Advanced Ensemble Machine Learning for Photovoltaic Production Forecasting in Tropical Microgrids: Application on the Katsepy Site, Madagascar
Linda Christelle Mevalaza1, Andrianajaina Todizara2, Rakotoarisoa Armand Jean Claude3, Herve Mangel4, Jean Nirinarison Razafinjaka5
1Linda Christelle Mevalaza, Student, Department of Electrical and Automation Engineering, Doctoral School of Renewable Energies and Environment, University of Antsiranana, Madagascar.
2Dr. Andrianajaina Todizara, Researcher, Department of Electrical and Electronic Engineering, Higher Polytechnic School, University of Antsiranana, Maagascar.
3Dr. Rakotoarisoa Armand Jean Claude, Professor, Department of Electrical and Electronic Engineering, University of Antsiranana, Madagascar.
4Hervé Mangel, Assistant Professor, Department of Electrical and Industrial Computing Engineering, Dupuy de Lôme, Research Institute (UMR CNRS 6027 IRDL).
5Jean Nirinarison Razafinjaka, Professor, Department of Electrical and Electronic Engineering, Higher Polytechnic School, Antsiranana, Madagascar.
Manuscript received on 20 October 2025 | First Revised Manuscript received on 07 November 2025 | Second Revised Manuscript received on 16 December 2025 | Manuscript Accepted on 15 January 2026 | Manuscript published on 30 January 2026 | PP: 1-7 | Volume-14 Issue-5, January 2026 | Retrieval Number: 100.1/ijrte.D830814041125 | DOI: 10.35940/ijrte.D8308.14041125
Open Access | Editorial and Publishing Policies | Cite | Zenodo | OJS | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open-access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: This article presents a Machine Learning ensemble model for photovoltaic (PV) production forecasting, developed to address energy management challenges in rural tropical microgrid environments. The site studied is located in Katsepy, Madagascar, where the reliability of energy forecasts remains a significant challenge due to high climate variability. The main objective is to design a more accurate and adaptable forecasting tool to enable adequate energy planning and system operation. The methodology is based on historical photovoltaic production data and meteorological data collected between 2005 and 2023 from the PVGIS online platform. Several regression algorithms were evaluated, including Random Forests, Bagging, and Gradient Boosting, to identify the models best suited to the local context. Among these, Gradient Boosting showed the best performance according to RMSE, MAE, MAPE and R² measurements, followed closely by Random Forest and Bagging. The experimental process consists of two stages: first, validation using actual 2023 data, and then forward-looking forecasts for 2024 incorporating real temperature data. To improve accuracy and robustness, a Stacking ensemble model was constructed, combining the three best performing algorithms as base estimators and the Extra Trees Regressor as the meta-model. This ensemble approach consistently outperformed the individual models and provided realistic production estimates for 2024, indicating a moderate decline in photovoltaic production compared to 2023, driven by observed climate variations. The proposed forecasting framework provides a solid foundation for future work on optimal energy management and fault diagnosis in the Katsepy microgrid system, with great potential for adaptation to other tropical coastal regions.
Keywords: Forecasting, Photovoltaic Production, Tropical Microgrid, Machine Learning Model, Climate Variation.
Scope of the Article: Electrical Engineering