EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Data-Driven Review of Machine Learning Approaches for Energy Optimization: Methods, Datasets and Limitations

Survi Sinha, Ritika Raj, Atreyi Pramanik, Pradeep Yadav

Applied Energy & Artificial Intelligence · 28.05.2026 · 2 (1) · 13-25

DOI: 10.55938/aeai.v2i1.430 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Energy & Artificial Intelligence, online erschienen am 28.05.2026. Verfasst von Survi Sinha und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid digitisation in the energy systems has led to the accelerated adoption of machine learning (ML) in energy efficiency in buildings, renewable energy systems and hybrid infrastructures. This review presents a summary of recent advances in data-driven energy efficiency, including popular ML techniques, the underlying data bases and implementation issues. The document takes a selective and critical approach as opposed to a comprehensive survey, focusing more on generalizability of models, data quality, interpretation and sustainability. A comparative analysis has pointed out trade-offs between accuracy, transparency and scalability, whereas research gaps identified in the research have shown that there are still obstacles to implementation in practice. The review finishes with a summary of where the standardised data sets, transparent and energy efficient ML and policy-oriented optimisation should be headed to assist with credible and impactful AI-based energy transitions.

Zitieren

APA

Sinha, S., Raj, R., Pramanik, A., & Yadav, P. (2026). A Data-Driven Review of Machine Learning Approaches for Energy Optimization: Methods, Datasets and Limitations. Applied Energy & Artificial Intelligence, 2(1), 13-25. https://doi.org/10.55938/aeai.v2i1.430

Vancouver

Sinha S, Raj R, Pramanik A, Yadav P. A Data-Driven Review of Machine Learning Approaches for Energy Optimization: Methods, Datasets and Limitations. Applied Energy & Artificial Intelligence. 2026;2(1):13-25. doi:10.55938/aeai.v2i1.430

BibTeX
@article{Sinha2026,
  author = {Sinha, Survi and Raj, Ritika and Pramanik, Atreyi and Yadav, Pradeep},
  title = {A Data-Driven Review of Machine Learning Approaches for Energy Optimization: Methods, Datasets and Limitations},
  journal = {Applied Energy & Artificial Intelligence},
  year = {2026},
  volume = {2},
  number = {1},
  pages = {13--25},
  doi = {10.55938/aeai.v2i1.430}
}
Kostenlos starten →