EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-Agent Deep Reinforcement Learning for Energy-Efficient and Adaptive Clustering in Wireless Sensor Networks

Muhammad Asim

Journal of Intelligent Decision Making and Information Science · 15.09.2026 · 3 (19s) · 854-871

DOI: 10.17762/jidmis.v3.6219 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Intelligent Decision Making and Information Science, online erschienen am 15.09.2026. Verfasst von Muhammad Asim. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Wireless sensor networks (WSNs) face critical challenges in energy optimization and network lifetime extension, particularly in dynamic environments where traditional static clustering protocols demonstrate limited adaptability. Existing approaches often suffer from inadequate real-time adaptation capabilities and suboptimal multi-objective optimization, failing to balance competing metrics of energy efficiency, coverage quality, and load distribution effectively. This paper presents a novel multi-agent deep reinforcement learning framework (MA-DQN) for intelligent clustering in WSNs that dynamically optimizes cluster head selection and resource allocation. The proposed system employs three specialized agent types Cluster Head Agents, Member Node Agents, and Network Coordinator Agent, operating through a multi-objective reward function integrating energy efficiency, coverage, lifetime, and load balance with weights 0.4, 0.2, 0.3, and 0.1, respectively. Experimental validation across four realistic scenarios (Intel Berkeley, Great Duck Island, Volcano Monitoring, and Smart City) demonstrates significant performance improvements: 22.2% average network lifetime enhancement and 13.2% energy efficiency gain compared to coverage-optimal algorithms. The framework achieves computational complexity enabling real-time deployment while maintaining statistical significance across diverse environmental conditions, establishing adaptive learning as a paradigm shift for sustainable WSN operations.

Zitieren

APA

Asim, M. (2026). Multi-Agent Deep Reinforcement Learning for Energy-Efficient and Adaptive Clustering in Wireless Sensor Networks. Journal of Intelligent Decision Making and Information Science, 3(19s), 854-871. https://doi.org/10.17762/jidmis.v3.6219

Vancouver

Asim M. Multi-Agent Deep Reinforcement Learning for Energy-Efficient and Adaptive Clustering in Wireless Sensor Networks. Journal of Intelligent Decision Making and Information Science. 2026;3(19s):854-871. doi:10.17762/jidmis.v3.6219

BibTeX
@article{Asim2026,
  author = {Asim, Muhammad},
  title = {Multi-Agent Deep Reinforcement Learning for Energy-Efficient and Adaptive Clustering in Wireless Sensor Networks},
  journal = {Journal of Intelligent Decision Making and Information Science},
  year = {2026},
  volume = {3},
  number = {19s},
  pages = {854--871},
  doi = {10.17762/jidmis.v3.6219}
}
Kostenlos starten →