CN-121997777-A - Particle swarm optimization-based power distribution design optimization method and system for power transmission network

CN121997777ACN 121997777 ACN121997777 ACN 121997777ACN-121997777-A

Abstract

The application relates to the technical field of electric digital data processing, in particular to a particle swarm algorithm-based power distribution design optimization method and system of a power transmission network, wherein the method comprises the steps of obtaining simulation time sequence power of each node in the operation process of the power transmission network under a simulation working condition, and synchronously obtaining frequency deviation of each node in the power transmission network; the method comprises the steps of constructing a working condition situation vector based on simulation time sequence power and frequency deviation, wherein the working condition situation vector at least comprises power grid state deviation degree representing overall simulation time sequence power fluctuation amplitude of a power transmission network and power trend characteristics representing overall simulation time sequence power trend of the power transmission network, retrieving the working condition situation vector closest to the current working condition situation vector from a pre-stored optimal solution knowledge base and an optimal power distribution scheme corresponding to the working condition situation vector, and optimizing the power of the power transmission network by using a particle swarm optimization algorithm, wherein the optimal power distribution scheme is used as the center of an initial particle swarm. The application can improve the running stability of the power transmission network.

Inventors

MIAO WEI
HUANG ZHIJIAN
HE ZHICHAO
KONG DAN
LIU JIANQUAN
ZHANG XIAODONG
CHEN WENZAO
ZHU GUOFU
YUAN QIUHUI

Assignees

江阴长仪集团有限公司

Dates

Publication Date: 20260508
Application Date: 20260409

Claims (10)

1. The power distribution design optimization method of the power transmission network based on the particle swarm optimization is characterized by obtaining the simulation time sequence power of each node in the operation process of the power transmission network under the simulation working condition and synchronously obtaining the frequency deviation of each node in the power transmission network; Constructing a working condition situation vector based on the simulation time sequence power and the frequency deviation, wherein the working condition situation vector at least comprises a power grid state deviation degree representing the overall simulation time sequence power fluctuation range of the power transmission network and a power trend characteristic representing the overall simulation time sequence power trend of the power transmission network; And retrieving a working condition situation vector closest to the current working condition situation vector and a corresponding optimal power distribution scheme from a pre-stored optimal solution knowledge base, and optimizing the power of the power transmission network by using a particle swarm optimization algorithm, wherein the optimal power distribution scheme is used as the center of an initial particle swarm.
2. The method for optimizing power distribution design of a power transmission network based on a particle swarm optimization according to claim 1, wherein the step of calculating the power transmission network state deviation degree comprises the steps of calculating local fluctuation intensity of each node in the power transmission network, taking an average value of the local fluctuation intensity of each node as a global fluctuation index, and taking a product of the global fluctuation index and a normalized value of frequency deviation as the power transmission network state deviation degree.
3. The optimization method of power distribution design of a power transmission network based on a particle swarm optimization according to claim 2, wherein the local fluctuation intensity is positively correlated with a fluctuation range of simulation time sequence power of a corresponding node and an importance coefficient of the node, the importance coefficient is directly proportional to electrical connectivity of the corresponding node and global topology centrality, wherein the electrical connectivity is a sum of admittances of all branches connected with the node, and the global topology centrality is an inverse of an average electrical distance from the node to all other nodes in the power transmission network.
4. The power distribution design optimization method for the power transmission network based on the particle swarm optimization is characterized in that the power trend feature acquisition method comprises the steps of calculating the sum of absolute values of simulation time sequence power differences of adjacent sampling points in a preset time window of any node in the power transmission network to obtain a local trend index, and taking the average value of the local trend indexes of all the nodes as the power trend feature.
5. The grid power distribution design optimization method based on the particle swarm optimization is characterized in that the construction method of the optimal solution knowledge base comprises the steps of conducting grid division in a characteristic space of a working condition situation vector to generate an initial grid point set, conducting particle swarm optimization on each grid point, saving the obtained working condition situation vector and an optimal power distribution scheme to obtain an initial knowledge base, obtaining the working condition situation vector in the historical operation process of the power transmission network, adjusting grid division intervals in the characteristic space according to the distribution of the historical working condition situation vector, conducting particle swarm optimization on the newly generated grid points to calculate an optimal power distribution scheme of the newly generated grid points, and saving the newly generated grid points to obtain the optimal solution knowledge base.
6. The grid power distribution design optimization method based on the particle swarm optimization method according to claim 1, wherein the step of searching the working condition situation vector closest to the current working condition situation vector and the optimal power distribution scheme corresponding to the working condition situation vector from a pre-stored optimal solution knowledge base comprises the step of calculating Euclidean distances between the current working condition situation vector and all historical working condition situation vectors in the knowledge base.
7. The method for optimizing power distribution design of a power transmission network based on a particle swarm optimization is characterized by further comprising the steps of obtaining an adaptability value of an optimal power distribution scheme obtained through current design simulation operation, and storing the current working condition situation vector and the optimal power distribution scheme corresponding to the current working condition situation vector into an optimal solution knowledge base when the adaptability value is superior to a preset effective threshold and the minimum distance between the current working condition situation vector and all working condition situation vectors in the knowledge base is greater than a preset threshold.
8. The method for optimizing power distribution design of a power transmission network based on a particle swarm optimization according to claim 1, further comprising the steps of forcibly terminating an iterative process of the particle swarm optimization within a preset response time, and outputting the optimal power distribution scheme.
9. The grid power distribution design optimization method based on the particle swarm optimization is characterized in that grid division intervals in a feature space are adjusted according to distribution of historical working condition situation vectors, the grid division intervals comprise the steps of clustering the historical working condition situation vectors to obtain a plurality of clusters, and for an area where any cluster is located, adjusting the grid division intervals of the corresponding area according to intra-cluster sample density of the cluster, wherein the intra-cluster sample density is inversely related to the grid division intervals.
10. A particle swarm algorithm based power distribution design optimization system, comprising a processor and a memory, the memory storing computer program instructions that when executed by the processor implement the particle swarm algorithm based power distribution design optimization method according to any of claims 1-9.

Description

Particle swarm optimization-based power distribution design optimization method and system for power transmission network Technical Field The application relates to the technical field of electric digital data processing, in particular to a power distribution design optimization method and system of a power transmission network based on a particle swarm algorithm. Background Along with the transformation of global energy structures, large-scale power transmission networks rapidly develop, and a direct current power optimization technology becomes a core link for guaranteeing stable operation of a power system after the power transmission network is built in a design stage. The Particle Swarm Optimization (PSO) is used as a classical swarm intelligent algorithm, and is applied to the fields of power distribution scheme Optimization design and simulation verification of power system network nodes due to the characteristics of strong global searching capability and easiness in implementation. In the current direct current power transmission network design and simulation verification work, a large-scale power transmission network is generally connected with high-proportion intermittent renewable energy sources such as photovoltaic power, wind power and the like. This complicates the system operating scenario that the design phase needs to cover and presents a high degree of dynamics. For example, in the design stage, simulation verification is required to verify that the sudden shielding of a cloud layer leads to the reduction of the output of a photovoltaic power station, or when a wind power plant is stopped accidentally due to sudden faults and other emergency working conditions, the power transmission network can face severe power fluctuation and frequency deviation. Under the working condition, the control system is required to rapidly complete the dynamic allocation of the whole network power in a short time (usually 200ms in a golden response window period) so as to maintain the stability of node voltage and power, and the dynamic allocation is a core working condition suitability requirement which is required to be verified in the design stage of the power transmission network. However, the existing technical means have certain limitations in coping with the multi-condition simulation optimization complex scene in the above-mentioned direct current transmission network design stage. In design simulation optimization under emergency situations that renewable energy source output or system load is suddenly changed, when a traditional particle swarm optimization algorithm is used for designing and simulating and optimizing a power distribution scheme, a large amount of time is wasted on invalid searching due to blindness of initial distribution of the algorithm and lack of self-adaptive mechanisms aiming at actual working conditions, so that the output of the power optimization scheme is seriously delayed from the short-time response requirement of a power system for 200ms, and the efficiency requirement of multi-working-condition quick simulation iteration in the design stage of a power transmission network cannot be met. The decision delay in the emergency scene cannot timely stabilize the severe oscillation of the power grid, is extremely easy to trigger the chain reaction of the power unbalance of the whole power grid in reality, and even triggers the misoperation of the relay protection device, so that the equipment safety and stable operation of the whole large-scale direct current network are directly threatened, and the reliability of the finally designed power transmission grid scheme cannot be ensured. Disclosure of Invention In order to improve timeliness of distribution optimization response and improve running stability of equipment in a power transmission network, the application provides a power transmission network power distribution design optimization method and system based on a particle swarm algorithm. In a first aspect, the present application provides a method for optimizing power distribution design of a power transmission network based on a particle swarm algorithm, which adopts the following technical scheme: The power distribution design optimization method of the power transmission network based on the particle swarm optimization comprises the steps of obtaining simulation time sequence power of each node in the operation process of the power transmission network under a simulation working condition, and synchronously obtaining frequency deviation of each node in the power transmission network; Constructing a working condition situation vector based on the simulation time sequence power and the frequency deviation, wherein the working condition situation vector at least comprises a power grid state deviation degree representing the overall simulation time sequence power fluctuation range of the power transmission network and a power trend characteristic representing the overall