基于多指标评价优选的风电功率融合预测  

Fusion forecasting of wind power based on multi-index evaluation and optimization

作　　者：刘婷婷 田建艳[1,2] 王芳 张传辉[1] LIU Ting ting;TIAN Jian yan;WANG Fang;ZHANG Chuan hui(College of Information Engineering, Taiyuan University of Technology, Taiyuan 030024, China;Key Lab of Power System Operation and Control, College of Electrical and Power Engineering, Taiyuan University of Technology, Taiyuan 030024, China)

机构地区：[1]太原理工大学信息工程学院,山西太原030024 [2]太原理工大学电气与动力工程学院电力系统运行与控制山西省重点实验室,山西太原030024

出　　处：《计算机工程与设计》2018年第5期1446-1450,共5页Computer Engineering and Design

基　　金：国家自然科学基金项目(51277127)

摘　　要：为提高风电功率的预测精度,提出一种基于多指标评价优选的风电功率融合预测方法。建立预测模型的评价指标体系,在此基础上对单一预测模型进行评价和优选。分别采用熵值法和层次分析法确定指标的客观和主观权重,得到模型的综合评价值和评价排序,优选参与模型融合的单一预测模型,采用诱导有序加权平均算子对单模型进行融合预测。通过风电场实际数据进行仿真研究,仿真结果表明,该方法能够有效提高风电功率的预测精度。To improve the wind power forecasting accuracy,a fusion forecasting method of wind power based on multi-index evaluation and optimization was presented.The evaluation index system of the forecasting model was established,and the individual forecasting model was evaluated and optimized.Entropy method and analytic hierarchy process were adopted to determine the objective and subjective weight of the indexes,the comprehensive evaluation value and the model prioritization were calculated.The individual forecasting models for fusion forecasting were selected,the induced ordered weighted averaging operator was used to achieve the fusion forecasting of wind power.Simulation results based on the actual data of wind farm demonstrate the proposed method can improve the forecasting accuracy of wind power effectively.

关 键 词：模型优选 熵值法 层次分析法 诱导有序加权平均算子 融合预测 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]