Prediction of Photovoltaic Power Output Using Environmental Parameters: A Comparative Study of Linear Regression and Random Forest

Read full text Summarise with VIRAT
Authors: Aarya Sawant, Prof. Kalpana Deorukhkar
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Accurate prediction of photovoltaic power output is essential for efficient energy management and reliable operation of smart grids. This study compares Linear Regression and Random Forest models for predicting photovoltaic AC power output using environmental parameters from a public solar dataset with more than 100,000 records. The input variables include solar irradiance, module temperature, ambient temperature, and wind speed, while direct electrical variables were excluded to avoid target leakage. The model performance was assessed using RMSE, MAE, and R². The results show that Random Forest achieved better performance than Linear Regression, with lower prediction errors and a higher R² value of 0.9831. The findings indicate that environmental-parameter-based machine learning models can provide accurate photovoltaic power prediction, and that Random Forest is better suited for capturing nonlinear relationships in the data.

Fields of Study & Subjects

Solar Radiation and Photovoltaics Photovoltaic System Optimization Techniques Energy Load and Power Forecasting

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
22 March 2026
Language
EN