Variational Regression for Multi-Target Energy Disaggregation

Abstract

Non-intrusive load monitoring systems that are based on deep learning methods produce high-accuracy end use detection; however, they are mainly designed with the one vs. one strategy. This strategy dictates that one model is trained to disaggregate only one appliance, which is sub-optimal in production. Due to the high number of parameters and the different models, training and inference can be very costly. A promising solution to this problem is the design of an NILM system in which all the target appliances can be recognized by only one model. This paper suggests a novel multi-appliance power disaggregation model. The proposed architecture is a multi-target regression neural network consisting of two main parts. The first part is a variational encoder with convolutional layers, and the second part has multiple regression heads which share the encoder’s parameters. Considering the total consumption of an installation, the multi-regressor outputs the individual consumption of all the target appliances simultaneously. The experimental setup includes a comparative analysis against other multi- and single-target state-of-the-art models.

HeartDIS: A Generalizable End-to-End Energy Disaggregation Pipeline

“…The main pain point is the fact that the previous years' NILM research produced models that can detect the power consumption of one appliance at the time. To address this issue, multi-target/multi-label approaches have been proposed [45][46][47][48][49] alongside with transfer learning approaches [13,50] and compression techniques (Kukunuri et al [51]). Finally, there have also been efforts to standardize the way NILM experiments are conducted in order to achieve the reproducibility and comparability of models with benchmark frameworks [1,52,53] and tool kits [14,54,55].…”