Industrial load disaggregation based on Hidden Markov Models

Abstract

Non-intrusive load monitoring (NILM) technology can identify the energy consumed by each individual device from the aggregate electricity measurements, contributing to energy saving and emission reduction. NILM methods have been widely studied for residential scenarios, where Hidden Markov Model (HMM) and its variants are popular. Although NILM methods have been proposed also for industrial scenarios, such methods applicable on both high- and low-consuming industrial scenarios are lacking. In this paper, two HMM-based methods are proposed for disaggregating industrial loads, where extra reactive power observation and state duration distribution are exploited. The graphical structure of the proposed models is illustrated. In the experiments, the two proposed industrial load disaggregation methods are benchmarked with three state-of-the-art industrial load disaggregation methods. All benchmarks are validated on two real industrial datasets sampled at 1 Hz and 1/5 Hz, respectively, and evaluated by two metrics. A comparison of the disaggregation results for all industrial devices is demonstrated and discussed, showing improvement for using extra reactive power observation and state duration distribution.