Time-frequency resource allocation method, equipment and device

Abstract

The embodiment of the invention provides a time-frequency resource allocation method, equipment and a device. The method comprises the following steps: receiving initial state information of a plurality of base stations; inputting a time-frequency resource allocation model based on the initial state information of the plurality of base stations to obtain initial time-frequency resource allocation results of the plurality of base stations; adjusting the initial time-frequency resource allocation results of the plurality of base stations based on a resource allocation adjustment rule to obtain target time-frequency resource allocation results of the plurality of base stations; and sending corresponding target time-frequency resource allocation results to the plurality of base stations, wherein the target time-frequency resource allocation results are used by the base stations to schedule the target terminal based on the target resource block allocated to the target terminal. The embodiment of the invention provides a time-frequency resource allocation method, equipment and device, which are used for realizing scheduling of all terminals with time-frequency resource requirements.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of time-frequency resource allocation, and in particular, to a method, device and apparatus for allocating time-frequency resources. Background Art

[0002] In a mobile communication system, data packets need to be transmitted with the help of resource blocks (RBs) (also called time-frequency resources).

[0003] In the related art, a round robin (RR) algorithm can be used to configure time-frequency resources for each base station in a mobile communication system to ensure that data packets generated in the service cell of the base station can be transmitted through the time-frequency resources configured for the base station. In the time-frequency resource allocation method based on the round robin algorithm, at the same scheduling moment, among all the terminals with time-frequency resource requirements served by each base station, some terminals may not be able to obtain resource blocks, resulting in scheduling failure of some terminals at the scheduling moment. Summary of the invention

[0004] The embodiments of the present application provide a method, device and apparatus for allocating time-frequency resources, so as to solve the defect of the prior art that the scheduling of some terminals at the scheduling moment fails, and realize the scheduling of all terminals with time-frequency resource requirements.

[0005] In a first aspect, an embodiment of the present application provides a time-frequency resource allocation method, including:

[0006] receiving initial state information of a plurality of base stations; the initial state information including: state information of each terminal accessing the base station, request information of each terminal and resource state information of the base station;

[0007] Based on the initial state information of the multiple base stations, a time-frequency resource allocation model is input to obtain initial time-frequency resource allocation results of the multiple base stations; the initial time-frequency resource allocation results include an initial resource block allocated to a target terminal, and the target terminal is a terminal with time-frequency resource demand among the terminals accessing the base station;

[0008] Based on the resource allocation adjustment rule, adjust the initial time-frequency resource allocation results of the multiple base stations to obtain target time-frequency resource allocation results of the multiple base stations, wherein the target time-frequency resource allocation results include a target resource block allocated to the target terminal;

[0009] The corresponding target time-frequency resource allocation results are sent to the multiple base stations, where the target time-frequency resource allocation results are used by the base station to schedule the target terminal based on the target resource block allocated to the target terminal.

[0010] According to a time-frequency resource allocation method provided in an embodiment of the present application, the initial time-frequency resource allocation results of the multiple base stations are adjusted based on the resource allocation adjustment rule to obtain the target time-frequency resource allocation results of the multiple base stations, including:

[0011] Performing an acquisition operation to acquire throughput rates and intermediate state information of the multiple base stations based on initial time-frequency resource allocation results of the multiple base stations;

[0012] Performing an input operation, when it is determined that the throughput rates of the multiple base stations do not satisfy the resource allocation adjustment rule, inputting the intermediate state information of the multiple base stations into the time-frequency resource allocation model to obtain intermediate time-frequency resource allocation results of the multiple base stations;

[0013] Perform a judgment operation to determine whether the throughput rates of the multiple base stations obtained based on the intermediate time-frequency resource allocation results of the multiple base stations meet the resource allocation adjustment rules; if so, determine the intermediate time-frequency resource allocation results of the multiple base stations as the target time-frequency resource allocation results of the multiple base stations; otherwise, update the initial time-frequency resource allocation results of the multiple base stations to the intermediate time-frequency resource allocation results of the multiple base stations, and repeat the acquisition operation, the input operation and the judgment operation.

[0014] According to a time-frequency resource allocation method provided in an embodiment of the present application, based on an initial time-frequency resource allocation result of the base station, obtaining a throughput rate and intermediate state information of the base station includes:

[0015] Sending the initial time-frequency resource allocation result to the base station;

[0016] After the base station and each target terminal accessing the base station perform data transmission based on the initial time-frequency resource allocation result, the throughput rate and the intermediate state information sent by the base station are received.

[0017] According to a time-frequency resource allocation method provided in an embodiment of the present application, determining that the throughput rates of the multiple base stations do not satisfy the resource allocation adjustment rule includes:

[0018] Determining a sum of throughput rates of the plurality of base stations;

[0019] When the sum is less than a preset throughput threshold, it is determined that the throughputs of the multiple base stations do not satisfy the resource allocation adjustment rule.

[0020] According to a time-frequency resource allocation method provided in an embodiment of the present application, the throughput rate is obtained through a throughput rate determination model;

[0021] The throughput determination model is:

[0022] Among them, R n represents the throughput rate, C C represents the total number of bytes correctly transmitted during data transmission between the base station and the target terminal among the terminals accessing the base station, C n Indicates the total number of bytes to be transmitted by the base station, M n represents the total number of initial resource blocks allocated to the base station, and M represents the total number of preset resource blocks;

[0023] The initial time-frequency resource allocation result also includes the M n And the M.

[0024] According to a time-frequency resource allocation method provided in an embodiment of the present application, the time-frequency resource allocation model is a model obtained by training a neural network based on multiple groups of sample trajectories and a target loss function; the multiple groups of sample trajectories are trajectories obtained by multiple rounds of communication between the neural network and each sample base station;

[0025] The objective loss function is: U(θ)=∑ τ P(τ|θ)R(τ);

[0026] Wherein, U(θ) represents the function value of the target loss function, θ represents the model parameter of the neural network, τ represents the τth sample trajectory in a set of sample trajectories, P(τ|θ) represents the occurrence probability of the τth sample trajectory, and R(τ) represents the reward value of the τth sample trajectory;

[0027] in,

[0028] Among them, T represents the number of steps of the τth sample trajectory, R t represents the sum of the throughput rates of the sample base stations obtained in the tth step of the τth sample trajectory.

[0029] In a second aspect, an embodiment of the present application further provides an electronic device, including: a memory, a transceiver, and a processor:

[0030] The memory is used to store computer programs;

[0031] The transceiver is used to send and receive data under the control of the processor;

[0032] The processor is configured to read the computer program in the memory and perform the following operations:

[0033] receiving initial state information of a plurality of base stations; the initial state information including: state information of each terminal accessing the base station, request information of each terminal and resource state information of the base station;

[0034] Based on the initial state information of the multiple base stations, a time-frequency resource allocation model is input to obtain initial time-frequency resource allocation results of the multiple base stations; the initial time-frequency resource allocation results include an initial resource block allocated to a target terminal, and the target terminal is a terminal with time-frequency resource demand among the terminals accessing the base station;

[0035] Based on the resource allocation adjustment rule, adjust the initial time-frequency resource allocation results of the multiple base stations to obtain target time-frequency resource allocation results of the multiple base stations, wherein the target time-frequency resource allocation results include a target resource block allocated to the target terminal;

[0036] The corresponding target time-frequency resource allocation results are sent to the multiple base stations, where the target time-frequency resource allocation results are used by the base station to schedule the target terminal based on the target resource block allocated to the target terminal.

[0037] According to an electronic device provided by an embodiment of the present application, the adjusting the initial time-frequency resource allocation results of the multiple base stations based on the resource allocation adjustment rule to obtain the target time-frequency resource allocation results of the multiple base stations includes:

[0038] Performing an acquisition operation to acquire throughput rates and intermediate state information of the multiple base stations based on initial time-frequency resource allocation results of the multiple base stations;

[0039] Performing an input operation, when it is determined that the throughput rates of the multiple base stations do not satisfy the resource allocation adjustment rule, inputting the intermediate state information of the multiple base stations into the time-frequency resource allocation model to obtain intermediate time-frequency resource allocation results of the multiple base stations;

[0040] Perform a judgment operation to determine whether the throughput rates of the multiple base stations obtained based on the intermediate time-frequency resource allocation results of the multiple base stations meet the resource allocation adjustment rules; if so, determine the intermediate time-frequency resource allocation results of the multiple base stations as the target time-frequency resource allocation results of the multiple base stations; otherwise, update the initial time-frequency resource allocation results of the multiple base stations to the intermediate time-frequency resource allocation results of the multiple base stations, and repeat the acquisition operation, the input operation and the judgment operation.

[0041] According to an electronic device provided by an embodiment of the present application, based on an initial time-frequency resource allocation result of the base station, the throughput rate and intermediate state information of the base station are obtained, including:

[0042] Sending the initial time-frequency resource allocation result to the base station;

[0043] After the base station and each target terminal accessing the base station perform data transmission based on the initial time-frequency resource allocation result, the throughput rate and the intermediate state information sent by the base station are received.

[0044] According to an electronic device provided by an embodiment of the present application, determining that the throughput rates of the multiple base stations do not satisfy the resource allocation adjustment rule includes:

[0045] Determining a sum of throughput rates of the plurality of base stations;

[0046] When the sum is less than a preset throughput threshold, it is determined that the throughputs of the multiple base stations do not satisfy the resource allocation adjustment rule.

[0047] According to an electronic device provided by an embodiment of the present application, the throughput is obtained by a throughput determination model;

[0048] The throughput determination model is:

[0049] Among them, R n represents the throughput rate, C C represents the total number of bytes correctly transmitted during data transmission between the base station and the target terminal among the terminals accessing the base station, C n Indicates the total number of bytes to be transmitted by the base station, M n represents the total number of initial resource blocks allocated to the base station, and M represents the total number of preset resource blocks;

[0050] The initial time-frequency resource allocation result also includes the M n And the M.

[0051] According to an electronic device provided by an embodiment of the present application, the time-frequency resource allocation model is a model obtained by training a neural network based on multiple groups of sample trajectories and a target loss function; the multiple groups of sample trajectories are trajectories obtained by multiple rounds of communication between the neural network and each sample base station;

[0052] The objective loss function is: U(θ)=∑ τ P(τ|θ)R(τ);

[0053] Wherein, U(θ) represents the function value of the target loss function, θ represents the model parameter of the neural network, τ represents the τth sample trajectory in a set of sample trajectories, P(τ|θ) represents the occurrence probability of the τth sample trajectory, and R(τ) represents the reward value of the τth sample trajectory;

[0054] in,

[0055] Among them, T represents the number of steps of the τth sample trajectory, R t represents the sum of the throughput rates of the sample base stations obtained in the tth step of the τth sample trajectory.

[0056] In a third aspect, an embodiment of the present application further provides a time-frequency resource allocation device, including:

[0057] A receiving module, configured to receive initial state information of a plurality of base stations; the initial state information includes: state information of each terminal accessing the base station, request information of each terminal, and resource state information of the base station;

[0058] A determination module, configured to input a time-frequency resource allocation model based on the initial state information of the multiple base stations to obtain initial time-frequency resource allocation results of the multiple base stations; the initial time-frequency resource allocation results include an initial resource block allocated to a target terminal, and the target terminal is a terminal having a time-frequency resource demand among the terminals accessing the base station;

[0059] The determination module is further configured to adjust the initial time-frequency resource allocation results of the multiple base stations based on the resource allocation adjustment rule to obtain target time-frequency resource allocation results of the multiple base stations, wherein the target time-frequency resource allocation results include a target resource block allocated to the target terminal;

[0060] The sending module is used to send the corresponding target time-frequency resource allocation results to the multiple base stations, and the target time-frequency resource allocation results are used by the base station to schedule the target terminal based on the target resource block allocated to the target terminal.

[0061] According to a time-frequency resource allocation device provided in an embodiment of the present application, the determination module is specifically used for:

[0062] Performing an acquisition operation to acquire throughput rates and intermediate state information of the multiple base stations based on initial time-frequency resource allocation results of the multiple base stations;

[0063] Performing an input operation, when it is determined that the throughput rates of the multiple base stations do not satisfy the resource allocation adjustment rule, inputting the intermediate state information of the multiple base stations into the time-frequency resource allocation model to obtain intermediate time-frequency resource allocation results of the multiple base stations;

[0064] Perform a judgment operation to determine whether the throughput rates of the multiple base stations obtained based on the intermediate time-frequency resource allocation results of the multiple base stations meet the resource allocation adjustment rules; if so, determine the intermediate time-frequency resource allocation results of the multiple base stations as the target time-frequency resource allocation results of the multiple base stations; otherwise, update the initial time-frequency resource allocation results of the multiple base stations to the intermediate time-frequency resource allocation results of the multiple base stations, and repeat the acquisition operation, the input operation and the judgment operation.

[0065] According to a time-frequency resource allocation device provided in an embodiment of the present application, the determination module is specifically used for:

[0066] Sending the initial time-frequency resource allocation result to the base station through a sending module;

[0067] After the base station and each target terminal connected to the base station perform data transmission based on the initial time-frequency resource allocation result, the receiving module receives the throughput rate and the intermediate state information sent by the base station.

[0068] According to a time-frequency resource allocation device provided in an embodiment of the present application, the determination module is specifically used for:

[0069] Determining a sum of throughput rates of the plurality of base stations;

[0070] When the sum is less than a preset throughput threshold, it is determined that the throughputs of the multiple base stations do not satisfy the resource allocation adjustment rule.

[0071] According to a time-frequency resource allocation device provided in an embodiment of the present application, the throughput rate is obtained through a throughput rate determination model;

[0072] The throughput determination model is:

[0073] Among them, R n represents the throughput rate, C C represents the total number of bytes correctly transmitted during data transmission between the base station and the target terminal among the terminals accessing the base station, C n Indicates the total number of bytes to be transmitted by the base station, M n represents the total number of initial resource blocks allocated to the base station, and M represents the total number of preset resource blocks;

[0074] The initial time-frequency resource allocation result also includes the M n And the M.

[0075] According to a time-frequency resource allocation device provided by an embodiment of the present application, the time-frequency resource allocation model is a model obtained by training a neural network based on multiple groups of sample trajectories and a target loss function; the multiple groups of sample trajectories are trajectories obtained by multiple rounds of communication between the neural network and each sample base station;

[0076] The objective loss function is: U(θ)=∑ τ P(τ|θ)R(τ);

[0077] Wherein, U(θ) represents the function value of the target loss function, θ represents the model parameter of the neural network, τ represents the τth sample trajectory in a set of sample trajectories, P(τ|θ) represents the occurrence probability of the τth sample trajectory, and R(τ) represents the reward value of the τth sample trajectory;

[0078] in,

[0079] Among them, T represents the number of steps of the τth sample trajectory, R t represents the sum of the throughput rates of the sample base stations obtained in the tth step of the τth sample trajectory.

[0080] In a fourth aspect, an embodiment of the present application further provides a processor-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the time-frequency resource allocation methods described above.

[0081] In a fifth aspect, an embodiment of the present application further provides a computer program product, including a computer program, which, when executed by a processor, implements any of the time-frequency resource allocation methods described above.

[0082] The embodiment of the present application provides a method, device and apparatus for allocating time-frequency resources. By inputting a time-frequency resource allocation model based on the initial state information of multiple base stations, the initial time-frequency resource allocation results of multiple base stations are obtained. Since the initial state information includes the state information of each terminal and the request information of each terminal, it is ensured that the initial time-frequency resource allocation result includes the initial resource block allocated to the target terminal with time-frequency resource demand. Further, based on the resource allocation adjustment rule, the initial time-frequency resource allocation results of multiple base stations are adjusted to obtain the target time-frequency resource allocation results of multiple base stations, so that the target time-frequency resource allocation results include the target resource block allocated to the target terminal. Further, the corresponding target time-frequency resource allocation results are sent to multiple base stations, so that the base station schedules the target terminal based on the target resource block allocated to the target terminal, thereby avoiding the scheduling failure of the target terminal with time-frequency resource demand, and realizing the scheduling of all terminals with time-frequency resource demand. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0084] Figure 1 This is one of the structural diagrams of the time-frequency resource allocation method provided in the embodiment of the present application;

[0085] Figure 2 This is the second structural diagram of the time-frequency resource allocation method provided in the embodiment of the present application;

[0086] Figure 3is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application;

[0087] Figure 4 It is a structural diagram of the time-frequency resource allocation device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0088] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the embodiments of the present application.

[0089] In the time-frequency resource allocation method based on the polling algorithm, at the same scheduling time, among all the terminals with resource requirements served by each base station, some terminals may be unable to obtain resource blocks, resulting in scheduling failure for some terminals at the scheduling time.

[0090] In order to avoid scheduling failure for some terminals in the embodiments of the present application, the inventors have conceived of a time-frequency resource allocation method, in which the initial state information of the base station is collected, and the time-frequency resource allocation result is obtained based on the initial state information. Since the initial state information includes the state information of each terminal accessing the base station, the request information of the terminal and the resource status information of the base station, it is guaranteed that the time-frequency resource allocation result includes the time-frequency resources allocated to each terminal accessing the base station.

[0091] The time-frequency resource allocation method of the embodiment of the present application is described below in conjunction with specific embodiments. Optionally, the execution subject of the time-frequency resource allocation method provided in the embodiment of the present application is an electronic device, or a time-frequency resource allocation device set in the electronic device.

[0092] The electronic device may be, for example, a resource scheduling device for managing multiple base stations.

[0093] The time-frequency resource allocation device can be implemented through a combination of software and / or hardware.

[0094] Figure 1 FIG. 1 is one of the structural diagrams of the time-frequency resource allocation method provided in the embodiment of the present application. Figure 1 As shown, the method includes:

[0095] S11: receiving initial status information of multiple base stations.

[0096] For each base station, the initial state information of the base station includes: state information of each terminal accessing the base station, request information of each terminal and resource state information of the base station.

[0097] The status information of the terminal indicates whether the terminal initiates a request at the current scheduling time.

[0098] The terminal status information is obtained in order to not consider terminals without time-frequency resource requirements in the time-frequency resource allocation process, thereby ensuring the effectiveness of time-frequency resource allocation (that is, allocating time-frequency resources to each terminal with time-frequency resource requirements, and not allocating time-frequency resources to each terminal without time-frequency resource requirements) and reducing the computational complexity of the time-frequency resource allocation process.

[0099] The request information of the terminal includes the parameters shown in Table 1 below.

[0100] Table 1

[0101]

[0102]

[0103] The resource status information of the base station indicates the status (unused status and used status) of each resource block of the base station at the current scheduling moment.

[0104] The purpose of acquiring the resource status information of the base station is to avoid erroneous scheduling of resource blocks in a used state during the time-frequency resource allocation process.

[0105] S12: Based on the initial state information of the multiple base stations, a time-frequency resource allocation model is input to obtain initial time-frequency resource allocation results of the multiple base stations.

[0106] For each base station, the initial time-frequency resource allocation result of the base station includes an initial resource block allocated to the target terminal.

[0107] The target terminal is a terminal having time-frequency resource requirements among the terminals accessing the base station.

[0108] Optionally, the number of target terminals may be one or more.

[0109] Optionally, the time-frequency resource allocation model is a model obtained by training a neural network.

[0110] S13: Based on the resource allocation adjustment rule, adjust the initial time-frequency resource allocation results of the multiple base stations to obtain the target time-frequency resource allocation results of the multiple base stations.

[0111] For each base station, the target time-frequency resource allocation result of the base station includes a target resource block allocated to a target terminal, where the target terminal is a terminal having a time-frequency resource demand among terminals accessing the base station.

[0112] Optionally, the resource allocation adjustment rule is:

[0113]

[0114] Where N represents the total number of base stations, R n represents the throughput rate of the nth base station among multiple base stations, represents the sum of the throughput rates of multiple base stations, and A represents the preset throughput rate threshold.

[0115] R n It is the throughput rate determined by the nth base station based on the time-frequency resource allocation result.

[0116] Optionally, A can be 1 or 2, etc.

[0117] Optionally, after obtaining the throughput of each base station based on the corresponding initial time-frequency resource allocation results, if the sum of the throughput rates of multiple base stations is greater than or equal to 1 (that is, the throughput rates of multiple base stations satisfy the resource allocation adjustment rules), the initial time-frequency resource allocation results of the multiple base stations can be determined as the target time-frequency resource allocation results of the multiple base stations; otherwise, the initial time-frequency resource allocation results of the multiple base stations are adjusted to obtain the target time-frequency resource allocation results of the multiple base stations.

[0118] The throughput rates obtained by the multiple base stations based on the corresponding target time-frequency resource allocation results meet the resource allocation adjustment rules.

[0119] S14: Send corresponding target time-frequency resource allocation results to multiple base stations.

[0120] The target time-frequency resource allocation result is used by the base station to schedule the target terminal based on the target resource block allocated to the target terminal.

[0121] Furthermore, for each base station, after receiving the corresponding target time-frequency resource allocation result, the base station schedules the target terminal based on the target resource block allocated to the target terminal.

[0122] When there are multiple target terminals, each target terminal is scheduled based on the target resource block allocated to the target terminal.

[0123] exist Figure 1In the time-frequency resource allocation method provided in the embodiment, based on the initial state information of multiple base stations, a time-frequency resource allocation model is input to obtain the initial time-frequency resource allocation results of multiple base stations. Since the initial state information includes the state information of each terminal and the request information of each terminal, it is guaranteed that the initial time-frequency resource allocation result includes the initial resource block allocated to the target terminal with time-frequency resource demand. Further, based on the resource allocation adjustment rule, the initial time-frequency resource allocation results of multiple base stations are adjusted to obtain the target time-frequency resource allocation results of multiple base stations, so that the target time-frequency resource allocation result includes the target resource block allocated to the target terminal. Further, the corresponding target time-frequency resource allocation results are sent to multiple base stations, so that the base station schedules the target terminal based on the target resource block allocated to the target terminal, thereby avoiding the scheduling failure of the target terminal with time-frequency resource demand.

[0124] In an embodiment of the present application, the request information of the terminal in the initial state information includes information such as the channel quality and user service (such as the number of newly requested bytes) of each resource block. Therefore, the time-frequency resource allocation model can flexibly, autonomously and reasonably allocate time-frequency resources to specific terminals based on information such as channel quality and user service from the entire system.

[0125] Based on the above embodiments, Figure 2 S13 will be described in detail.

[0126] Figure 2 This is the second structural diagram of the time-frequency resource allocation method provided in the embodiment of the present application. Figure 2 As shown, the method includes:

[0127] S21: Perform an acquisition operation to acquire throughput rates and intermediate state information of the multiple base stations based on initial time-frequency resource allocation results of the multiple base stations.

[0128] In some embodiments, for each base station, S21 specifically includes:

[0129] Sending an initial time-frequency resource allocation result to the base station;

[0130] After the base station and each target terminal accessing the base station perform data transmission based on the initial time-frequency resource allocation result, the throughput rate and intermediate state information sent by the base station are received.

[0131] In some embodiments, the throughput rate sent by the base station is obtained by the base station through a throughput rate determination model.

[0132] The throughput determination model is:

[0133] Among them, R n represents the throughput rate, C CIndicates the total number of bytes correctly transmitted during data transmission between the base station and the target terminal among the terminals accessing the base station, C n Indicates the total number of bytes to be transmitted by the base station, M n represents the total number of initial resource blocks allocated to the base station, and M represents the total number of preset resource blocks.

[0134] It should be noted that Where J represents the total number of multiple target terminals accessing the base station, N h Represents the number of initial resource blocks allocated to the jth target terminal.

[0135] For example, when multiple target terminals accessing the base station include terminals 1, 2, and 3, the total number of initial resource blocks allocated to terminal 1 is 10, the total number of initial resource blocks allocated to terminal 2 is 5, and the total number of initial resource blocks allocated to terminal 3 is 6. n is equal to 21 (ie, the total number of initial resource blocks allocated to the base station is 16).

[0136] Optionally, the initial time-frequency resource allocation result may include M n and M.

[0137] Optionally, the initial time-frequency resource allocation result may not include M n .

[0138] In the absence of M n In the case of, based on the initial time-frequency resource allocation result, count the number of initial resource blocks allocated to each target terminal, and Get M n .

[0139] Optionally, when the base station receives the initial time-frequency resource allocation result, it can update the initial state information based on the initial time-frequency resource allocation result to obtain the intermediate state information.

[0140] S22: Perform an input operation. When it is determined that the throughput rates of the multiple base stations do not satisfy the resource allocation adjustment rule, input the intermediate state information of the multiple base stations into the time-frequency resource allocation model to obtain the intermediate time-frequency resource allocation results of the multiple base stations.

[0141] In some embodiments, determining that throughput rates of the plurality of base stations do not satisfy a resource allocation adjustment rule includes:

[0142] Determining a sum of throughput rates of a plurality of base stations;

[0143] When the sum value is less than the preset throughput threshold, it is determined that the throughputs of the multiple base stations do not satisfy the resource allocation adjustment rule.

[0144] S23: Execute a judgment operation to judge whether the throughput rates of the multiple base stations obtained based on the intermediate time-frequency resource allocation results of the multiple base stations meet the resource allocation adjustment rule.

[0145] If yes, execute S24, otherwise execute S25.

[0146] S24: Determine the intermediate time-frequency resource allocation results of the multiple base stations as the target time-frequency resource allocation results of the multiple base stations.

[0147] S25: Update the initial time-frequency resource allocation results of the multiple base stations in S21 to the intermediate time-frequency resource allocation results of the multiple base stations, and repeat S21 to S24 until the throughput rates of the multiple base stations meet the resource allocation adjustment rules.

[0148] exist Figure 2 In the embodiment, S21 to S24 are repeatedly executed until the throughput rates of the multiple base stations meet the resource allocation adjustment rules, and the intermediate time-frequency resource allocation results of the multiple base stations obtained when the throughput rates of the multiple base stations meet the resource allocation adjustment rules are determined as the target time-frequency resource allocation results of the multiple base stations. This can obtain accurate target time-frequency resource allocation results while improving the throughput performance of the base stations.

[0149] In some embodiments, the time-frequency resource allocation model in the embodiments of the present application is a model obtained by training a neural network based on multiple groups of sample trajectories and target loss functions.

[0150] Optionally, the multiple groups of sample trajectories are trajectories obtained by performing multiple rounds of communication between the neural network and each sample base station, wherein a group of sample trajectories can be obtained by performing one round of communication between the neural network and each sample base station.

[0151] Optionally, a group of sample trajectories includes at least one sample trajectory.

[0152] For example, a sample trajectory is {s0,a0,s1,a1,r1,…s t ,a t ,r t ……s T ,a T ,r T,}, where s t represents the set of sample intermediate state information obtained by the neural network and each sample base station in the tth step (including the sample intermediate state information of each sample base station in the tth step), a t represents the sample intermediate time-frequency resource allocation set obtained in step t (including the sample intermediate time-frequency resource allocation results of each sample base station in step t), r trepresents the sum of the throughputs of multiple sample base stations obtained by the neural network in the tth step, s0 represents the predicted state information set (including the preset sample state information of each sample base station), a0 represents the preset time-frequency resource allocation result set (including the preset time-frequency resource allocation result of each sample base station), and T represents the number of steps of a sample trajectory. It should be noted that in different sample trajectories, the value of T can be the same or different.

[0153] In a communication round, when r t When the throughput rate is greater than or equal to the preset throughput rate threshold, it indicates the end of a communication round.

[0154] In the present invention, the sample base station may be a virtual base station implemented by software.

[0155] Optionally, the objective loss function is: U(θ)=∑ τ P(τ|θ)R(τ);

[0156] Among them, U(θ) represents the function value of the target loss function, θ represents the model parameters of the neural network, τ represents the τth sample trajectory in a set of sample trajectories, P(τ|θ) represents the occurrence probability of the τth sample trajectory, and R(τ) represents the reward value of the τth sample trajectory.

[0157] R(τ) is used to control the direction and step size of the model parameter update. If R(τ) is a positive number and the larger it is, the greater the probability of the sample trajectory appearing after the model parameter update. If R(τ) is a negative number, the appearance of the sample trajectory is suppressed.

[0158] Optionally,

[0159] Among them, ρ0(s0) represents the probability of the sample trajectory τ appearing at step 0, P(s t+1 | t ,a t ) indicates that a is executed at each sample base station t Afterwards from s t Switch to s t+1 The probability of θ (a t |s t ) indicates that each sample base station executes a t The probability of , ∏· represents the cumulative multiplication.

[0160] Optionally,

[0161] Among them, T represents the number of steps of the τth sample trajectory, R t represents the sum of the throughput rates of the sample base stations obtained in the tth step of the τth sample trajectory.

[0162] In an embodiment of the present invention, The convergence speed of the target loss function can be improved, thereby improving the efficiency of obtaining the time-frequency resource allocation model.

[0163] In the process of training the neural network, the update strategy of θ is:

[0164]

[0165] Among them, θ old In the previous parameter update process, a set of sample trajectories is used to train the neural network to obtain model parameters, θ new In order to use another set of sample trajectories to train the neural network and obtain the model parameters in the current parameter update process.

[0166] For example, when the other set of sample trajectories includes M sample trajectories, the following formula can be used to obtain

[0167]

[0168] in, Represents the gradient operator.

[0169] In an embodiment of the present application, the time-frequency resource allocation model obtained by training the neural network can quickly adapt to environmental changes in scenarios where terminals are evenly or unevenly distributed, learn stable, high-return time-frequency resource allocation results, and its performance under the same conditions is better than that of common resource scheduling algorithms.

[0170] Figure 3 Schematic diagram of the structure of the electronic device provided in the embodiment of the present application. Figure 3 As shown, the electronic device includes: a memory 320 , a transceiver 300 , and a processor 310 .

[0171] A memory 320, for storing computer programs;

[0172] The transceiver 300 is used to send and receive data under the control of the processor 310;

[0173] The processor 310 is configured to read the computer program in the memory 320 and perform the following operations:

[0174] receiving initial state information of a plurality of base stations; the initial state information including: state information of each terminal accessing the base station, request information of each terminal and resource state information of the base station;

[0175] Based on the initial state information of the multiple base stations, a time-frequency resource allocation model is input to obtain initial time-frequency resource allocation results of the multiple base stations; the initial time-frequency resource allocation results include an initial resource block allocated to a target terminal, and the target terminal is a terminal with time-frequency resource demand among the terminals accessing the base station;

[0176] Based on the resource allocation adjustment rule, adjust the initial time-frequency resource allocation results of the multiple base stations to obtain target time-frequency resource allocation results of the multiple base stations, wherein the target time-frequency resource allocation results include a target resource block allocated to the target terminal;

[0177] The corresponding target time-frequency resource allocation results are sent to the multiple base stations, where the target time-frequency resource allocation results are used by the base station to schedule the target terminal based on the target resource block allocated to the target terminal.

[0178] Specifically, the transceiver 300 is used to receive and send data under the control of the processor 310 .

[0179] Among them, Figure 3 In the embodiment, the bus architecture may include any number of interconnected buses and bridges, specifically linking various circuits of one or more processors represented by processor 310 and memory represented by memory 320. The bus architecture may also link various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 300 may be a plurality of components, namely, a transmitter and a receiver, providing modules for communicating with various other devices on a transmission medium, such as a wireless channel, a wired channel, an optical cable, and the like. The processor 310 is responsible for managing the bus architecture and general processing, and the memory 320 may store data used by the processor 310 when performing operations.

[0180] The processor 310 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or a complex programmable logic device (CPLD). The processor may also adopt a multi-core architecture.

[0181] According to an electronic device provided by an embodiment of the present application, the adjusting the initial time-frequency resource allocation results of the multiple base stations based on the resource allocation adjustment rule to obtain the target time-frequency resource allocation results of the multiple base stations includes:

[0182] Performing an acquisition operation to acquire throughput rates and intermediate state information of the multiple base stations based on initial time-frequency resource allocation results of the multiple base stations;

[0183] Performing an input operation, when it is determined that the throughput rates of the multiple base stations do not satisfy the resource allocation adjustment rule, inputting the intermediate state information of the multiple base stations into the time-frequency resource allocation model to obtain intermediate time-frequency resource allocation results of the multiple base stations;

[0184] Perform a judgment operation to determine whether the throughput rates of the multiple base stations obtained based on the intermediate time-frequency resource allocation results of the multiple base stations meet the resource allocation adjustment rules; if so, determine the intermediate time-frequency resource allocation results of the multiple base stations as the target time-frequency resource allocation results of the multiple base stations; otherwise, update the initial time-frequency resource allocation results of the multiple base stations to the intermediate time-frequency resource allocation results of the multiple base stations, and repeat the acquisition operation, the input operation and the judgment operation.

[0185] According to an electronic device provided by an embodiment of the present application, based on an initial time-frequency resource allocation result of the base station, the throughput rate and intermediate state information of the base station are obtained, including:

[0186] Sending the initial time-frequency resource allocation result to the base station;

[0187] After the base station and each target terminal accessing the base station perform data transmission based on the initial time-frequency resource allocation result, the throughput rate and the intermediate state information sent by the base station are received.

[0188] According to an electronic device provided by an embodiment of the present application, determining that the throughput rates of the multiple base stations do not satisfy the resource allocation adjustment rule includes:

[0189] Determining a sum of throughput rates of the plurality of base stations;

[0190] When the sum is less than a preset throughput threshold, it is determined that the throughputs of the multiple base stations do not satisfy the resource allocation adjustment rule.

[0191] According to an electronic device provided by an embodiment of the present application, the throughput is obtained by a throughput determination model;

[0192] The throughput determination model is:

[0193] Among them, Rn represents the throughput rate, C C represents the total number of bytes correctly transmitted during data transmission between the base station and the target terminal among the terminals accessing the base station, C n Indicates the total number of bytes to be transmitted by the base station, M n represents the total number of initial resource blocks allocated to the base station, and M represents the total number of preset resource blocks;

[0194] The initial time-frequency resource allocation result also includes the M n And the M.

[0195] According to an electronic device provided by an embodiment of the present application, the time-frequency resource allocation model is a model obtained by training a neural network based on multiple groups of sample trajectories and a target loss function; the multiple groups of sample trajectories are trajectories obtained by multiple rounds of communication between the neural network and each sample base station;

[0196] The objective loss function is: U(θ)=∑ τ P(τ|θ)R(τ);

[0197] Wherein, U(θ) represents the function value of the target loss function, θ represents the model parameter of the neural network, τ represents the τth sample trajectory in a set of sample trajectories, P(τ|θ) represents the occurrence probability of the τth sample trajectory, and R(τ) represents the reward value of the τth sample trajectory;

[0198] in,

[0199] Among them, T represents the number of steps of the τth sample trajectory, R t represents the sum of the throughput rates of the sample base stations obtained in the tth step of the τth sample trajectory.

[0200] It should be noted here that the above-mentioned electronic device provided in the embodiment of the present application can implement all the method steps implemented by the method embodiment in which the execution subject is the electronic device, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

[0201] Figure 4 Schematic diagram of the structure of the time-frequency resource allocation device provided in the embodiment of the present application. Figure 4 As shown, the time-frequency resource allocation device includes:

[0202] The receiving module 401 is used to receive initial state information of multiple base stations; the initial state information includes: state information of each terminal accessing the base station, request information of each terminal and resource state information of the base station;

[0203] The determination module 402 is used to input a time-frequency resource allocation model based on the initial state information of the multiple base stations to obtain initial time-frequency resource allocation results of the multiple base stations; the initial time-frequency resource allocation results include an initial resource block allocated to a target terminal, and the target terminal is a terminal with time-frequency resource demand among the terminals accessing the base station;

[0204] The determining module 402 is further configured to adjust the initial time-frequency resource allocation results of the multiple base stations based on the resource allocation adjustment rule to obtain target time-frequency resource allocation results of the multiple base stations, wherein the target time-frequency resource allocation results include a target resource block allocated to the target terminal;

[0205] The sending module 403 is used to send corresponding target time-frequency resource allocation results to the multiple base stations, and the target time-frequency resource allocation results are used by the base station to schedule the target terminal based on the target resource block allocated to the target terminal.

[0206] According to a time-frequency resource allocation device provided in an embodiment of the present application, the determination module 402 is specifically used for:

[0207] Performing an acquisition operation to acquire throughput rates and intermediate state information of the multiple base stations based on initial time-frequency resource allocation results of the multiple base stations;

[0208] Performing an input operation, when it is determined that the throughput rates of the multiple base stations do not satisfy the resource allocation adjustment rule, inputting the intermediate state information of the multiple base stations into the time-frequency resource allocation model to obtain intermediate time-frequency resource allocation results of the multiple base stations;

[0209] Perform a judgment operation to determine whether the throughput rates of the multiple base stations obtained based on the intermediate time-frequency resource allocation results of the multiple base stations meet the resource allocation adjustment rules; if so, determine the intermediate time-frequency resource allocation results of the multiple base stations as the target time-frequency resource allocation results of the multiple base stations; otherwise, update the initial time-frequency resource allocation results of the multiple base stations to the intermediate time-frequency resource allocation results of the multiple base stations, and repeat the acquisition operation, the input operation and the judgment operation.

[0210] According to a time-frequency resource allocation device provided in an embodiment of the present application, the determination module 402 is specifically used for:

[0211] Sending the initial time-frequency resource allocation result to the base station through the sending module 403;

[0212] After the base station and each target terminal connected to the base station perform data transmission based on the initial time-frequency resource allocation result, the receiving module 401 receives the throughput rate and the intermediate state information sent by the base station.

[0213] According to a time-frequency resource allocation device provided in an embodiment of the present application, the determination module 402 is specifically used for:

[0214] Determining a sum of throughput rates of the plurality of base stations;

[0215] When the sum is less than a preset throughput threshold, it is determined that the throughputs of the multiple base stations do not satisfy the resource allocation adjustment rule.

[0216] According to a time-frequency resource allocation device provided in an embodiment of the present application, the throughput rate is obtained through a throughput rate determination model;

[0217] The throughput determination model is:

[0218] Among them, R n represents the throughput rate, C C represents the total number of bytes correctly transmitted during data transmission between the base station and the target terminal among the terminals accessing the base station, C n Indicates the total number of bytes to be transmitted by the base station, M n represents the total number of initial resource blocks allocated to the base station, and M represents the total number of preset resource blocks;

[0219] The initial time-frequency resource allocation result also includes the M n And the M.

[0220] According to a time-frequency resource allocation device provided by an embodiment of the present application, the time-frequency resource allocation model is a model obtained by training a neural network based on multiple groups of sample trajectories and a target loss function; the multiple groups of sample trajectories are trajectories obtained by multiple rounds of communication between the neural network and each sample base station;

[0221] The objective loss function is: U(θ)=∑ τ P(τ|θ)R(τ);

[0222] Wherein, U(θ) represents the function value of the target loss function, θ represents the model parameter of the neural network, τ represents the τth sample trajectory in a set of sample trajectories, P(τ|θ) represents the occurrence probability of the τth sample trajectory, and R(τ) represents the reward value of the τth sample trajectory;

[0223] in,

[0224] Among them, T represents the number of steps of the τth sample trajectory, R t represents the sum of the throughput rates of the sample base stations obtained in the tth step of the τth sample trajectory.

[0225] It should be noted that the division of modules in the embodiments of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional module in each embodiment of the present application may be integrated into a processing module, or each module may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated modules may be implemented in the form of hardware or in the form of software functional modules.

[0226] If the integrated module is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a processor-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor (processor) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program code.

[0227] It should be noted here that the above-mentioned device provided in the embodiment of the present application can implement all the method steps implemented in the above-mentioned method embodiment, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as those in the method embodiment will not be described in detail here.

[0228] On the other hand, an embodiment of the present application further provides a processor-readable storage medium, wherein the processor-readable storage medium stores a computer program, and the computer program is used to enable the processor to execute the time-frequency resource allocation method provided in the above embodiments.

[0229] The processor-readable storage medium can be any available medium or data storage device that can be accessed by the processor, including but not limited to magnetic storage (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc.), optical storage (such as CD, DVD, BD, HVD, etc.), and semiconductor storage (such as ROM, EPROM, EEPROM, non-volatile memory (NANDFLASH), solid-state drive (SSD)), etc.

[0230] On the other hand, an embodiment of the present application further provides a computer program product, including a computer program, which, when executed by a processor, implements the time-frequency resource allocation method provided in any of the above embodiments.

[0231] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) that contain computer-usable program code.

[0232] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer executable instructions. These computer executable instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0233] These processor executable instructions may also be stored in a processor readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the processor readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0234] These processor-executable instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0235] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A time-frequency resource allocation method, characterized in that: include: receiving initial status information of a plurality of base stations; The initial state information includes: state information of each terminal accessing the base station, request information of each terminal and resource state information of the base station; Based on the initial state information of the multiple base stations, a time-frequency resource allocation model is input to obtain initial time-frequency resource allocation results of the multiple base stations; the initial time-frequency resource allocation results include an initial resource block allocated to a target terminal, and the target terminal is a terminal with time-frequency resource demand among the terminals accessing the base station; Based on the resource allocation adjustment rule, adjusting the initial time-frequency resource allocation results of the multiple base stations to obtain target time-frequency resource allocation results of the multiple base stations; the target time-frequency resource allocation results include a target resource block allocated to the target terminal; The corresponding target time-frequency resource allocation results are sent to the multiple base stations, where the target time-frequency resource allocation results are used by the base station to schedule the target terminal based on the target resource block allocated to the target terminal.

2. The time-frequency resource allocation method according to claim 1, characterized in that: The adjusting the initial time-frequency resource allocation results of the multiple base stations based on the resource allocation adjustment rule to obtain the target time-frequency resource allocation results of the multiple base stations includes: Performing an acquisition operation to acquire throughput rates and intermediate state information of the multiple base stations based on initial time-frequency resource allocation results of the multiple base stations; Performing an input operation, when it is determined that the throughput rates of the multiple base stations do not satisfy the resource allocation adjustment rule, inputting the intermediate state information of the multiple base stations into the time-frequency resource allocation model to obtain intermediate time-frequency resource allocation results of the multiple base stations; Perform a judgment operation to determine whether the throughput rates of the multiple base stations obtained based on the intermediate time-frequency resource allocation results of the multiple base stations meet the resource allocation adjustment rules; if so, determine the intermediate time-frequency resource allocation results of the multiple base stations as the target time-frequency resource allocation results of the multiple base stations; otherwise, update the initial time-frequency resource allocation results of the multiple base stations to the intermediate time-frequency resource allocation results of the multiple base stations, and repeat the acquisition operation, the input operation and the judgment operation.

3. The time-frequency resource allocation method according to claim 2, characterized in that: Based on the initial time-frequency resource allocation result of the base station, obtaining the throughput rate and intermediate state information of the base station includes: Sending the initial time-frequency resource allocation result to the base station; After the base station and each target terminal accessing the base station perform data transmission based on the initial time-frequency resource allocation result, the throughput rate and the intermediate state information sent by the base station are received.

4. The time-frequency resource allocation method according to claim 2, characterized in that: Determining that the throughput rates of the multiple base stations do not satisfy the resource allocation adjustment rule includes: Determining a sum of throughput rates of the plurality of base stations; When the sum is less than a preset throughput threshold, it is determined that the throughputs of the multiple base stations do not satisfy the resource allocation adjustment rule.

5. The time-frequency resource allocation method according to any one of claims 2 to 4, characterized in that: The throughput rate is obtained through a throughput rate determination model; The throughput determination model is: Among them, R n represents the throughput rate, C C represents the total number of bytes correctly transmitted during data transmission between the base station and the target terminal among the terminals accessing the base station, C n Indicates the total number of bytes to be transmitted by the base station, M n represents the total number of initial resource blocks allocated to the base station, and M represents the total number of preset resource blocks; The initial time-frequency resource allocation result also includes the M n And the M.

6. The time-frequency resource allocation method according to any one of claims 1 to 4, characterized in that: The time-frequency resource allocation model is a model obtained by training a neural network based on multiple groups of sample trajectories and a target loss function; the multiple groups of sample trajectories are sample trajectories obtained by multiple rounds of communication between the neural network and each sample base station; The objective loss function is: U(θ)=∑ τ P(τ|θ)R(τ); Wherein, U(θ) represents the function value of the target loss function, θ represents the model parameter of the neural network, τ represents the τth sample trajectory in a set of sample trajectories, P(τ|θ) represents the occurrence probability of the τth sample trajectory, and R(τ) represents the reward value of the τth sample trajectory; in, Among them, T represents the number of steps of the τth sample trajectory, R t represents the sum of the throughput rates of the sample base stations obtained in the tth step of the τth sample trajectory.

7. An electronic device, characterized in that: include: Memory, transceivers and processors: The memory is used to store computer programs; The transceiver is used to send and receive data under the control of the processor; The processor is configured to read the computer program in the memory and perform the following operations: receiving initial status information of a plurality of base stations; The initial state information includes: state information of each terminal accessing the base station, request information of each terminal and resource state information of the base station; Based on the initial state information of the multiple base stations, a time-frequency resource allocation model is input to obtain initial time-frequency resource allocation results of the multiple base stations; the initial time-frequency resource allocation results include an initial resource block allocated to a target terminal, and the target terminal is a terminal with time-frequency resource demand among the terminals accessing the base station; Based on the resource allocation adjustment rule, adjust the initial time-frequency resource allocation results of the multiple base stations to obtain target time-frequency resource allocation results of the multiple base stations, wherein the target time-frequency resource allocation results include a target resource block allocated to the target terminal; The corresponding target time-frequency resource allocation results are sent to the multiple base stations, where the target time-frequency resource allocation results are used by the base station to schedule the target terminal based on the target resource block allocated to the target terminal.

8. The electronic device according to claim 7, characterized in that: The adjusting the initial time-frequency resource allocation results of the multiple base stations based on the resource allocation adjustment rule to obtain the target time-frequency resource allocation results of the multiple base stations includes: Performing an acquisition operation to acquire throughput rates and intermediate state information of the multiple base stations based on initial time-frequency resource allocation results of the multiple base stations; Performing an input operation, when it is determined that the throughput rates of the multiple base stations do not satisfy the resource allocation adjustment rule, inputting the intermediate state information of the multiple base stations into the time-frequency resource allocation model to obtain intermediate time-frequency resource allocation results of the multiple base stations; Perform a judgment operation to determine whether the throughput rates of the multiple base stations obtained based on the intermediate time-frequency resource allocation results of the multiple base stations meet the resource allocation adjustment rules; if so, determine the intermediate time-frequency resource allocation results of the multiple base stations as the target time-frequency resource allocation results of the multiple base stations; otherwise, update the initial time-frequency resource allocation results of the multiple base stations to the intermediate time-frequency resource allocation results of the multiple base stations, and repeat the acquisition operation, the input operation and the judgment operation.

9. The electronic device according to claim 8, characterized in that: Based on the initial time-frequency resource allocation result of the base station, obtaining the throughput rate and intermediate state information of the base station includes: Sending the initial time-frequency resource allocation result to the base station; After the base station and each target terminal accessing the base station perform data transmission based on the initial time-frequency resource allocation result, the throughput rate and the intermediate state information sent by the base station are received.

10. The electronic device according to claim 8, characterized in that: Determining that the throughput rates of the multiple base stations do not satisfy the resource allocation adjustment rule includes: Determining a sum of throughput rates of the plurality of base stations; When the sum is less than a preset throughput threshold, it is determined that the throughputs of the multiple base stations do not satisfy the resource allocation adjustment rule.

11. The electronic device according to any one of claims 8 to 10, characterized in that: The throughput rate is obtained through a throughput rate determination model; The throughput determination model is: Among them, R n represents the throughput rate, C C represents the total number of bytes correctly transmitted during data transmission between the base station and the target terminal among the terminals accessing the base station, C n Indicates the total number of bytes to be transmitted by the base station, M n represents the total number of initial resource blocks allocated to the base station, and M represents the total number of preset resource blocks; The initial time-frequency resource allocation result also includes the M n And the M.

12. The electronic device according to any one of claims 7 to 10, characterized in that: The time-frequency resource allocation model is a model obtained by training a neural network based on multiple groups of sample trajectories and a target loss function; the multiple groups of sample trajectories are trajectories obtained by multiple rounds of communication between the neural network and each sample base station; The objective loss function is: U(θ)=∑ τ P(τ|θ)R(τ); Wherein, U(θ) represents the function value of the target loss function, θ represents the model parameter of the neural network, τ represents the τth sample trajectory in a set of sample trajectories, P(τ|θ) represents the occurrence probability of the τth sample trajectory, and R(τ) represents the reward value of the τth sample trajectory; in, Among them, T represents the number of steps of the τth sample trajectory, R t represents the sum of the throughput rates of the sample base stations obtained in the tth step of the τth sample trajectory.

13. A time-frequency resource allocation device, characterized in that: include: A receiving module, used for receiving initial status information of multiple base stations; The initial state information includes: state information of each terminal accessing the base station, request information of each terminal and resource state information of the base station; A determination module, configured to input a time-frequency resource allocation model based on the initial state information of the multiple base stations to obtain initial time-frequency resource allocation results of the multiple base stations; the initial time-frequency resource allocation results include an initial resource block allocated to a target terminal, and the target terminal is a terminal having a time-frequency resource demand among the terminals accessing the base station; The determination module is further configured to adjust the initial time-frequency resource allocation results of the multiple base stations based on the resource allocation adjustment rule to obtain target time-frequency resource allocation results of the multiple base stations, wherein the target time-frequency resource allocation results include a target resource block allocated to the target terminal; The sending module is used to send the corresponding target time-frequency resource allocation results to the multiple base stations, and the target time-frequency resource allocation results are used by the base station to schedule the target terminal based on the target resource block allocated to the target terminal.

14. A processor-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the time-frequency resource allocation method according to any one of claims 1 to 6 is implemented.

Images