Scholarlink

Photovoltaic (PV) systems are essential to sustainable energy, but maintaining long-term efficiency requires data-efficient tools for predictive maintenance—especially when historical data is scarce. We propose a reinforcement learning (RL) framework combining digital twin simulations with a power loss regression model to estimate degradation from environmental inputs. The agent learns maintenance policies by maximizing an interpretable, economically grounded reward based on the net value of the PV system. We train our agent using three different RL algorithms (PPO, Maskable PPO, and Recurrent PPO) on observed and clear-sky irradiance data from real PV systems. All strategies outperform the no-maintenance baseline, with RPPO improving the net value by up to 37%, showing that effective, generalizable policies can be learned even under data constraints.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A Reinforcement Learning Framework for Optimizing Predictive Maintenance of Photovoltaic Systems

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Andrés F. Pérez,
  • Giulia Lombardi

摘要

Photovoltaic (PV) systems are essential to sustainable energy, but maintaining long-term efficiency requires data-efficient tools for predictive maintenance—especially when historical data is scarce. We propose a reinforcement learning (RL) framework combining digital twin simulations with a power loss regression model to estimate degradation from environmental inputs. The agent learns maintenance policies by maximizing an interpretable, economically grounded reward based on the net value of the PV system. We train our agent using three different RL algorithms (PPO, Maskable PPO, and Recurrent PPO) on observed and clear-sky irradiance data from real PV systems. All strategies outperform the no-maintenance baseline, with RPPO improving the net value by up to 37%, showing that effective, generalizable policies can be learned even under data constraints.