Attention-Based Multitask Probabilistic Network for Nonintrusive Appliance Load Monitoring
Suryalok Dash, N. C. Sahoo
Abstract
Monitoring individual appliances’ operating state and energy consumption in a building enables significant energy-saving opportunities. These days, smart meters perform this task non-intrusively using sophisticated signal processing, machine learning, or deep learning approaches. To this end, this paper proposes a novel multi-task deep learning model that uses readily available low-frequency energy data from the smart meter for simultaneous appliance state detection and energy disaggregation. The model creatively adopts and customizes the famous transformer model from the field of language modeling for the above task. Further, the model output is produced as a mixture of probability density functions to handle uncertainties. The model performance is evaluated using the publicly available REFIT and UKDALE datasets. The test results indicate the proposed model’s superiority, generalizability, and transferability compared to other state-of-the-art models.