摘要
变电站负荷聚类是应对负荷特性多样性问题的有效途径,并对指导电网规划及运行等具有重要意义。为进一步提高变电站负荷聚类的有效性,挖掘利用更多数据价值,提出了考虑构成的变电站负荷双层聚类模型,先对下层用户依照用电特性进行聚类,而后计算聚类所得各类用户在所属上层变电站中的占比作为分析上层构成的依据,上层变电站的聚类综合地考虑自身负荷特性和构成情况。针对提出的双层聚类模型,根据上下层特点分别提出、使用改进K-means算法及考虑权重的分裂式FCM算法予以求解。最后对构造算例的变电站以及对某地区的实际变电站进行聚类分析,结果表明:考虑构成的变电站负荷双层聚类方法有效地补充了现有方法的不足,提高变电站聚类的有效性。
Substation load clustering is an effective way to deal with the diversity problem of load characteristics. In order to further improve reliability of substation load clustering, a bi-level clustering model of substation load considering its composition is proposed. The model consists of two parts: the lower-level consumer clustering and the upper-level substation clustering. Users’ utility attribute is considered in the upper level, and its results are used to analyze the composition of the substation. Both the composition and synthesis power consumption feature are considered in the lower level. The improved K-means algorithm and divisive FCM algorithm are adopted to solve the model. The method is utilized to analyze substation load in a certain area. The method can make up for the shortcomings of existing methods, and its reliability is illustrated in an example based on simulated load data.
作者
何哲楠
吴浩
程祥
占震滨
孙维真
HE Zhenan;WU Hao;CHENG Xiang;ZHAN Zhenbin;SUN Weizhen(College of Electrical Engineering, Zhejiang University, Hangzhou 310027, Zhejiang Province, China;State Grid Zhejiang Electric Power Co., Ltd., Hangzhou 310007, Zhejiang Province, China;Zhejiang Electric Power Dispatching and Communication Center, Hangzhou 310007, Zhejiang Province, China)
出处
《电网技术》
EI
CSCD
北大核心
2019年第8期2983-2990,共8页
Power System Technology
基金
国家自然科学基金资助项目(51377143)
国家电网公司科技项目“基于智能测量终端量测数据的负荷特性分析及建模方法研究”(52110415000B)~~
作者简介
通信作者:何哲楠(1994),男,硕士研究生,研究方向为负荷辨识、模型预测控制,E-mail:hezhenan@zju.edu.cn;吴浩(1973),男,博士,副教授,主要研究方向为负荷特性和负荷模型、电力系统运行与优化,E-mail:zjuwuhao@zju.edu.cn;程祥(1991),男,硕士,研究方向为负荷辨识及负荷特性;占震滨(1978),男,硕士,工程师,主要研究方向为电力调度自动化;孙维真(1963),男,硕士,高级工程师,主要研究方向为电网调度与运行、电力市场等。
