EUVIMEDEUVIMED entdecken
Studienprotokoll

QRPL: Q-Learning-Based Routing Protocol for Low-Power and Lossy IoT Networks

Badis Djamaa, Mustapha Reda Senouci, Issam Eddine Lakhlaf, Abbas Bradai, Walid Moussaoui, Yacine Moussaoui

IEEE Transactions on Mobile Computing · 2026-07 · 25 (7) · 9437-9453

DOI: 10.1109/tmc.2026.3657189 ↗

Kurz gefasst

Studienprotokoll in der Zeitschrift IEEE Transactions on Mobile Computing, 2026-07. Verfasst von Badis Djamaa und 5 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 27 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The Internet of Things (IoT) refers to the interconnection of numerous computationally, memory, communication, and energy-constrained objects over the Internet and local communication technologies by leveraging unicast and multicast routing solutions. These device and network limitations have resulted in several challenges for IoT routing protocols, leading to the standardization of RPL; the Routing Protocol for Low-power and Lossy Networks (LLNs). Nonetheless, while RPL addresses some hardware and software limitations, its decisions still rely on basic hand-crafted algorithms. The recent success of machine learning in several domains has motivated us to consider intelligent algorithms based on Reinforcement Learning (RL) as a solution to this problem. Therefore, we contribute in this paper three Q-learning-based algorithms for intelligent information dissemination and routing in IoT networks, named SMART, TRAP, and TRAST. SMART focuses on the intelligent suppression of unnecessary messages, TRAP dynamically adapts communication intervals to the network’s needs, and TRAST combines the two. These proposals have been integrated into RPL, evaluated through extensive simulations on dedicated IoT platforms, and validated via real experiments on the publicly available large-scale IoT-Lab testbed. The obtained results demonstrate the performance of our solutions compared to the state of the art in terms of energy consumption, load balancing, and end-to-end delay.

Zitieren

APA

Djamaa, B., Senouci, M. R., Lakhlaf, I. E., Bradai, A., Moussaoui, W., & Moussaoui, Y. (2026). QRPL: Q-Learning-Based Routing Protocol for Low-Power and Lossy IoT Networks. IEEE Transactions on Mobile Computing, 25(7), 9437-9453. https://doi.org/10.1109/tmc.2026.3657189

Vancouver

Djamaa B, Senouci MR, Lakhlaf IE, Bradai A, Moussaoui W, Moussaoui Y. QRPL: Q-Learning-Based Routing Protocol for Low-Power and Lossy IoT Networks. IEEE Transactions on Mobile Computing. 2026;25(7):9437-9453. doi:10.1109/tmc.2026.3657189

BibTeX
@article{Djamaa2026,
  author = {Djamaa, Badis and Senouci, Mustapha Reda and Lakhlaf, Issam Eddine and Bradai, Abbas and Moussaoui, Walid and Moussaoui, Yacine},
  title = {QRPL: Q-Learning-Based Routing Protocol for Low-Power and Lossy IoT Networks},
  journal = {IEEE Transactions on Mobile Computing},
  year = {2026},
  volume = {25},
  number = {7},
  pages = {9437--9453},
  doi = {10.1109/tmc.2026.3657189}
}
Kostenlos starten →