ISSN 0254-0096　CN 11-2082/K

• •

基于EVMD和布谷鸟算法的短期风功率区间预测

1. 新能源电力系统国家重点实验室（华北电力大学）,北京 102206
• 收稿日期:2020-12-10 出版日期:2022-08-28 发布日期:2023-02-28
• 通讯作者: 张亚刚（1978—）,男,博士、教授,主要从事电力系统自动化、新能源电力系统等方面的研究。yagangzhang@ncepu.edu.cn
• 基金资助:
国家自然科学基金重点项目（51637005）; 河北省自然科学基金（G2020502001）

SHORT TERM WIND POWER INTERVAL PREDICTION BASED ON EVMD AND CUCKOO ALGORITHM

Zhang Yagang, Zhao Yunpeng, Wang Siqi

1. State Key Laboratory of New Energy Power System（North China Electric Power University）, Beijing 102206, China
• Received:2020-12-10 Online:2022-08-28 Published:2023-02-28

Abstract: In order to improve the accuracy and controllability of short-term wind power prediction, a short-term wind power prediction model based on energy difference optimal variational mode decomposition and cuckoo optimal combination neural network is proposed. The energy difference is used to optimize the number of modes of the variational modal decomposition （EVMD）, and EVMD is used for short-term wind power decomposition. Based on the different modal characteristics of the EVMD decomposition sequence, a cuckoo optimized back propagation neural network is used for the nonlinear sequence （CS-BPNN）. The autoregressive moving average model （ARMA） is used for the stationary series, and the weighted point prediction value is reconstructed. The kernel density estimation is constructed based on the sequence information lost by EVMD decomposition. Based on the point prediction model, the interval prediction of wind power is carried out. The proposed prediction method is applied to a practical example of wind farms in Australia. The experimental results show that the method can improve the accuracy of short-term wind power prediction.