Main content area

Sequence transfer correction algorithm for numerical weather prediction wind speed and its application in a wind power forecasting system

Wang, Han, Han, Shuang, Liu, Yongqian, Yan, Jie, Li, Li
Applied energy 2019 v.237 pp. 1-10
algorithms, models, uncertainty, weather forecasting, wind farms, wind power, wind speed, China
Little Numerical Weather Prediction (NWP) error may incur huge error in wind power forecasting due to the cubic relationship between wind speed and wind power. The current correction algorithms for NWP wind speed are all based on the priori statistics laws of NWP error at the same time, i.e., the mapping relationship between NWP error and NWP wind speed at time t + 1. However, this mapping relationship has strong random uncertainty, which limits the correction accuracy of existing algorithms. To address this problem, a sequence transfer correction algorithm (STCA) for NWP wind speed is proposed in this paper. In addition to the NWP wind speed at time t + 1, the measured wind speed at time t is also introduced as an input variable in the wind speed correction model, thus the sequence transfer relationship is incorporated, and the certainty of the mapping relationship between inputs and outputs of the correction model is improved. By applying STCA, 5 frequently-used models are established for correcting the NWP wind speed error. The actual operation data of two wind farms in northern and southern China are taken as examples for this study. The correction error for NWP wind speed is reduced by 0.2–1.5 m/s in wind farm 1 and 0–0.7 m/s in wind farm 2, when compared with the second-ranking algorithm model. It can be seen that the proposed correction algorithm for NWP wind speed has higher accuracy in both ultra-short-term and short-term time scales, and has strong generalization ability to different correction models. To validate that the proposed correction algorithm can be used for real applications, STCA is also applied to the wind power forecasting system for these 2 wind farms. Results show that the wind power forecasting accuracy is improved by 3.2–16.1% in wind farm 1 and 1.7–7.5% in wind farm 2.