Semi-intrusive load monitoring (SILM) is an appliance load monitoring approach using multiple meters, each meter measuring power for a subgroup of appliances. As an effective solution for demand response programs, SILM is used to get granular power measurements at the level of individual appliances in buildings. Hall effect sensors (HES) on each wire attached to a circuit breaker in distribution panels are one means of providing SILM. However, HES are greatly affected by crosstalk noise generated by neighboring wires, up to 35% of interfering signals. To remove crosstalk noise, this work proposes a blind source separation (BSS) approach designed to deal with sparse matrices, making SILM measurements accurate for home energy management systems. Our approach leverages two key elements: (i) a BSS algorithm based on non-correlation for sparse mixing matrix; (ii) a sensor gain compensation that leverages smart meter readings. The results demonstrate that the total power estimation error is reduced from 15% to 2% on the Tracebase dataset, and from 55% to 9% on our HES dataset monitored in a family home. Furthermore, the proposed approach outperforms standard BSS algorithms such as FastICA and InfoMax. This work shows that HES can be used for load monitoring in smart buildings.
Crosstalk Suppression in Semi-Intrusive Load Monitoring Systems Using Hall Effect Sensors
About the Author: antoine langevin
Antoine Langevin received his BSc in Electrical Engineering from the École de Technologie Supérieure, Montreal in 2016. He then started graduate studies by joining the Synchromedia laboratory of the École de Technologie Supérieure. His current research project is on energy disaggregation using machine learning techniques. He also participates in the Smart ÉTS Residence project. His areas of interest in research are artiﬁcial intelligence, smart home/city, prototyping and embedded systems.