基于贝叶斯理论输入特征选取的在线学习支撑向量机的短期负荷预测.pdfVIP

25 卷 13 期 中 国 电 机 工 程 学 报 Vol.25 No.13 Jul. 2005 2005 年7 月 Proceedings of the CSEE 2005 Chin.Soc.for Elec.Eng. 文章编号：0258-8013 (2005) 13-0008-06 中图分类号：TM711 文献标识码：A 学科分类号：47040 基于贝叶斯理论和在线学习支持 向量机的短期负荷预测 赵登福，庞文晨，张讲社，王锡凡 （西安交通大学，陕西省西安市710049 ） BASED ON BAYESIAN THEORY AND ONLINE LEARNING SVM FOR SHORT TERM LOAD FORECASTING ZHAO Deng-fu, PANG Wen-chen, ZHANG Jiang-she, WANG Xi-fan (Xi’an Jiaotong University, Xi’an 710049, Shaanxi Province, China) ABSTRACT: The paper adopts Bayesian theory to input 关键词：电力系统；短期负荷预测；支持向量机；贝叶斯理 feature selection for short term load forecasting (STLF). It 论；特征选取；在线学习 makes use of the information from both samples and prior knowledge. In this way, not only can the over-fitting problem 1 引言 be effectively solved but also the model of forecasting can be simplified. Simultaneously, an online learning support vector 短期负荷预测(STLF)是一项重要的决策支持技 machine (SVM) method for short-term load forecasting model 术，是电力系统调度和管理部门制订负荷分配以及 is presented here. The method comprises incremental algorithm 开停机计划的主要依据。随着电力改革的深入和电 and decrement algorithm, which efficiently updates a trained 力市场的逐步建立，电网的安全运行和经济运行， regression function whenever a sample is added to or removed [1] 发电公司的竞 上网 及电力公司或供电公司的购 from the training set. So it is favorable for applications like online learning or leave-one-out cross-validation. The practical 电计划的制定等，都与STLF 有着密切的关系。