Efficient Time Series Disaggregation for Non-intrusive Appliance Load Monitoring

The growing concerns on urgent environmental and economical issues, such as global warming and rising energy cost, have motivated research studies on various green computing technologies. For example, Non-Intrusive Appliance Load Monitor (NIALM) techniques, aiming at energy monitoring, load forecasting and improved control of residential electrical appliances, have been developed by monitoring one electrical circuit that contains a number of electrical appliances without using separate sub-meters. By employing pattern recognition algorithms, the NIALM techniques estimate the consumption of individual appliances. While the basic ideas behind the NIALM techniques are valid, existing proposals suffer from the issue of poor estimation accuracy. In this paper, we model the process of load separation in NIALM as a time series disaggregation problem. Aiming at achieving high estimation accuracy and alleviating excessive computation, we develop a time-series disaggregation algorithm which incorporates two novel techniques, namely, DE-pruning and monotonic enumeration, for search space pruning. A comprehensive set of experiments are conducted to validate our proposals and to evaluate the effectiveness and the efficiency of the proposed methods. The result shows that our proposal is effective and efficient.