Wind Speed Data Repairing Method Based on Bidirectional Prediction

• Published in: 2021 IEEE International Conference on Power Electronics, Computer Applications (ICPECA) pp. 715 - 721
• Main Authors: Shen, Xincheng, Qu, Yi, Huang, Shaoxiong, Li, Zhi, Zhang, Kaifeng
• Format: Conference Proceeding
• Language: English
• Published: IEEE 22-01-2021
• Subjects: autoregressive integrated moving average; Data models; data repairing; Distributed databases; ensemble empirical mode decomposition; long short-term memory neural network; Maintenance engineering; Predictive models; Savitzky-Golay filter; Wind forecasting; Wind power generation; Wind speed
• DOI: 10.1109/ICPECA51329.2021.9362540

In order to repair the lost data in distributed wind power system, this paper puts forward a wind speed data repairing model based on a new bidirectional prediction method. This model consists of two one-way prediction models. In each prediction model, the original wind speed data are decomposed into several intrinsic mode functions (IMFs) and a residue signal by ensemble empirical mode decomposition (EEMD) method. Then the Savitzky-Golay (SG) filter is used to reduce noise for high-frequency IMFs. Next the long short-term memory (LSTM) model and autoregressive integrated moving average (ARIMA) model are combined to predict low-frequency IMFs and the noise reduction results respectively. At the end, all those forecast results are added and form a one-way result. By weighted average of two one -way results, the repairing result is calculated. The experimental results from multiple prediction cases show that this method can get more accurate results.