Discovering residential electricity consumption patterns through smart-meter data mining: A case study from China

With the increasing penetration of information and communication technologies (ICTs) in energy systems, traditional energy systems are being digitized. Advanced analysis of the energy production and consumption data and data-driven decision support can be combined to promote the fortnation and development of smart energy systems. Smart grids are a specific application of smart energy systems. Different electricity consumption patterns of residential users can be discovered and extracted by clustering analysis of the electricity consumption data collected by smart meters and other data acquisition terminals in a smart grid. This research explores daily electricity consumption patterns of low-voltage residential users in China. The service architecture of smart power use and the structure of electric energy data acquisition system of the State Grid Corporation of China (SGCC) are introduced and a process model for mining daily electricity consumption data is presented. The analysis is based on the fuzzy c-means (FCM) clustering method and a fuzzy cluster validity index (PBMF). A case study of Kunshan City, Jiangsu Province, China is presented, using the daily electricity consumption data of 1312 low-voltage users within a month. (C) 2017 Elsevier Ltd. All rights reserved.