A Survey of Cloudlet-Based Mobile Augmentation Approaches for Resource Optimization

Abstract

Mobile devices (MDs) face resource scarcity challenges owing to limited energy and computational resources. Mobile cloud computing (MCC) offers a resource-rich environment to MDs for offloading compute-intensive tasks encountering resource scarcity challenges. However, users are unable to exploit its full potential owing to challenges of distance, limited bandwidth, and seamless connectivity between the remote cloud (RC) and MDs in the conventional MCC model. The cloudlet-based solution is widely used to address these challenges. The response of the cloudlet-based solution is faster than the conventional mobile cloud-computing model, rendering it suitable for the Internet of Things (IoT) and Smart Cities (SC). However, with the increase in devices and workloads, the cloudlet-based solution has to deal with resource-scarcity challenges, thus, forwarding the requests to remote clouds. This study has been carried out to provide an insight into existing cloudlet-based mobile augmentation (CtMA) approaches and highlights the underlying limitations for resource optimization. Furthermore, numerous performance parameters have been identified and their detailed comparative analysis has been used to quantify the efficiency of CtMA approaches.