Access Type

Open Access Dissertation

Date of Award

January 2015

Degree Type

Dissertation

Degree Name

Ph.D.

Department

Electrical and Computer Engineering

First Advisor

Kun Wang

Abstract

The last five years have witnessed the proliferation of smart mobile devices, the explosion of various mobile applications and the rapid adoption of cloud computing in business, governmental and educational IT deployment. There is also a growing trends of combining mobile computing and cloud computing as a new popular computing paradigm nowadays. This thesis envisions the future of mobile computing which is primarily affected by following three trends: First, servers in cloud equipped with high speed multi-core technology have been the main stream today. Meanwhile, ARM processor powered servers is growingly became popular recently and the virtualization on ARM systems is also gaining wide ranges of attentions recently. Second, high-speed internet has been pervasive and highly available. Mobile devices are able to connect to cloud anytime and anywhere. Third, cloud computing is reshaping the way of using computing resources. The classic pay/scale-as-you-go model allows hardware resources to be optimally allocated and well-managed. These three trends lend credence to a new mobile computing model with the combination of resource-rich cloud and less powerful mobile devices. In this model, mobile devices run the core virtualization hypervisor with virtualized phone instances, allowing for pervasive access to more powerful, highly-available virtual phone clones in the cloud. The centralized cloud, powered by rich computing and memory recourses, hosts virtual phone clones and repeatedly synchronize the data changes with virtual phone instances running on mobile devices. Users can flexibly isolate different computing environments.

In this dissertation, we explored the opportunity of leveraging cloud resources for mobile computing for the purpose of energy saving, performance augmentation as well as secure computing enviroment isolation. We proposed a framework that allows mo- bile users to seamlessly leverage cloud to augment the computing capability of mobile devices and also makes it simpler for application developers to run their smartphone applications in the cloud without tedious application partitioning. This framework was built with virtualization on both server side and mobile devices. It has three building blocks including agile virtual machine deployment, efficient virtual resource management, and seamless mobile augmentation. We presented the design, imple- mentation and evaluation of these three components and demonstrated the feasibility of the proposed mobile cloud model.

Download

Share

COinS