Short-Term Wind Speed Interval Prediction Based on Ensemble GRU Model

• Published in: IEEE transactions on sustainable energy Vol. 11; no. 3; pp. 1370 - 1380
• Main Authors: Li, Chaoshun, Tang, Geng, Xue, Xiaoming, Saeed, Adnan, Hu, Xin
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.07.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Decomposition; Error correction; gated recurrent unit; Indexes; interval prediction; Logic gates; Neural networks; Prediction models; Predictive models; Time series analysis; variational mode decomposition; Wind fields; Wind power; Wind power generation; Wind speed; Wind speed prediction
• ISSN: 1949-3029; 1949-3037
• DOI: 10.1109/TSTE.2019.2926147

Wind speed interval prediction is playing an increasingly important role in wind power production. The intermittent and fluctuant characteristics of wind power make high-quality prediction interval challenging. In this paper, a novel hybrid model based on a gated recurrent unit neural network and variational mode decomposition is proposed for wind speed interval prediction. Initially, variational mode decomposition is employed to decompose the complex wind speed time series into simplified modes. Interval prediction model and a point prediction model based on a gated recurrent unit neural network are designed to conduct interval prediction in primary mode and point prediction in rest modes, respectively, before the composition and construction of the prediction interval. Then, an error prediction model based on a gated recurrent unit neural network is proposed to enhance the model performance by error correction. Eight cases from two wind fields are used to test and verify the proposed method. The results indicate that the proposed method is a highly qualified method that has a much higher prediction interval coverage probability and narrower prediction interval width.