eeRIS-NILM: An Open Source, Unsupervised Baseline for Real-Time Feedback Through NILM

Awareness of residential consumers about the impact of their behavior on electricity consumption is an important determinant for energy efficiency and for their participation in electricity markets. Non-intrusive load monitoring (NILM) has been proposed as a cost-effective approach for providing detailed information about the consumption of individual appliances and help achieve these goals. In this context, the ideal NILM algorithm should be unsupervised and provide real-time consumption feedback (i.e., the appliances should be detected immediately after they start consuming power). Solutions with these characteristics have not been sufficiently studied in the NILM bibliography. This paper introduces an attempt to address this problem, by suggesting the use of a "Live" algorithm that provides real-time feedback. The Live algorithm runs in parallel with a more robust NILM procedure, and a periodic synchronization step ensures that the two processes share the same appliance models. The paper presents the details and implementation of the algorithm, along with an evaluation methodology and its results on the REDD dataset. Although the Live algorithm presented here has significant room for improvement, it can serve as a baseline for evaluating more sophisticated approaches in the future. The source code for the implemented system is available at https://github.com/eeris-nilm/.