基于相似日误差校正的光伏功率预测  

Photovoltaic Power Prediction Based on Similar Day Error Correction

作　　者：王军辉[1] 李民 畅蓬博[1] 刘宁[1] WANG Junhui;LI Min;CHANG Pengbo;LIU Ning(Shaanxi Province Hydraulic Power Survey and Design Institute,Xi’an 710001,Shaanxi,China)

机构地区：[1]陕西省水利电力勘测设计研究院,陕西西安710001

出　　处：《电网与清洁能源》2020年第11期134-138,共5页Power System and Clean Energy

基　　金：国家自然科学基金项目(51779206)。

摘　　要：光伏发电的功率预测是电网运行调度普遍关注的问题。光伏电站大量历史数据的挖掘和利用为波动的光伏功率建模提供了新方向。在采用气象相似日进行光伏发电功率预测的基础上,引入了相似日的光伏发电功率预测误差对预测日的光伏功率进行校正,更进一步提高了光伏发电功率预测的准确性。Power prediction of photovoltaic power generation is a common concern in the operation and scheduling of a power grid. Mining and utilizing a large amount of historical data of photovoltaic power plants provides a new direction for modeling fluctuating photovoltaic power. On the basis of photovoltaic power prediction using similar weather days,this paper introduces the photovoltaic power prediction errors of similar days to correct the photovoltaic power of predicted days,which further improves the accuracy of photovoltaic power prediction.

关 键 词：光伏发电 功率预测 相似日 误差校正 

分 类 号：TM922.5[电气工程—电力电子与电力传动]