Variational Regression for Multi-Target Energy Disaggregation

Virtsionis Gkalinikis, N.; Nalmpantis, C.; Vrakas, D. Variational Regression for Multi-Target Energy Disaggregation. Sensors 2023, 23, 2051. https://doi.org/10.3390/s23042051

non-intrusive load monitoring; energy disaggregation; nilm; deep learning; variational inference; multi-target regression; kl divergence; convolution neural networks

Non-intrusive load monitoring systems that are based on deep learning methods produce high accuracy end-use detection, but 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 a NILM system where 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 which consists 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. Given 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.