Cuckoo search algorithm-based SVM (Support Vector Machine) power distribution network topology identification method

Abstract

The invention discloses a cuckoo search algorithm-based SVM (Support Vector Machine) power distribution network topology identification method, which comprises the following steps of: acquiring section voltage amplitude measurement data of various load levels of observation nodes under different topological structures and corresponding topological labels by using an SCADA (Supervisory Control and Data Acquisition) system, and carrying out standardized preprocessing to obtain a training data set; performing training learning on the support vector machine according to the training data set, and performing search analysis on the initial penalty factor C and the kernel function parameter through a cuckoo search algorithm to respectively obtain optimal values of the initial penalty factor C and the kernel function parameter; determining a power distribution network topology identification model of the support vector machine optimized based on the cuckoo search algorithm; acquiring section voltage amplitude measurement data of the observation node from the monitoring node, and performing standardized preprocessing; and analyzing section voltage amplitude measurement data after observation node preprocessing by using the obtained power distribution network topology identification model, and determining a circuit topology structure of the node. Compared with the traditional method, the method provided by the invention has great superiority.

Description

technical field [0001] The invention relates to the field of distribution network topology identification, in particular to an SVM distribution network topology identification method based on a cuckoo search algorithm. Background technique [0002] The task of power grid topology identification is to transform the physical model described by nodes into the mathematical model described by busbars, and convert the original physical nodes into topological nodes considering the switch state for the change of given switch information. [0003] The power grid is divided into transmission network and distribution network. The data acquisition and monitoring configuration of the transmission network has been quite complete. Dispatchers can easily obtain the topology of the transmission network, and can also identify topology errors through state estimation and other methods. With the advancement of distribution network intelligence, the number of distributed power sources in the di...

AI Technical Summary

Problems solved by technology

These methods avoid the problem that the voltage phase angle data is difficult to obtain, but the solution speed is slow and the search efficiency is low

Images