Article (Scientific journals)
Actor‑critic learning‑based energy optimization for UAV access and backhaul networks
Yuan, Yaxiong; Lei, Lei; Vu, Thang Xuan et al.
2021In EURASIP Journal on Wireless Communications and Networking
Peer Reviewed verified by ORBi
 

Files


Full Text
(EURASIP) Actor‑critic learning‑based energy optimization for UAV access and backhaul networks.pdf
Publisher postprint (3.51 MB)
Download

All documents in ORBilu are protected by a user license.

Send to



Details



Keywords :
UAV; Deep reinforcement learning; User scheduling; Backhaul power allocation; Energy optimization; Actor-critic
Abstract :
[en] In unmanned aerial vehicle (UAV)-assisted networks, UAV acts as an aerial base station which acquires the requested data via backhaul link and then serves ground users (GUs) through an access network. In this paper, we investigate an energy minimization problem with a limited power supply for both backhaul and access links. The difficul- ties for solving such a non-convex and combinatorial problem lie at the high compu- tational complexity/time. In solution development, we consider the approaches from both actor-critic deep reinforcement learning (AC-DRL) and optimization perspectives. First, two offline non-learning algorithms, i.e., an optimal and a heuristic algorithms, based on piecewise linear approximation and relaxation are developed as benchmarks. Second, toward real-time decision-making, we improve the conventional AC-DRL and propose two learning schemes: AC-based user group scheduling and backhaul power allocation (ACGP), and joint AC-based user group scheduling and optimization-based backhaul power allocation (ACGOP). Numerical results show that the computation time of both ACGP and ACGOP is reduced tenfold to hundredfold compared to the offline approaches, and ACGOP is better than ACGP in energy savings. The results also verify the superiority of proposed learning solutions in terms of guaranteeing the feasibility and minimizing the system energy compared to the conventional AC-DRL.
Research center :
Interdisciplinary Centre for Security, Reliability and Trust (SnT) > SIGCOM
Disciplines :
Electrical & electronics engineering
Author, co-author :
Yuan, Yaxiong ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SigCom
Lei, Lei ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SigCom
Vu, Thang Xuan  ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SigCom
Chatzinotas, Symeon  ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SigCom
Sun, Sumei;  Institute for Infocomm Research, Agency for Science, Technology, and Research, Singapore
Ottersten, Björn ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
External co-authors :
yes
Language :
English
Title :
Actor‑critic learning‑based energy optimization for UAV access and backhaul networks
Publication date :
07 April 2021
Journal title :
EURASIP Journal on Wireless Communications and Networking
ISSN :
1687-1499
Publisher :
Springer, Germany
Peer reviewed :
Peer Reviewed verified by ORBi
FnR Project :
FNR12173206 - Learning-assisted Optimization For Resource And Security Management In Slicing-based 5g Networks - LARGOS, 2017 (15/03/2018-14/03/2022) - Srikanth Bommaraven
Funders :
FNR - Fonds National de la Recherche [LU]
Available on ORBilu :
since 31 May 2021

Statistics


Number of views
132 (31 by Unilu)
Number of downloads
40 (11 by Unilu)

Scopus citations®
 
2
Scopus citations®
without self-citations
1
OpenCitations
 
3
WoS citations
 
3

Bibliography


Similar publications



Contact ORBilu