Scholarlink

This research aims to analyze solar irradiance prediction by drawing on the HI-SEAS weather station’s meteorological data estimating from September 2016 to December 2016. Machine learning algorithms such as XGBoost and Multi-Layer Perceptron(MLP) were implemented to measure solar irradiance. The implementation was based on parameters such as temperature, humidity, pressure, wind speed, and cloud cover. XGBoost surpassed MLP by achieving Root Mean Squared Error(RMSE) value of 81.45 W/m2, Mean Absolute Error(MAE) of 32.43 W/m2 and an R-squared score of 0.93, in comparison to the MLP’s RMSE of 100.06 W/m2, MAE of 43.75 W/m2, and R-squared score of 0.89. Key feature selection techniques utilised were SelectKBest and Extra Tree Classifier which helped in identifying cloud cover and temperature as crucial factors in predicting solar irradiance. The results fully demonstrated the performance of XGBoost in producing precise forecasts for enhancing renewable energy systems.

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

Performance Evaluation of a Machine Learning Based Framework for Solar Irradiance Prediction

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Arpit Tripathi,
  • Aabhya Jain,
  • Oshin Sharma

摘要

This research aims to analyze solar irradiance prediction by drawing on the HI-SEAS weather station’s meteorological data estimating from September 2016 to December 2016. Machine learning algorithms such as XGBoost and Multi-Layer Perceptron(MLP) were implemented to measure solar irradiance. The implementation was based on parameters such as temperature, humidity, pressure, wind speed, and cloud cover. XGBoost surpassed MLP by achieving Root Mean Squared Error(RMSE) value of 81.45 W/m2, Mean Absolute Error(MAE) of 32.43 W/m2 and an R-squared score of 0.93, in comparison to the MLP’s RMSE of 100.06 W/m2, MAE of 43.75 W/m2, and R-squared score of 0.89. Key feature selection techniques utilised were SelectKBest and Extra Tree Classifier which helped in identifying cloud cover and temperature as crucial factors in predicting solar irradiance. The results fully demonstrated the performance of XGBoost in producing precise forecasts for enhancing renewable energy systems.