Learning Driven Elastic Task Multi-Connectivity Immersive Computing Systems

2025-05-19

AI Summary

This work addresses the dynamic task offloading optimization problem for elastic virtual reality (VR) applications in multi-user edge computing systems operating over multi-connectivity networks, aiming to maximize computational energy efficiency (throughput per unit energy) while jointly optimizing communication latency, computation load, energy consumption, and immersive quality of experience (QoE). We propose the first constrained stochastic energy-efficiency optimization model that integrates VR task elasticity with multi-connectivity and multi-user action spaces. To solve it online, we design a hybrid framework combining collaborative policy gradient (CPPG) and independent policy gradient (IPPG) in a phased manner, coupled with a decentralized shared multi-armed bandit (DSMAB) mechanism for coordinated decision-making. Experimental results demonstrate that CPPG reduces end-to-end latency by 28% and energy consumption by 78% compared to IPPG, while significantly improving QoE, system scalability, and adaptability across heterogeneous networks—including 4G, 5G, WiGig, and 360° video-driven environments.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Computer Vision: Learning & Optimization for CV

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Virtualization and resource management in Web systems and infrastructures
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems

Abstract

In virtual reality (VR) environments, computational tasks exhibit an elastic nature, meaning they can dynamically adjust based on various user and system constraints. This elasticity is essential for maintaining immersive experiences; however, it also introduces challenges for communication and computing in VR systems. In this paper, we investigate elastic task offloading for multi-user edge-computing-enabled VR systems with multi-connectivity, aiming to maximize the computational energy-efficiency (computational throughput per unit of energy consumed). To balance the induced communication, computation, energy consumption, and quality of experience trade-offs due to the elasticity of VR tasks, we formulate a constrained stochastic computational energy-efficiency optimization problem that integrates the multi-connectivity/multi-user action space and the elastic nature of VR computational tasks. We formulate a centralized phasic policy gradient (CPPG) framework to solve the problem of interest online, using only prior elastic task offloading statistics (energy consumption, response time, and transmission time), and task information (i.e., task size and computational intensity), while observing the induced system performance (energy consumption and latency). We further extend our approach to decentralized learning by formulating an independent phasic policy gradient (IPPG) method and a decentralized shared multi-armed bandit (DSMAB) method. We train our methods with real-world 4G, 5G, and WiGig network traces and 360 video datasets to evaluate their performance in terms of response time, energy efficiency, scalability, and delivered quality of experience. We also provide a comprehensive analysis of task size and its effect on offloading policy and system performance. In particular, we show that CPPG reduces latency by 28% and energy consumption by 78% compared to IPPG.

Problem

• Optimize elastic task offloading in VR systems for energy efficiency
• Balance communication, computation, and quality of experience trade-offs
• Develop centralized and decentralized learning methods for multi-connectivity VR

Innovation

• Centralized phasic policy gradient for elastic task offloading
• Decentralized learning with independent policy gradient method
• Multi-connectivity optimization for energy-efficient VR systems