Computation Offloading and Task Scheduling with Fault-Tolerance for Minimizing Redundancy in Edge Computing

Abstract

Edge computing can effectively overcome the problems of long transmission distance and high response delay of traditional cloud computing because it can offload computing tasks to edge or cloud. However, edge resources are relatively limited, so the design of an appropriate task scheduling mechanism is critical. Furthermore, ensuring reliability in edge computing is also an urgent problem to be solved. For a 3-layer architecture with local device layer, edge layer, and cloud layer, this paper presents a computing offloading and task scheduling approach with fault-tolerance for minimizing redundancy. It consists of three procedures, i.e., offloading decision, task scheduling, and minimizing redundancy. The offloading decision algorithm is used to decide which layer the task will be executed. As for the primary-backup task scheduling algorithm, the execution time, the energy consumption, the CPU utilization and the reliability are considered for the task scheduling of edge and cloud. To meet the reliability requirement of an application, the minimizing redundancy algorithm is used during the replication process. The experimental results obtained by using EdgeCloudSim show that the proposed approach is superior to other methods given in [21] [24] [38], in terms of execution time, energy consumption and redundancy.