Variational Autoencoder Generative Adversarial Network for Synthetic Data Generation in Smart Home
This addresses data scarcity issues for smart home and grid researchers, but it is incremental as it combines existing VAE and GAN methods.
The paper tackled the problem of limited data availability in smart grid applications by proposing a VAE-GAN model for synthetic data generation, which outperformed a vanilla GAN in matching real data distributions as measured by metrics like KL divergence and statistical parameters.
Data is the fuel of data science and machine learning techniques for smart grid applications, similar to many other fields. However, the availability of data can be an issue due to privacy concerns, data size, data quality, and so on. To this end, in this paper, we propose a Variational AutoEncoder Generative Adversarial Network (VAE-GAN) as a smart grid data generative model which is capable of learning various types of data distributions and generating plausible samples from the same distribution without performing any prior analysis on the data before the training phase.We compared the Kullback-Leibler (KL) divergence, maximum mean discrepancy (MMD), and Wasserstein distance between the synthetic data (electrical load and PV production) distribution generated by the proposed model, vanilla GAN network, and the real data distribution, to evaluate the performance of our model. Furthermore, we used five key statistical parameters to describe the smart grid data distribution and compared them between synthetic data generated by both models and real data. Experiments indicate that the proposed synthetic data generative model outperforms the vanilla GAN network. The distribution of VAE-GAN synthetic data is the most comparable to that of real data.