Distribution network planning method based on hybrid genetic algorithm

Yunfeng Shao, Yuanming Sun, Yajing Wang, Zhongjing Ma*, Yongqiang Liu, Yang Zhao

*Corresponding author for this work

Research output: Contribution to journalConference articlepeer-review

1 Citation (Scopus)

Abstract

Facing the discrete, multi-constrained, non-linear, multi-objective combination optimization problem of distribution network grid planning, some traditional heuristic algorithms such as genetic algorithms sometimes fall into local optimum. This paper proposes a distribution network planning method based on hybrid genetic algorithm. The algorithm consists of two stages. In the first stage, the genetic algorithm is used to obtain the initial planning scheme. In the second stage, the initial planning scheme obtained in the first stage is used to form the planned route set. The improved minimum spanning tree method is used to obtain the final planning scheme. In order to make full use of the effective information obtained in the first stage, this paper proposes a transmission line classification method to assess the importance of the transmission line, provide guidance for the second stage, and improve the search efficiency and accuracy. The algorithm solves the problem that heuristic algorithms such as genetic algorithm often fall into local optimization to a certain extent, and the problem of slow convergence when the minimum spanning tree algorithm has a large number of lines to be planned.

Original languageEnglish
Article number012032
JournalJournal of Physics: Conference Series
Volume1673
Issue number1
DOIs
Publication statusPublished - 23 Nov 2020
Event6th Annual International Conference on Computer Science and Applications, CSA 2020 - Guangzhou, Virtual, China
Duration: 25 Sept 202027 Sept 2020

Fingerprint

Dive into the research topics of 'Distribution network planning method based on hybrid genetic algorithm'. Together they form a unique fingerprint.

Cite this