Temporal and Meteorological Adaptation of Artificial Intelligence Models for Photovoltaic Power Plant Operation Planning
Abstract
This paper presents a temporal and meteorological adaptation method for machine learning forecasting models applied to short-term power generation forecasting. The proposed method is based on the combined use of input data clustering and periodic model adaptation during operation. Clustering enables the identification of different operating conditions of the target system and the development of specialized local forecasting models, while temporal adaptation compensates for forecasting performance degradation caused by data drift. To evaluate the effectiveness of the proposed approach, an experimental study was conducted on a short-term photovoltaic power generation forecasting problem. A multi-year dataset of hourly meteorological observations was used. The baseline forecasting approach was compared with temporal adaptation, meteorological adaptation, and combined temporal–meteorological adaptation strategies. The best forecasting performance was achieved through the combined application of temporal and meteorological adaptation, demonstrating the effectiveness of accounting for both data drift and the heterogeneity of meteorological conditions.
Full Text:
PDF (Russian)References
A. A. Makarov, V. A. Kulagin, D. A. Grushevenko, and A. A. Galkina, Eds., Prognoz razvitiya energetiki mira i Rossii 2024 [Forecast of World and Russian Energy Development 2024]. Moscow: ERI RAS, 2024.
P. V. Ilyushin, “Integratsiya elektrostantsiy na osnove vozobnovlyaemykh istochnikov energii v Yedinuyu energeticheskuyu sistemu Rossii: obzor problemnykh voprosov i podkhodov k ikh resheniyu [Integration of renewable energy power plants into the Unified Energy System of Russia: review of challenges and solution approaches],” Vestnik Moskovskogo energeticheskogo instituta, no. 4, pp. 98–107, 2022.
P. V. Matrenin, V. Z. Manusov, M. Kh. Safaraliev, and N. Kh. Nazarov, Modeli i metody mashinnogo obucheniya v zadachakh prognozirovaniya generatsii na osnove vozobnovlyaemykh istochnikov energii [Machine Learning Models and Methods for Forecasting Renewable Energy Generation]. Novosibirsk: Novosibirsk State Technical University, 2024.
V. Prema, M. S. Bhaskar, D. Almakhles [et al.], “Critical Review of Data, Models and Performance Metrics for Wind and Solar Power Forecast,” IEEE Access, vol. 10, pp. 667–688, 2022.
A. M. Glazunova and D. V. Kovalchuk, “Algoritm formirovaniya sutochnykh grafikov nagruzok aktivnogo energeticheskogo kompleksa s vetrovoy i solnechnoy stantsiyami [Algorithm for forming daily load curves of an active energy complex with wind and solar power plants],” Elektrichestvo, no. 8, pp. 50–59, 2024.
P. Wang, E. Du, N. Zhang [et al.], “Power system planning with high renewable energy penetration considering demand response,” Global Energy Interconnection, vol. 4 (1), pp. 69–80, 2021.
N. E. Benti, M. D. Chaka, and A. G. Semie, “Forecasting Renewable Energy Generation with Machine Learning and Deep Learning: Current Advances and Future Prospects,” Sustainability, vol. 15, art. 7087, 2023.
N. N. Sergeev and P. V. Matrenin, “Obzor mezhdunarodnogo opyta v prognozirovanii generatsii vozobnovlyaemykh istochnikov energii s pomoshchyu metodov mashinnogo obucheniya [Review of international experience in forecasting renewable energy generation using machine learning methods],” iPolytech Journal, vol. 27 (2), pp. 354–369, 2023.
A. Yu. Gorshenin, A. S. Gritsay, and L. A. Denisova, “Primenenie mashinnogo obucheniya derevyev resheniy dlya kratkosrochnogo prognozirovaniya elektropotrebleniya [Application of decision-tree machine learning for short-term electricity demand forecasting],” Izvestiya Tulskogo gosudarstvennogo universiteta. Tekhnicheskie nauki, vol. 11, pp. 226–231, 2023.
S. Fang and H. Chiang, “A High-Accuracy Wind Power Forecasting Model,” IEEE Transactions on Power Systems, vol. 32 (2), pp. 1589–1590, 2017.
D. E. Namiot and E. A. Ilyushin, “Monitoring sdviga dannykh v modelyakh mashinnogo obucheniya [Data drift monitoring in machine learning models],” International Journal of Open Information Technologies, vol. 10 (12), pp. 84–93, 2022.
M. H. Bin Kamilin, S. Yamaguchi, and M. A. Bin Ahmadon, “Radian Scaling and Its Application to Enhance Electricity Load Forecasting in Smart Cities Against Concept Drift,” Smart Cities, vol. 7, pp. 3412–3436, 2024.
Yu. N. Isaev, O. V. Arkhipova, V. Z. Kovalev, and R. N. Khamitov, “Adaptivnoe kratkosrochnoe prognozirovanie potrebleniya elektroenergii avtonomnymi energosistemami malykh severnykh poseleniy na osnove metodov korrelyatsionnogo analiza [Adaptive short-term electricity demand forecasting for autonomous power systems of small northern settlements based on correlation analysis methods],” Izvestiya Tomskogo politekhnicheskogo universiteta. Inzhiniring georesursov, vol. 334 (2), pp. 224–239, 2023.
A. S. Glazyrin, E. V. Bolovin, O. V. Arkhipova [et al.], “Adaptivnoe kratkosrochnoe prognozirovanie potrebleniya elektroenergii avtonomnymi energosistemami malykh severnykh poseleniy na osnove metodov retrospektivnogo regressionnogo analiza [Adaptive short-term electricity demand forecasting for autonomous power systems of small northern settlements based on retrospective regression analysis methods],” Izvestiya Tomskogo politekhnicheskogo universiteta. Inzhiniring georesursov, vol. 334 (4), pp. 231–248, 2023.
P. V. Matrenin and R. N. Khamitov, “Algoritm formirovaniya strategii avtomaticheskogo obnovleniya modeley iskusstvennogo intellekta v zadachakh prognozirovaniya v elektroenergetike [Algorithm for forming a strategy for automatic updating of artificial intelligence models in electric power forecasting problems],” Inzhenernyy vestnik Dona, no. 7, pp. 228–247, 2025.
Z. Zhang, C. Wang, X. Peng [et al.], “Solar Radiation Intensity Probabilistic Forecasting Based on K-Means Time Series Clustering and Gaussian Process Regression,” IEEE Access, vol. 9, pp. 89079–89092, 2021.
J. F. L. de Oliveira, P. S. G. de Mattos Neto, H. V. Siqueira [et al.], “Forecasting Methods for Photovoltaic Energy in the Scenario of Battery Energy Storage Systems: A Comprehensive Review,” Energies, vol. 16, p. 6638, 2023.
M. Brenna, F. Foiadelli, M. Longo, and D. Zaninelli, “Energy Storage Control for Dispatching Photovoltaic Power,” IEEE Transactions on Smart Grid, vol. 9 (4), pp. 2419–2428, 2018.
V. Sharma, A. Cortes, and U. Cali, “Use of Forecasting in Energy Storage Applications: A Review,” IEEE Access, vol. 9, pp. 114690–114704, 2021.
P. V. Matrenin, A. I. Khalyasmaa, V. V. Gamaley [et al.], “Povyshenie tochnosti prognozirovaniya generatsii fotoelektricheskikh stantsiy na osnove algoritmov k-srednikh i k-blizhayshikh sosedey [Improving photovoltaic generation forecasting accuracy using k-means and k-nearest neighbors algorithms],” Energetika. Izvestiya vysshikh uchebnykh zavedeniy i energeticheskikh obedineniy SNG, vol. 66 (4), pp. 305–321, 2023.
P. V. Matrenin and R. N. Khamitov, “Operativnoe prognozirovanie vyrabotki vetroenergeticheskikh ustanovok s ispolzovaniem klasterizatsii i detektirovaniya vybrosov [Short-term forecasting of wind power generation using clustering and outlier detection],” Problemy regionalnoy energetiki, no. 1 (69), pp. 138–149, 2026.
R. M. Arias Velasquez, “A Case Study of NeuralProphet and Nonlinear Evaluation for High Accuracy Prediction in Short-Term Forecasting in PV Solar Plant,” Heliyon, vol. 8 (9), art. e10639, 2022.
A. A. du Plessis, J. M. Strauss, and A. J. Rix, “Short-Term Solar Power Forecasting: Investigating the Ability of Deep Learning Models to Capture Low-Level Utility-Scale Photovoltaic System Behaviour,” Applied Energy, vol. 285, art. 116395, 2021.
Holmgren W. F., Hansen C. W., Mikofski M. A. pvlib python: a python package for modeling solar energy systems. Journal of Open Source Software, 2018, 3(29), 884. DOI: 10.21105/joss.00884
Refbacks
- There are currently no refbacks.
Abava Кибербезопасность ИТ-КОНГРЕСС ВМК МГУ 2026 СНЭ
ISSN: 2307-8162