A novel asexual-reproduction evolutionary neural network for wind power prediction based on generative adversarial networks. (1st November 2021)

• Record Type: Journal Article
• Authors: Yin, Hao; Ou, Zuhong; Zhu, Zibin; Xu, Xuancong; Fan, Jingmin; Meng, Anbo
• Is Part Of: Energy conversion and management. Volume 247(2021)
• Publication Date: 2021-11-01
• Subjects: Asexual-reproduction evolutionary neural network -- New-built wind farm -- Wind power prediction -- Generative adversarial network -- Decomposition technique; Direct energy conversion -- Periodicals; Energy storage -- Periodicals; Energy transfer -- Periodicals; Énergie -- Conversion directe -- Périodiques; Direct energy conversion; Periodicals; 621.3105
• DOI: 10.1016/j.enconman.2021.114714
• Languages: English
• ISSNs: 0196-8904

Abstract

Highlights: A novel asexual-reproduction evolutionary neural network is proposed. Three kinds of generative adversarial networks are applied to augment the training data. The wind data are decomposed by the ensemble empirical mode decomposition technology. The proposed approach outperforms much better than other SIA-based models. Abstract: Accurate forecasts of wind power generation are essential for the operation of wind farms. But for the newly developed stations, it is difficult to make accurate prediction because there are no sufficient historical data available. It will thus be interesting to explore new data augmentation and prediction modeling approach adaptive to such new-built wind farms. In this regard, a novel asexual-reproduction evolutionary neural network (ARENN) for short-term wind power prediction based on Wasserstein generative adversarial network with gradient penalty (WGANGP) and ensemble empirical mode decomposition (EEMD) is presented in this paper. To solve the dilemma that new-built wind farms lack sufficient wind power data, the WGANGP is first applied to generate realistic data with a similar distribution of real data to augment the training dataset, which is further decomposed into a series of more stable subsequences by the EEMD so as to reduce the prediction difficulty of the machine learning model. In this study, a novel ARENN prediction model is developed to make the short-term wind power prediction, in which an asexual-reproduction evolutionary approach is first proposed to optimize the neural network based on a set of different loss functions that facilitate the population of network parameters approximating to the global optimum along different error surfaces in the evolutionary process. The proposed approach is validated on the data collected from the wind farm located in Spain and the predicted results demonstrate the advantage of our proposed approach over other methods involved in this study.