基于高斯过程回归的短期风速预测

Short-term Wind Speed Forecasting Based on Gaussian Process Regression Model

准确预测风速能有效减轻风电场对整个电网的不利影响,提高风电场在电力市场中的竞争能力。为了提高风速预测的精度,提出一种基于高斯过程(Gaussian processes,GP)的风速预测模型。首先运用自相关法和假近邻法分别求取风速时间序列的延迟时间和嵌入维数,进而对混沌风速时间序列进行相空间重构。其次运用GP模型对重构后的风速时间序列进行训练,同时在贝叶斯框架下,确定协方差函数中的"超参数"。最后利用训练好的GP模型风速时间序列进行预测,并与支持向量机、最小二乘支持向量机和BP神经网络进行比较。仿真结果表明,基于GP的风速预测模型具有很好的稳定性,能够满足预测精度的要求,具有很大的工程实际应用价值。

The short-term wind speed forecasting is very important for the operation of grid-connected wind power generation systems. The accuracy forecasting of the wind speed can also effectively reduces or avoids the adverse effect of wind farm on power grid, meanwhile, strengthens competition ability of wind farm in electricity market. In order to improve the forecasting accuracy, a wind speed forecasting method based on the Gaussian process （GP） was proposed. Firstly, the embedding dimension and the delay time of the wind speed time series were respectively calculated by autocorrelation method and false neighbor method, the phase space reconstruction of the chaotic wind speed time series was received. Then, the reconstructed wind speed time series was predicted by the GP model, at the same time the ＂super parameter＂ in the covariance function was determined under the Bayesian framework. Finally, wind speed time series was used to predict by the trained GP, which was compared with support vector machine （SVM）, least squares support vector machine （LSSVM） and BP neural network （BPNN）. The simulation results show that GP predict model can be used to accurately predict and has stable performance. So it can be widely used in engineering practice.