Short-term wind power prediction method based on deep clustering-improved Temporal Convolutional Network

• Published in: Energy reports 2023-12, Vol.9, p.2118-2129
• Main Authors: Sheng, Yiwei, Wang, Han, Yan, Jie, Liu, Yongqian, Han, Shuang
• Format: Article
• Language: English
• Subjects: Categorical Generative Adversarial Network; Deep clustering; Numerical weather prediction; Temporal Convolutional Network; Wind power prediction
• ISSN: 2352-4847; 2352-4847
• DOI: 10.1016/j.egyr.2023.01.015

Carbon neutrality has become the global consensus, and wind power is one of the key technologies to achieve carbon neutrality in the power system. However, the randomness and fluctuation of wind energy pose a great challenge to the safe and stable operation of the power system. Accurate wind power prediction results can effectively reduce the adverse effects of wind power uncertainty on power system operation. The high proportion of wind power connected to the grid requires higher prediction accuracy. However, the existing wind power prediction methods exist the problems of inaccurate classification of numerical weather prediction (NWP) and insufficient consideration of actual characteristics. Therefore, a short-term wind power prediction method based on deep clustering-improved Temporal Convolutional Network (TCN) is proposed in this paper. First, 22 typical features of NWP are extracted (including maximum and minimum wind speed, maximum and minimum temperature, etc.). Then, a deep clustering model based on Categorical Generative Adversarial Network is constructed to classify the extracted NWP features accurately. Finally, to address the problem of partial feature loss in the training process of traditional TCN, a gating mechanism is introduced to improve the activation function of its residual block, and an improved TCN prediction model for each class is established. The actual operation data of three wind farms are used to verify the effectiveness and robustness of the proposed wind power prediction method. The results show that the proposed method can reduce the prediction error (Root Mean Squared Error) from 7.18% to 12.87% in three wind farms, compared with other traditional prediction methods.