To Offload or Not? An Analysis of Big Data Offloading Strategies from Edge to Cloud

Abstract

Large reductions in completion times can result from transfer of Big Data tasks from edge nodes to cloud resources, which can reduce the completion times by up to 97 % and meet client deadlines for computational tasks with responsive and agile solutions. Using scientific programs of varying computational complexity to model resource-intensive tasks, we demonstrate that the task complexity of the computational jobs, the Wide Area Network (WAN) speed and the potential overload of edge servers (as reflected by CPU workloads) are crucial for achieving total reductions in task completion time edge-cloud orchestrators are situated in edge nodes. With continuous access to the parameters of Wireless Local Area Network (WLAN) speed (for data exchanges between client and edge resources), WAN speed (for data exchanges between edge and cloud resources) edge server CPU workload and the complexities in Big Data analytics requirements, accurate edge-to-cloud offloading decisions can be made to minimise total task completion time by the use of cloud computing resources. This work supports the major research efforts have been recently made to develop novel resource orchestration solutions to flexibly link edge nodes with centralised cloud resources so as to maximise the efficiency with which such a continuum of resources can be accessed by users.