MEDIUM AND LONG-TERM FORECASTING USING PSO FUZZY N-SUPPORT VECTOR REGRESSION MACHINES ON CONTINUOUS SPACE

摘要：

Load forecasting is essential to the operation and plan of electric companies.To improve the accuracy of the load forecasting, a novel approach based PSO (particle swarm optimization) fuzzy v-Support vector machines is proposed in this paper for months electric load forecasting.PSO is used to optimize the parameters of the model.It considers the uncertain factors in load forecasting by fuzzy theory.The performance of the new model is evaluated with a typical region and compared with traditional support vector machines for regression.The experiment results demonstrate that the new method is more accurate than the traditional support vector regression.

关键词： Fuzzy Support vector regression Load forecasting Particle swarm optimization

作者: LU FANG-CHENG ZHANG YAN-JUN

作者单位: Hebei Provincial Key Laboratory of Power Transmission Equipment Security Defense,North China Electric Power University,Baoding 071003,China

会议类型: 国际会议

会议名称: 3rd International Conference on Mechanical and Electrical Technology(ICMET2011) (2011第三届机械与电气技术国际会议)

会议地点: 大连

会议语种:英文

页码: 323-327

在线出版日期: 2011-08-26（万方平台首次上网日期，不代表论文的发表时间）