EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Joint optimization of task offloading and energy trading in edge-enabled smart grids using deep reinforcement learning

Rui Xue, Bin Li iD, Wenyue He, Yihang Wang

PLOS One · 12.06.2026 · 21 (6) · e0342888

DOI: 10.1371/journal.pone.0342888 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 12.06.2026. Verfasst von Rui Xue und 3 weiteren Autor:innen. Beteiligte Einrichtung: Nanjing Institute of Technology, Nanjing, Jiangsu, China. Hauptthemen laut MEDLINE: Deep Learning, Internet of Things. Die Arbeit nennt 16 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Nanjing Institute of Technology Scientific Research Start-up Fund for High-level Introduced Talents.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The proliferation of distributed energy resources (DERs) and the ubiquity of Internet of Things (IoT) devices are driving the integration of mobile edge computing (MEC) into smart grids. This convergence enables real-time data processing for prosumers but introduces a complex cyber-physical coupling: computational offloading decisions directly impact local energy consumption, thereby altering the prosumer’s status in the peer-to-peer (P2P) energy market. Conversely, dynamic market prices influence the economic viability of offloading. This paper addresses the joint optimization of computational task offloading and P2P energy trading in an edge-assisted smart grid ecosystem. We formulate the problem as a mixed-integer nonlinear programming (MINLP) model aimed at maximizing long-term system utility, balancing throughput, latency, and economic incentives under strict edge server capacity and community energy neutrality constraints. To tackle the curse of dimensionality and system stochasticity, we propose a hybrid framework combining Deep Q-Networks (DQN) with a constraint-aware heuristic mechanism. The DQN agent learns adaptive offloading policies from high-dimensional states, while a deterministic rule-based layer ensures strict adherence to community energy balance. Simulation results based on real-world solar generation and market data demonstrate that our proposed method outperforms baseline strategies—including local-only execution and greedy heuristics—improving average utility by 12.3% and reducing task delay by 16.5%, while maintaining robust operational feasibility.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningInternet of ThingsReinforcement Machine LearningAlgorithmsComputer Simulation

Autor:innen und Institutionen

  • Nanjing Institute of Technology, Nanjing, Jiangsu, China.

ORCID-Profile: Bin Li

Förderung

  • Nanjing Institute of Technology Scientific Research Start-up Fund for High-level Introduced Talents

Zitieren

APA

Xue, R., Li, B., He, W., & Wang, Y. (2026). Joint optimization of task offloading and energy trading in edge-enabled smart grids using deep reinforcement learning. PLOS One, 21(6), e0342888. https://doi.org/10.1371/journal.pone.0342888

Vancouver

Xue R, Li B, He W, Wang Y. Joint optimization of task offloading and energy trading in edge-enabled smart grids using deep reinforcement learning. PLOS One. 2026;21(6):e0342888. doi:10.1371/journal.pone.0342888

BibTeX
@article{Xue2026,
  author = {Xue, Rui and Li, Bin and He, Wenyue and Wang, Yihang},
  title = {Joint optimization of task offloading and energy trading in edge-enabled smart grids using deep reinforcement learning},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {6},
  pages = {e0342888},
  doi = {10.1371/journal.pone.0342888}
}
Kostenlos starten →