim 12, wherein, The model accuracy of the local master system behavior model increases as the amount of user data involved in the local master system behavior model increases, and decreases as the loss of the local master system behavior model increases.

14. The electronic device according to any one of claims 9 to 13, wherein, As the loss of the local master system behavior model monotonically decreases, the aggregation period also monotonically decreases.

15. The electronic device according to claim 14, wherein, If the loss of the local master system behavior model is not monotonically decreasing, the aggregation period decreases by a predetermined ratio.

16. The electronic device according to any one of claims 1 to 15, wherein, The spectrum management device acts as a federated learning server, and the processing circuit is configured to use the final global model obtained by aggregating the local master system behavior models trained by one or more other spectrum management devices that are federated learning clients participating in the federated learning as the master system behavior model.

17. The electronic device according to claim 16, wherein, The processing circuit is configured to send a federated learning request to other spectrum management devices within the federated prediction region associated with it, and receive a federated learning response from other spectrum management devices that agree to participate in the federated learning.

18. The electronic device according to claim 17, wherein, The federated learning response includes the number of geographical units occupied by the user equipment in the subsystem associated with the federated learning client.

19. The electronic device according to any one of claims 16 to 18, wherein, The processing circuit is configured to: In each round of training of the federated learning, aggregate the local master system behavior models trained by each federated learning client based on weights to obtain a global model, and send the global model to each federated learning client so that each federated learning client can perform the next round of training based on the global model; And Until a predetermined condition is met, stop the federated learning and use the obtained final global model as the master system behavior model.

20. The electronic device according to claim 19, wherein, The predetermined condition includes that the final global model reaches a predetermined accuracy and / or has been trained for a predetermined number of rounds.

21. The electronic device according to any one of claims 1 to 15, wherein, The spectrum management device uses the final global model obtained from the federated learning server as the master system behavior model, where the federated learning server aggregates the local master system behavior models trained by each federated learning client participating in the federated learning to obtain the final global model.

22. The electronic device according to claim 21, wherein, The federated learning server sends a federated learning request to other devices within the federated prediction region associated with it, and receives a federated learning response from other devices that agree to participate in the federated learning.

23. The electronic device according to claim 22, wherein, The federated learning response includes the number of geographical units occupied by the user equipment in the subsystem associated with the federated learning client.

24. The electronic device according to any one of claims 21 to 23, wherein, The federated learning server: In each round of training of the federated learning, aggregate the local master system behavior models trained by each federated learning client based on weights to obtain a global model, and send the global model to each federated learning client so that each federated learning client can perform the next round of training based on the global model; And Until a predetermined condition is met, stop the federated learning and obtain the final global model.

25. The electronic device according to claim 24, wherein, The predetermined condition includes that the final global model reaches a predetermined accuracy and / or has been trained for a predetermined number of rounds.

26. The electronic device according to any one of claims 21 to 25, wherein, The federated learning server is implemented by the Network Data Analytics Function (NWDAF).

27. The electronic device according to any one of claims 1 to 15, wherein, The spectrum management device serves as a federated learning client. The processing circuit is configured to jointly perform federated learning with one or more other spectrum management devices that serve as federated learning clients, and use the global model obtained by aggregating the local master system behavior models trained by each federated learning client as the master system behavior model.

28. The electronic device according to claim 27, wherein, The processing circuit is configured to send to other federated learning clients the number of geographical units occupied by user equipment in the subsystem associated with the spectrum management device.

29. The electronic device according to claim 27 or 28, wherein, The processing circuit is configured to, in each round of training of the federated learning, aggregate, based on weights, the local master system behavior model trained by the spectrum management device and the local master system behavior models received from other federated learning clients via broadcast to obtain a global model, and use the global model as the new local master system behavior model for the next round of training; and until a predetermined condition is met, stop the federated learning and use the finally obtained global model as the master system behavior model.

30. The electronic device according to claim 27 or 28, wherein, The spectrum management device is selected for the aggregation when the following predetermined conditions are satisfied: Based on the channel information between the spectrum management device and the one or more other spectrum management devices, calculate the sum value of the transmission energy consumption of the transmission paths between the spectrum management device and the one or more other spectrum management devices when the spectrum management device serves as an aggregation device for aggregating the local master user behavior models within the federated prediction region associated therewith, wherein the sum value of the transmission energy consumption when the spectrum management device serves as the aggregation device is less than the sum value of the transmission energy consumption of any other spectrum management device among the one or more other spectrum management devices when serving as the aggregation device.

31. The electronic device according to claim 30, wherein, The processing circuit is configured to exchange the channel information with the one or more other spectrum management devices via broadcast.

32. The electronic device according to claim 30 or 31, wherein, The transmission energy consumption of the transmission path is calculated based on the transmission rate and transmission power of the transmission path.

33. The electronic device according to any one of claims 27 to 33, wherein, The spectrum management device is implemented by a base station in the subsystem or an edge server associated with the subsystem.

34. An electronic device for a spectrum management device, comprising: A processing circuit, configured to: For one of a plurality of federated prediction regions constructed based on a subsystem, assist in obtaining a master system behavior model for predicting the behavior of the master system using spectrum resources through federated learning.

35. The electronic device according to claim 34, wherein the spectrum management device serves as a federated learning client participating in the federated learning, the processing circuit is configured to preprocess a data set uploaded from the subsystem associated with the spectrum management device, and train a local master system behavior model based on the preprocessed data set.

36. The electronic device according to claim 35, wherein, The preprocessing includes: when there are multiple master system signal reception powers corresponding to the same geographical unit in the data set, averaging the multiple master system signal reception powers, where the geographical unit has a predetermined geographical size.

37. The electronic device according to claim 35 or 36, wherein, The processing circuit is configured to send the trained local master system behavior model to a federated learning server participating in the federated learning, so that the federated learning server aggregates based on the local master system behavior model to obtain the master system behavior model.

38. The electronic device according to claim 34, wherein the spectrum management device obtains the trained local master system behavior model from a corresponding federated learning client participating in the federated learning corresponding to it, the corresponding federated learning client preprocesses a data set uploaded from a subsystem associated with the spectrum management device, and trains a local master system behavior model based on the preprocessed data set.

39. The electronic device according to claim 38, wherein, The preprocessing includes: when there are multiple master system signal reception powers corresponding to the same geographical unit in the data set, averaging the multiple master system signal reception powers, wherein the geographical unit has a predetermined geographical size.

40. The electronic device according to claim 38 or 39, wherein, The corresponding federated learning client sends the trained local master system behavior model to a federated learning server participating in the federated learning, so that the federated learning server aggregates based on the local master system behavior model to obtain the master system behavior model.

41. The electronic device according to any one of claims 38 to 40, wherein, The corresponding federated learning client is implemented by a network data analysis function NWDAF.

42. A method for a spectrum management device, comprising: For at least one federated prediction region among a plurality of federated prediction regions constructed based on subsystems, the spectrum management device obtains a master system behavior model for predicting the behavior of the master system using spectrum resources through federated learning.

43. A method for a spectrum management device, comprising: For one federated prediction region among a plurality of federated prediction regions constructed based on subsystems, assist in obtaining a master system behavior model for predicting the behavior of the master system using spectrum resources through federated learning.

44. A computer-readable storage medium, on which computer-executable instructions are stored, and when the computer-executable instructions are executed by a processor, the processor is caused to execute the method for a spectrum management device according to any one of claims 42 to 43.

Images