A Bibliometric Analysis on the Application of Deep Learning in Wind Energy Forecasting

Abstract

In recent years, the intersection of deep learning (DL) and wind energy forecasting has seen substantial academic growth, reflecting both the rise of artificial intelligence in engineering and the global transition toward renewable power systems. This study presents a comprehensive bibliometric evaluation of scientific publications related to DL-based wind forecasting, covering the period from 2013 to 2024. Data were extracted from the Web of Science (WoS) Core Collection using the keywords “deep learning” and “wind.” Through quantitative analysis, the research explores publication dynamics, citation behaviors, and the collaborative networks of leading authors, institutions, and countries. Additionally, trends in keyword usage and thematic focus were assessed to identify core research areas and evolving interests in the field. This paper aims to provide researchers and energy forecasters with a structured overview of the academic terrain, highlighting influential contributions and strategic directions for future investigations into hybrid deep learning models for wind energy prediction.