SolarGAN: Multivariate Solar Data Imputation Using Generative Adversarial Network
Wenjie Zhang, Yonghong Luo, Ying Zhang, Dipti Srinivasan
Abstract
Photovoltaic (PV) is receiving increasing attention due to its sustainability and low carbon footprint. However, the penetration level of PV is still relatively low because of its intermittency. This uncertainty can be handled by accurate PV forecasting, which requires high-quality solar data. Nevertheless, up to 40% of solar data can be found missing, which significantly worsens the quality of solar data. This letter proposes a novel solarGAN method for multivariate solar data imputation, in which necessary modifications are made on the input of generative adversarial network (GAN) to effectively tackle the relatively independent solar time series data. Case studies on a public dataset show that the proposed solarGAN outperforms several commonly-used machine learning and GAN based data imputation methods with at least 23.9% reduction of mean squared error.