基于独立分量分析—支持向量机的系统边际价格预测模型.pdfVIP

25 卷 17 期 中 国 电 机 工 程 学 报 Vol.25 No.17 Sep. 2005 2005 年9 月 Proceedings of the CSEE 2005 Chin.Soc.for Elec.Eng. 文章编号：0258-8013 (2005) 17-0066-06 中图分类号：TM46 文献标识码：A 学科分类号：47040 电力市场下系统边际价格混合预测模型的新研究 华，谢 莉，张粒子，申景娜 （华北电力大学电气工程学院，北京市昌平区 102206 ） STUDY ON HYBRID MODEL FOR SYSTEM MARGINAL PRICE FORECASTING IN ELECTRICITY MARKET ZHENG Hua, XIE Li, ZHANG Li-zi, SHEN Jing-na (Electric Engineering College of North China Electric Power University, Changping District, Beijing 102206, China) ABSTRACT: Price forecasting has been a useful tool for 该模型充分发挥独立分量分析的特征提取优势，增强了支持 market participants to provide important economic information. 向量机模型输入样本的表征能力，使电价预测模型更加准 But the complicated influence factors of the price make the 确。美国加州现货电能量市场的实例数据验证了该文所建模 forecasting more difficult. So a novel hybrid model for 型的有效性。 forecasting system marginal price (SMP) in spot market is 关键词 电力市场；系统边际价格；独立分量分析；特征提 presented, which integrates independent component analysis 取；支持向量机 with support vector machine, called ICA-SVM. First, this paper designs the ICA self-adapting iteration method by constructing 1 引言 hybrid optimal transform function, and a new de-redundancy function based on higher-order statistic information. Then the 在电力市场交易中，交易中心将发电商的功率 feature extraction of SMP influencing factors is realized, which 段按报价由低到高排序，形成不同供电水平下的系 produces SMP effective influencing factor sample set. After the 统边际成本曲