Title: A multi-objective optimisation configuration method for photovoltaic access microgrid energy storage capacity based on improved genetic algorithm

Authors: Lide Zhou; Zheng Liu; Siyan Pang; Jingyi Wei

Addresses: Dongguan Power Supply Bureau of Guangdong Power Grid Co., Ltd., Dongguan, China; Southern Power Grid, Dongguan, 523000, China ' Dongguan Power Supply Bureau of Guangdong Power Grid Co., Ltd., Dongguan, China; Southern Power Grid, Dongguan, 523000, China ' Dongguan Power Supply Bureau of Guangdong Power Grid Co., Ltd., Dongguan, China; Southern Power Grid, Dongguan, 523000, China ' Dongguan Power Supply Bureau of Guangdong Power Grid Co., Ltd., Dongguan, China; Southern Power Grid, Dongguan, 523000, China

Abstract: This study proposes to improve the genetic algorithm and based on the improved genetic algorithm, to complete the optimisation method design of photovoltaic microgrid energy storage configuration. Considering the goal of jointly establishing a new type of energy microgrid, a mathematical model of energy storage is established. Then, determine the configuration constraints of multiple micro energy grid energy storage stations, including battery operation constraints and micro energy grid operation constraints. In the final stage, the genetic algorithm was enhanced using extreme learning machine (ELM), and this improved algorithm was then utilised to address the design model mentioned earlier. The design simulation experiment proves the advanced nature of the proposed method. The experimental results show that after applying the proposed method, the energy efficiency can reach 99.21%, the power balance is only 0.01, and the voltage stability is 0.95, which can guarantee the stability of photovoltaic micro-grid operation to the maximum extent and meet its energy storage needs.

Keywords: genetic operators; extreme learning machine; ELM; genetic operators; configuration constraints; multi-objective optimisation.

DOI: 10.1504/IJETP.2025.144306

International Journal of Energy Technology and Policy, 2025 Vol.20 No.1/2, pp.66 - 79

Received: 01 Mar 2024
Accepted: 08 Jul 2024
Published online: 05 Feb 2025 *

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