面向大规模样本的核心向量回归电力负荷快速预测方法.pdfVIP

第30 卷 第28 期 中 国 电 机 工 程 学 报 Vol.30 No.28 Oct.5, 2010 2010 年10 月5 日 Proceedings of the CSEE ©2010 Chin.Soc.for Elec.Eng. 33 文章编号：0258-8013 (2010) 28-0033-06 中图分类号：TM 715 文献标志码：A 学科分类号：470·40 面向大规模样本的 核心向量回归电力负荷快速预测方法 1 2 李元诚 ，刘克文 (1．华北电力大学控制与计算机工程学院，北京市 昌平区 102206; 2．中国电力科学研究院自动化研究所，北京市 海淀区 100192) A Rapid Electric Load Forecasting Method Using Core Vector Regression for Large Scale Data Set 1 2 LI Yuancheng , LIU Kewen (1. School of Control and Computer Engineering, North China Electric Power University, Changping District, Beijing 102206, China; 2. Department of Power System Automation, China Electric Power Research Institute, Haidian District, Beijing 100192, China) ABSTRACT: This paper presents a new electric load regression ，SVR)方法更高的预测精度。 forecasting algorithm based on the core vector regression 关键词：负荷预测；大规模样本；核心向量回归；粒子群优化 (CVR) for large scale data set. Particle swarm optimization (PSO) is applied for determining the parameters of CVR, so we 0 引言 get a novel scheme named PSO-CVR. The load data is analyzed for finding factors that may have great influence on 随着电力系统数据采集与监控(supervisory load forecasting. We create several training sets in diffident size control and data acquisition，SCADA)技术的发展， and then use CVR to train them for observing whether more 采集的负荷数据越来越多，如何充分利用这些数据 accurate results could be made on a larger training data