Scholarlink

<p>This study proposes a hybrid framework integrating a Transformer-based deep learning model for solar radiation forecasting with a Deep Deterministic Policy Gradient (DDPG) reinforcement learning agent for optimizing battery energy storage system (BESS) management in a photovoltaic (PV)-powered microgrid. Leveraging historical meteorological data from the National Solar Radiation Database (NSRDB) India dataset, the Transformer model predicts Global Horizontal Irradiance (GHI), which is used to estimate PV power output. This predicted PV power drives the DDPG agent, trained over 1000 episodes using MATLAB, to dynamically manage BESS charge/discharge rates. Compared to a rule-based baseline controller, the hybrid approach achieves superior performance, with an energy efficiency of 98.5% (vs. 85.2% for the baseline) and a 64% reduction in unmet demand over a 1749-hour simulation, alongside greater battery utilization. This work demonstrates the effectiveness of integrating advanced forecasting with adaptive control, offering a scalable solution for enhancing renewable energy systems in microgrids.</p>

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

Hybrid transformer DDPG framework for solar radiation forecasting and battery energy storage optimization in a PV-powered microgrid

  • 期刊论文

  • 发表日期：

    2025年10月25日

查看全文
  • Lijo Thomas J,
  • Balaji Ganesh Rajagopal,
  • V. N. Senthil Kumaran

摘要

This study proposes a hybrid framework integrating a Transformer-based deep learning model for solar radiation forecasting with a Deep Deterministic Policy Gradient (DDPG) reinforcement learning agent for optimizing battery energy storage system (BESS) management in a photovoltaic (PV)-powered microgrid. Leveraging historical meteorological data from the National Solar Radiation Database (NSRDB) India dataset, the Transformer model predicts Global Horizontal Irradiance (GHI), which is used to estimate PV power output. This predicted PV power drives the DDPG agent, trained over 1000 episodes using MATLAB, to dynamically manage BESS charge/discharge rates. Compared to a rule-based baseline controller, the hybrid approach achieves superior performance, with an energy efficiency of 98.5% (vs. 85.2% for the baseline) and a 64% reduction in unmet demand over a 1749-hour simulation, alongside greater battery utilization. This work demonstrates the effectiveness of integrating advanced forecasting with adaptive control, offering a scalable solution for enhancing renewable energy systems in microgrids.