UAV-assisted integrated sensing and communication for emergency rescue activities based on transfer deep reinforcement learning

Loading...
Thumbnail Image

Access rights

openAccess
acceptedVersion

URL

Journal Title

Journal ISSN

Volume Title

A4 Artikkeli konferenssijulkaisussa

Date

2024

Major/Subject

Mcode

Degree programme

Language

en

Pages

6

Series

Proceedings of the 30th Annual International Conference on Mobile Computing and Networking, pp. 2142-2147

Abstract

Joint task scheduling and resource allocation for unmanned aerial vehicle (UAV)-assisted integrated sensing and communication (ISAC) in emergency rescue activities has become an essential and challenging problem. However, the existing works have only considered such a problem for standalone UAV networks without considering the cooperation between UAVs and ground base stations (BSs), nor have they considered the uncertainty in terms of the availability of BSs due to damage/reconstruction in disaster events. In this paper, we consider a novel post-disaster UAV-assisted ISAC system where the UAVs are used to supplement the networking capacity of out-of-service ground BSs while using their radio signals for sensing. We apply transfer learning with deep reinforcement learning (DRL) to learn task scheduling and resource allocation strategies that can rapidly adapt to uncertainty in the environment. Experimental results show that the proposed algorithm outperforms the state-of-the-art in both communication and sensing performance and convergence speed. Moreover, the transfer learning-based DRL shows faster convergence and better robustness when the availability of BSs suddenly changes.

Description

Keywords

integrated sensing and communication, unmanned aerial vehicle, task scheduling, resource allocation, deep reinforcement learning, transfer learning

Other note

Citation

Liu, Y, Mao, W, Li, X, Huangfu, W, Ji, Y & Xiao, Y 2024, UAV-assisted integrated sensing and communication for emergency rescue activities based on transfer deep reinforcement learning . in Proceedings of the 30th Annual International Conference on Mobile Computing and Networking . ACM, pp. 2142-2147, Annual International Conference on Mobile Computing and Networking, Washington, District of Columbia, United States, 18/11/2024 . https://doi.org/10.1145/3636534.3698220