Scholarlink

<p>A bibliometric analysis of Photovoltaic (PV) power forecasting techniques based on Scopus database publications from 2013 to 15th Jan 2025 is conducted in this study. The primary aim is to develop a valuable dataset to support researchers in the field. A total of 787 publications were downloaded &amp; categorized from Scopus database. Utilizing VOSviewer &amp; Topic Modelling the datasets were analysed. The inspection of the identified keywords revealed that research conducted globally during this period primarily focused on key aspects such as PV power generation, forecasting techniques, data-driven models and error reduction. This bibliometric analysis not only provides an overview of advancements in the field but also highlights key research trends, influential publications, prominent contributors &amp; effective keywords. Furthermore, it identifies research gaps and recommends potential avenues for future research, offering valuable insights to develop accurate PV power forecasting models that minimize errors and enhance power quality for reliable supply and grid management. A detailed analysis reveals that solar irradiance is a critical factor for PV output, it necessitates weather classification and cloudy motion analysis for accurate forecasting. While very short-term and short-term horizons are preferred, deep neural networks, especially with ensemble or hybrid approaches, outperform traditional PV power forecasting methods in efficiency and accuracy.</p>

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

Bibliometric Analysis of Photovoltaic Power Forecasting Techniques with Focus on Data Driven Methods

  • 期刊论文

  • 发表日期：

    2026年5月20日

查看全文
  • Ankur Kumar Gupta,
  • Rishi Kumar Singh,
  • Uliya Mitra,
  • Jatoth Rajender

摘要

A bibliometric analysis of Photovoltaic (PV) power forecasting techniques based on Scopus database publications from 2013 to 15th Jan 2025 is conducted in this study. The primary aim is to develop a valuable dataset to support researchers in the field. A total of 787 publications were downloaded & categorized from Scopus database. Utilizing VOSviewer & Topic Modelling the datasets were analysed. The inspection of the identified keywords revealed that research conducted globally during this period primarily focused on key aspects such as PV power generation, forecasting techniques, data-driven models and error reduction. This bibliometric analysis not only provides an overview of advancements in the field but also highlights key research trends, influential publications, prominent contributors & effective keywords. Furthermore, it identifies research gaps and recommends potential avenues for future research, offering valuable insights to develop accurate PV power forecasting models that minimize errors and enhance power quality for reliable supply and grid management. A detailed analysis reveals that solar irradiance is a critical factor for PV output, it necessitates weather classification and cloudy motion analysis for accurate forecasting. While very short-term and short-term horizons are preferred, deep neural networks, especially with ensemble or hybrid approaches, outperform traditional PV power forecasting methods in efficiency and accuracy.