A Framework of Energy Disaggregation Based on Adaptive Association Rules Mining

Abstract

Non-intrusive load monitoring (NILM) process intends to deduce the individual energy consumption of appliances used in the house, which is mainly based on measuring the aggregate power consumption with a single smart meter. Comprehensive device consumption information can facilitate the improvements of the energy usage habits of the users. This work presents a novel framework on NILM via adaptive association rules mining, which aims to address the following issues. 1) The failure of detection for the appliances or group of appliances consuming the same or similar power. 2) Small power appliances' signals get overwhelmed by noise in the aggregate power data. To evaluate the effectiveness of our proposed framework, we implemented experiments based on the public datasets in production environment. By comparing with the state-of-art algorithms in general evaluation metrics, our framework gets around 10% gain on average in the performance of NILM task.