Non-Intrusive Load Monitoring Based on Swarm Intelligence

Abstract

Electrical energy demands requested from down-stream sectors in a smart grid continuously increase recently. One way to meet those demands is to monitor and manage industrial, commercial as well as residential electrical loads efficiently in response to demand response programs for Demand-Side Management (DSM). Compared with energy management systems, Non-Intrusive Load Monitoring (NILM), a cost-effective technique, deduces used electrical appliances from a measured total load according to the individual characteristics. This paper presents an NILM system based on Particle Swarm Optimization (PSO) for DSM, which is considered as a combinatorial optimization problem. The PSO-based load disaggregation presented in this paper is evaluated in a real house environment. As the experimentation reported in this paper shows, the presented NILM approach gave an average load identification rate of 64.06%.