Sign in Subscribe
Green technology

Solar Power Generation Forecasting: A Study on Machine Learning Models

Strategic Insights

— 1 min read

A recent study from Sunway University has shed light on the importance of precise solar power generation forecasting for a renewable energy system to operate effectively and economically. Researchers applied various machine learning models to forecast solar power generation, with Random Forest outperforming all other models, achieving an R value of 0.877. The study highlights the challenges posed by unpredictable environmental and climatic conditions, emphasizing the need for accurate forecasting to integrate PV panels into traditional electrical grid systems.

Key Takeaways:

  • Solar power generation is a renewable energy source that uses sunlight to generate electricity, with photovoltaic (PV) panels converting sunlight into electrical energy.
  • The unpredictability of environmental and climatic conditions challenges the production of consistent and efficient electrical energy through PV panels.
  • Precise solar power generation forecasting is necessary for a renewable energy system to operate effectively and economically.
  • Random Forest outperformed all other machine learning models, achieving an R value of 0.877, while Support Vector Regression had the least performance with R2 = 0.487.
  • The study applied six machine learning models: Polynomial Regression, Support Vector Regression (SVR), K-Nearest Neighbours, Random Forest, Extreme Gradient Boosting (XGBoost), and Artificial Neural Network (ANN).
  • The research concluded that the predicted solar power generation is important in integrating PV panels into traditional electrical grid systems.

Statistics:

  • R value of 0.877 achieved by Random Forest model.
  • R2 value of 0.487 achieved by Support Vector Regression model.
  • Six machine learning models were applied in the study: Polynomial Regression, Support Vector Regression, K-Nearest Neighbours, Random Forest, Extreme Gradient Boosting, and Artificial Neural Network.
  • The study focused on predicting solar power generation in Selangor Darul, Malaysia.

Sources:

  • Forecasting Solar Power Generation As a Renewable Energy Utilizing Various Machine Learning Models. Theoretical and Applied Climatology, 2025;156(7).
  • NewsRx. New Renewable Energy Findings from Sunway University Discussed (Forecasting Solar Power Generation As a Renewable Energy Utilizing Various Machine Learning Models). Ecology, Environment & Conservation. July 11, 2025; p 587.

Read more