Title: Research on load prediction of back propagation neural networks based on genetic algorithms

Authors: Lei Yan; GuoXing Mu; Qibing Wang; Zhifang He; Yanfang Zhu

Addresses: State Grid Shanxi Electric Power Company of China, Taiyuan, Shanxi, 030000, China ' State Grid Shanxi Electric Power Company of China, Taiyuan, Shanxi, 030000, China ' State Grid Shanxi Electric Power Company of China, Taiyuan, Shanxi, 030000, China ' State Grid Shanxi Electric Power Company of China, Taiyuan, Shanxi, 030000, China ' State Grid Shanxi Electric Power Company of China, Taiyuan, Shanxi, 030000, China

Abstract: To address the problem that back propagation (BP) neural networks are prone to overfitting and falling into local optimality, resulting in low accuracy of electricity load forecasting, this paper proposes a method for electricity load forecasting based on an improved genetic algorithm (GA) and the BP neural network. Through modelling and analysis of load data, better root mean square error (RMSE) and mean absolute percentage error (MAPE) are obtained compared with the traditional BP neural networks, proving the method's superiority.

Keywords: electricity market; genetic algorithm; load prediction; BP neural network; local optimality; overfitting; electricity load forecasting.

DOI: 10.1504/IJHPSA.2023.139895

International Journal of High Performance Systems Architecture, 2023 Vol.11 No.4, pp.198 - 205

Received: 19 Nov 2022
Accepted: 17 Aug 2023
Published online: 09 Jul 2024 *

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