Learn to Optimize Resource Allocation under QoS Constraint of AR

2025-01-27

AI Summary

To address the joint optimization of energy consumption, latency, and reliability in mobile augmented reality (AR) gaming, this paper models end-to-end AR transmission as a tandem queuing system. It formulates, for the first time, a joint uplink-downlink power allocation problem subject to probabilistic latency and reliability quality-of-service (QoS) constraints. A structure-guided deep neural network (SG-DNN) is proposed, explicitly embedding both the analytical queuing model structure and QoS constraint priors to efficiently learn high-dimensional, non-convex power control policies. Simulation results demonstrate that, while guaranteeing sub-millisecond end-to-end latency and 99.9% reliability, the proposed method reduces average uplink and downlink transmit power by 37.2%, outperforming conventional convex approximation and reinforcement learning baselines.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Learning to Search
• Multiagent Systems: Adversarial Agents

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Search and Retrieval-Augmented AI: Ad search and search for Web retail
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

This paper studies the uplink and downlink power allocation for interactive augmented reality (AR) services, where 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 with the QoS constraints results in a functional optimization problem. To address it, we design a deep neural network to learn the power allocation policy, leveraging the structure of optimal power allocation to enhance learning performance. Simulation results demonstrate that the proposed method effectively reduces transmit powers while meeting the QoS requirement.

Problem

• Energy Optimization
• Augmented Reality Gaming
• Power Management

Innovation

• Deep Neural Networks
• Power Allocation Optimization
• Augmented Reality Gaming