EUVIMEDEUVIMED entdecken
Crossref

DRL-Driven Dynamic Resource Allocation for Task-Oriented Semantic Communication

Haijun Zhang, Hongyu Wang, Yabo Li, Keping Long, Arumugam Nallanathan

IEEE Transactions on Communications · 2023-07 · 71 (7) · 3992-4004

DOI: 10.1109/tcomm.2023.3274145 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Communications, 2023-07. Verfasst von Haijun Zhang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 192-mal zitiert (Crossref) und nennt 32 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Beijing Natural Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Semantic communication has been regarded as a promising technology to serve upcoming intelligent applications. However, few studies have addressed the problem of resource allocation in semantic communication networks. Most resource allocation mechanisms act fairly to all original data, ignoring the meaning behind the transmitted bits. In this paper, a dynamic resource allocation scheme for the task-oriented semantic communication network (TOSCN) based on deep reinforcement learning (DRL) is proposed, which allows data with richer semantic information to preferentially occupy limited communication resources. This paper aims to design a deep deterministic policy gradient (DDPG) agent at the micro base station to maximize the long-term transmission efficiency of tasks. Firstly, the relationship between semantic information and task performance is investigated. Subsequently, a novel wireless resource allocation model for TOSCN is proposed by taking the image classification task as an example. Then, a joint optimization problem of the semantic compression ratio, transmit power, and bandwidth of each user is formulated. The agent is trained in an interactive learning environment to obtain a decent trade-off between the amount of data delivered to the receiver and the accuracy of intelligent tasks. Simulation results demonstrate that the proposed scheme achieves significant advantages in relieving communication pressure and improving task performance in resource-constrained wireless networks.

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • Beijing Natural Science Foundation
  • Xiaomi Fund of Young Scholar, and China University Industry-University-Research Collaborative Innovation Fund

Zitieren

APA

Zhang, H., Wang, H., Li, Y., Long, K., & Nallanathan, A. (2023). DRL-Driven Dynamic Resource Allocation for Task-Oriented Semantic Communication. IEEE Transactions on Communications, 71(7), 3992-4004. https://doi.org/10.1109/tcomm.2023.3274145

Vancouver

Zhang H, Wang H, Li Y, Long K, Nallanathan A. DRL-Driven Dynamic Resource Allocation for Task-Oriented Semantic Communication. IEEE Transactions on Communications. 2023;71(7):3992-4004. doi:10.1109/tcomm.2023.3274145

BibTeX
@article{Zhang2023,
  author = {Zhang, Haijun and Wang, Hongyu and Li, Yabo and Long, Keping and Nallanathan, Arumugam},
  title = {DRL-Driven Dynamic Resource Allocation for Task-Oriented Semantic Communication},
  journal = {IEEE Transactions on Communications},
  year = {2023},
  volume = {71},
  number = {7},
  pages = {3992--4004},
  doi = {10.1109/tcomm.2023.3274145}
}
Kostenlos starten →