Online Collaborative Resource Allocation and Task Offloading for Multi-access Edge Computing

TL;DR

This paper proposes an online joint resource allocation and task offloading method for multi-access edge computing, aiming to minimize energy consumption while meeting delay constraints through an innovative edge-cloud collaborative architecture.

Contribution

It introduces a novel online optimization approach using Lyapunov framework and decomposition techniques for energy-efficient task offloading in MEC systems.

Findings

Achieves lower energy consumption compared to benchmarks.

Effectively manages delay constraints in dynamic MEC environments.

Demonstrates superior system performance through simulations.

Abstract

Multi-access edge computing (MEC) is emerging as a promising paradigm to provide flexible computing services close to user devices (UDs). However, meeting the computation-hungry and delay-sensitive demands of UDs faces several challenges, including the resource constraints of MEC servers, inherent dynamic and complex features in the MEC system, and difficulty in dealing with the time-coupled and decision-coupled optimization. In this work, we first present an edge-cloud collaborative MEC architecture, where the MEC servers and cloud collaboratively provide offloading services for UDs. Moreover, we formulate an energy-efficient and delay-aware optimization problem (EEDAOP) to minimize the energy consumption of UDs under the constraints of task deadlines and long-term queuing delays. Since the problem is proved to be non-convex mixed integer nonlinear programming (MINLP), we propose an online joint communication resource allocation and task offloading approach (OJCTA). Specifically, we transform EEDAOP into a real-time optimization problem by employing the Lyapunov optimization framework. Then, to solve the real-time optimization problem, we propose a communication resource allocation and task offloading optimization method by employing the Tammer decomposition mechanism, convex optimization method, bilateral matching mechanism, and dependent rounding method. Simulation results demonstrate that the proposed OJCTA can achieve superior system performance compared to the benchmark approaches.