EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Generative AI Architectures for Next-Generation Peer-to-Peer Energy Markets: A Review

Nicola Sorrentino, Daniele Menniti, Giovanni Brusco, Giada Tucci, Gioanna Loi

Energies · 20.11.2026 · 19 (22) · 5611

DOI: 10.3390/en19225611 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Energies, online erschienen am 20.11.2026. Verfasst von Nicola Sorrentino und 4 weiteren Autor:innen. Die Arbeit nennt 81 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Italian Ministry of University and Research.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The growing diffusion of renewable energy sources, storage systems, and distributed energy resources is fostering a transformation in electricity markets, characterized by increasingly active participation by end users. In this context, peer-to-peer (P2P) energy trading models enable producers, consumers, and prosumers to exchange energy within energy communities and local systems, introducing new methods of negotiation and resource management. This paper analyzes the contribution of generative artificial intelligence, with particular reference to large language models (LLMs), to the automation of decision-making processes in P2P energy markets. The review adopts a targeted narrative approach, covering recent literature together with selected foundational studies, and organizes the evidence according to LLM roles in forecasting, trading and negotiation, MARL-assisted decision making, and hybrid architectures. The analysis focuses on automated trading, bidding and negotiation strategies, LLM–MARL integration, and complementary technologies such as blockchain, smart contracts, forecasting, and storage management. The reviewed evidence suggests that current architectures are most credible when LLMs support interpretation, strategy generation, and higher-level decisions, while network feasibility, market clearing, settlement, and other safety-critical functions remain assigned to deterministic or otherwise verifiable modules.

Förderung

  • Italian Ministry of University and Research

Zitieren

APA

Sorrentino, N., Menniti, D., Brusco, G., Tucci, G., & Loi, G. (2026). Generative AI Architectures for Next-Generation Peer-to-Peer Energy Markets: A Review. Energies, 19(22), 5611. https://doi.org/10.3390/en19225611

Vancouver

Sorrentino N, Menniti D, Brusco G, Tucci G, Loi G. Generative AI Architectures for Next-Generation Peer-to-Peer Energy Markets: A Review. Energies. 2026;19(22):5611. doi:10.3390/en19225611

BibTeX
@article{Sorrentino2026,
  author = {Sorrentino, Nicola and Menniti, Daniele and Brusco, Giovanni and Tucci, Giada and Loi, Gioanna},
  title = {Generative AI Architectures for Next-Generation Peer-to-Peer Energy Markets: A Review},
  journal = {Energies},
  year = {2026},
  volume = {19},
  number = {22},
  pages = {5611},
  doi = {10.3390/en19225611}
}
Kostenlos starten →