A Coalition-Based Contextual Adversarial Bandit Approach for Dynamic Relay Selection in Seaport Heterogeneous Communication Network
IEEE Transactions on Vehicular Technology · 2026-08 · 75 (8) · 17030-17046
DOI: 10.1109/tvt.2026.3673552 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Vehicular Technology, 2026-08. Verfasst von Kai Ma und 5 weiteren Autor:innen. Die Arbeit nennt 41 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Hebei Province, Science Research Project of Hebei Education Department.
Abstract (Originalsprache)
In seaport communication networks, harsh environment and high terminal node mobility make channel state information (CSI) highly dynamic and unpredictable. Diverse communication requirements further complicate system design. To address these challenges, this paper proposes a coalition-based contextual adversarial bandit (CBCAB) model that estimates relay performance under uncertain CSI. Firstly, a parameter update mechanism dynamically adjusts the decay factor based on the deviation between estimated and actual relay performance, with a time sensitivity coefficient prioritizing recent observations to reduce outdated errors. Moreover, coalition game theory improves learning efficiency by enabling terminal nodes in similar conditions to form coalitions, share information, and collaboratively train parameters. Finally, a utility function is developed to comprehensively evaluate multiple communication performance metrics, enabling the selection of the optimal relay and adaptation to diverse scenarios. Simulation results show that the CBCAB model effectively addresses dynamic relay selection, significantly improving system performance and transmission efficiency under challenging seaport scenario.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Hebei Province
- Science Research Project of Hebei Education Department
- S&T Program of Hebei
Zitieren
APA
Ma, K., Li, Y., Yang, J., Yuan, Y., Yang, B., & Guan, X. (2026). A Coalition-Based Contextual Adversarial Bandit Approach for Dynamic Relay Selection in Seaport Heterogeneous Communication Network. IEEE Transactions on Vehicular Technology, 75(8), 17030-17046. https://doi.org/10.1109/tvt.2026.3673552
Vancouver
Ma K, Li Y, Yang J, Yuan Y, Yang B, Guan X. A Coalition-Based Contextual Adversarial Bandit Approach for Dynamic Relay Selection in Seaport Heterogeneous Communication Network. IEEE Transactions on Vehicular Technology. 2026;75(8):17030-17046. doi:10.1109/tvt.2026.3673552
BibTeX
@article{Ma2026,
author = {Ma, Kai and Li, Yifu and Yang, Jie and Yuan, Yazhou and Yang, Bo and Guan, Xinping},
title = {A Coalition-Based Contextual Adversarial Bandit Approach for Dynamic Relay Selection in Seaport Heterogeneous Communication Network},
journal = {IEEE Transactions on Vehicular Technology},
year = {2026},
volume = {75},
number = {8},
pages = {17030--17046},
doi = {10.1109/tvt.2026.3673552}
}
EUVIMED