基于横向联邦学习的分布式光伏超短期功率预测方法

蒙飞; 李江鹏; 王鑫; 徐恒山; 祁鑫; 杨慧彪

doi:10.19912/j.0254-0096.tynxb.2023-1553

PDF(1236 KB)

太阳能学报 ›› 2025, Vol. 46 ›› Issue (1) : 686-695. DOI: 10.19912/j.0254-0096.tynxb.2023-1553

基于横向联邦学习的分布式光伏超短期功率预测方法

祁鑫¹, 杨慧彪², 蒙飞¹, 李江鹏¹, 王鑫¹, 徐恒山³

作者信息 +

DISTRIBUTED PHOTOVOLTAIC SHORT-TERM POWER PREDICITION METHOD BASED ON HORIZONTAL FEDERAL LEARNING

Qi Xin¹, Yang Huibiao², Meng Fei¹, Li Jiangpeng¹, Wang Xin¹, Xu Hengshan³

Author information +

文章历史 +

摘要

针对目前大多数分布式光伏系统无法应对其所承载用户的复杂用能行为给并网过程造成的影响,且用户数据隐私问题导致传统集中式的预测算法并不适用的问题,提出一种基于横向联邦学习的分布式光伏超短期功率预测方法,结合历史数据、光伏阵列的出力和用户用能行为等信息在本地站点构建基于AdaRNN的功率预测模型,利用门控循环单元提取特征参数,用于横向联邦学习网络对模型参数的聚合优化,实现了用户数据的可用不可见。通过仿真验证表明,该方法实现了用户隐私数据的保护,并有效提升了分布式光伏超短期预测功率的精度。

Abstract

Aiming at the problem that most distributed PV systems are unable to cope with the impact of the complex energy-use behaviour of the users they carry on the grid-connection process, and that the privacy of user data leads to the inapplicability of traditional centralized prediction algorithms, an ultra-short-term distributed PV power prediction method based on transversal federated learning is proposed, which combines the information on historical data, PV array's output and users' energy-use behaviour to construct an AdaRNN-based power prediction model at the local site. The power prediction model based on AdaRNN is constructed at the local site, and the feature parameters are extracted using gated loop units, which are used for the aggregation and optimisation of the model parameters by the horizontal federated learning network to achieve the availability of the user data without visibility. Simulation validation shows that the method achieves the protection of user privacy data and effectively improves the accuracy of distributed PV ultra-short-term prediction power.

导出引用

祁鑫, 杨慧彪, 蒙飞, 李江鹏, 王鑫, 徐恒山. 基于横向联邦学习的分布式光伏超短期功率预测方法[J]. 太阳能学报. 2025, 46(1): 686-695 https://doi.org/10.19912/j.0254-0096.tynxb.2023-1553

Qi Xin, Yang Huibiao, Meng Fei, Li Jiangpeng, Wang Xin, Xu Hengshan. DISTRIBUTED PHOTOVOLTAIC SHORT-TERM POWER PREDICITION METHOD BASED ON HORIZONTAL FEDERAL LEARNING[J]. Acta Energiae Solaris Sinica. 2025, 46(1): 686-695 https://doi.org/10.19912/j.0254-0096.tynxb.2023-1553

中图分类号： TM615

参考文献

[1] 张智刚, 康重庆. 碳中和目标下构建新型电力系统的挑战与展望[J]. 中国电机工程学报, 2022, 42(8): 2806-2819.
ZHANG Z G, KANG C Q.Challenges and prospects for constructing the new-type power system towards a carbon neutrality future[J]. Proceedings of the CSEE, 2022, 42(8): 2806-2819.
[2] 卓振宇, 张宁, 谢小荣, 等. 高比例可再生能源电力系统关键技术及发展挑战[J]. 电力系统自动化, 2021, 45(9): 171-191.
ZHUO Z Y, ZHANG N, XIE X R, et al.Key technologies and developing challenges of power system with high proportion of renewable energy[J]. Automation of electric power systems, 2021, 45(9): 171-191.
[3] WANG P, ZHANG S N, PU Y R, et al.Estimation of photovoltaic power generation potential in 2020 and 2030 using land resource changes: an empirical study from China[J]. Energy, 2021, 219: 119611.
[4] 张迪. 分布式发电市场化环境下光伏发电规划与电网协调优化运行技术研究[D]. 武汉: 华中科技大学, 2021.
ZHANG D.Research on photovoltaic generation planning and coordinated optimal operation technology of power grid in the marketization environment of distributed generation[D]. Wuhan: Huazhong University of Science and Technology, 2021.
[5] 孙玲玲, 李海滨, 贾清泉, 等. 面向用户侧分布式光伏资源集群开发的博弈策略[J]. 电力系统自动化, 2023, 47(10): 26-37.
SUN L L, LI H B, JIA Q Q, et al.Game strategy for cluster development of user-side distributed photovoltaic resources[J]. Automation of electric power systems, 2023, 47(10): 26-37.
[6] 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.
[7] 赵杰. 光伏发电并网系统的相关技术研究[D]. 天津: 天津大学, 2012.
ZHAO J.Study on related technologies of grid-connected photovoltaic power system[D]. Tianjin: Tianjin University, 2012.
[8] 王洪坤, 葛磊蛟, 李宏伟, 等. 分布式光伏发电的特性分析与预测方法综述[J]. 电力建设, 2017, 38(7): 1-9.
WANG H K, GE L J, LI H W, et al.A review on characteristic analysis and prediction method of distributed PV[J]. Electric power construction, 2017, 38(7): 1-9.
[9] 王春平. 基于光伏功率预测的分布式能源系统优化[D]. 上海: 上海交通大学, 2020.
WANG C P.Distributed energy system optimization based on photovoltaic power prediction[D]. Shanghai: Shanghai Jiao Tong University, 2020.
[10] 陈璨, 白明辉, 张婉明, 等. 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.
CHEN C, BAI M H, ZHANG W M, et al.Fast positioning of marginal hosting capacity and optimal selection of accommodation scheme for distributed PVs[J]. Electric power, 2022, 55(8): 40-50.
[11] 马原, 张雪敏, 甄钊, 等. 基于修正晴空模型的超短期光伏功率预测方法[J]. 电力系统自动化, 2021, 45(11): 44-51.
MA Y, ZHANG X M, ZHEN Z, et al.Ultra-short-term photovoltaic power prediction method based on modified clear-sky model[J]. Automation of electric power systems, 2021, 45(11): 44-51.
[12] 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.
[13] 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 H J, WEI D, GUO Q, 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.
[14] 陈昌松, 段善旭, 殷进军. 基于神经网络的光伏阵列发电预测模型的设计[J]. 电工技术学报, 2009, 24(9): 153-158.
CHEN C S, DUAN S X, YIN J J.Design of photovoltaic array power forecasting model based on neutral network[J]. Transactions of China Electrotechnical Society, 2009, 24(9): 153-158.
[15] 陈昌松. 光伏微网的发电预测与能量管理技术研究[D]. 武汉: 华中科技大学, 2011.
CHEN C S.Research on power forecasting and energy management for photovoltaic microgrid[D]. Wuhan: Huazhong University of Science and Technology, 2011.
[16] WANG F, MI Z Q, SU S, et al.A practical model for single-step power prediction of grid-connected PV plant using artificial neural network[C]//2011 IEEE PES Innovative Smart Grid Technologies. Perth, WA, 2011: 1-4.
[17] 王超洋, 张蓝宇, 刘铮, 等. 基于特征挖掘的indRNN光伏发电功率预测[J]. 电力系统及其自动化学报, 2021, 33(4): 17-22.
WANG C Y, ZHANG L Y, LIU Z, et al.Feature mining based indRNN photovoltaic power generation prediction[J]. Proceedings of the CSU-EPSA, 2021, 33(4): 17-22.
[18] 刘国海, 孙文卿, 吴振飞, 等. 基于Attention-GRU 的短期光伏发电功率预测[J]. 太阳能学报, 2022, 43(2): 226-232.
LIU G H, SUN W Q, WU Z F, et al.Shortterm photovoltaic power forecasting based on Attention-GRU model[J]. Acta energiae solaris sinica, 2022, 43(2): 226-232.
[19] 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.
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.
[20] KAREVAN Z, SUYKENS J A K. Transductive LSTM for time-series prediction: an application to weather forecasting[J]. Neural networks, 2020, 125: 1-9.
[21] 郝颖, 车建峰, 冬雷, 等. 一种基于邻域保持的数值天气预报数据降维可信度评估准则[J]. 太阳能学报, 2022, 43(6): 106-114.
HAO Y, CHE J F, DONG L, et al.A reliability evaluation criterion for dimension reduction of numerical weather prediction data based on neighborhood preservation[J]. Acta energiae solaris sinica, 2022, 43(6): 106-114.
[22] DONG L, WANG L J, KHAHRO S F, et al.Wind power day-ahead prediction with cluster analysis of NWP[J]. Renewable and sustainable energy reviews, 2016, 60: 1206-1212.
[23] WANG F, ZHANG Z Y, LIU C, et al.Generative adversarial networks and convolutional neural networks based weather classification model for day ahead short-term photovoltaic power forecasting[J]. Energy conversion and management, 2019, 181: 443-462.
[24] 王超. 基于卫星云图的光伏电站集群功率波动模式识别与预测方法研究[D]. 北京: 华北电力大学, 2021.
WANG C.Research on fluctuation pattern recognition and forecasting method of photovoltaic power station cluster power based on satellite cloud images[D]. Beijing: North China Electric Power University, 2021.
[25] 张臻, 陈天鹏, 王磊, 等. 基于地基云图的超短期太阳辐照预测方法与装置研究[J]. 太阳能学报, 2023, 44(1): 133-140.
ZHANG Z, CHEN T P, WANG L, et al.Research on ultra-short-term solar irradiance prediction method and device based on ground-based cloud images[J]. Acta energiae solaris sinica, 2023, 44(1): 133-140.
[26] 丁明, 徐志成, 赵波, 等. 考虑云层影响的大型光伏发电系统辐照强度计算模型[J]. 中国电机工程学报, 2015, 35(17): 4291-4299.
DING M, XU Z C, ZHAO B, et al.Solar irradiance model for large-scale photovoltaic generation considering passing cloud shadow effect[J]. Proceedings of the CSEE, 2015, 35(17): 4291-4299.
[27] 陈志宝, 丁杰, 周海, 等. 地基云图结合径向基函数人工神经网络的光伏功率超短期预测模型[J]. 中国电机工程学报, 2015, 35(3): 561-567.
CHEN Z B, DING J, ZHOU H, et al.A model of very short-term photovoltaic power forecasting based on ground-based cloud images and RBF neural network[J]. Proceedings of the CSEE, 2015, 35(3): 561-567.
[28] WANG K J, QI X X, LIU H D.Photovoltaic power forecasting based LSTM-convolutional network[J]. Energy, 2019, 189: 116225.
[29] ZHU L G, LIU Z J, HAN S.Deep leakage from gradients[J].Advances in neural information processing systems,2019, 32(5): 32-44.