基于小波分析和高斯过程的短期风速预测

Short-term Wind Speed Prediction Based on Wavelet Analysis and Gaussian Process

风能是近年来快速发展的一种绿色可再生能源,准确的短期风速预测是保证其安全性和经济性的必要条件。文章提出了一种基于小波分析和高斯过程的短期风速预测模型。首先利用小波分解将非平稳非线性原始风速序列分解为一组子序列。然后,对每个子序列采用高斯过程建立回归模型进行预测,将预测结果累加得到原始风速序列的预测。最后,使用江苏某海上风电场的数据验证了模型的有效性。

Wind energy is a kind of green renewable energy that has developed rapidly in recent years.Accurate wind speed prediction is a necessary condition to ensure its safety and economy.The paper proposes a short-term wind speed prediction model based on wavelet and Gaussian processes.Firstly,the wavelet decomposition is used to decompose the non-stationary nonlinear original wind speed sequence into a set of sub-sequences.Then,a Gaussian process is used to establish a regression model for each subsequence to make predictions,and the prediction results are accumulated to obtain the prediction of the original wind speed sequence.Finally,the data of an offshore wind farm in Jiangsu was used to verify the validity of the model.