An Integrated Optimization-Learning Framework for Online Combinatorial Computation Offloading in MEC Networks

doi:10.1109/MWC.201.2100155

An Integrated Optimization-Learning Framework for Online Combinatorial Computation Offloading in MEC Networks

2022-02-01

22

OA

AI

张影 (Ying–Jun Angela Zhang)

DOI：10.1109/MWC.201.2100155

Original

Original request for help

Save

Abstract

En 中文

Mobile edge computing (MEC) is a promising paradigm to accommodate the increasingly prosperous delay-sensitive and computation-intensive applications in 5G systems. To achieve optimum computation performance in a dynamic MEC environment, mobile devices often need to make online decisions on whether to offload the computation tasks to nearby edge terminals under the uncertainty of future system information (e.g., random wireless channel gain and task arrivals). The design of an efficient online offloading algorithm is challenging. On one hand, the fast-varying edge environment requires frequently solving a hard combinatorial optimization problem where the integer offloading decision and continuous resource allocation variables are strongly coupled. On the other hand, the uncertainty of future system parameters makes it hard for the online decisions to satisfy long-term system constraints. To address these challenges, this article overviews the existing methods and introduces a novel framework that efficiently integrates model-based optimization and model-free learning techniques. We suggest some promising future research directions for online computation offloading control in MEC networks.

Keywords:

Task analysis

Optimization

Computational modeling

Resource management

Mathematical models

Load modeling

Real-time systems

An Integrated Optimization-Learning Framework for Online Combinatorial Computation Offloading in MEC Networks

Abstract

Journal

Organization