RESEARCH ON ARTIFICIAL INTELLIGENCE-BASED MULTI-MODEL ENSEMBLE FORECAST OF GLOBAL HORIZONTAL IRRADIANCE IN PV STATIONS

Yuan Bin; Yu Tingzhao; Shen Yanbo; Mo Jingyue; Deng Hua

doi:10.19912/j.0254-0096.tynxb.2023-2100

PDF(1896 KB)

Acta Energiae Solaris Sinica ›› 2025, Vol. 46 ›› Issue (4) : 291-300. DOI: 10.19912/j.0254-0096.tynxb.2023-2100

RESEARCH ON ARTIFICIAL INTELLIGENCE-BASED MULTI-MODEL ENSEMBLE FORECAST OF GLOBAL HORIZONTAL IRRADIANCE IN PV STATIONS

Yuan Bin^1,2, Yu Tingzhao^1,2, Shen Yanbo^1,2, Mo Jingyue^1,2, Deng Hua³

Author information +

History +

Abstract

Based on the forecast of 4 numerical models: CMA-WSP, CMA-MESO, CMA-GD and WRF-SOLAR, as well as the observation data of 2022 collecting from 4 PV stations in Yangjiang city, Guangdong Province, the monthly multi-model ensemble forecasting experiments of global horizontal irradiance （GHI） were conducted by using LightGBM ensemble model. The results show that multi-model ensemble, when compared with the monthly optimal numerical model, can effectively reduce MAE and RMSE of GHI forecast by a range of 2.47%-32.71% and 5.46%-32.29%,respectively. There are considerable differences in the results of multi-model ensemble at different GHI value intervals. When GHI is below 400 W/m², the multi-model ensemble achieves the best performance, with 6.25%-44.44% decrease of MAE and 14.62%-43.07% decrease of RMSE, for 10 months in the entire year. The effect of the ensemble in the GHI interval between 400 W/m² and 700 W/m²ranks second, and the decreasing ranges of MAE and RMSE, for 6 months in the entire year, are 0.76%-34.59% and 4.14%-31.11% respectively. The multi-model ensemble has no effect, due to insufficient sample, when GHI is greater than 700 W/m². Under 4 typical weather conditions, i.e clear, partly cloudy, cloudy and overcast, the multi-model ensemble forecast is the closest to the real observation trend, and it also can illustrate the radiation fluctuation caused by variation of cloud cover.

Key words

solar radiation / forecasting / artificial intelligence / multi-model ensemble / PV station

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

Yuan Bin, Yu Tingzhao, Shen Yanbo, Mo Jingyue, Deng Hua. RESEARCH ON ARTIFICIAL INTELLIGENCE-BASED MULTI-MODEL ENSEMBLE FORECAST OF GLOBAL HORIZONTAL IRRADIANCE IN PV STATIONS[J]. Acta Energiae Solaris Sinica. 2025, 46(4): 291-300 https://doi.org/10.19912/j.0254-0096.tynxb.2023-2100

References

[1] 国家能源局2023年全国电力工业统计数据[EB/OL].2024: (2024-01-26)[2024-02-02]. https://www.nea.gov.cn/2024-01/26/c_1310762246.htm.
NEA statistical data of national power industry of2023[EB/OL]. 2024:(2024-01-26)[2024-02-02]. https://www.nea.gov.cn/2024-01/26/c_1310762246.htm.
[2] 金秋实, 王晓, 倪依琳, 等. “双碳” 背景下光伏行业发展研究与展望[J]. 环境保护, 2022, 50(S1): 44-50.
JIN Q S, WANG X, NI Y L, et al.Development research and outlook on photovoltaic industry under carbon peaking and carbon neutrality goals[J]. Environmental protection, 2022, 50(S1): 44-50.
[3] SINGLA P, DUHAN M, SAROHA S.A comprehensive review and analysis of solar forecasting techniques[J]. Frontiers in energy, 2022, 16(2): 187-223.
[4] GB/T 40607—2021, 调度侧风电或光伏功率预测系统技术要求[S].
GB/T 40607—2021, Technical requirements for dispatching side forecasting system of wind or photovoltaic power[S].
[5] SINGLA P, DUHAN M, SAROHA S.A point and interval forecasting of solar irradiance using different decomposition based hybrid models[J]. Earth science informatics, 2023, 16(3): 2223-2240.
[6] SILBER I, VERLINDE J, WANG S H, et al.Cloud influence on ERA5 and AMPS surface downwelling longwave radiation biases in West Antarctica[J]. Journal of climate, 2019, 32(22): 7935-7949.
[7] SOBRI S, KOOHI-KAMALI S, RAHIM N A.Solar photovoltaic generation forecasting methods: a review[J]. Energy conversion and management, 2018, 156: 459-497.
[8] RAHIMI N, PARK S, CHOI W, et al.A comprehensive review on ensemble solar power forecasting algorithms[J]. Journal of electrical engineering & technology, 2023, 18(2): 719-733.
[9] JOSE D M, VINCENT A M, DWARAKISH G S.Improving multiple model ensemble predictions of daily precipitation and temperature through machine learning techniques[J]. Scientific reports, 2022, 12(1): 4678.
[10] MEENAL R, BINU D, RAMYA K C, et al.Weather forecasting for renewable energy system: a review[J]. Archives of computational methods in engineering, 2022, 29(5): 2875-2891.
[11] GUERMOUI M, BENKACIALI S, GAIRAA K, et al.A novel ensemble learning approach for hourly global solar radiation forecasting[J]. Neural computing and applications, 2022, 34(4): 2983-3005.
[12] SUN S L, WANG S Y, ZHANG G W, et al.A decomposition-clustering-ensemble learning approach for solar radiation forecasting[J]. Solar energy, 2018, 163: 189-199.
[13] CHOI S, HUR J.An ensemble learner-based bagging model using past output data for photovoltaic forecasting[J]. Energies, 2020, 13(6): 1438.
[14] LEE J, WANG W, HARROU F, et al.Reliable solar irradiance prediction using ensemble learning-based models: a comparative study[J]. Energy conversion and management, 2020, 208: 112582.
[15] VAISH J, DATTA S S, SEETHALEKSHMI K.Short term load forecasting using ANN and ensemble models considering solar irradiance[C]//2020 International Conference on Electrical and Electronics Engineering (ICE3). Gorakhpur, India, 2020.
[16] ARORA I, GAMBHIR J, KAUR T.Solar irradiance forecasting using decision tree and ensemble models[C]//2020 Second International Conference on Inventive Research in Computing Applications (ICIRCA). Coimbatore, India, 2020.
[17] RAJASUNDRAPANDIYANLEEBANON T, KUMARESAN K, MURUGAN S, et al.Solar energy forecasting using machine learning and deep learning techniques[J]. Archives of computational methods in engineering, 2023, 30(5): 3059-3079.
[18] SINGLA P, DUHAN M, SAROHA S.An ensemble method to forecast 24-h ahead solar irradiance using wavelet decomposition and BiLSTM deep learning network[J]. Earth science informatics, 2022, 15(1): 291-306.
[19] 蒋锋, 杨嘉伟. 基于多目标优化集成学习的短期太阳辐射预测[J]. 云南大学学报(自然科学版), 2021, 43(3): 451-461.
JIANG F, YANG J W.Short-term solar radiation forecast based on ensemble learning of multi-objective optimization[J]. Journal of Yunnan University (natural sciences edition), 2021, 43(3): 451-461.
[20] 张鸿皓, 杨国华, 郑豪丰, 等. 基于多维特征分析的双层协同太阳辐照度预测[J]. 太阳能学报, 2022, 43(8): 143-149.
ZHANG H H, YANG G H, ZHENG H F, et al.Prediction of bi-layer cooperative solar radiation intensity based on multi-feature analysis[J]. Acta energiae solaris sinica, 2022, 43(8): 143-149.
[21] 马景奕, 王帅, 闫文君, 等. 基于RNN的短期太阳辐照度预测算法研究[J]. 科技通报, 2022, 38(5): 16-22.
MA J Y, WANG S, YAN W J, et al.Research on short term solar radiation prediction algorithm based on RNN[J]. Bulletin of science and technology, 2022, 38(5): 16-22.
[22] 官松泽, 唐钰本, 蔡争, 等. 基于K means++-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 S Z, TANG Y B, CAI Z, et al.Ultra-short-term forecast of solar irradiance based on K means++-BI-LSTM[J]. Acta energiae solaris sinica, 2023, 44(12): 170-174.
[23] 师浩琪, 郭力, 刘一欣, 等. 基于多源气象预报总辐照度修正的光伏功率短期预测[J]. 电力自动化设备, 2022, 42(3): 104-112.
SHI H Q, GUO L, LIU Y X, et al.Short-term forecasting of photovoltaic power based on total irradiance correction of multi-source meteorological forecast[J]. Electric power automation equipment, 2022, 42(3): 104-112.
[24] GB/T 37526—2019, 太阳能资源评估方法[S].
GB/T 37526—2019, Assessment method for solar energy[S].
[25] PARK J, MOON J, JUNG S, et al.Multistep-ahead solar radiation forecasting scheme based on the light gradient boosting machine: a case study of Jeju Island[J]. Remote sensing, 2020, 12(14): 2271.
[26] 李张群, 肖子牛, 丁煌, 等. 河南地区降水量和云量与地面太阳短波辐射的关系[J]. 气候与环境研究, 2022, 27(4): 504-512.
LI Z Q, XIAO Z N, DING H, et al.Relationship of surface solar shortwave radiation with precipitation and cloud cover in Henan Province[J]. Climatic and environmental research, 2022, 27(4): 504-512.
[27] 王传辉, 申彦波, 姚锦烽, 等. 3种再分析资料在太阳能资源评估中的适用性[J]. 太阳能学报, 2022, 43(8): 164-173.
WANG C H, SHEN Y B, YAO J F, et al.Applicability of three reanalysis data in assessment of solar energy resources in China[J]. Acta energiae solaris sinica, 2022, 43(8): 164-173.
[28] 杨溯, 石广玉, 王标, 等. 1961—2009年我国地面太阳辐射变化特征及云对其影响的研究[J]. 大气科学, 2013, 37(5): 963-970.
YANG S, SHI G Y, WANG B, et al.Trends in surface solar radiation (SSR) and the effect of clouds on SSR during 1961—2009 in China[J]. Chinese journal of atmospheric sciences, 2013, 37(5): 963-970.
[29] 秦放, 李登宣, 丁煌, 等. 基于CERES数据分析中国云对地表太阳辐射影响特征[J]. 太阳能学报, 2022, 43(9): 8-14.
QIN F, LI D X, DING H, et al.Chracteristics of surface solar radiation and cloud fraction in China based on CERES[J]. Acta energiae solaris sinica, 2022, 43(9): 8-14.
[30] GB/T 35663—2017, 天气预报基本术语[S].
GB/T 35663—2017, Basic terminology of weather forecast[S].