Occupancy detection for enhanced energy disaggregation

Abstract

Non-Intrusive Load Monitoring (NILM) attempts to break down the aggregated electrical consumption signal into the power consumption of each individual appliance, which can provide helpful understanding on energy consumption patterns and helps reduce overall energy usage and costs. This paper proposes an occupancy-aided energy disaggregation approach to address the NILM problem. Our methodology encompasses three key steps: firstly, features extraction from environmental sensors through the training of a DAE model; secondly, inference of occupancy information using the K-means algorithm; and finally, the disaggregation process using a Recurrent Neural Network (RNN) model, incorporating the detected occupancy status alongside power data. Experiments conducted on our real-world dataset demonstrate that our method significantly outperforms the state-of-the-art models while having good generalization capacity, achieving roughly 40% Mean Absolute Error (MAE) gain and 30% Root Mean Squared Error (RMSE) gain on a specific appliances disaggregation compared to the conventional NILM approach where only the power data is used.