Scientific Mapping of Machine Learning Methods in Predicting Power Output of Solar Photovoltaic Power Systems

Abstract

Objective: This study aimed to conduct a scientometric mapping of the scientific literature on prediction models in photovoltaic solar energy generation, with a special focus on grid-connected photovoltaic systems (GCPV), aiming to provide important insights for researchers, policymakers, and professionals interested in advancing the integration of photovoltaic solar energy into the current energy distribution system.   Theoretical Framework: In this section, the main concepts and theories underpinning the research are presented, focusing on prediction models in photovoltaic solar energy generation, as well as grid-connected photovoltaic systems (GCPV).   Method: The methodology adopted comprised a bibliometric approach, analyzing publications indexed in the Scopus and Web of Science databases over the last decade, using the Biblioshiny software from RStudio.   Results and Discussion: The results revealed a significant growth in academic production, identifying key authors, leading research countries, and influential journals in the field. Central and emerging themes were also mapped, along with research gaps and opportunities in the field of photovoltaic solar energy.   Research Implications: The practical and theoretical implications of this research include insights into how the results may influence the integration of photovoltaic solar energy into the energy distribution system, impacting areas such as scientific research, policy development, and professional practice.   Originality/Value: This study contributes to the literature by offering a comprehensive mapping of research on prediction models in photovoltaic solar energy generation, highlighting gaps and opportunities to advance the field, as well as providing valuable insights for various stakeholders interested in this area.