Cloudlet-based ad hoc mobile cloud computing: design and evaluation

Abstract

In this paper, a cloudlet-based approach for a new ad hoc model for mobile-based cloud computing is proposed. The performance of the model is evaluated using destinationsequenced distance-vector (DSDV) for routing protocol and random way point (RWP) mechanism for mobility fashion. The important parameters used to evaluate the model are endto-end (e2e) packet delay, system scalability and mobility management. The performance of the model has been studied using various workload sizes that are offloaded to cloudlets and for different node speeds. The variation of hand-off delay as well as workload size gives significant impact on the e2e delay results. Even with the maximum hand-off delay, passing various workloads through multiple cloudlets is still quicker than using an enterprise cloud unless offloading small workload size.