为提高光伏短期出力预测精确问题,提出一种基于图卷积神经网络（GCN）的光伏短期出力预测方法。首先,构建考虑多气象影响因素的光伏短期出力模型,开展光伏出力影响因素和出力特性分析。其次,对光伏出力历史时序数据进行图形化转换和数据重构,构建邻接矩阵并提取光伏短期出力图形化特征数据。在多时间尺度场景下,建立基于GCN的光伏出力预测模型,并与基于长短期记忆网络（LSTM）、反向传播网络（BP）、图注意力模型（GAT）等算法的预测模型做比对分析。最后,以某地区光伏出力实测数据开展仿真验证研究,仿真结果表明所提方法具有良好的预测效果。
Abstract
To improve the accuracy of short-term photovoltaic output prediction, a photovoltaic short-term output prediction method based on graph convolutional network （GCN） is proposed. Firstly, construct a short-term photovoltaic output model that considers multiple meteorological factors, and conduct an analysis of the influencing factors and output characteristics of photovoltaic system. Secondly, graphical transformation and data reconstruction are performed on the historical time series data of photovoltaic output, and an adjacency matrix is constructed to extract graphical feature data of short-term photovoltaic output. Establish a photovoltaic output prediction model based on GCN in a multi time scale scenario, and compare and analyze it with prediction models based on LSTM, BP, GAT and other algorithms. Finally, simulation validation research is conducted using measured photovoltaic output data from a certain region, and the simulation results show that the proposed method has good predictive performance.
关键词
光伏发电 /
图卷积神经网络 /
图形数据结构 /
多时间尺度
Key words
photovoltaic power /
graph convolutional neural network /
graph data structure /
multi-time scale
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 李德鑫, 王佳蕊, 张家郡. 基于光伏波动性的储能出力特性分析[J]. 电网与清洁能源, 2021, 37(2): 99-107.
LI D X, WANG J R, ZHANG J J.Analysis of energy storage output characteristics based on photovoltaic volatility[J]. Power system and clean energy, 2021, 37(2): 99-107.
[2] 赵俊浩, 吴杰康, 张文杰, 等. 基于布谷鸟-Elman算法的光伏发电预测[J]. 电力工程技术, 2020, 39(2): 81-88.
ZHAO J H, WU J K, ZHANG W J, et al.Photovoltaic power prediction based on Elman neural network with improved cuckoo algorithm[J]. Electric power engineering technology, 2020, 39(2): 81-88.
[3] 宋阳, 张静页, 王磊, 等. 计及预测偏差的光伏消纳多时间尺度调度研究[J]. 电力工程技术, 2018, 37(1): 58-64.
SONG Y, ZHANG J Y, WANG L, et al.Research on multi-time scheduling of accommodating photovoltaic considering the error of photovoltaic prediction[J]. Electric power engineering technology, 2018, 37(1): 58-64.
[4] 刘丹, 刘方, 许彦平. 基于MIV-PSO-BPNN的光伏出力短期预测[J]. 太阳能学报, 2022, 43(6): 94-98.
LIU D, LIU F, XU Y P.Short-term photovoltaic power forecasting based on MIV-PSO-BPNN model[J]. Acta energiae solaris sinica, 2022, 43(6): 94-98.
[5] 袁晓玲, 施俊华, 徐杰彦. 计及天气类型指数的光伏发电短期出力预测[J]. 中国电机工程学报, 2013, 33(34): 57-64, 12.
YUAN X L, SHI J H, XU J Y.Short-term power forecasting for photovoltaic generation considering weather type index[J]. Proceedings of the CSEE, 2013, 33(34): 57-64, 12.
[6] 邢晨, 张照贝. 基于改进时间卷积网络的短期光伏出力概率预测方法[J]. 太阳能学报, 2023, 44(2): 373-380.
XING C, ZHANG Z B.Short-term probabilistic forecasting method of photovoltaic output power based on improved temporal convolutional network[J]. Acta energiae solaris sinica, 2023, 44(2): 373-380.
[7] 朱玥, 顾洁, 孟璐. 基于EMD-LSTM的光伏发电预测模型[J]. 电力工程技术, 2020, 39(2): 51-58.
ZHU Y, GU J, MENG L.Photovoltaic power generation prediction model based on EMD-LSTM[J]. Electric power engineering technology, 2020, 39(2): 51-58.
[8] 刘嘉诚, 刘俊, 赵宏炎, 等. 基于DKDE与改进mRMR特征选择的短期光伏出力预测[J]. 电力系统自动化, 2021, 45(14): 13-21.
LIU J C, LIU J, ZHAO H Y, et al.Short-term photovoltaic output forecasting based on diffusion kernel density estimation and improved max-relevance and Min-redundancy feature selection[J]. Automation of electric power systems, 2021, 45(14): 13-21.
[9] 高博, 茆超, 张冲标, 等. 基于时空图网络的分布式光伏发电出力预测[J]. 电力系统及其自动化学报, 2023, 35(3): 125-133.
GAO B, MAO C, ZHANG C B, et al.Output prediction of distributed photovoltaic power generation based on spatialtemporal graph neural network[J]. Proceedings of the CSU-EPSA, 2023, 35(3): 125-133.
[10] 王玉庆, 徐飞, 刘志坚, 等. 基于动态关联表征与图网络建模的分布式光伏超短期功率预测[J]. 电力系统自动化, 2023, 47(20): 72-82.
WANG Y Q, XU F, LIU Z J, et al.Ultra-short-term power forecasting of distributed photovoltaic based on dynamic correlation characterization and graph network modeling[J]. Automation of electric power systems, 2023, 47(20): 72-82.
[11] 卞海红, 孙健硕. 基于典型气象周的GRNN光伏发电量预测模型[J]. 电力工程技术, 2021, 40(5): 94-99.
BIAN H H, SUN J S.Photovoltaic power generation prediction model based on optimized TMY Method-GRNN[J]. Electric power engineering technology, 2021, 40(5): 94-99.
基金
国网江苏省电力公司科技项目（J2022049）; 江苏省重点研发计划（BE2017169）
PDF(1191 KB)
