Multi-Agent Task Assignment in Vehicular Edge Computing: A Regret-Matching Learning-Based Approach

TL;DR

This paper introduces a regret-matching learning algorithm for dynamic task assignment in vehicular edge computing, effectively reducing delay and cost while adapting to high mobility in large-scale vehicle networks.

Contribution

It develops a distributed regret-matching learning approach for task assignment in vehicular edge computing, ensuring fast convergence and adaptability to high mobility.

Findings

The algorithm converges to correlated equilibrium solutions.

It achieves lower total delay and processing costs.

It outperforms existing methods in convergence speed for large networks.

Abstract

Vehicular edge computing has recently been proposed to support computation-intensive applications in Intelligent Transportation Systems (ITS) such as self-driving cars and augmented reality. Despite progress in this area, significant challenges remain to efficiently allocate limited computation resources to a range of time-critical ITS tasks. To this end, the current paper develops a new task assignment scheme for vehicles in a highway. Because of the high speed of vehicles and the limited communication range of road side units (RSUs), the computation tasks of participating vehicles are to be dynamically migrated across multiple servers. We formulate a binary nonlinear programming (BNLP) problem of assigning computation tasks from vehicles to RSUs and a macrocell base station. To deal with the potentially large size of the formulated optimization problem, we develop a distributed multi-agent regret-matching learning algorithm. Based on the regret minimization principle, the proposed algorithm employs a forgetting method that allows the learning process to quickly adapt to and effectively handle the high mobility feature of vehicle networks. We theoretically prove that it converges to the correlated equilibrium solutions of the considered BNLP problem. Simulation results with practical parameter settings show that the proposed algorithm offers the lowest total delay and cost of processing tasks, as well as utility fairness among agents. Importantly, our algorithm converges much faster than existing methods as the problem size grows, demonstrating its clear advantage in large-scale vehicular networks.