Fully Decentralized Computation Offloading in Priority-Driven Edge Computing Systems

2025-01-10

AI Summary

This paper addresses the task offloading decision problem for energy-constrained end devices in multi-access edge computing (MEC) under tasks with high, medium, or low urgency levels. We propose a fully decentralized offloading framework that jointly optimizes information freshness—quantified by weighted average Age of Information (AoI)—and local energy consumption. Our key innovation lies in integrating priority-aware task modeling with mean-field game (MFG) theory, enabling the first distributed computation of an approximate Nash equilibrium for large-scale non-cooperative devices—without requiring a central controller or global state knowledge. The MFG equilibrium is solved via projected gradient descent, ensuring stable convergence even for networks comprising thousands of devices. Experimental results demonstrate that our approach reduces average AoI by 37% and local power consumption by 22% compared to baseline schemes.

Technology Category

• Multiagent Systems: Mechanism Design
• Machine Learning: Hardware-aware ML
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

We develop a novel framework for fully decentralized offloading policy design in multi-access edge computing (MEC) systems. The system comprises $N$ power-constrained user equipments (UEs) assisted by an edge server (ES) to process incoming tasks. Tasks are labeled with urgency flags, and in this paper, we classify them under three urgency levels, namely, high, moderate, and low urgency. We formulate the problem of designing computation decisions for the UEs within a large population noncooperative game framework, where each UE selfishly decides on how to split task execution between its local onboard processor and the ES. We employ the weighted average age of information (AoI) metric to quantify information freshness at the UEs. Increased onboard processing consumes more local power, while increased offloading may potentially incur a higher average AoI due to other UEs' packets being offloaded to the same ES. Thus, we use the mean-field game (MFG) formulation to compute approximate decentralized Nash equilibrium offloading and local computation policies for the UEs to balance between the information freshness and local power consumption. Finally, we provide a projected gradient descent-based algorithm to numerically assess the merits of our approach.

Problem

• Multi-access Edge Computing
• Energy Optimization
• Task Scheduling

Innovation

• Distributed Computing Task Offloading
• Large Population Stochastic Games
• Mean Field Game Theory