Middle-long power load forecasting based on particle swarm optimization

Authors:
Dongxiao Niu;Jinchao Li;Jinying Li;Da Liu
Affiliations:
School of Business Administration, North China Electric Power University, Beijing, 102206, China;School of Business Administration, North China Electric Power University, Beijing, 102206, China;Department of Economic Administration, North China Electric Power University, Baoding, 071000, China;School of Business Administration, North China Electric Power University, Beijing, 102206, China
Venue:
Computers & Mathematics with Applications
Year:
2009

Citing 1
Cited 4

Data Mining: An Overview from a Database Perspective

IEEE Transactions on Knowledge and Data Engineering

Tax forecasting theory and model based on SVM optimized by PSO

Expert Systems with Applications: An International Journal
Cauchy mutation for decision-making variable of Gaussian particle swarm optimization applied to parameters selection of SVM

Expert Systems with Applications: An International Journal
Cauchy mutation based on objective variable of Gaussian particle swarm optimization for parameters selection of SVM

Expert Systems with Applications: An International Journal
Hybrid forecasting model based on support vector machine and particle swarm optimization with adaptive and Cauchy mutation

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	0.10

Visualization

Abstract

Middle-long forecasting of electric power load is crucial to electric investment, which is the guarantee of the healthy development of electric industry. In this paper, the particle swarm optimization (PSO) is used as a training algorithm to obtain the weights of the single forecasting method to form the combined forecasting method. Firstly, several forecasting methods are used to do middle-long power load forecasting. Then the upper forecasting methods are measured by several indices and the entropy method is used to form a comprehensive forecasting method evaluation index, following which the PSO is used to attain a combined forecasting method (PSOCF) with the best objective function value. We then obtain the final result by adding all the results of every single forecasting method. Taking actual load data of a power grid company in North China as a sample, the results show that PSOCF model improves the forecasting precision compared to the traditional models.