基于ACO-PAM综合算法的电力负荷聚类分析  

Power load clustering analysis based on ACO-PAM synthesis algorithm

作　　者：刘建华[1] 王进[1] 杨洪春 孟颖[3] 

机构地区：[1]长沙理工大学电气与信息工程学院智能电网运行与控制湖南省重点实验室,湖南长沙410004 [2]广东理文造纸有限公司,广东东莞523160 [3]长沙理工大学计算机与通信工程学院,湖南长沙410004

出　　处：《电力科学与技术学报》2011年第4期94-99,共6页Journal of Electric Power Science And Technology

基　　金：国家自然科学基金(71071025)

摘　　要：负荷特性分类与综合是实现负荷模型实用化的关键.为建立合适的变电站负荷模型,将聚类方法引入负荷特性分析,提出一种基于ACO-PAM的综合聚类算法.该综合算法是PAM算法对蚁群的历史最优位置进行聚类分析,将此位置代替PAM的参考点,作为新的聚类中心,数据将自适应地加入到适合它的聚类中.ACO算法具有全局搜索能力强、易于与其他方法结合的优点,改进了PAM算法易陷入局部最优、实际数据聚类效果差等不足.实例分析验证了ACO-PAM综合算法应用的可行性和有效性.Load characteristics classification and synthesis play an important role in practical load modeling. In order to establish a proper substation load model, an ACO-PAM based synthetic algorithm applying clustering method for load characteristics analysis is proposed in this paper. The algorithm makes clustering analysis for history optimal position of ACO, and it replaces the reference point for the new clustering center. The clustering data can be clustered adaptively to the classification. The ACO algorithm has strong global search ability and is easy to combine with other methods. It improves the shortcomings of PAM, such as easily sinking into local optimum and poor clustering effect. Finally, cases analysis results show that the synthesis algorithm has high feasibility and effectivity.

关 键 词：ACO-PAM综合算法 电力负荷 负荷特性分类 聚类分析 

分 类 号：TM714[电气工程—电力系统及自动化]