Development of A Linear Regression-Based Predictive Model of Solar Panel Efficiency To Enhance Students’ Understanding of Renewable Energy And Data Analysis Skills

Abstract

The global energy crisis and the need to reduce carbon emissions have increased interest in renewable energy, with solar energy emerging as a key solution. Yet, students’ understanding of solar panel efficiency and their data analysis skills remain limited, restricting their ability to evaluate renewable energy technologies effectively. This study maps research trends on linear regression–based predictive models for solar panel efficiency and explores their potential to enhance students’ understanding of renewable energy and analytical skills. A bibliometric approach was applied to publications indexed in Scopus from 2005 to 2025. Metadata—including titles, abstracts, keywords, authors, years, and sources—were extracted, cleaned using Microsoft Excel, and analyzed with the Bibliometrix package in R (Biblioshiny interface). Analyses covered annual scientific production, relevant sources, authorship networks, country contributions, and keyword co-occurrence. Results indicate notable growth in publications, peaking in 2024, reflecting rising global interest in predictive modeling for solar efficiency and its educational applications. Leading journals such as Energies, Energy Reports, and Solar Energy dominate this area, while keyword clusters reveal an interdisciplinary focus linking renewable energy technology, computational modeling, and education. Theoretically, the study demonstrates the ongoing relevance of linear regression for educational contexts, while practically offering guidance for educators and researchers to integrate predictive modeling into renewable energy learning. Future research should broaden bibliometric sources, explore advanced predictive techniques, and test these models in diverse educational settings to further strengthen students’ analytical competencies and renewable energy literacy.