支持向量机在短期负荷预测中的应用概况  

Application Profiles of Support Vector Machine in Short-term Load Forecasting

作　　者：王奔[1] 冷北雪[1] 张喜海[1] 单翀皞[1] 从振[1] 

机构地区：[1]西南交通大学电气工程学院,成都610031

出　　处：《电力系统及其自动化学报》2011年第4期115-121,共7页Proceedings of the CSU-EPSA

摘　　要：全面总结了支持向量机(SVM)在短期负荷预测中的应用概况,并从SVM的原理出发,对比人工神经网络方法,从本质上阐述了SVM方法在短期负荷预测中应用的优越性。同时针对SVM在应用中存在的问题,包括数据预处理、核函数构造及选取和参数优化的方法,做出分析,并归纳了现行的解决方法。从SVM算法用于负荷预测的机理及提高预测精度和速度的角度,对于一系列SVM的改进方法,全面地进行了归纳,并提出需进一步探讨的关键问题。最后对基于SVM的短期负荷预测所需注意的关键问题做出总结,并提出建议。The application profiles of support vector machine（SVM） in the field of short-term load forecasting （STLF） is summarized in the paper. Based on the principle of SVM and compared with artificial neural net work,the superiority of the SVM method in the application of STLF is elaborated. Some problems about the application of SVM,including data pre-processing, the consturcting and current solutions are provided respectively. For a series of SVM-based improvements and some mixed forecasting methods consisting of SVM with other algorithms,a comprehensive summary is given, from the perpective of the mechanism about SVM algorithm being applied to load forecasting, and the elevation of prediction accuracy and speed. Meantime, some key issues needing further discussion are put forward. Finally, some key issues about SVM-based STLF are summarized and some recommendations are given.

关 键 词：支持向量机 人工神经网络 短期负荷预测 数据预处理 核函数 参数优化 混合预测方法 

分 类 号：TM71[电气工程—电力系统及自动化]