[关键词]
[摘要]
为提高光伏发电功率预测的精度和时效性,降低电网调度的安全隐患,提出了一种基于数字孪生模型、联合神经网络以及融合预测模型的光伏发电功率预测技术。该技术以针对常态预测的CNNLSTM网络和针对超短期预测的集成学习融合预测模型为核心,以光伏发电系统的数字孪生模型为基础框架,以某光伏电站的实测数据为基础进行了分析,实现了实时的多模式光伏发电功率精确预测。结果表明:改进的CNNLSTM联合网络模型能够实现较高预测精度,相比于现有的主流预测算法精度提高了约36%~58%;针对超短期的发电功率预测这一难点,集成学习融合框架可以进一步将预测精度提高25%左右。
[Key word]
[Abstract]
In order to improve the accuracy and timeliness of photovoltaic power prediction and reduce the security risks of power grid dispatching,this paper proposed a photovoltaic power prediction technology based on digital twin model,joint neural network and fusion prediction model. This technology took CNNLSTM network for normal prediction and integrated learning fusion prediction model for ultrashort term prediction as the core,and took the digital twin model of photovoltaic power generation system as the basic framework to realize the realtime accurate prediction of multimode photovoltaic power generation based on the measured data of a photovoltaic power station. The experimental results show that the improved CNNLSTM joint network model can achieve high prediction accuracy,which is about 36% to 58% higher than the existing mainstream prediction algorithm; aiming at the difficulty of ultrashort term electricity generation power prediction,the integrated learning fusion framework can further improve the prediction accuracy by about 25%.
[中图分类号]
TP391
[基金项目]