THE EVOLUTION OF RENEWABLE ENERGY FORECASTING WITH MACHINE LEARNING: A STATE-OF-THE-ART BIBLIOMETRIC ANALYSIS AND SUGGESTIONS FOR FUTURE RESEARCH
- 문서 유형
- 연구출판물 · 학술지 논문
- 등재
- SCIEScopus
- 저널 순위
- JCR Q4Scopus Q3
- 저널
- APPLIED ECOLOGY AND ENVIRONMENTAL RESEARCH23(5) · pp.8913 · 2025
- 피인용
- Web of Science 0Scopus 0
- FWCI (Scopus)
- 0
- JCR IF
- JCR 2024 0.6
- ISSN
- 1589-1623
저자
- Hau, Y. S.제1저자Yeungnam Univ, Dept Business Adm, Gyongsan 38541, South Korea
- 김은미교신저자Pusan Natl Univ, Inst Management Res, Busan 46241, South Korea
초록
This study performed bibliometric analyses to evaluate the evolution of machine learning (ML) and renewable energy forecasting (REF) in terms of the article, author, source, country, and topic dimensions from 1990 to 2023, based on 1232 articles from the Web of Science, with Bibliometrics (Biblioshiny) and VOSviewer. Results revealed that article publications and citations regarding ML and REF have grown rapidly since 2012 and 2013, respectively. The articles were distributed across 53 research areas. Deo, R. C. and Trans, K. were the most productive and influential authors in terms of article publications and citations, respectively. Energies and Applied Energies were the most productive and influential sources, respectively. Geographically, China ranked first in terms of both article publications and citations. It played an important role in bridging collaborative relationships between countries from 2017 to 2023. Over time, the major themes in ML and REF evolved from artificial neural network into predictive models, and smart grid. Interdisciplinarity, topic diversification, and sophistication of techniques were identified as key features in the evolution of ML and REF. Applying hybrid models with various deep learning algorithms, utilizing large language models, and diversifying topics into anaerobic digestion are suggested for future ML and REF research.
키워드
topics digestion suggested bibliometric analysismachine learningrenewable energy forecastingBiblioshinyVOSviewerARTIFICIAL-INTELLIGENCECLIMATE-CHANGEREGRESSIONTRENDSIMPACT
식별자
- Scopus EID
- 2-s2.0-105020732257
- WoS UID
- 001560952800001



로그인
연구물 목록으로