[1]宋　玲,常隆涛,吕舜铭,等.基于多站点预测模型的分布式光伏电站智能选址方法[J].郑州大学学报(工学版),2025,46(02):119-126.[doi:10.13705/j.issn.1671-6833.2025.02.016]
　SONG Ling,CHANG Longtao,LYU Shunming,et al.Intelligent Site Selection of Distributed Photovoltaic Power Stations Based on a Multi-site Forecasting Model[J].Journal of Zhengzhou University (Engineering Science),2025,46(02):119-126.[doi:10.13705/j.issn.1671-6833.2025.02.016]
点击复制

基于多站点预测模型的分布式光伏电站智能选址方法()
分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
46
期数:
2025年02期
页码:
119-126
栏目:
出版日期:
2025-03-10

文章信息/Info

Title:
Intelligent Site Selection of Distributed Photovoltaic Power Stations Based on a Multi-site Forecasting Model
文章编号:
1671-6833(2025)02-0119-08
作者:
宋　玲1;  常隆涛1;  吕舜铭2;  杨朝晖1;  刘新锋1;  陈关忠1
1.山东建筑大学 计算机科学与技术学院,山东 济南 250101;2.国家电网信息通信云运营中心,北京 100000
Author(s):
SONG Ling1;  CHANG Longtao1;  LYU Shunming2;  YANG Zhaohui1;  LIU Xinfeng1;  CHEN Guanzhong1
1.College of Computer Science and Technology, ShanDong JianZhu University, Jinan 250101,China;2.Cloud Operations Center, State Grid Information & Telecommunication Branch, Beijing 100000, China
关键词:
智能选址;  多站点电力输出预测;  深度残差网络;  模型融合;  时空相关性
Keywords:
intelligent site selection;  multi-site power output forecasting;  deep residual networks;  model fusion;  spatiotemporal correlation
分类号:
TP391
DOI:
10.13705/j.issn.1671-6833.2025.02.016
文献标志码:
A
摘要:
为了提升光伏电站运营效率,针对多站点选址问题提出了一种多站点预测模型(MSFM),通过时空相关性、事件数据和气象因素来预测多站点的电力输出。引入三维张量来表示时空数据,采用张量分解技术恢复零条目,并利用三维张量和ResNet模型模拟时空邻接性、趋势、事件文本数据及气象影响。根据山东省济南市的 1 155 个光伏发电站运行数据和气象数据建立实验数据集,通过平均绝对误差、相对绝对误差、均方根误差和相对均方根误差来验证所提方法的效果,4个评价指标分别至少降低了2.3%、0.9%、2.6%、2.5%。实验结果表明:所提方法能够应用于多站点选址问题。
Abstract:
In order to improve the operational efficiency of photovoltaic (PV) power stations a proposal of multi-site forecasting model (MSFM) was proposed to addressing the multi-site location selection problem. In the proposed model, spatiotemporal correlation, event data, and meteorological factors were leveraged to predict power output across multiple sites. A three-dimensional tensor was introduced to represent spatiotemporal data, and tensor decomposition techniques were utilized to recover missing entries. Additionally, the spatiotemporal adjacency, trends, event text data, and meteorological impacts were modeled using both the three-dimensional tensor and the ResNet model. An experimental dataset was established using operational and meteorological data from 1,155 PV power stations in Jinan, Shandong Province. The performance of the proposed method was validated through mean absolute error, relative absolute error, root mean square error, and relative root mean square error, with at least 2.3%, 0.9%, 2.6%, and 2.5% reductions, respectively, in these four evaluation metrics, the experimental results demonstrated that the proposed method was applicable to multi-site location selection problems.

参考文献/References:

[1]DOLARA A, LEVA S, MANZOLINI G. Comparison of different physical models for PV power output prediction [J]. Solar Energy, 2015, 119: 83-99. 

[2]QIU X H, ZHANG L, REN Y, et al. Ensemble deep learning for regression and time series forecasting[C]∥ 2014 IEEE Symposium on Computational Intelligence in Ensemble Learning (CIEL). Piscataway: IEEE, 2014: 1-6. 
[3]TIAN J, OOKA R, LEE D. Multi-scale solar radiation and photovoltaic power forecasting with machine learning algorithms in urban environment: a state-of-the-art review [J]. Journal of Cleaner Production, 2023, 426: 139040. 
[4]MOO E J A, DZIB J T, CANTO-ESQUIVEL J, et al. Deep learning for photovoltaic power plant forecasting[C]∥ Communications in Computer and Information Science. Cham:Springer International Publishing, 2018:56-66. 
[5]李章晓, 宋微, 田野. 基于深度学习和进化计算的外汇预测与投资组合优化[J]. 郑州大学学报(工学版), 2019,40(1): 92-96. 
LI Z X, SONG W, TIAN Y. Exchange rate forecasting and portfolio optimization based on deep learning and evolutionary computation[J]. Journal of Zhengzhou University (Engineering Science), 2019, 40(1): 92-96. 
[6]YANG X Y, XU M L, XU S C, et al. Day-ahead forecasting of photovoltaic output power with similar cloud space fusion based on incomplete historical data mining [J]. Applied Energy, 2017, 206: 683-696. 
[7]LAI C S, ZHONG C K, PAN K D, et al. A deep learning based hybrid method for hourly solar radiation forecasting[J]. Expert Systems with Applications, 2021, 177: 114941. 
[8]GAO Y Y, LI P, YANG H F, et al. A solar radiation intelligent forecasting framework based on feature selection and multivariable fuzzy time series[J]. Engineering Applications of Artificial Intelligence, 2023, 126: 106986. 
[9]FANG H, LI J, SONG W Y. Sustainable site selection for photovoltaic power plant: an integrated approach based on prospect theory[J]. Energy Conversion and Management, 2018, 174: 755-768. 
[10] ALAMI MERROUNI A, ELWALI ELALAOUI F, MEZRHAB A, et al. Large scale PV sites selection by combining GIS and analytical hierarchy process. case study: eastern Morocco[J]. Renewable Energy, 2018, 119: 863-873. 
[11] BAWAZIR R O, ÇETIN N S, FADEL W. Optimum PV distributed generation based on grid and geographical area: a case study of Aden governorate, Yemen[J]. Energy Conversion and Management, 2023, 297: 117703. 
[12] LAN H, YIN H, HONG Y Y, et al. Day-ahead spatiotemporal forecasting of solar irradiation along a navigation route[J]. Applied Energy, 2018, 211: 15-27. 
[13] JEONG J, KIM H. Multi-site photovoltaic forecasting exploiting space-time convolutional neural network[J]. Energies, 2019, 12(23): 4490. 
[14] AGOUA X G, GIRARD R, KARINIOTAKIS G. Shortterm spatio-temporal forecasting of photovoltaic power production[J]. IEEE Transactions on Sustainable Energy, 2018, 9(2): 538-546. 
[15]WANG Y L, ZHENG Y, XUE Y X. Travel time estimation of a path using sparse trajectories[C]∥Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York : ACM, 2014: 25-34. 
[16] SHAFIQ M, GU Z Q. Deep residual learning for image recognition: a survey[J]. Applied Sciences, 2022, 12 (18): 8972. 
[17] HE K M, ZHANG X Y, REN S Q, et al. Identity mappings in deep residual networks[M]∥Lecture Notes in Computer Science. Cham: Springer International Publishing, 2016: 630-645.
[18] CUBILLOS M. Multi-site household waste generation forecasting using a deep learning approach[J]. Waste Management, 2020, 115: 8-14. 
[19] GUTIERREZ-COREA F V, MANSO-CALLEJO M A, MORENO-REGIDOR M P, et al. Forecasting short-term solar irradiance based on artificial neural networks and data from neighboring meteorological stations[J]. Solar Energy, 2016, 134: 119-131. 
[20] MARZOUQ M, ELFADILI H, ZENKOUAR K, et al. Short term solar irradiance forecasting via a novel evolutionary multi-model framework and performance assessment for sites with no solar irradiance data[J]. Renewable Energy, 2020, 157: 214-231. 
[21] PERSSON C, BACHER P, SHIGA T, et al. Multi-site solar power forecasting using gradient boosted regression trees[J]. Solar Energy, 2017, 150: 423-436. 
[22]WANG K J, QI X X, LIU H D. A comparison of day-ahead photovoltaic power forecasting models based on deep learning neural network[J]. Applied Energy, 2019, 251: 113315. 
[23] ZHANG J B, ZHENG Y, QI D K. Deep spatio-temporal residual networks for citywide crowd flows prediction[EB/ OL].(2016-10-01)[2024-09-02].https:∥doi. org/ 10.48550/arXiv.1610.00081.

更新日期/Last Update: 2025-03-13