基于蚁群优化算法的电力系统负荷序列的聚类分析.pdfVIP

25 卷 18 期 中 国 电 机 工 程 学 报 Vol.25 No.18 Sep.2005 2005 年9 月 Proceedings of the CSEE 2005 Chin.Soc.for Elec.Eng. 文章编号：0258-8013 (2005) 18-0040-06 中图分类号：TM71 文献标识码：A 学科分类号：47040 基于蚁群优化算法的电力系统负荷 序列的聚类分析 孙雅明, 王晨力，张智晟, 刘尚伟 （天津大学电气与自动化工程学院，天津市南开区300072 ） CLUSTERING ANALYSIS OF POWER SYSTEM LOAD SERIES BASED ON ANT COLONY OPTIMIZATION ALGORITHM SUN Ya-ming, WANG Chen-li, ZHANG Zhi-sheng, LIU Shang-wei (School of Electrical Engineering and Automation, Tianjin University, Nankai District, Tianjin 300072,China) ABSTRACT: According to the performance of short-term load 证实基于ACOA 的聚类比Kohonen 神经网络聚类对气候异 forecasting （STLF ）model based on the principle of artificial 常情况、高温区域、节假日都具有更高的敏感性和分辨率； neural networks(ANN), the forecasting accuracy is influenced 对负荷曲线轮廓的相似性具有更细腻和更均匀的聚类特性。 by the distributed feature of load sample space, and the 上述的聚类特性对STLF 精度的提高是极其重要的。 complex nonlinear relation which is formed by the sensibility of 关键词：电力系统；负荷时间序列；蚁群优化算法；Kohonen external weather factors to power load will also lead to the 神经网络；负荷曲线相似性；聚类分析 reduce of forecasting accuracy. To use power load series for characteristic clustering combination with pattern recognition 1 引言 may use as one method of solving the problem. In this paper, the characteristic clustering and its analysis to power load series 短期负荷预测(short-term load forecasting，STLF) based on Ant Colony Op