Particle Swarm Optimization Based SVM Model for Short-Term Load Forecasting

摘要：

In this paper, principle component analysis based support vector machine forecasting model with particle swarm optimization is proposed. Main factors are first selected from so many load influential factors by principle component analysis theory in order to simplify the input neurons for neural structure. And then, particle swarm optimization is applied to train support vector machine to solve quadratic programming problem which is an effective method with better convergence and stability. Last, the presented model is tested for a certain practical electric market. The results of experiment showed that the forecasting model with particle swarm optimization technique training the support vector machine is more accurate and also faster. And the forecasting accuracy is satisfactory.

作者: Wei Sun Jianchang Lu Ming Meng

作者单位: Department of Economics and Management , North China Electric Power University, Baioding, Hebei, 071003,P.R.China

会议类型: 国际会议

会议名称: Fourth International Conference on Impulsive and Hybrid Dynamical Systems(ICIHDS 2007)(第四届国际脉冲和混合动力系统学术会议)

会议地点: 南宁

会议语种:英文

在线出版日期: 2007-07-20（万方平台首次上网日期，不代表论文的发表时间）