CN-121485154-B - Distribution network source load storage resource configuration method, device and medium based on artificial intelligence

CN121485154BCN 121485154 BCN121485154 BCN 121485154BCN-121485154-B

Abstract

The invention relates to a distribution network source load storage resource allocation method, a device and a medium based on artificial intelligence, wherein the method comprises the following steps of constructing a distribution network system model comprising battery energy storage, an electric vehicle charging station and a distributed power supply; and solving the configuration optimization model by combining a power flow calculation model with a real number coding genetic algorithm to obtain an optimal configuration scheme of the distributed resources. Compared with the prior art, the invention has the advantages of system stability, renewable energy consumption, power grid benefit and the like.

Inventors

SHI JIAWEI
JIANG XINGXIN
ZHANG LU
FANG HUANHUAN
Fan Daifu
XU YANYAN
XU CHENGCHENG
GAN LIN
JIANG BENJIAN

Assignees

国网上海市电力公司

Dates

Publication Date: 20260512
Application Date: 20251230

Claims (8)

1. The distribution network source load storage resource allocation method based on artificial intelligence is characterized by comprising the following steps of: constructing a power distribution network system model comprising battery energy storage, an electric vehicle charging station and a distributed power supply; Constructing a configuration optimization model of distributed resources taking minimized power loss of the power distribution network as an optimization target based on the model; Solving a configuration optimization model by adopting a tide calculation model and combining a real number coding genetic algorithm to obtain an optimal configuration scheme of distributed resources; solving a configuration optimization model by combining a power flow calculation model with a real number coding genetic algorithm, and obtaining an optimal configuration scheme of distributed resources comprises the following specific steps: construction of node admittance matrix for whole distribution system The matrix is formed by integrating the original admittance matrix Y of all circuit elements, and then the voltage of each node is solved iteratively through a tide calculation model; The voltage of each node is input into a configuration optimization model, and then a global optimal solution is obtained through a real number coding genetic algorithm to be used as an optimal configuration scheme; the voltage at node j is: In the formula, Is the current through the power converter; Is the voltage at node j.
2. The method for configuring power distribution network source load storage resources based on artificial intelligence according to claim 1, wherein the power distribution network system model comprises: Battery energy storage model, electric vehicle charging station model, and distributed power model.
3. The method for configuring the source load storage resources of the power distribution network based on artificial intelligence according to claim 1, wherein the configuration optimization model of the distributed resources is as follows: In the formula, Is a set of time periods; is the collection of elements in the system that produce power loss; is the equivalent resistance of the element; Is the current flowing through element l during time period t.
4. The method for configuring power distribution network source load storage resources based on artificial intelligence according to claim 1, wherein the constraint condition of the optimization model comprises: power balance, bus voltage limit, line current, distributed power source output range, distributed power source permeability limit, electric vehicle charging station capacity, battery energy storage system charge-discharge power and battery energy storage system state of charge.
5. The distribution network source load storage resource allocation method based on artificial intelligence according to claim 1, wherein the specific steps of obtaining a global optimal solution as an optimal allocation scheme through a real number coding genetic algorithm are as follows: (1) Initializing parameters, namely initializing the number of individuals of the population as ; (2) Decoding the numbers of individual nodes in the population into integers, inputting the voltage of the node j into an objective function, and calculating an objective function value; (3) Setting fitness: The fitness is as follows: In the formula, Is the ith individual; is an objective function value; Is a penalty base value; Is the deviation value of the d constraint; (4) Carrying out iterative solution based on the selection, crossing, variation and truncation processes of a genetic algorithm; (5) And (3) stopping the algorithm and outputting the optimal solution, namely ending the algorithm if a preset ending condition is met, otherwise, returning to the step (2), and finally outputting the global optimal solution.
6. The method for allocating power distribution network source load storage resources based on artificial intelligence according to claim 5, wherein the variation solution during variation is: In the formula, Respectively a lower bound and an upper bound of the decision variable; Is a random number uniformly distributed between [0,1], For the first decision variable s denotes a variable following the power profile.
7. An artificial intelligence based power distribution network source load storage resource allocation device, comprising a memory, a processor and a program stored in the memory, wherein the processor implements the method of any one of claims 1-6 when executing the program.
8. A storage medium having a program stored thereon, wherein the program, when executed, implements the method of any of claims 1-6.

Description

Distribution network source load storage resource configuration method, device and medium based on artificial intelligence Technical Field The invention relates to the technical field of power distribution network source load storage, in particular to a power distribution network source load storage resource allocation method, device and medium based on artificial intelligence. Background The battery energy storage system is used as a key technology for improving the reliability of a power grid, has remarkable potential in promoting the high-proportion renewable energy consumption, and can realize load regulation and control and optimize the electric energy quality. Meanwhile, the electric automobile is used as an important carrier for decarburization in the traffic field, and the large-scale application of the electric automobile brings new challenges to the operation of a power distribution network, wherein the plug-in electric automobile is required to be connected with the power grid to complete battery charging, and if ordered management is lacking, the stability problems of line overload, voltage fluctuation, peak-valley difference expansion and the like can be caused. In addition, the access scale of distributed power generation is continuously increased, renewable energy sources such as solar photovoltaic and wind energy are mainly used, and however, the intermittence, the fluctuation and the uncertainty of wind and light output can also cause the problem of system operation. Under the background, how to realize the collaborative optimization configuration of battery energy storage, electric vehicle charging stations and distributed power sources so as to reduce adverse effects and maximize the benefits of a power distribution system is particularly important. However, the existing power distribution network planning method lacks a systematic framework for three types of resources including battery energy storage, electric vehicle charging stations and distributed power sources, and is difficult to consider the system stability, renewable energy consumption and power grid benefits. Disclosure of Invention The invention aims to provide an artificial intelligence-based distribution network source load storage resource allocation method for considering system stability, renewable energy consumption and power grid benefits. The aim of the invention can be achieved by the following technical scheme: a distribution network source load storage resource allocation method based on artificial intelligence comprises the following steps: constructing a power distribution network system model comprising battery energy storage, an electric vehicle charging station and a distributed power supply; Constructing a configuration optimization model of distributed resources taking minimized power loss of the power distribution network as an optimization target based on the model; And solving the configuration optimization model by combining the tide calculation model with a real number coding genetic algorithm to obtain an optimal configuration scheme of the distributed resource. Further, the power distribution network system model includes: Battery energy storage model, electric vehicle charging station model, and distributed power model. Further, the configuration optimization model of the distributed resource is as follows: In the formula, Is a set of time periods; is the collection of elements in the system that produce power loss; is the equivalent resistance of the element; Is the current flowing through element l during time period t. Further, the constraints of the optimization model include: power balance, bus voltage limit, line current, distributed power source output range, distributed power source permeability limit, electric vehicle charging station capacity, battery energy storage system charge-discharge power and battery energy storage system state of charge. Further, the optimal configuration scheme of the distributed resources is obtained by adopting a power flow calculation model and combining a real number coding genetic algorithm to solve and configure an optimization model, and the method comprises the following specific steps of: construction of node admittance matrix for whole distribution system The matrix is formed by integrating the original admittance matrix Y of all circuit elements, and then the voltage of each node is solved iteratively through a tide calculation model; And the voltage of each node is input into a configuration optimization model, and then a global optimal solution is obtained through a real number coding genetic algorithm to be used as an optimal configuration scheme. Further, the voltage at node j is: In the formula, Is the current through the power converter; Is the voltage at node j. Further, the specific steps of obtaining the global optimal solution as the optimal configuration scheme through the real number coding genetic algorithm are as follows: (1) Initializing