CN-119110414-B - Wireless sensor network resource allocation method and device and electronic equipment

CN119110414BCN 119110414 BCN119110414 BCN 119110414BCN-119110414-B

Abstract

The invention discloses a wireless sensor network resource allocation method and device and electronic equipment. The method comprises the steps of obtaining position information corresponding to a plurality of terminals in a wireless sensor network, determining data transmission rates between the plurality of terminals and corresponding remote radio units, obtaining an initial resource allocation strategy of the wireless sensor network, and optimizing the initial resource allocation strategy to obtain a target resource allocation strategy of the wireless sensor network based on the position information corresponding to the plurality of terminals and the data transmission rates between the plurality of terminals and the corresponding remote radio units, wherein the maximum total throughput of a system in the wireless sensor network is used as an optimization target. The invention solves the technical problems of low network resource allocation efficiency and low accuracy in the wireless sensor network resource allocation method in the related technology.

Inventors

GUO TIAN
QI QING
LI GUANG
MA XIANWEI
LI KEXIN
WU MENGHAN

Assignees

国网北京市电力公司
国家电网有限公司

Dates

Publication Date: 20260508
Application Date: 20240815

Claims (7)

1. The wireless sensor network resource allocation method is characterized by comprising the following steps: acquiring position information respectively corresponding to a plurality of terminals included in a wireless sensor network; Determining data transmission rates between the terminals and the corresponding remote radio units respectively; Acquiring an initial resource allocation strategy of the wireless sensor network, wherein the initial resource allocation strategy is used for indicating deployment positions and initial bandwidth resource allocation strategies respectively corresponding to a plurality of remote radio units included in the wireless sensor network; Optimizing the initial resource allocation strategy by taking the maximum total throughput of a system in the wireless sensor network as an optimization target to obtain a target resource allocation strategy of the wireless sensor network based on position information corresponding to the terminals and data transmission rates between the terminals and the corresponding remote radio units, constructing a state space based on candidate resource allocation strategies, constructing a reward function based on the total throughput of the system, optimizing parameters of the initial resource allocation model by adopting a depth deterministic strategy gradient algorithm based on the state space and the maximum function value of the reward function as targets under the conditions that the initial resource allocation model comprises a strategy network, a comment home network, a target strategy network and the target comment home network, obtaining a motion value based on a first estimated motion function, obtaining a motion value, an estimated motion value, and obtaining a motion value, and a second estimated motion value based on the estimated motion function, and the estimated motion value based on the estimated motion value and the estimated motion value, obtaining second loss, carrying out parameter optimization on the strategy network, the evaluator network, the target strategy network and the target evaluator network based on the first loss and the second loss, repeatedly executing the operations until a preset termination condition is reached, constructing the target resource allocation model based on the strategy network after parameter updating, the evaluator network after parameter updating and the target evaluator network after parameter updating which are obtained when the preset termination condition is reached, and obtaining the target resource allocation strategy by adopting the target resource allocation model.
2. The method of claim 1, wherein the deriving a second loss based on the second action value function estimate comprises: Obtaining a target action value function based on the reward function, the second action and the second action value function estimated value; And obtaining the second loss based on the mean square error between the target action value function and the second action value function estimated value.
3. The method according to claim 1, wherein the performing parameter optimization on the initial resource allocation model based on the state space and the action space with the function value of the reward function being the maximum as a target, to obtain a target resource allocation model includes: determining constraint conditions, wherein the constraint conditions at least comprise bandwidth resource allocation constraint, data transmission power constraint and data transmission rate constraint: and carrying out parameter optimization on an initial resource allocation model by taking the maximum function value of the reward function as a target based on the state space, the action space and the constraint condition to obtain the target resource allocation model.
4. The method of claim 3, wherein the step of, The bandwidth resource allocation constraint is used for indicating that the total amount of bandwidth resources allocated by the plurality of remote radio units to the corresponding terminal is smaller than or equal to a preset resource amount; The data transmission power constraint is used for indicating that the data transmission power corresponding to any one of the plurality of terminals is within a preset transmission power range; The data transmission rate constraint is used for indicating that the data transmission rate between any one of the plurality of terminals and the corresponding remote radio unit is smaller than a predetermined transmission rate.
5. The method of claim 4, wherein the data transmission rate constraint is obtained by: ; Wherein, the Representing the preset transmission rate corresponding to any terminal; representing bandwidth resources allocated by any remote radio unit to any terminal; Representing the data transmission power of the data transmitted by any terminal to any remote radio unit; Indicating channel gain between any remote radio unit and any terminal; representing a preset noise power.
6. A wireless sensor network resource allocation apparatus, comprising: the position acquisition module is used for acquiring position information corresponding to a plurality of terminals in the wireless sensor network respectively; The transmission rate determining module is used for determining data transmission rates between the plurality of terminals and the corresponding remote radio units respectively; An initial policy determining module, configured to obtain an initial resource allocation policy of the wireless sensor network, where the initial resource allocation policy is used to indicate deployment positions and initial bandwidth resource allocation policies that respectively correspond to a plurality of remote radio units included in the wireless sensor network; The policy optimization module is configured to optimize the initial resource allocation policy with a maximum system total throughput in the wireless sensor network as an optimization target based on position information corresponding to the plurality of terminals and data transmission rates between the plurality of terminals and corresponding remote radio units, respectively, to obtain a target resource allocation policy of the wireless sensor network, and the policy optimization module includes constructing a state space based on position information corresponding to the plurality of terminals and data transmission rates between the plurality of terminals and corresponding remote radio units, respectively, constructing an action space based on a plurality of candidate resource allocation policies, constructing a reward function based on the system total throughput, optimizing parameters of the initial resource allocation model based on a depth deterministic policy gradient algorithm based on the state space and the action space with a maximum function value of the reward function as a target in a case that the initial resource allocation model includes a policy network, a comment home network, a target policy network and a target comment home network, obtaining an estimated action value based on a first estimated action function, obtaining an estimated action value from the first estimated action function, obtaining an estimated action value based on the first estimated action function, and a second estimated action value based on the first estimated action function estimated action value and a second estimated action value based on the first estimated action value and a second estimated action value, obtaining second loss, carrying out parameter optimization on the strategy network, the evaluator network, the target strategy network and the target evaluator network based on the first loss and the second loss, repeatedly executing the operations until a preset termination condition is reached, constructing the target resource allocation model based on the strategy network after parameter updating, the evaluator network after parameter updating and the target evaluator network after parameter updating which are obtained when the preset termination condition is reached, and obtaining the target resource allocation strategy by adopting the target resource allocation model.
7. An electronic device comprising one or more processors and a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the wireless sensor network resource allocation method of any of claims 1-5.

Description

Wireless sensor network resource allocation method and device and electronic equipment Technical Field The invention relates to the field of artificial intelligence, in particular to a wireless sensor network resource allocation method and device and electronic equipment. Background In recent years, the construction of the electric power Internet of things is deep, the number of wired channels is continuously increased, and the monitoring requirement on the wired channels is increasingly urgent. There is a strong need for a low cost, efficient digital operation and maintenance approach to support this need. Deploying a low cost wireless sensor network (Wireless Sensor Network, WSN) system coverage monitoring sensor is one of the important ways to implement channel communication systems in the related art. However, in the related art, no mature resource allocation solution suitable for the wireless sensor network of the wired channel exists, and the determination of the resource allocation strategy of the wireless sensor network is mainly performed manually, so that the method has strong subjectivity and also has the problems of low resource allocation efficiency, poor accuracy and the like. In view of the above problems, no effective solution has been proposed at present. Disclosure of Invention The embodiment of the invention provides a wireless sensor network resource allocation method, a wireless sensor network resource allocation device and electronic equipment, which are used for at least solving the technical problems of low network resource allocation efficiency and low accuracy in the wireless sensor network resource allocation method in the related technology. According to one aspect of the embodiment of the invention, a wireless sensor network resource allocation method is provided, which comprises the steps of obtaining position information respectively corresponding to a plurality of terminals included in a wireless sensor network, determining data transmission rates between the plurality of terminals and corresponding remote radio units, obtaining an initial resource allocation strategy of the wireless sensor network, wherein the initial resource allocation strategy is used for indicating deployment positions and initial bandwidth resource allocation strategies respectively corresponding to the plurality of remote radio units included in the wireless sensor network, and optimizing the initial resource allocation strategy to obtain a target resource allocation strategy of the wireless sensor network by taking the total throughput of a system in the wireless sensor network as an optimization target at maximum based on the position information respectively corresponding to the plurality of terminals and the data transmission rates between the plurality of terminals and the corresponding remote radio units. According to another aspect of the embodiment of the invention, a wireless sensor network resource allocation device is provided, which comprises a position acquisition module, a transmission rate determination module, an initial strategy determination module and a strategy optimization module, wherein the position acquisition module is used for acquiring position information respectively corresponding to a plurality of terminals in a wireless sensor network, the transmission rate determination module is used for determining data transmission rates between the plurality of terminals and corresponding remote radio units, the initial strategy determination module is used for acquiring an initial resource allocation strategy of the wireless sensor network, the initial resource allocation strategy is used for indicating deployment positions and initial bandwidth resource allocation strategies respectively corresponding to the plurality of remote radio units in the wireless sensor network, and the strategy optimization module is used for optimizing the initial resource allocation strategy to obtain a target resource allocation strategy of the wireless sensor network based on the position information respectively corresponding to the plurality of terminals and the data transmission rates between the plurality of terminals and the corresponding remote radio units by taking the total throughput of a system in the wireless sensor network as an optimization target. According to another aspect of the embodiments of the present invention, there is further provided an electronic device, including one or more processors and a memory, where the memory is configured to store one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement any one of the wireless sensor network resource allocation methods. In the embodiment of the invention, the data transmission rate between the terminals and the corresponding remote radio units is determined by acquiring the position information respectively corresponding to the terminals in