提出一种基于有向图卷积循环网络的分布式光伏超短期功率预测方法,该方法可同时提取光伏出力的时序特征和空间相关性,有效减小预测误差。首先,分析光伏出力数据兼具时序性和空间相关性,利用门控循环网络提取时序特征,构建有向图卷积网络提取传统图卷积无法捕捉的光伏出力有向空间相关性;然后,融合门控循环单元和有向图卷积网络,构建有向图卷积循环网络以提取多光伏站点出力的时空相关性,并利用注意力机制为不同时刻的时空特征分配权重;最后,通过全连接层输出最终的预测结果。采用某地区屋顶光伏实际出力数据在不同预测时间尺度下比较所提方法与其他方法的预测性能,结果表明,预测时间尺度为15、30和60 min时,相对于传统循环网络,所提方法的MAE分别减少16.3%、20.7%和28.1%。
Abstract
Most distributed photovoltaic power forecasting methods focus on mining the temporal features of photovoltaic output, ignoring the spatial correlations between multiple adjacent PV stations’ output, which leads to a large forecasting error. This paper proposes an ultra-short-term prediction method of distributed photovoltaic power method based on a directed graph convolution recurrent network, which can simultaneously extract the temporal features and spatial correlation of photovoltaic output so as to effectively reduce the forecasting error. Firstly, the temporal features and spatial correlations of photovoltaic output data are analyzed, and the temporal features are extracted by a gated recurrent unit, and the directed graph convolution network is constructed to extract the directed spatial correlations of photovoltaic output that traditional graph convolution network cannot capture. Then, the gated recurrent unit and the directed graph convolution network are fused to construct the directed graph convolution cyclic network to extract the spatio-temporal correlations of multiple photovoltaic stations’ output, and the attention mechanism is used to assign weights to the spatio-temporal features at different timesteps. Finally, the prediction results are obtained through the fully connected layer. A case study is conducted with actual power data of 79 rooftop photovoltaics under different forecasting horizons. The results illustrate that compared with traditional gated recurrent unit, the MAE of the proposed method decreases by 16.3%, 20.7% and 28.1% for 15-min, 30-min and 60-min-ahead forecasting tasks.
关键词
分布式光伏 /
超短期预测 /
有向图卷积循环网络 /
时空相关性
Key words
distributed photovoltaic /
ultra-short-term prediction /
directed graph convolution recurrent network /
temporal-spatial correlation
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 贾凌云, 云斯宁, 赵泽妮, 等. 神经网络短期光伏发电预测的应用研究进展[J]. 太阳能学报, 2022, 43(12): 88-97.
JIA L Y, YUN S N, ZHAO Z N, et al.Recent progress of short-term forecasting of photovoltaic generation based on artificial neural networks[J]. Acta energiae solaris sinica, 2022, 43(12): 88-97.
[2] 赖昌伟, 黎静华, 陈博, 等. 光伏发电出力预测技术研究综述[J]. 电工技术学报, 2019, 34(6): 1201-1217.
LAI C W, LI J H, CHEN B, et al.Review of photovoltaic power output prediction technology[J]. Transactions of China Electrotechnical Society, 2019, 34(6): 1201-1217.
[3] 王俊杰, 毕利, 张凯, 等. 基于多特征融合和XGBoost-LightGBM-ConvLSTM的短期光伏发电量预测[J]. 太阳能学报, 2023, 44(7): 168-174.
WANG J J, BI L, ZHANG K, et al.Short-term photovoltaic power generation prediction based on multi-feature fusion and XGBoost-LightGBM-ConvLSTM[J]. Acta energiae solaris sinica, 2023, 44(7): 168-174.
[4] 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.
[5] 董雪, 赵宏伟, 赵生校, 等. 基于SOM聚类和二次分解的BiGRU超短期光伏功率预测[J]. 太阳能学报, 2022, 43(11): 85-93.
DONG X, ZHAO H W, ZHAO S X, et al.Ultra-short-term forecasting method of photovoltaic power based on SOM clustering, secondary decomposition and BiGRU[J]. Acta energiae solaris sinica, 2022, 43(11): 85-93.
[6] 谭海旺, 杨启亮, 邢建春, 等. 基于XGBoost-LSTM组合模型的光伏发电功率预测[J]. 太阳能学报, 2022, 43(8): 75-81.
TAN H W, YANG Q L, XING J C, et al.Photovoltaic power prediction based on combined XGBoost-LSTM model[J]. Acta energiae solaris sinica, 2022, 43(8): 75-81.
[7] 刘晓艳, 王珏, 姚铁锤, 等. 基于卫星遥感的超短期分布式光伏功率预测[J]. 电工技术学报, 2022, 37(7): 1800-1809.
LIU X Y, WANG J, YAO T C, et al.Ultra short-term distributed photovoltaic power prediction based on satellite remote sensing[J]. Transactions of China Electrotechnical Society, 2022, 37(7): 1800-1809.
[8] 张童彦, 廖清芬, 唐飞, 等. 基于气象资源插值与迁移学习的广域分布式光伏功率预测方法[J]. 中国电机工程学报, 2023, 43(20): 7929-7940.
ZHANG T Y, LIAO Q F, TANG F, et al.Wide-area distributed photovoltaic power forecast method based on meteorological resource interpolation and transfer learning[J]. Proceedings of the CSEE, 2023, 43(20): 7929-7940.
[9] 乔颖, 孙荣富, 丁然, 等. 基于数据增强的分布式光伏电站群短期功率预测(一): 方法框架与数据增强[J]. 电网技术, 2021, 45(5): 1799-1808.
QIAO Y, SUN R F, DING R, et al.Distributed photovoltaic station cluster gridding short-term power forecasting part Ⅰ: methodology and data augmentation[J]. Power system technology, 2021, 45(5): 1799-1808.
[10] 王彪, 吕洋, 陈中, 等. 考虑信息时移的分布式光伏机理-数据混合驱动短期功率预测[J]. 电力系统自动化, 2022, 46(11): 67-74.
WANG B, LYU Y, CHEN Z, et al.Hybrid mechanism-data-driven short-term power forecasting of distributed photovoltaic considering information time shift[J]. Automation of electric power systems, 2022, 46(11): 67-74.
[11] 李俊伟, 龚新勇, 朱元富, 等. 基于SVR-LSTM-BP的分布式光伏短期出力预测方法研究[J]. 电气应用, 2023, 42(2): 79-84.
LI J W, GONG X Y, ZHU Y F, et al.A research on short-term distributed photovoltaic power prediction model based on SVR-LSTM-BP[J]. Electrotechnical application, 2023, 42(2): 79-84.
[12] 甄皓. 有限信息下基于深度学习模型的小型分布式光伏电站功率预测[J]. 上海节能, 2020(4): 302-308.
ZHEN H.Power prediction of small distributed photovoltaic power plant based on deep learning model with limited information[J]. Shanghai energy conservation, 2020(4): 302-308.
[13] YANG C, THATTE A A, XIE L.Multitime-scale data-driven spatio-temporal forecast of photovoltaic generation[J]. IEEE transactions on sustainable energy, 2015, 6(1): 104-112.
[14] ZHEN H, NIU D X, WANG K K, et al.Photovoltaic power forecasting based on GA improved Bi-LSTM in microgrid without meteorological information[J]. Energy, 2021, 231: 120908.
[15] ZHAO L, SONG Y J, ZHANG C, et al.T-GCN: a temporal graph convolutional network for traffic prediction[J]. IEEE transactions on intelligent transportation systems, 2020, 21(9): 3848-3858.
[16] QI Y L, LI Q, KARIMIAN H, et al.A hybrid model for spatiotemporal forecasting of PM2.5 based on graph convolutional neural network and long short-term memory[J]. Science of the total environment, 2019, 664: 1-10.
[17] DONG X C, SUN Y Y, LI Y, et al.Spatio-temporal convolutional network based power forecasting of multiple wind farms[J]. Journal of modern power systems and clean energy, 2022, 10(2): 388-398.
[18] 王晶, 黄越辉, 李驰, 等. 考虑空间相关性和天气类型划分的多光伏电站时间序列建模方法[J]. 电网技术, 2020, 44(4): 1376-1383, 13.
WANG J, HUANG Y H, LI C, et al.Time series modeling method for multi-photovoltaic power stations considering spatial correlation and weather type classification[J]. Power system technology, 2020, 44(4): 1376-1383, 13.
[19] 李兢, 乔颖, 龚莺飞. 考虑时空相关性的光辐照度序列估计方法[J]. 电力系统自动化, 2017, 41(22): 96-101.
LI J, QIAO Y, GONG Y F.Estimation method of solar irradiance sequence considering temporal-spatial correlation[J]. Automation of electric power systems, 2017, 41(22): 96-101.
[20] CHAI D, WANG L Y, YANG Q.Bike flow prediction with multi-graph convolutional networks[C]//Proceedings of the 26th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, Seattle Washington, 2018: 397-400.
[21] KIPF T N. WELLING M.Semi-supervised classification with graph convolutional networks[C]//Proceedings of the International Conference on Learning Representations, Toulon: ICLR, 2017.
[22] 蒋维楣. 空气污染气象学[M]. 南京: 南京大学出版社, 2003: 107-117.
JIANG W M.Air pollution meteorology[M]. Nanjing: Nanjing University Press, 2003: 107-117.
基金
国家电网公司总部科技项目《基于智能量测的低压高渗透率分布式光伏接入可测可控技术研究》 （5700-202255222A-1-1-ZN)
PDF(1079 KB)
