Power system short-term load forecasting based on PSO clustering analysis and Elman neural network

  • Authors:

  • Song Yufei;Jiang Chuanwen

  • Affiliations:

  • Department of Electrical Engineering, Shanghai Jiaotong University, P. R. China;Department of Electrical Engineering, Shanghai Jiaotong University, P. R. China

  • Venue:
  • SMO'05 Proceedings of the 5th WSEAS international conference on Simulation, modelling and optimization
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper proposes a new approach based on particle swarm optimization (PSO) clustering analysis for short-term load forecasting (STLF). PSO is an intelligent evolutionary computation technique, it is a population-based stochastic search process, used to group historical load and weather data to each cluster which have highest similar characteristic data point. A forecasting model for each day in 24 points is established though selecting the data of learning samples by PSO clustering and using Elman neural network. This method gives sufficient play to the ability of processing non-linear problems by artificial neural network and intelligent evolutionary computation technique. The simulation results of daily and weekly loads forecasting for actual power system show that the proposed forecasting model can effectively improve the accuracy of short-term load forecasting.