Scholarlink

An accurate solar energy prediction is vital in today’s world for optimizing the renewable energy systems and to lead sustainable energy future. As solar power generation depends upon the weather that changes continuously, reliable prediction is critical for balancing supply and demand, minimizing energy wastage, and enhancing grid resilience. This study employs a Random Forest Regressor to forecast solar power generation using historical meteorological data and other time-based features. By incorporating key environmental factors such as temperature, humidity, wind speed, and solar radiation, along with temporal attributes, the model effectively captures complex, nonlinear patterns in solar power fluctuations. With an ensemble learning approach utilizing 1000 decision trees, the model enhances predictive accuracy while mitigating overfitting. This study contributes to the development of more reliable forecasting techniques, enabling smarter energy planning, improved grid stability, and transition towards a more sustainable future powered by renewable energy sources.

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

Solar Energy Prediction Using Machine Learning for Sustainable Energy Future

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Samridhi Goyal,
  • Somya R. Goyal

摘要

An accurate solar energy prediction is vital in today’s world for optimizing the renewable energy systems and to lead sustainable energy future. As solar power generation depends upon the weather that changes continuously, reliable prediction is critical for balancing supply and demand, minimizing energy wastage, and enhancing grid resilience. This study employs a Random Forest Regressor to forecast solar power generation using historical meteorological data and other time-based features. By incorporating key environmental factors such as temperature, humidity, wind speed, and solar radiation, along with temporal attributes, the model effectively captures complex, nonlinear patterns in solar power fluctuations. With an ensemble learning approach utilizing 1000 decision trees, the model enhances predictive accuracy while mitigating overfitting. This study contributes to the development of more reliable forecasting techniques, enabling smarter energy planning, improved grid stability, and transition towards a more sustainable future powered by renewable energy sources.