Single-Location and Multi-Locations Scenarios Generation for Wind Power Based On WGAN-GP

Abstract

To address the randomness of renewable energy, scenario generation can simulate the random process of renewable energy. Still, most of the previous scenario generation algorithms are based on assumed probability distribution models, which are difficult to grasp the dynamic characteristics of renewable energy accurately. Based on an improved generative adversarial network algorithm, this paper generates single-site and multi-site scenarios for wind power generation data. The temporal and spatial correlations of the generated data were judged based on the maximum mean difference and the Pearson coefficient. Finally, multiple sets of wind power generation data are used to verify that the proposed method can reflect not only the volatility of renewable energy but also ensure the temporal and spatial correlation between the data.