###
DOI:
上海电力学院学报:2019,35(6):-
←前一篇   |   后一篇→
本文二维码信息
基于主成分分析和LightGBM算法的风电场发电功率超短期预测
曹渝昆, 朱萌
(上海电力学院)
Ultra-short-term prediction of wind farm power generation based on principal component analysis and LightGBM algorithm
ZHU Meng
(Shanghai University of Electric Power)
摘要
图/表
参考文献
相似文献
本文已被:浏览 46次   下载 21
投稿时间:2019-01-11    修订日期:2019-04-11
中文摘要: 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和GBM算法的风电场发电功率超短期预测方法。该方法首先进行PCA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GBM算法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GBM算法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的功率预测上的精度。
Abstract: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 GBM algorithm is proposed.The method first performs PCA to eliminate the low dimension with correlation on wind power, and reduces data redundancy.Then use GBM algorithm 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.
文章编号:     中图分类号:TM614    文献标志码:
基金项目:
引用文本:
曹渝昆,朱萌.基于主成分分析和LightGBM算法的风电场发电功率超短期预测[J].上海电力学院学报,2019,35(6):.
ZHU Meng.Ultra-short-term prediction of wind farm power generation based on principal component analysis and LightGBM algorithm[J].Journal of Shanghai University of Electric Power,2019,35(6):.