Learn to Optimize Resource Allocation under QoS Constraint of AR

TL;DR

This paper proposes a deep learning-based resource allocation method for AR services that optimizes power usage while satisfying strict latency and reliability QoS constraints, modeled through a tandem queuing system.

Contribution

It introduces a novel neural network approach that learns optimal power allocation policies considering AR transmission's unique QoS requirements and queuing model.

Findings

Reduces transmit power effectively under QoS constraints

Achieves end-to-end latency and reliability targets

Outperforms traditional allocation methods

Abstract

This paper studies the uplink and downlink power allocation for interactive augmented reality (AR) services, where the live video captured by an AR device is uploaded to the network edge, and then the augmented video is subsequently downloaded. By modeling the AR transmission process as a tandem queuing system, we derive an upper bound for the probabilistic quality of service (QoS) requirement concerning end-to-end latency and reliability. The resource allocation under the QoS requirement results in a functional optimization problem. To address it, we design a deep neural network to learn the power allocation policy, leveraging the optimal power allocation structure to enhance learning performance. Simulation results demonstrate that the proposed method effectively reduces transmit power while meeting the QoS requirement.