Abstract
Energy disaggregation, namely the separation of the aggregated household energy consumption signal into its additive sub-components, bears resemblance to the signal (source) separation problem and poses several challenges, not only as an ill-posed problem, but also, due to unsteady appliance signatures, abnormal behaviour that is usually detected in appliances operation and the existence of noise in the aggregated signal. In this paper, we propose EnerGAN++, a model based on Generative Adversarial Networks (GAN) 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, among 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.
Highlights
Non-Intrusive Load Monitoring (NILM) or energy disaggregation can be considered as an efficient and cost effective framework to reduce energy consumption [1]
We investigate the ability of generative adversarial networks to create robust appliance power patterns for energy disaggregation in the presence of noise
To address the aforementioned difficulties, this paper proposes an extension of the previous EnerGAN model, named EnerGAN++ which enriches the discriminator with recurrent properties to increase robustness and precision accuracy in adversarial energy disaggregation modelling
Summary
Non-Intrusive Load Monitoring (NILM) or energy disaggregation can be considered as an efficient and cost effective framework to reduce energy consumption [1]. We enrich the concept of adversarial learning in NILM by introducing a more efficient discriminator in our proposed EnerGAN++ model which is constitute of a combined convolutional layer with a recurrent GRU unit instead of a simple binary classifier Advanced structures such as the recurrent GRU approximate long range recurrent dependencies in a better way, compared to traditional recurrent neural networks that suffer from the vanishing gradient problem [35], [36]. Since our target is to approximate real energy consumption of a specific appliance, EnerGAN++ uses labeled time-series of single appliance as input vectors of the generator during the training phase in contrast to conventional GAN modelling where only random noise signals are considered as input triggers.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
