Slides for: EnerGAN++: A Generative Adversarial Gated Recurrent Networkfor Robust Energy Disaggregation

Separating the household aggregated energy consumption signal into its additive sub-components (the power signal from individual appliances), is called energy (power) disaggregation or non-intrusive load monitoring (NILM). NILM resembles the signal source separation problem and poses several challenges, not only as an ill-posed problem, but also, due to unsteady appliance signatures, abnormal behavior that is usually detected in appliances operation and the existence of noise in the aggregated signal. Currently, we are in the mature NILM period where there is an attempt for NILM to be applied in real-life application scenarios. Thus, the robustness of the algorithms, reliability, practicality, and, in general, trustworthiness are the main issues of interest.

In this talk, we propose the EnerGAN++, a model based on Generative Adversarial Networks for robust energy disaggregation. We attempt to unify the autoencoder (AE) and GAN architectures into a single framework, in which the autoencoder achieves a non-linear power signal source separation. EnerGAN++ is trained adversarially using a novel discriminator to enhance robustness to noise. The discriminator performs sequence classification using a recurrent convolutional neural network to handle the temporal dynamics of an appliance energy consumption time series. In particular, the proposed architecture of the discriminator leverages the ability of Convolutional Neural Networks (CNN) in rapid processing and optimal feature extraction, along with the need to infer the data temporal character and time dependence. Experimental results indicate the proposed method�s superiority compared to the current state of the art.