A hybrid approach to ultra short-term wind speed prediction using CEEMDAN and Informer

Abstract

To lower the risk of the electricity system from wind power uncertainties, accurate wind speed forecasting (WSF) is essential. However, the complex fluctuating properties of wind speed series make it challenging to get accurate results in wind speed prediction. Hence, this paper proposes a hybrid approach using complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and a robust attention mechanism based informer model for WSF. First, CEEMDAN is used to decompose raw wind speed data into a set of intrinsic mode functions to produce a new denoised signal. Then, the informer model extracts the dynamic characteristics of the denoised signals and predicts the wind speed. The 5-minute wind speed data from two wind farms located at Block island, Rhode Island State and Gulf Coast, Texas State are used to evaluate the proposed approach’s effectiveness. The proposed approach’s performance is compared using eight robust models and assessed through different performance indices. From the two case studies, the proposed approach outperforms the second-best WSF method by 56%, and 78%, respectively.