A novel Wasserstein generative adversarial network for stochastic wind power output scenario generation
Xiurong Zhang, Daoliang Li, Xueqian Fu
Abstract
Abstract A novel Wasserstein generative adversarial network (WGAN) is proposed for stochastic wind power output scenario generation. Wasserstein distance with gradient penalty adapts to the gradient vanishing problem that is easy to occur in the new energy generation scenario. This model has better robustness and generalization ability than the traditional generative adversarial network. WGAN is optimized to simulate ideal wind power scenarios. The generated data are measured by cumulative distribution function (CDF) and continuously ranked probability score to evaluate the performance of the proposed model. Compared with the probability models, the proposed model is data‐driven, that is, it can simulate wind power scenarios based on historical samples rather than probability hypothesis, and it can independently learn the space‐time correlation of wind power generation in different locations. Experiments show that the CDF curve of data generated by the proposed WGAN is highly coincident with that of real data.