Distributed Baseline Load Estimation for Load Aggregators Based on Joint FCM Clustering
Liyin Zhang, Gengfeng Li, Yuxiong Huang, Jiangfeng Jiang, Zhaohong Bie, Xin Li, Yuchang Ling, Huili Tian
Abstract
Residential customer baseline load (CBL) estimation is critical to Demand Response (DR) implementation. The accurate estimation of baseline load is challenging because of the complexity and uncertainty of customer behavior. In addition, conventional methods are based on centralized datasets, which may be unrealistic considering the customer privacy issues and the geographical distribution of data storage under multiple load aggregators (LA). This paper proposes a fully distributed framework for CBL estimation based on joint Fuzzy C-Means (FCM). The fuzzy membership matrix is utilized to capture the load features. LAs can acquire the joint clustering result through limited information exchange in a privacy-preserving way. At last, the CBL is calculated through an inverse process of clustering. Case studies have been conducted utilizing the dynamic Time of Use trail data from Low Carbon London project. Compared with widely used averaging methods, the proposed method significantly improves the estimation accuracy.