Deep Reinforcement Learning for Global Maximum Power Point Tracking: Design and Experiments in Real Photovoltaic Systems

Jorge Felipe GaviriaMaría Isabella TorresLuis Felipe GiraldoCorinne AlonsoMichaël Bressan2026-03-222026-03-22202310.2139/ssrn.4621061https://doi.org/10.2139/ssrn.4621061https://andeanlibrary.org/handle/123456789/84233enPhotovoltaic systemReinforcement learningTracking (education)Power (physics)Maximum power point trackingComputer sciencePoint (geometry)Artificial intelligenceReinforcementDeep Reinforcement Learning for Global Maximum Power Point Tracking: Design and Experiments in Real Photovoltaic Systemspreprint