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

doi:10.11930/j.issn.1004-9649.202310049

中国电力 ›› 2024, Vol. 57 ›› Issue (7): 74-80.DOI: 10.11930/j.issn.1004-9649.202310049

• 新型电力系统不确定性建模与运行决策 • 上一篇下一篇

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

王海军¹(), 居蓉蓉²(), 董颖华²()

1. 南京铁道职业技术学院，江苏南京　210031
2. 中国电力科学研究院有限公司，江苏南京　210003

收稿日期:2023-10-18 出版日期:2024-07-28 发布日期:2024-07-23
作者简介:王海军（1982—），男，硕士，副教授，高级工程师，从事电力系统规划研究，E-mail：whj0421@163.com
居蓉蓉（1983—），女，通信作者，硕士，高级工程师，从事新型电力系统的不确定性建模研究，E-mail：1321929676@qq.com
董颖华（1985—），男，硕士，高级工程师，从事新能源发电检测与评估技术研究，E-mail：85090353@qq.com
基金资助:
江苏省自然科学基金资助项目（BK20210046）；江苏省333项目（500RC33322003 、5002023006-1）；南京铁道职业技术学院“青蓝工程”（QLXJ202111）；南京铁道职业技术学院轨道交通基础设施智能检测研究中心科研平台资助项目（KYPT2023003）。

Distributed Photovoltaic Power Interval Prediction Based on Spatio-Temporal Correlation Feature and B-LSTM Model

Haijun WANG¹(), Rongrong JU²(), Yinghua DONG²()

1. Nanjing Vocational Institute of Railway Technology, Nanjing 210031, China
2. China Electric Power Research Institute, Nanjing 210003, China

Received:2023-10-18 Online:2024-07-28 Published:2024-07-23
Supported by:
This work is supported by Natural Science Foundation of Jiangsu Province (No.BK20210046), the Sixth "333" Project of Jiangsu Province (No.500RC33322003, No.5002023006-1), Qing Lan Project of Nanjing Vocational Institute of Railway Technology (No.QLXJ202111), Funding for Scientific Research Platform for Railway Infrastructure Intelligent Inspection Research Centre of Nanjing Railway Vocational and Technical College (No.KYPT2023003).

摘要/Abstract

摘要：

提出一种基于时空关联特征与贝叶斯-长短期记忆神经网络（bayesian long short-term memory，B-LSTM）模型的分布式光伏功率区间预测方法。以长短期记忆神经网络（long short-term memory，LSTM）为基础构建近似贝叶斯神经网络，建立考虑时空关联特征的B-LSTM模型，利用其强大的记忆能力和特征提取不同特征尺度的模态分量，并进行分布式光伏功率区间预测。以某地区实际分布式光伏数据集进行算例分析，验证了所提方法的优越性。

关键词: 分布式光伏, 时空关联性, 区间预测

Abstract:

A distributed photovoltaic (PV) power interval prediction method based on spatio-temporal correlation features and bayesian long short-term memory (B-LSTM) model is proposed. The approximate Bayesian neural network is constructed by adding a Dropout layer based on the LSTM neural network to establish a B-LSTM model considering spatio-temporal correlation features, and its powerful memory and feature extraction capabilities are used to extract deep features for distributed PV power interval prediction for intrinsic mode function components with different feature scales. An arithmetic example is analysed with an actual distributed PV dataset in a region to verify the superiority of the proposed method.

Key words: distributed photovoltaics, spatio-temporal correlation, interval prediction

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.

Haijun WANG, Rongrong JU, Yinghua DONG. Distributed Photovoltaic Power Interval Prediction Based on Spatio-Temporal Correlation Feature and B-LSTM Model[J]. Electric Power, 2024, 57(7): 74-80.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202310049

https://www.electricpower.com.cn/CN/Y2024/V57/I7/74

图/表 9

表 1 预测结果评价

Table 1 Evaluation of projected results

方法	P_icp	P_iaw/kW
本文所提模型	0.932	0.934
B-LSTM	0.859	0.953
CEEMDAN-QRNN	0.833	1.158
QRNN	0.799	1.257

图 1 场站1预测结果对比

Fig.1 Comparison of forecast results for site 1

图 2 场站2预测结果对比

Fig.2 Comparison of forecast results for site 2

表 2 场站1预测结果评价

Table 2 Evaluation of predicted results for site 1

方法	P_icp	P_iaw/kW
本文所提模型	0.994	0.963
B-LSTM	0.946	1.020
CEEMDAN-QRNN	0. 972	1.318
QRNN	0.969	1.426

表 3 场站2预测结果评价

Table 3 Evaluation of predicted results for site 2

方法	P_icp	P_iaw/kW
本文所提模型	0.982	0.908
B-LSTM	0.968	0.983
CEEMDAN-QRNN	0. 975	1.383
QRNN	0.971	1.406

图 3 强波动日场站1预测结果对比

Fig.3 Comparison of forecast results for site 1 on days of strong volatility

图 4 强波动日场站2预测结果对比

Fig.4 Comparison of forecast results for site 2 on days of strong volatility

表 4 强波动日场站1预测结果评价

Table 4 Evaluation of prediction results for site 1 on strongly fluctuating days

方法	P_icp	P_iaw/kW
本文所提模型	0.922	1.096
B-LSTM	0.833	1.382
CEEMDAN-QRNN	0. 858	1.469
QRNN	0.832	1.594

表 5 强波动日场站2预测结果评价

Table 5 Evaluation of prediction results for site 2 on strongly fluctuating days

方法	P_icp	P_iaw/kW
本文所提模型	0.928	1.088
B-LSTM	0.858	1.268
CEEMDAN-QRNN	0. 830	1.348
QRNN	0.821	1.396

参考文献 35

1	郑伟民, 但扬清, 王晨轩, 等. 计及风-光-水-火多能协同的电网可再生能源消纳能力评估[J]. 中国电力, 2023, 56 (12): 248- 254.
	ZHENG Weimin, DAN Yangqing, WANG Chenxuan, et al. Evaluation of renewable energy consumption capacity in power grid considering the synergistic effect of wind-photovoltaic-hydro-thermal power[J]. Electric Power, 2023, 56 (12): 248- 254.
2	孙志媛, 彭博雅, 孙艳. 考虑多能互补的电力电量平衡优化调度策略[J]. 中国电力, 2024, 57 (1): 115- 122.
	SUN Zhiyuan, PENG Boya, SUN Yan. Optimal dispatch strategy of power and electricity balance based on multi-energy complementation[J]. Electric Power, 2024, 57 (1): 115- 122.
3	陈习勋, 吴凯彤, 何杰, 等. 基于集成机器学习模型的短期光伏出力区间预测[J]. 智慧电力, 2024, 52 (2): 87- 93, 107.
	CHEN Xixun, WU Kaitong, HE Jie, et al. Short term photovoltaic output interval prediction based on integrated machine learning model[J]. Smart Power, 2024, 52 (2): 87- 93, 107.
4	叶洪吉, 卫东, 郭倩, 等. 基于设计信息的分布式光伏电站预测发电量计算方法[J]. 太阳能学报, 2021, 42 (4): 253- 259.
	YE Hongji, WEI Dong, GUO Qian, et al. Calculation method of power generation forecast of distributed pv power station based on design information[J]. Acta Energiae Solaris Sinica, 2021, 42 (4): 253- 259.
5	董志强, 郑凌蔚, 苏然, 等. 一种基于IGWO-SNN的光伏出力短期预测方法[J]. 电力系统保护与控制, 2023, 51 (1): 131- 138.
	DONG Zhiqiang, ZHENG Lingwei, SU Ran, et al. An IGWO-SNN-based method for short-term forecast of photovoltaic output[J]. Power System Protection and Control, 2023, 51 (1): 131- 138.
6	王鑫. 分布式光伏发电全气象系统及出力预测方法研究[D]. 徐州: 中国矿业大学, 2021.
	WANG Xin. Research on meteorological system of distributed photovoltaic power generation and its output prediction method[D]. Xuzhou: China University of Mining and Technology, 2021.
7	吴春华, 董阿龙, 李智华, 等. 基于图相似日和PSO-XGBoost的光伏功率预测[J]. 高电压技术, 2022, 48 (8): 3250- 3259.
	WU Chunhua, DONG Along, LI Zhihua, et al. Photovoltaic power prediction based on graph similarity day and PSO-XGBoost[J]. High Voltage Engineering, 2022, 48 (8): 3250- 3259.
8	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/OL]. 电力系统自动化: 1–14.(2023-10-13). https://kns.cnki.net/kcms/detail/32.1180.TP.20231010.1627.011.html.
	ZHAO Yao, GAO Shaowei, LI Dongdong, et al. Short-term interval probability prediction of photovoltaic power based on the classification of similar weather and QRNN model[J/OL]. Automation of Electric Power Systems: 1–14.(2023-10-13). https://kns.cnki.net/kcms/detail/32.1180.TP.20231010.1627.011.html.
9	许彪, 徐青山, 黄煜, 等. 基于藤copula分位数回归的光伏功率日前概率预测[J]. 电网技术, 2021, 45 (11): 4426- 4435.
	XU Biao, XU Qingshan, HUANG Yu, et al. Day-ahead probabilistic forecasting of photovoltaic power based on vine copula quantile regression[J]. Power System Technology, 2021, 45 (11): 4426- 4435.
10	闫钇汛, 王丽婕, 郭洪武, 等. 基于多特征分析和提取的短期光伏功率预测[J]. 高电压技术, 2022, 48 (9): 3734- 3743.
	YAN Yixun, WANG Lijie, GUO Hongwu, et al. Short-term photovoltaic power prediction based on multi-feature analysis and extraction[J]. High Voltage Engineering, 2022, 48 (9): 3734- 3743.
11	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. DOI
	WANG Biao, LYU Yang, CHEN Zhong, 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. DOI
12	潘忠志, 孔宁, 王燕涛. 改进新能源消纳的配电网资源优化配置研究[J]. 东北电力大学学报, 2023, 43 (6): 71- 78.
	PAN Zhongzhi, KONG Ning, WANG Yantao. Joint optimal allocation method of energy-load-storage in power supply area to improve new energy consumption capacity[J]. Journal of Northeast Electric Power University, 2023, 43 (6): 71- 78.
13	焦田利, 章坚民, 李熊, 等. 基于空间相关性的大规模分布式用户光伏空间分群方法[J]. 电力系统自动化, 2019, 43 (21): 97- 102, 162. DOI
	JIAO Tianli, ZHANG Jianmin, LI Xiong, et al. Spatial clustering method for large-scale distributed user photovoltaics based on spatial correlation[J]. Automation of Electric Power Systems, 2019, 43 (21): 97- 102, 162. DOI
14	刘康, 刘鑫, 张蓬鹤, 等. 基于负荷尖峰特征LSTM自编码器的窃电识别方法[J]. 电力系统自动化, 2023, 47 (2): 96- 104. DOI
	LIU Kang, LIU Xin, ZHANG Penghe, et al. Identification method of electricity theft based on long short-term memory autoencoder with load peak features[J]. Automation of Electric Power Systems, 2023, 47 (2): 96- 104. DOI
15	刘昳娟, 陈云龙, 刘继彦, 等. 基于集成学习的分布式光伏发电功率日前预测[J]. 中国电力, 2022, 55 (9): 38- 45.
	LIU Yijuan, CHEN Yunlong, LIU Jiyan, et al. Ensemble learning-based day-ahead power forecasting of distributed photovoltaic generation[J]. Electric Power, 2022, 55 (9): 38- 45.
16	吉锌格, 李慧, 刘思嘉, 等. 基于MIE-LSTM的短期光伏功率预测[J]. 电力系统保护与控制, 2020, 48 (7): 50- 57.
	JI Xinge, LI Hui, LIU Sijia, et al. Short-term photovoltaic power forecasting based on MIE-LSTM[J]. Power System Protection and Control, 2020, 48 (7): 50- 57.
17	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. DOI
	WANG Yuqing, XU Fei, LIU Zhijian, 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. DOI
18	赵会茹, 赵一航, 郭森. 基于互补集合经验模态分解和长短期记忆神经网络的短期电力负荷预测[J]. 中国电力, 2020, 53 (6): 48- 55.
	ZHAO Huiru, ZHAO Yihang, GUO Sen. Short-term load forecasting based on complementary ensemble empirical mode decomposition and long short-term memory[J]. Electric Power, 2020, 53 (6): 48- 55.
19	HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9 (8): 1735- 1780. DOI
20	苏晨博, 刘崇茹, 徐诗甜, 等. 利用贝叶斯线性回归结合混合Copula函数分析风电功率的相关性[J]. 中国电力, 2021, 54 (8): 182- 189.
	SU Chenbo, LIU Chongru, XU Shitian, et al. Mix copula function based wind power correlation analysis: a Bayesian linear regression approach[J]. Electric Power, 2021, 54 (8): 182- 189.
21	杨京渝, 罗隆福, 阳同光, 等. 基于气象特征挖掘和改进深度学习模型的风电功率短期预测[J]. 电力自动化设备, 2023, 43 (3): 110- 116.
	YANG Jingyu, LUO Longfu, YANG Tongguang, et al. Wind power short-term forecasting based on meteorological feature exploring and improved deep learning model[J]. Electric Power Automation Equipment, 2023, 43 (3): 110- 116.
22	LIU Hui, LING Ningqing, LUO Zhiqiang, et al. Power grid short-term load forecasting method based on TCN-LSTM and meteorological similar day sets[J]. Smart Power, 2022, 50 (8): 30- 37.
23	WAN C, XU Z, PINSON P. Direct interval forecasting of wind power[J]. IEEE Transactions on Power Systems, 2013, 28 (4): 4877- 4878. DOI
24	黎敏, 林湘宁, 张哲原, 等. 超短期光伏出力区间预测算法及其应用[J]. 电力系统自动化, 2019, 43 (3): 10- 16. DOI
	LI Min, LIN Xiangning, ZHANG Zheyuan, et al. Interval prediction algorithm for Ultra-short-term photovoltaic output and its application[J]. Automation of Electric Power Systems, 2019, 43 (3): 10- 16. DOI
25	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.
26	黄南天, 郭玉, 赵暄远. 计及辐照区间划分的含光伏电源配电网源-荷联合场景生成[J]. 东北电力大学学报, 2023, 43 (5): 78- 84.
	HUANG Nantian, GUO Yu, ZHAO Xuanyuan. Combined source-load scenario generation for PV-containing distribution networks with calculation andirradiation interval classification[J]. Journal of Northeast Electric Power University, 2023, 43 (5): 78- 84.
27	佟曦, 侯朗博, 孙昊, 等. 高比例光伏和电动汽车接入配电网的无功优化[J]. 智慧电力, 2023, 51 (10): 31- 37, 102.
	TONG Xi, HOU Langbo, SUN Hao, et al. Reactive power optimization of distribution networks with high proportion of PV and EVs[J]. Smart Power, 2023, 51 (10): 31- 37, 102.
28	马君亮, 王智冬, 张述铭. 考虑县域光伏潜力评估的源网荷储协同规划[J]. 东北电力大学学报, 2023, 43 (3): 82- 90.
	MA Junliang, WANG Zhidong, ZHANG Shuming. Collaborative planning of Source-grid-load-storage considering county PV potential assessment[J]. Journal of Northeast Electric Power University, 2023, 43 (3): 82- 90.
29	魏欣荣, 吴俊勇, 丁然, 等. 基于光伏重心理论的配电网分布式光伏最大准入容量计算[J]. 电网技术, 2023, 47 (11): 4533- 4549.
	WEI Xinrong, WU Junyong, DING Ran, et al. Distributed PV hosting capacity calculation of distribution network based on PV barycenter theory[J]. Power System Technology, 2023, 47 (11): 4533- 4549.
30	时珊珊, 魏新迟, 张宇, 等. 考虑多模式融合的光储充电站储能系统优化运行策略[J]. 中国电力, 2023, 56 (3): 144- 153, 161.
	SHI Shanshan, WEI Xinchi, ZHANG Yu, et al. Optimal operation strategy of energy storage system in photovoltaic-storage charging station considering multi-mode integration[J]. Electric Power, 2023, 56 (3): 144- 153, 161.
31	钱仲豪, 胡骏, 沈思辰, 等. 考虑条件风险价值的多源协调优化运行策略[J]. 发电技术, 2023, 44 (6): 781- 789.
	QIAN Zhonghao, HU Jun, SHEN Sichen, et al. Multi-power coordinated optimization operation strategy considering conditional value at risk[J]. Power Generation Technology, 2023, 44 (6): 781- 789.
32	王鹤, 王钲淇, 韩皓, 等. 使用蒙特卡罗逐时估算模型的住宅配电网光伏准入容量研究[J]. 东北电力大学学报, 2023, 43 (1): 9- 19, 2, 99.
	WANG He, WANG Zhengqi, HAN Hao, et al. Research on photovoltaic hosting capacity of residential distribution network based on Monte Carlo hourly estimation framework[J]. Journal of Northeast Electric Power University, 2023, 43 (1): 9- 19, 2, 99.
33	丁琦欣, 覃洪培, 万灿, 等. 基于机会约束规划的配电网分布式光伏承载能力评估[J]. 东北电力大学学报, 2022, 42 (6): 28- 38.
	DING Qixin, QIN Hongpei, WAN Can, et al. Chance-constrained optimization-based distributed photovoltaic hosting capacity assessment of distribution networks[J]. Journal of Northeast Electric Power University, 2022, 42 (6): 28- 38.
34	付小标, 侯嘉琪, 李宝聚, 等. 一种二模态天气分型方法及其在光伏功率概率预测的应用[J]. 发电技术, 2024, 45 (2): 299- 311.
	FU Xiaobiao, HOU Jiaqi, LI Baoju, et al. A two-modal weather classification method and its application in photovoltaic power probability prediction[J]. Power Generation Technology, 2024, 45 (2): 299- 311.
35	钱乙卫, 田浩, 刘财华, 等. 考虑概率分布的分布式光伏无功下垂控制策略[J]. 发电技术, 2024, 45 (2): 273- 281.
	QIAN Yiwei, TIAN Hao, LIU Caihua, et al. Droop control strategy of distributed photovoltaic reactive power considering probability distribution[J]. Power Generation Technology, 2024, 45 (2): 273- 281.

[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]	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.
[4]	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.
[5]	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.
[6]	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.
[7]	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.
[8]	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.
[9]	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.
[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]	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.
[12]	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.
[13]	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.
[14]	李丰君, 王磊, 赵健, 张建宾, 张世尧, 田杨阳. 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.
[15]	庞传军, 张波, 余建明, 刘艳. 基于结构化负荷模型的电力负荷概率区间预测[J]. 中国电力, 2021, 54(9): 89-95.

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

Distributed Photovoltaic Power Interval Prediction Based on Spatio-Temporal Correlation Feature and B-LSTM Model

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 35

相关文章 15

编辑推荐

Metrics

模态框（Modal）标题

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

Distributed Photovoltaic Power Interval Prediction Based on Spatio-Temporal Correlation Feature and B-LSTM Model

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 35

相关文章 15

编辑推荐

Metrics