Semi-Intrusive Load Monitoring for Large-Scale Appliances

Non-intrusive appliance load monitoring (NIALM) is to identify major energy guzzlers in a house or building without introducing extra metering cost. To develop an easy-to-use and scalable solution to energy disaggregation for contemporary large-scale appliance groups, we propose a Semi-Intrusive Appliance Load Monitoring (SIALM) approach in this paper. Based on a simple power model, a Sparse Switching Event Recovering (SSER) model is established to recover appliance states from their aggregated load data, and the necessary conditions for unambiguous state recovery of multiple appliances are provided. Under the constraints of necessary conditions, the minimum number of required smart meters is pursued via a greedy cliquecovering algorithm. We evaluate the performance of SIALM with Monte Carlo simulation. The results show that our method achieves high accuracy not only in appliances’ state recovery but also in energy disaggregation.