摘要
为提高风电功率预测精度,提出一种基于不同优化准则和广义回归神经网络(GRNN)的风电功率非线性组合预测方法。首先,基于灰色关联度理论,筛选出综合灰色关联度大于0的单项预测模型。然后,利用筛选出的单项预测模型以平均绝对误差最小、平均相对误差最小和均方根误差最小为优化准则构建线性组合优化模型。最后,利用GRNN神经网络对基于不同优化准则的线性组合模型进行非线性组合,得到优化模型。以实测风电功率数据对所提方法进行验证,仿真结果表明:与各单项预测模型、线性组合模型相比,所提优化模型的整体预测精度高,证明了该方法的有效性和实用性。
In order to improve the accuracy of wind power forecasting, a nonlinear combined model for wind power forecasting based on different optimization criteria and generalized regression neural network(GRNN) is proposed. The grey correlation analysis method is applied to select the forecasting models in which the comprehensive grey correlation values are greater than zero. Based on the three selected models, different linear combined forecasting models are built with the minimum average relative error, minimum mean absolute error, and minimum root mean square error as the optimization criterion, respectively. The GRNN is used to establish the nonlinear combined forecasting model by the three linear combined models and then obtain the optimized model. The verification with the real measured data of a wind farm shows that, compared with the single forecasting models, linear combined forecasting models, the proposed optimized model improves the forecasting accuracy effectively, which proves its effectiveness and practicability.
作者
喻华
卢继平
曾燕婷
段盼
刘加林
苟鑫
YU Hua;LU Jiping;ZENG Yanting;DUAN Pan;LIU Jialin;GOU Xin(State Key Laboratory of Power Transmission Equipment&System Security and New Technology,Chongqing University,Chongqing 400030,China;Nan'an Power Supply Branch Company of State Grid Chongqing Electric Power Company,Chongqing 400066,China)
出处
《高电压技术》
EI
CAS
CSCD
北大核心
2019年第3期1002-1008,共7页
High Voltage Engineering
基金
高等学校学科创新引智计划("111"计划)(B08036)~~
关键词
广义回归神经网络
优化准则
灰色关联度
非线性组合预测
优化模型
generalized regression neural network(GRNN)
optimization criterion
grey correlation
nonlinear combined forecasting
optimized model
