Optimal Offloading Strategies for Edge-Computing via Mean-Field Games and Control

TL;DR

This paper develops a mean-field game approach to determine optimal task offloading strategies in large-scale edge computing systems, providing theoretical guarantees and numerical solutions that are accurate even for systems with dozens of devices.

Contribution

It introduces a mean-field formulation for offloading in large edge-computing systems, offering a tractable method with proven approximation accuracy for both cooperative and competitive scenarios.

Findings

Mean-field solutions accurately approximate large system behaviors.

Numerical methods effectively solve the mean-field problems.

Approach scales well with dozens of edge devices.

Abstract

The optimal offloading of tasks in heterogeneous edge-computing scenarios is of great practical interest, both in the selfish and fully cooperative setting. In practice, such systems are typically very large, rendering exact solutions in terms of cooperative optima or Nash equilibria intractable. For this purpose, we adopt a general mean-field formulation in order to solve the competitive and cooperative offloading problems in the limit of infinitely large systems. We give theoretical guarantees for the approximation properties of the limiting solution and solve the resulting mean-field problems numerically. Furthermore, we verify our solutions numerically and find that our approximations are accurate for systems with dozens of edge devices. As a result, we obtain a tractable approach to the design of offloading strategies in large edge-computing scenarios with many users.