TraceGAN: Synthesizing Appliance Power Signatures Using Generative Adversarial Networks

Non-intrusive load monitoring (NILM) allows users and energy providers to gain insight into home appliance electricity consumption using only the building's smart meter. Most current techniques for NILM are trained using significant amounts of labeled appliances power data. The collection of such data is challenging, making data a major bottleneck in creating well generalizing NILM solutions. To help mitigate the data limitations, we present the first truly synthetic appliance power signature generator. Our solution, TraceGAN, is based on conditional, progressively growing, 1-D Wasserstein generative adversarial network (GAN). Using TraceGAN, we are able to synthesise truly random and realistic appliance power data signatures. We evaluate the samples generated by TraceGAN in a qualitative way as well as numerically by using traditional GAN evaluation methods such as the Inception score. Finally, we provide a simplistic example for the use of TraceGAN as a data augmentation tool for supervised NILM training.

Automated summary

Non-intrusive load monitoring (NILM) allows users and energy providers to monitor home appliance electricity consumption using only the smart meter, but data collection is challenging. To address data limitations, a synthetic appliance power signature generator called TraceGAN is introduced to provide realistic appliance power data for NILM training. Serving as a data augmentation tool, TraceGAN improves supervised NILM training outcomes.