Motif-Based Pattern Detection Method for Smart Energy Meter Data

Nowadays, smart energy meters are being used to record periodic electricity consumption. The real time data produced by smart meters provide the detailed information about the electricity usage of a particular consumer. In this paper, we propose the motif-based pattern detection technique to discover regular behaviors of smart meter users. The electric energy usage pattern within a specific time window characterizes behaviors of energy user. Experiments on an Irish CER dataset justify that the proposed motif-based pattern detection method discovers the useful routine behavior of smart energy meters users, which are helpful for electricity utility experts and also for users. Further, in this paper, detailed motif analysis have been presented with respect to various parameter settings such as motif size, alphabet size etc. Also, interesting motifs are extracted within the households which help distribution network operator (DNO) for LV network modeling and management.