Modeling and Evaluating a Cloudlet-based Architecture for Mobile Cloud Computing

With the rising popularity of Internet-enabled mobile devices, users are increasingly demanding better quality of service (QoS). However, the resources of these devices and their connectivity levels remain insufficient, even though they are improving, for offering acceptable levels of QoS to users. Cloud computing infrastructures offer large and scalable resources that allow shifting the physical location of computation and storage to the cloud. Nevertheless, the integration of mobile computing with cloud computing would not guarantee adequate levels of service for mobile users. It rather delivers scalability at the cost of higher delay and higher power consumption on the mobile device. Instead, using local resources based on users geographical locations has the potential to improve the performance and QoS for mobile users. In this paper, we present and study a centralized architecture that relies on the concept of local clouds, cloudlets, to leverage the geographical proximity of resources to mobile users and offer them a better user experience. We use a continuous time Markov-chain (CTMC) to model the different nodes of the architecture: user nodes, cloudlets, and the main cloud. We estimate the delay incurred in the proposed architecture by simulating search engine queries generated by mobile users using the CTMC state models. Initial simulation results show that the usage of a cloudlet-based architecture especially centralized architecture has an efficient gains in terms of latency delay and synchronisation mechanisms.