No abstract

Smart homes play a crucial role in reducing the residential sector electricity consumption and Greenhouse Gases (GHG) emissions. In this work, we present a time series approach to predict GHG emissions to be integrated into smart home management systems. More specifically, we used Long Short-Term Memory (LSTM), a variant of Recurrent Neural Networks. The prediction results get mean absolute percentage error (MAPE) close to 2 % when the region under study has an energy matrix mostly based on fossil fuels, less intermittent. For regions in which more renewable sources are present, the MAPE is around 12 %. However, in either case, LSTM can predict the hours well with smaller emissions among the next 24 hours. Such day-ahead information brings awareness to the users and allows the scheduling of appliances to work in the hours in which the emissions are minimal, reducing them without significantly affecting the consumers' behavior.

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.