Throughput maximization for online request admissions in mobile cloudlets

In mobile cloud computing (MCC) paradigm, cloud service providers not only offer powerful cloud data centers but also provide small-scale cloudlets in some strategic locations for mobile users to access their rich resources. Due to the flexibility and locality of cloudlets, most requests of mobile users can be processed locally. However, the cloudlets usually have limited resources and processing abilities, which implies that they may not be capable to process every incoming request. Instead, some resource-intensive requests need to be sent to remote data centers for processing and such a processing is transparent to users. In this paper, we address the online request admission issue in a cloudlet with an objective to maximize the system throughput, for which we first propose a novel admission cost model to model critical resource consumptions. We then devise efficient control algorithms for online request admissions. We finally conduct experiments by simulations to evaluate the performance of the proposed algorithms. Experimental results indicate that the proposed algorithms are promising and outperform other heuristics.