摘要
短期光伏发电功率的预测精度与天气类型紧密相关,云层的无规则运动导致光伏发电功率波动。因此该文通过监测不同天气类型下云层的运动形态提高预测精度。首先,基于NWP因子将天气划分为5种类型,并通过变分模态分解将光伏发电功率分为平滑过程与波动过程数据。其次,采用云层灰度值判断云层厚度,由加速鲁棒特征(SURF)监测得到云层特征点,跟踪特征点的移动得到云层的运动速度和方向。然后,提出波动特征参数,结合云层运动状态分析波动形态,从而将云层运动状态与波动形态相关联实现“云层分型”。最后,针对平滑数据和波动过程的数据特征,结合机器学习算法自身的适应性条件,提出基于CNN-LSTM的组合预测算法。该算法实现了基于NWP相关因子,以光伏功率历史平滑数据和历史波动数据为输入、以光伏功率预测值为输出的预测方法,显著提高了光伏发电功率的预测精度。
The fluctuation of PV power is caused by the irregular movement of cloud,and its fluctuation is closely related to the weather type,which affects the prediction accuracy of short term PV power forecast,the cloud motion pattern improves the prediction accuracy.Firstly,the weather types are divided into 5 types based on NWP factor,and the PV power is divided unsmooth data and fluctuating data by variational mode decomposition.Secondly,the cloud thickness is judged by the cloud gray level,and the use of SURF is to detect the cloud feature points,and the velocity and direction of the cloud are obtained by tracking the movement of the feature points.Then,the wave shape is analyzed by the wave characteristic parameters and the wave data,so that the cloud motion state is related to the wave shape to realize the“cloud classification”.Finally,a combined forecasting algorithm based on CNN-LSTM is proposed according to the characteristics of smooth data and fluctuating pro-cess and the adaptability of machine learning algorithm.Based on the NWP correlation factor,the daily fluctuation process of PV power is taken as input and the daily fluctuation process of PV power is taken as output.
作者
张蕊
李安燚
刘世岩
薛世伟
贾清泉
巩秦海
Zhang Rui;Li Anyi;Liu Shiyan;Xue Shiwei;Jia Qingquan;Gong Qinhai(State Grid Hebei Electric Power Research Institute,Shijiazhuang 050021,China;Hebei Energy Technology Services,Shijiazhuang 051430,China;School of Electrical Engineering,Yanshan University,Qinhuangdao 066004,China)
出处
《太阳能学报》
EI
CAS
CSCD
北大核心
2024年第11期330-342,共13页
Acta Energiae Solaris Sinica
基金
国网河北能源技术服务有限公司科技项目(基于台区光伏功率预测的分布式资源协同调控技术研究TSS2022-13)。
关键词
光伏发电
NWP
组合预测
变分模态分解
波动特征SUBF云层监测
CNN-LSTM
PV power generation
NWP
combination prediction
variational modal decomposition
fluctuation characteristics SUBF cloud cover monitoring
CNN-LSTM
作者简介
通信作者:巩秦海(1997-),男,硕士研究生,主要从事光伏发电功率预测方面的研究。2025945515@qq.com。
