Latency-sensitive Service Delivery with UAV-Assisted 5G Networks

TL;DR

This paper proposes a UAV-assisted 5G network framework for latency-sensitive URLLC services, optimizing resource allocation and UAV deployment, and introducing a GPR-based traffic prediction model to enhance performance.

Contribution

It introduces a novel joint optimization framework for resource and UAV deployment in UAV-assisted 5G networks with a GPR-based traffic prediction model for URLLC.

Findings

Optimized resource and UAV deployment strategies improve network performance.

GPR-based traffic prediction effectively manages sporadic URLLC traffic.

Simulation results validate the efficiency of the proposed approach.

Abstract

In this letter, a novel framework to deliver critical spread out URLLC services deploying unmanned aerial vehicles (UAVs) in an out-of-coverage area is developed. To this end, the resource optimization problem, i.e., resource blocks (RBs) and power allocation, and optimal UAV deployment strategy are studied for UAV-assisted 5G networks to jointly maximize the average sum-rate and minimize the transmit power of UAV while satisfying the URLLC requirements. To cope with the sporadic URLLC traffic problem, an efficient online URLLC traffic prediction model based on Gaussian Process Regression (GPR) is proposed which derives optimal URLLC scheduling and transmit power strategy. The formulated problem is revealed as a mixed-integer nonlinear programming (MINLP), which is solved following the introduced successive minimization algorithm. Finally, simulation results are provided to show our proposed solution approach's efficiency.