基于主成分分析和LightGBM的风电场发电功率超短期预测

Ultra-short-term Prediction of Wind Farm Power Generation Based on Principal Component Analysis and Light GBM

风力发电场发电功率的超短期预测越精确,越有利于电力系统的稳定运行和优化调度。为提高风电场发电功率超短期预测的准确率,提出了一种基于主成分分析(PCA)和轻量梯度提升树(LightGBM)的风电场发电功率超短期预测方法。该方法首先进行主成分分析,将与风电功率相关程度低的维度剔除,降低数据的冗余性。然后利用LightGBM建模,实现风电场发电功率的超短期预测。实验结果表明,基于LightGBM的风电场发电功率超短期预测效果良好,优于传统机器学习方法在风电场超短期功率预测上的精度。

The more accurate in the ultra-short-term prediction of wind farm power generation,the more favorable on the stable operation and optimal dispatch of the power system.In order to improve the accuracy of ultra-short-term prediction of wind farm power generation,an ultra-short-term prediction method for wind farm power generation based on principal component analysis and gradient boosting macheine(GBM)algorithm is proposed.The method first performs PCA to eliminate the low dimension with correlation on wind power,and reduces data redundancy.Then GBM algorithm is used to model the ultra-short-term prediction of wind farm power generation.The experimental results show that the wind power generation power based on GBM algorithm has a good short-term prediction effect,which is better than the traditional machine learning method in the ultra-short-term power prediction of wind farms.