Short-term power load forecasting based on BP neural network optimized by genetic algorithm

Conference: ICETIS 2022 - 7th International Conference on Electronic Technology and Information Science
01/21/2022 - 01/23/2022 at Harbin, China

Proceedings: ICETIS 2022

Pages: 4Language: englishTyp: PDF

Authors:
Xiong, Neng; Liang, Quan; Xiong, Neng; Yu, Wenze; Hong, Chuanbo; Wang, Hansong (School of Computer Science and Mathematics, Fujian University of Technology, Fujian Provincial Key Laboratory of Big Data Mining and Applications, Fuzhou, China)

Abstract:
Accurate short-term power load forecasting is of great significance to the safe operation of power systems. Aiming at the defects of traditional BP neural network that it is easy to fall into local optimization and low prediction accuracy, Proposed to optimize the BP neural network with genetic algorithm, To improve the initial weights and thresholds of the network, increase the convergence speed, And then establish the genetic algorithm to optimize the prediction model of the BP neural network. The model uses one input, output layer, double hidden layers, Analyze and forecast the power load data of a company. Experiment simulation through matlab platform, The results show that the BP neural network model optimized by genetic algorithm has higher prediction accuracy, better stability, and more practical value.