An effective wind speed prediction model combining secondary decomposition and regularised extreme learning machine optimised by cuckoo search algorithm

• Published in: Wind energy (Chichester, England) Vol. 25; no. 8; pp. 1406 - 1433
• Main Authors: Zhang, Ye, Zhang, Wenyu, Guo, Zhenhai, Zhang, Shuwen
• Format: Journal Article
• Language: English
• Published: Bognor Regis John Wiley & Sons, Inc 01.08.2022; Wiley
• Subjects: Algorithms; Artificial neural networks; Decomposition; ensemble empirical mode decomposition; Frequencies; Impact analysis; Learning algorithms; Machine learning; Prediction models; regularised extreme learning machine; Search algorithms; secondary decomposition; Statistical analysis; wavelet packet transform; Wavelet transforms; Wind farms; Wind power; Wind speed; wind speed prediction
• ISSN: 1095-4244; 1099-1824
• DOI: 10.1002/we.2737

Wind speed prediction has an important impact on the planning, economic operation and safe maintenance of wind power systems. However, the high volatility and intermittency of wind speed make it difficult to predict accurately. To improve the prediction accuracy, we developed a hybrid multistep wind speed prediction model named EWP‐CS‐RELM. In this model, a secondary decomposition technique of ensemble empirical mode decomposition (EEMD) and wavelet packet transform (WPT) is used, and it is called the EWP decomposition technique. This decomposition technique can achieve an adaptive processing of the data and accurately extract the characteristic components of the signal, avoiding the occurrence of pattern overlap and reducing the mutual interference between components. At the same time, the high and low‐frequency parts of the complex signal (component) can be decomposed into different frequency bands, and the corresponding frequency band can be selected adaptively to match the signal spectrum. The subsequence obtained after EWP decomposition is then predicted using a regularised extreme learning machine (RELM) optimised by the cuckoo search (CS) algorithm with strong global search ability to obtain the results. The hybrid prediction model is validated using four seasons of wind speed data from two wind farms in Shandong, China, and compared with seven other prediction models. Simulation results illustrate that the EWP‐CS‐RELM model outperforms the other seven models with the smallest statistical errors.