Multi-User and Multi-Task Offloading Decision Algorithms Based on Imbalanced Edge Cloud

Wen-Jiang Feng,Chong-Hai Yang,Xiao-Shan Zhou

doi:10.1109/access.2019.2928377

Abstract

The mobile edge computing (MEC) technology can provide mobile users (MU) with high reliability and low time-delay computing and communication services. The imbalanced edge cloud deployment can better adapt to the non-uniform spatial-time distribution of tasks and reduce the deployment cost of edge cloud servers. For multi-user and multi-task offloading decision based on the imbalanced edge cloud, a new offloading cost criteria, based on the tradeoff among time delay-energy consumption-cost, is designed to quantify the user experience of task offloading and to be the optimization target of offloading decision. Both the optimization problems of minimizing the sum offloading costs for all MUs (efficiency-based) and minimizing the maximal offloading cost per MU (fairness-based) are discussed. Efficiency-based offloading decision algorithm [centralized greedy algorithm (CGA) and modified greedy algorithm (MGA)] and fairness-based offloading decision algorithm [fairness-based greedy algorithm (FGA)] are proposed, respectively, and the performance bounds of the algorithm are analyzed. The simulation results show that the offloading cost of the MGA is lower than the CGA, the efficiency of resource utilization of the CGA is higher than that of the FGA, and the fairness of the FGA is stronger than that of the CGA.

Highlights

Mobile Edge Computing (MEC) technology provides mobile users (MU) with high reliability, low time-delay computing and communication services by deploying Edge Cloud Server (ECS) at the edge of the mobile network [1]
In this paper, we studied the multi-user and multi-task offloading decision algorithm based on unbalanced edge cloud, and proposed a new criteria for task offloading performance evaluation, which is based on the tradeoff among time delay-energy consumption-cost
The centralized algorithms, centralized greedy algorithm (CGA), modified greedy algorithm (MGA) based on efficiency, and fairness-based greedy algorithm (FGA) fairness-based, are proposed

Summary

INTRODUCTION

Mobile Edge Computing (MEC) technology provides mobile users (MU) with high reliability, low time-delay computing and communication services by deploying Edge Cloud Server (ECS) at the edge of the mobile network [1]. This paper studies multi-user and multi-task offloading decisions based on unbalanced edge cloud, where multiple users share multiple ECS computing resources via multiple APs. Each mobile user processes multiple compute-intensive or delaysensitive tasks, and offloading decisions involve AP and ECS selection. The former indicates that the sum of computing resources required by all MUs does not exceed the amount of total computing resources that all ECSs can provide The latter indicates that the number of tasks requesting services does not exceed the number of connections supported by the APs. even if (5) and (6) are satisfied, the feasible set may still be an empty set since the computational resource demands of multiple tasks cannot be aligned on each ECS. The system is equipped with a central cloud server with sufficient computing resources or a offloading decision algorithm with built-in user scheduling strategy in [6] to support the computations mentioned above

LINEAR RELAXATION

SIMULATION ANALYSIS

COMPARISON OF CGA AND FGA

COMPARISON OF CGA AND MGA

CONCLUSION