基于改进集成学习算法的海上风电发电功率预测研究  

Research on Offshore Wind Power Generation Power Prediction Based on Improved Ensemble Learning Algorithm

作　　者：叶凡 白志阳 Fan Ye;Zhiyang Bai(School of Management,University of Shanghai for Science and Technology,Shanghai;Hudong Zhonghua Shipbuilding(Group)Co.Ltd.,Shanghai)

机构地区：[1]上海理工大学管理学院,上海 [2]沪东中华造船(集团)有限公司,上海

出　　处：《建模与仿真》2025年第2期291-303,共13页Modeling and Simulation

摘　　要：针对海上风电功率预测的复杂性,建立以发电功率预测精度为主要优化目标,以风速、风向、空气密度等多维气象数据输入方式的海上风电功率预测模型,同时在构建XG-Boost算法的基础上,提出了一种引入模拟退火算法的参数寻优机制,以避免算法陷入局部最优解。将该算法应用于企业数据,并与其他三种算法进行对比,结果表明:改进的SA-XG-Boost算法能够有效提高预测精度,为海上风电企业的稳定运行提供了可靠的支撑。Aiming at the complexity of offshore wind power prediction,an offshore wind power prediction model is established with the power generation prediction accuracy as the main optimization objective,and multi-dimensional meteorological data input methods such as wind speed,wind direction,air density,etc.At the same time,on the basis of constructing the XG-Boost algorithm,a parameter-seeking optimization mechanism that introduces the simulated annealing algorithm is proposed to avoid the algorithm from falling into the local optimal solution.The algorithm is applied to enterprise data and compared with the other three algorithms,and the results show that the improved SA-XG-Boost algorithm can effectively improve the prediction accuracy and provide reliable support for the stable operation of offshore wind power enterprises.

关 键 词：海上风电 发电功率预测 改进XG-Boost 皮尔逊相关分析法 

分 类 号：TM614[电气工程—电力系统及自动化]