Probabilistic forecasting of regional solar power incorporating weather pattern diversity

被引:3
作者
Huang, Hao-Hsuan [1 ]
Huang, Yun-Hsun [1 ]
机构
[1] Natl Cheng Kung Univ, Dept Resources Engn, Tainan 701, Taiwan
关键词
Solar PV; Regional probabilistic forecasting; Regional weather patterns; Unsupervised learning; Ensemble voting; PREDICTION; IRRADIANCE; RADIATION; MODELS; DISTRIBUTIONS;
D O I
10.1016/j.egyr.2024.01.039
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
Power grid stability depends on the ability to forecast solar power generation at the regional level. Most previous research on probabilistic forecasting has focused on the use of machine learning to predict the output of individual solar power plants rather than regional solar power generation, and few studies have considered the effects of seasonal weather patterns at the regional level. In this study, climate and geographic data were collected from 83 weather stations between 2019 and 2021 for use in developing a probabilistic model by which to predict regional solar power generation. The results of weather pattern analysis based on unsupervised machine learning and ensemble voting were used to build a probabilistic quantile regression model for the shortterm prediction of regional solar power generation capacity. The efficacy of the model was assessed using data from 48 solar PV power plants, which included four sub-datasets pertaining to four target regions. Highly accurate results were consistently obtained across all regions in both the winter and summer seasons. The proposed probabilistic model outperformed conventional deterministic model by 6.55% and conventional probabilistic model by 4.03% in terms of total normalized mean absolute error (NMAE). Prediction intervals generated by the proposed model could be used as input parameters for regional power dispatch decisions.
引用
收藏
页码:1711 / 1722
页数:12
相关论文
共 59 条
[1]  
Aillaud P, 2020, IEEE PHOT SPEC CONF, P2688, DOI [10.1109/PVSC45281.2020.9300538, 10.1109/pvsc45281.2020.9300538]
[2]   Short-term probabilistic forecasting models using Beta distributions for photovoltaic plants [J].
Alfredo Fernandez-Jimenez, L. ;
Monteiro, Claudio ;
Ramirez-Rosado, Ignacio J. .
ENERGY REPORTS, 2023, 9 :495-502
[3]  
[Anonymous], 2021, INT ENERGY AGENCY, P224
[4]   Fast short-term global solar irradiance forecasting with wrapper mutual information [J].
Bouzgou, Hassen ;
Gueymard, Christian A. .
RENEWABLE ENERGY, 2019, 133 :1055-1065
[5]  
Bureau of Energy (BOE), 2023, Energy Statistics Annual Report
[6]  
Central Weather Bureau (CWB), 2022, Observation data inquire system
[7]   Computational solar energy - Ensemble learning methods for prediction of solar power generation based on meteorological parameters in Eastern India [J].
Chakraborty, Debojyoti ;
Mondal, Jayeeta ;
Barua, Hrishav Bakul ;
Bhattacharjee, Ankur .
RENEWABLE ENERGY FOCUS, 2023, 44 :277-294
[8]   A novel multiseed nonhierarchical data clustering technique [J].
Chaudhuri, D ;
Chaudhuri, BB .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 1997, 27 (05) :871-877
[9]   Proactively selection of input variables based on information gain factors for deep learning models in short-term solar irradiance forecasting [J].
Chen, Yunxiao ;
Bai, Mingliang ;
Zhang, Yilan ;
Liu, Jinfu ;
Yu, Daren .
ENERGY, 2023, 284
[10]   Short-term Solar Power Prediction Learning Directly from Satellite Images With Regions of Interest [J].
Cheng, Lilin ;
Zang, Haixiang ;
Wei, Zhinong ;
Ding, Tao ;
Xu, Ruiqi ;
Sun, Guoqiang .
IEEE TRANSACTIONS ON SUSTAINABLE ENERGY, 2022, 13 (01) :629-639