Search

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. [ABSTRACT FROM AUTHOR]

• Data preprocessing is used to extract the chief characters of wind speed series. • l 2.1 -norm Regularization strategy is used to reduce over-fitting of predictors. • Multi-objective optimization algorithm is used to optimize weights and thresholds. • A scientific evaluation system including nine criteria are constructed. Researching wind speed forecasting is increasingly important given the growing importance of wind energy in power system operation. Precise and reliable wind speed forecasting methods can effectively enhance the operational stability of power grids and improve their economic and environmental benefits. In recent decades, numerous methods have been proposed to reduce the forecasting errors caused by the non-stationary and non-linear properties of wind speed data. However, some traditional forecasting methods are restricted by the limitations of single prediction methods and do not consider the necessity of applying data processing technology and optimization algorithms, which leads to poor prediction accuracy. To overcome the limitations of traditional forecasting methods and provide more precise and stable wind speed prediction results, an advanced hybrid prediction system based on data reconstruction and kernel approximation (random Fourier mapping) is proposed in this paper. The proposed system successfully maximizes the forecasting capabilities of the component methods and effectively improves the wind speed prediction performance. Based on 10-min and 30-min data collected from Shandong province, China, the simulation results indicate that the forecasted values obtained using the proposed strategy are considerably better than those obtained using the compared strategies, which is beneficial for electrical energy conversion and power grid security. [ABSTRACT FROM AUTHOR]