Title: A multi-objective optimisation of relay protection settings in distribution networks based on improved grey wolf algorithm

Authors: Haicheng Zhou; Hengchu Shi; Qiutao Chen; Penghui Yang; Xi Zhang

Addresses: Yunnan Pu'er Power Supply Bureau of Southern Power Grid, Yunnan, Pu'er, 655000, China ' Yunnan Electric Power Dispatching and Controlling Center, Yunnan, Kunming, 650011, China ' Yunnan Pu'er Power Supply Bureau of Southern Power Grid, Yunnan, Pu'er, 655000, China ' Yunnan Pu'er Power Supply Bureau of Southern Power Grid, Yunnan, Pu'er, 655000, China ' Yunnan Pu'er Power Supply Bureau of Southern Power Grid, Yunnan, Pu'er, 655000, China

Abstract: In order to overcome the problems of high data mining accuracy, poor effectiveness, and long relay protection action time in traditional methods, a multi-objective optimisation method of relay protection settings in distribution networks based on improved grey wolf algorithm is proposed. Random forest algorithm is used for mining relay protection data in distribution networks. Taking the relay protection settings as the parameters to be optimised, a multi-objective optimisation function for relay protection settings is constructed using parameters such as relay protection action time, transmission line weight coefficient, and weight factors of vulnerability and sensitivity constraints. The improved grey wolf algorithm is used to solve the objective function and obtain relevant results. According to the analysis of relevant test results, the maximum data mining accuracy of the proposed method is 98.75%, good optimisation effect, and a maximum relay protection action time of 0.87 s.

Keywords: improved grey wolf algorithm; distribution network; relay protection settings; multi-objective optimisation; random forest algorithms; objective function.

DOI: 10.1504/IJETP.2024.141387

International Journal of Energy Technology and Policy, 2024 Vol.19 No.3/4, pp.302 - 320

Received: 30 Nov 2023
Accepted: 28 Feb 2024
Published online: 10 Sep 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article