基于自适应神经网络的风光互补电站出力预测研究  

Research on Output Forecasting of Wind Power and Photovoltaic Complementary Power Plant Based on Adaptive Neural Network

作　　者：邓韦斯 戴仲覆 鲁聪 张旭东 王皓怀[1] 卢斯煜 李崇浩[1] 刘显茁 DENG Weisi;DAI Zhongfu;LU Cong;ZHANG Xudong;WANG Haohuai;LU Siyu;LI Chonghao;LIU Xianzhuo(Power Dispatch and Control Center of China Southern Power Grid,Guangzhou 510663,China;State Key Laboratory of HVDC(Electric Power Research Institute of China Southern Power Grid Company Limited),Guangzhou 510663,China)

机构地区：[1]中国南方电网电力调度控制中心,广州510663 [2]直流输电技术国家重点实验室(南方电网科学研究院有限责任公司),广州510663

出　　处：《自动化与仪器仪表》2024年第3期97-100,105,共5页Automation & Instrumentation

基　　金：中国南方电网有限责任公司科技项目(ZDKJXM20210047)。

摘　　要：为提升风光互补电站出力预测准确度,研究了风光互补电站的出力预测方法。分析了风光互补电站机组出力情况,建立了广义回归神经网络模型和径向基神经网络模型用于训练历史数据。提出改进动态组群合作优化求解算法,利用该算法对风光互补电站出力进行预测,并利用仿真分析论证了提出模型的有效性,说明提出的方法能够有效降低预测误差,改善预测精度。In order to improve the output prediction accuracy of wind-solar hybrid power plants,an output prediction model of wind-solar hybrid power plants based on adaptive neural network was proposed.The unit output of the wind-solar hybrid power plant is analyzed,and a generalized regression neural network model and a radial basis neural network model are established.A solution model of joint dynamic group cooperative optimization algorithm and sine-cosine optimization algorithm is proposed,and the model is used to calculate the wind-solar hybrid forecast,and the effectiveness of the model proposed in this paper is demonstrated by simulation analysis.

关 键 词：神经网络 风光互补 出力预测 自适应网络 

分 类 号：TP29[自动化与计算机技术—检测技术与自动化装置] TM73[自动化与计算机技术—控制科学与工程]