基于分层关联性建模的分布式光伏功率超短期概率预测

doi:10.11930/j.issn.1004-9649.202405022

中国电力 ›› 2024, Vol. 57 ›› Issue (12): 50-59.DOI: 10.11930/j.issn.1004-9649.202405022

• 面向新型电力系统的源荷预测技术 • 上一篇下一篇

基于分层关联性建模的分布式光伏功率超短期概率预测

陈璨¹(), 苏紫诺²(), 马原¹(), 刘佳林¹(), 王玉庆²(), 王飞²^,³^,⁴()

1. 国网冀北电力有限公司电力科学研究院，北京　100045
2. 华北电力大学电力工程系，河北保定　071003
3. 新能源电力系统全国重点实验室（华北电力大学），北京　102206
4. 河北省分布式储能与微网重点实验室（华北电力大学），河北保定　071003

收稿日期:2024-05-09 出版日期:2024-12-28 发布日期:2024-12-27
作者简介:陈璨（1988—），女，通信作者，博士，高级工程师，从事新能源及分布式电源调控技术研究，E-mail：wscc0621@163.com
苏紫诺（2000—），女，硕士研究生，从事分布式光伏功率预测技术研究，E-mail：suzinuo@ncepu.edu.cn
马原（1998—），男，硕士，从事配电网数字化、运行优化控制技术研究，E-mail：ma.yuan.cn@outlook.com
基金资助:
国网冀北电力有限公司科技项目（基于智能融合终端的乡村有源配电网源荷协调调控技术研究与应用，52018K22001Z）。

Ultra-short-term Probabilistic Forecasting of Distributed Photovoltaic Power Generation Based on Hierarchical Correlation Modeling

Can CHEN¹(), Zinuo SU²(), Yuan MA¹(), Jialin LIU¹(), Yuqing WANG²(), Fei WANG²^,³^,⁴()

1. Electric Power Research Institute, State grid Jibei Electric Power Co., Ltd., Beijing 100045, China
2. Department of Power Engineering, North China Electric Power University, Baoding 071003, China
3. State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources (North China Electric Power University), Beijing 102206, China
4. Hebei Key Laboratory of Distributed Energy Storage and Microgrid (North China Electric Power University), Baoding 071003, China

Received:2024-05-09 Online:2024-12-28 Published:2024-12-27
Supported by:
This work is supported by Science and Technology Project of State Grid Jibei Electric Power Co., Ltd. (Research and Application of Source-Load Coordinated Control Technology for Rural Active Distribution Network Based on Intelligent Fusion Terminal, No.52018K22001Z).

摘要/Abstract

摘要：

准确的区域分布式光伏功率概率预测可为有源配电网优化运行提供更全面的信息支撑。当缺乏气象测量或预报数据时，对分布式光伏时空相关信息的挖掘利用可以有效提升功率预测精度，然而，现有研究或难以针对性挖掘时空关联信息，或在建模过程中丢失大量有效信息。为此，提出了一种基于分层关联建模的区域分布式光伏功率超短期概率预测方法。首先，采用基于深度一致性的聚类方法对分布式光伏集群进行子区域划分，支撑对子区域内部时空关联的针对性建模；在此基础上，构建分层图结构以同步建模子域内与子域间时空关联关系，有效利用不同层级间关联信息；然后，提出了基于分层图卷积神经网络的概率预测模型，挖掘光伏电站之间的深度时空关联特征，提升区域分布式光伏超短期功率概率预测精度。最后，利用实际分布式光伏功率数据集验证了该方法的有效性。

关键词: 分布式光伏, 概率预测, 分层关联建模, 深层时空关联性

Abstract:

Accurate probabilistic forecasting of regional distributed photovoltaic (PV) power can provide more comprehensive information support for the optimal operation of active distribution networks. When meteorological measurement or forecasting data is lacking, mining and utilizing spatio-temporal correlation information of distributed PV can effectively improve power forecasting accuracy. However, existing research either struggles to specifically mine spatio-temporal correlation information or loses a significant amount of valuable information during the modeling process. To address this, a method for ultra-short-term probabilistic forecasting of regional distributed PV power based on hierarchical correlation modeling is proposed. Firstly, a clustering method based on deep consistency is employed to divide the distributed PV clusters into subregions, which supports targeted modeling of the spatio-temporal correlations within the subregions. On this basis, a hierarchical graph structure is constructed to simultaneously model the intra-subregion and inter-subregion spatio-temporal correlations, enabling effective utilization of correlation information across different hierarchical levels. Then, a probabilistic forecasting model based on hierarchical graph convolutional neural networks (GCNs) is proposed to mine deep spatio-temporal correlation features between PV power stations, thereby enhancing the accuracy of ultra-short-term probabilistic forecasting of regional distributed PV power. Finally, the effectiveness of the proposed method is validated using actual distributed PV power data sets.

Key words: distributed photovoltaic, probabilistic forecasting, hierarchical association modeling, deep temporal and spatial correlation

陈璨, 苏紫诺, 马原, 刘佳林, 王玉庆, 王飞. 基于分层关联性建模的分布式光伏功率超短期概率预测[J]. 中国电力, 2024, 57(12): 50-59.

Can CHEN, Zinuo SU, Yuan MA, Jialin LIU, Yuqing WANG, Fei WANG. Ultra-short-term Probabilistic Forecasting of Distributed Photovoltaic Power Generation Based on Hierarchical Correlation Modeling[J]. Electric Power, 2024, 57(12): 50-59.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202405022

https://www.electricpower.com.cn/CN/Y2024/V57/I12/50

图/表 12

图 1 区域分布式光伏功率超短期概率预测流程

Fig.1 Flowchart of ultra-short-term probabilistic forecasting of regional distributed PV power

图 2 子图和全局图的分层结构示意

Fig.2 Schematic of the hierarchical structure of subgraphs and global graphs.

图 3 分层图卷积神经网络预测模型结构示意

Fig.3 The structure of the proposed HGCN prediction model

表 1 不同聚类方法下的点预测精度

Table 1 Forecasting accuracy of different clustering methods

方法	E_MA/MW	E_RMS/MW
K-means聚类+GCN	23.8284	30.5803
深度一致性聚类+GCN	23.6658	30.2521
K-means聚类+HGCN	22.8821	30.0161
深度一致性聚类+HGCN	22.8191	29.8063

图 4 不同方法下点预测的预测曲线

Fig.4 Prediction curves for point prediction under different methods

表 2 提前4 h下光伏发电功率的预测性能

Table 2 Predictive performance of PV power under 4 h lead time

方法	置信度95%			置信度85%
方法	E_PICP/%	E_PINAW	E_ICE	E_PICP/%	E_PINAW	E_ICE
本文方法	91.72	93.11	102.31	78.52	66.27	84.40
方法1	92.86	98.28	105.83	80.80	73.53	91.01
方法2	94.79	105.91	111.73	86.94	81.69	93.96
方法3	95.00	108.10	113.78	86.50	82.16	94.97
方法4	98.69	130.75	132.48	92.38	96.38	104.33

表 4 阴天天气提前4 h下光伏发电功率的预测性能

Table 4 Predictive performance of photovoltaic power generation under cloudy weather with 4 h lead time

方法	置信度95%			置信度85%
方法	E_PICP/%	E_PINAW	E_ICE	E_PICP/%	E_PINAW	E_ICE
本文方法	93.42	94.05	100.66	78.68	63.24	80.38
方法1	94.39	100.86	106.85	84.77	74.23	87.56
方法2	95.99	108.76	113.30	89.42	81.79	91.47
方法3	96.15	111.31	115.76	88.46	82.12	92.83
方法4	99.83	131.12	131.33	93.26	95.54	102.43

图 5 本文方法3种天气场景的区间预测结果

Fig.5 Interval forecasting results for three weather scenarios of the method in this paper

图 6 方法1下3种天气场景的区间预测结果

Fig.6 Interval forecasting results for three weather scenarios of the method 1

图 7 方法2下3种天气场景的区间预测结果

Fig.7 Interval forecasting results for three weather scenarios of the method 2

表 3 晴天天气提前4 h下光伏发电功率的预测性能

Table 3 Predictive performance of photovoltaic power generation under sunny weather with 4 h lead time

方法	置信度95%			置信度85%
方法	E_PICP/%	E_PINAW	E_ICE	E_PICP/%	E_PINAW	E_ICE
本文方法	92.44	94.09	101.78	79.16	59.10	74.65
方法1	97.65	100.79	103.21	80.41	68.43	85.09
方法2	93.12	103.57	111.24	85.41	75.04	87.85
方法3	98.95	110.43	111.59	84.16	76.34	90.70
方法4	95.42	126.51	132.59	90.17	91.97	101.99

表 5 雨天天气提前4 h下光伏发电功率的预测性能

Table 5 Predictive performance of photovoltaic power generation under rainy weather with 4 h lead time

方法	置信度95%			置信度85%
方法	E_PICP/%	E_PINAW	E_ICE	E_PICP/%	E_PINAW	E_ICE
本文方法	90.41	95.01	105.07	78.54	74.31	94.61
方法1	91.25	97.97	107.36	75.83	75.53	99.60
方法2	93.54	105.54	112.83	84.46	84.37	99.89
方法3	93.54	106.79	114.16	83.95	85.78	102.17
方法4	99.63	132.33	132.84	92.36	100.38	108.68

参考文献 16

1	2023年前三季度光伏发电建设运行情况[EB/OL]. (2023-11-03)[2024-08-20]. https://www.nea.gov.cn/2023-11/03/c_1310748819.htm.
2	李丰君, 王磊, 赵健, 等. 基于天气融合和LSTM网络的分布式光伏短期功率预测方法[J]. 中国电力, 2022, 55 (11): 149- 154.
	LI Fengjun, WANG Lei, ZHAO Jian, et al. Research on distributed photovoltaic short-term power prediction method based on weather fusion and LSTM-Net[J]. Electric Power, 2022, 55 (11): 149- 154.
3	刘洁, 林舜江, 梁炜焜, 等. 基于高阶马尔可夫链和高斯混合模型的光伏出力短期概率预测[J]. 电网技术, 2023, 47 (1): 266- 274.
	LIU Jie, LIN Shunjiang, LIANG Weikun, et al. Short-term probabilistic forecast for power output of photovoltaic station based on high order Markov chain and Gaussian mixture model[J]. Power System Technology, 2023, 47 (1): 266- 274.
4	林帆, 张耀, 东琦, 等. 基于分位数插值和深度自回归网络的光伏出力概率预测[J]. 电力系统自动化, 2023, 47 (9): 79- 87. DOI
	LIN Fan, ZHANG Yao, DONG Qi, et al. Probability prediction of photovoltaic output based on quantile interpolation and deep autoregressive network[J]. Automation of Electric Power Systems, 2023, 47 (9): 79- 87. DOI
5	赵耀, 高少炜, 李东东, 等. 基于天气相似聚类与QRNN的短期光伏功率区间概率预测[J]. 电力系统自动化, 2023, 47 (23): 152- 161. DOI
	ZHAO Yao, GAO Shaowei, LI Dongdong, et al. Short-term interval probability prediction of photovoltaic power based on weather similarity clustering and quantile regression neural network[J]. Automation of Electric Power Systems, 2023, 47 (23): 152- 161. DOI
6	JIAO X, LI X S, LIN D Y, et al. A graph neural network based deep learning predictor for spatio-temporal group solar irradiance forecasting[J]. IEEE Transactions on Industrial Informatics, 2022, 18 (9): 6142- 6149. DOI
7	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. DOI
8	王海军, 居蓉蓉, 董颖华. 基于时空关联特征与B-LSTM模型的分布式光伏功率区间预测[J]. 中国电力, 2024, 57 (7): 74- 80.
	WANG Haijun, JU Rongrong, DONG Yinghua. Distributed photovoltaic power interval prediction based on spatio-temporal correlation feature and B-LSTM model[J]. Electric Power, 2024, 57 (7): 74- 80.
9	LIAO W L, BAK-JENSEN B, PILLAI J R, et al. Short-term power prediction for renewable energy using hybrid graph convolutional network and long short-term memory approach[J]. Electric Power Systems Research, 2022, 211, 108614. DOI
10	赵洪山, 孙承妍, 温开云, 等. 无气象信息条件下基于AGCRN的分布式光伏出力超短期预测方法[J]. 高电压技术, 2024, 50 (1): 65- 73.
	ZHAO Hongshan, SUN Chengyan, WEN Kaiyun, et al. Ultra-short-term prediction of distributed photovoltaic power method based on AGCRN in the absence of meteorological information[J]. High Voltage Engineering, 2024, 50 (1): 65- 73.
11	WANG Y Q, FU W J, ZHANG X D, et al. Dynamic directed graph convolution network based ultra-short-term forecasting method of distributed photovoltaic power to enhance the resilience and flexibility of distribution network[J]. IET Generation, Transmission & Distribution, 2024, 18 (2): 337- 352.
12	ZHU Y, YANG L, YANG X Z, et al. The regional distributed PV ultra-short-term power forecasting based on static-dynamic spatiotemporal correlation modeling[C]//2023 IEEE International Conference on Energy Technologies for Future Grids (ETFG). Wollongong, Australia. IEEE, 2023: 1–6.
13	马畅. 考虑时空特性的分布式光伏短期概率预测[D]. 北京: 华北电力大学, 2023.
	MA Chang. Short-term probabilistic prediction of distributed photovoltaics considering temporal and spatial characteristics [D]. Beijing: North China Electric Power University, 2023.
14	官松泽, 唐钰本, 蔡争, 等. 基于Kmeans++-Bi-LSTM的太阳辐照度超短期预测[J]. 太阳能学报, 2023, 44 (12): 170- 174.
	GUAN Songze, TANG Yuben, CAI Zheng, et al. Ultra-short-term forecast of solar irradiance based on Kmeans++-Bi-LSTM[J]. Acta Energiae Solaris Sinica, 2023, 44 (12): 170- 174.
15	CHEN R F, LIU J M, WANG F, et al. Graph neural network-based wind farm cluster speed prediction[C]//2020 IEEE 3rd Student Conference on Electrical Machines and Systems (SCEMS). Jinan, China. IEEE, 2020: 982-987.
16	苏向敬, 宇海波, 符杨, 等. 基于DALSTM和联合分位数损失的海上风电功率概率预测[J]. 中国电力, 2023, 56 (11): 10- 19.
	SU Xiangjing, YU Haibo, FU Yang, et al. Probabilistic forecasting of offshore wind power based on dual-stage attentional LSTM and joint quantile loss function[J]. Electric Power, 2023, 56 (11): 10- 19.

[1]	孙通, 张沈习, 曹毅, 曹佳晨, 程浩忠. 计及5G基站可调特性的配电网分布式光伏准入容量鲁棒优化[J]. 中国电力, 2025, 58(2): 140-146.
[2]	周才期, 刘静利, 孙鹏凯, 张玉敏. 分布式光伏波动事件多级区间滚动预警方法[J]. 中国电力, 2024, 57(8): 96-107.
[3]	王海军, 居蓉蓉, 董颖华. 基于时空关联特征与B-LSTM模型的分布式光伏功率区间预测[J]. 中国电力, 2024, 57(7): 74-80.
[4]	刘韵艺, 汤渊, 苏盛, 吴裕宙, 王晓倩. 基于STL-Bayesian时空模型的分布式光伏系统异常检测[J]. 中国电力, 2024, 57(5): 222-231.
[5]	高岩, 吴汉斌, 张纪欣, 张华铭, 张沛. 基于组合深度学习的光伏功率日前概率预测模型[J]. 中国电力, 2024, 57(4): 100-110.
[6]	张宇, 魏新迟, 冯凯辉, 时珊珊, 孟子涵, 梁媛. 计及分布式光伏承载力的配电网侧独立储能充放电策略[J]. 中国电力, 2024, 57(4): 111-117.
[7]	杨鹏伟, 赵丽萍, 陈军法, 甄钊, 王飞, 李利明. 基于相似时段匹配与Transformer网络建模的分布式光伏超短期功率预测方法[J]. 中国电力, 2024, 57(12): 60-70.
[8]	陈奇芳, 李若凡, 夏明超, 吴迪, 邵尹池. 计及多维性能评估的新型配电网光伏选址定容方法[J]. 中国电力, 2024, 57(10): 172-178, 207.
[9]	白晶, 金广厚, 孙鹤林, 胡楚樊, 赵晋泉, 陈天华. 高渗透光伏配电网第三方主体调压辅助服务补偿与获取[J]. 中国电力, 2023, 56(4): 95-103,111.
[10]	段瑶, 高崇, 程苒, 吴亚雄, 黄烨, 刘志文. 考虑5G基站可调度潜力的配电网分布式光伏最大准入容量评估[J]. 中国电力, 2023, 56(12): 80-85, 99.
[11]	王晶, 袁懿, 邵尹池, 张晋奇, 丁然, 巩彦江. 考虑资源储备度的主动配电网多目标集群划分与电压控制方法[J]. 中国电力, 2023, 56(12): 69-79.
[12]	李娟, 汪家铭, 许苏迪, 姜云龙, 杨雄. 基于量子萤火虫算法的配电网故障恢复策略[J]. 中国电力, 2023, 56(12): 191-198.
[13]	苏向敬, 宇海波, 符杨, 田书欣, 李海瑜, 耿福海. 基于DALSTM和联合分位数损失的海上风电功率概率预测[J]. 中国电力, 2023, 56(11): 10-19.
[14]	李世辉, 王琪, 贾晓卜, 吴文传, 梁华洋, 朱琳. 考虑热泵负荷和分布式光伏的配微网协调调度[J]. 中国电力, 2022, 55(9): 29-37.
[15]	陈璨, 白明辉, 张婉明, 席海阔, 尹兆磊, 邵尹池, 王枭枭, 马原. 分布式光伏边界渗透率快速定位及消纳方案择优[J]. 中国电力, 2022, 55(8): 40-50.

基于分层关联性建模的分布式光伏功率超短期概率预测

Ultra-short-term Probabilistic Forecasting of Distributed Photovoltaic Power Generation Based on Hierarchical Correlation Modeling

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献 16

相关文章 15

编辑推荐

Metrics

模态框（Modal）标题

基于分层关联性建模的分布式光伏功率超短期概率预测

Ultra-short-term Probabilistic Forecasting of Distributed Photovoltaic Power Generation Based on Hierarchical Correlation Modeling

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献 16

相关文章 15

编辑推荐

Metrics