UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

A Deep Learning-Based Approach to Resource Allocation in UAV-aided Wireless Powered MEC Networks

Feng, W; Tang, J; Zhao, N; Zhang, X; Wang, X; Wong, KK; (2021) A Deep Learning-Based Approach to Resource Allocation in UAV-aided Wireless Powered MEC Networks. In: ICC 2021 - IEEE International Conference on Communications. IEEE Green open access

[thumbnail of m89456-feng.pdf]
Preview
Text
m89456-feng.pdf - Accepted Version

Download (298kB) | Preview

Abstract

Beamforming and non-orthogonal multiple access (NOMA) are two key techniques for achieving spectral efficient communication in the fifth generation and beyond wireless networks. In this paper, we jointly apply a hybrid beamforming and NOMA techniques to an unmanned aerial vehicle (UAV)-carried wireless-powered mobile edge computing (MEC) system, within which the UAV is mounted with a wireless power charger and the MEC platform delivers energy and computing services to Internet of Things (IoT) devices. We aim to maximize the sum computation rate at all IoT devices whilst satisfying the constraint of energy harvesting and coverage. The considered optimization problem is non-convex involving joint optimization of the UAV’s 3D placement and hybrid beamforming matrices as well as computation resource allocation in partial offloading pattern, and thus is quite difficult to tackle directly. By applying the polyhedral annexation method and the deep deterministic policy gradient (DDPG) algorithm, we propose an effective algorithm to derive the closed-form solution for the optimal 3D deployment of the UAV, and find the solution for the hybrid beamformer. A resource allocation algorithm for partial offloading pattern is thereby proposed. Simulation results demonstrate that our designed algorithm yields a significant computation performance enhancement as compared to the benchmark schemes.

Type: Proceedings paper
Title: A Deep Learning-Based Approach to Resource Allocation in UAV-aided Wireless Powered MEC Networks
Event: IEEE International Conference on Communications
ISBN-13: 9781728171227
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/ICC42927.2021.9500582
Publisher version: https://doi.org/10.1109/ICC42927.2021.9500582
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher's terms and conditions.
Keywords: Hybrid beamforming, mobile edge computing, non-orthogonal multiple access, unmanned aerial vehicle
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Electronic and Electrical Eng
URI: https://discovery.ucl.ac.uk/id/eprint/10136411
Downloads since deposit
53Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item