Csr: Medium: Mobile Distributed Computing In The Cloud

Project: Research project

Project Details


This project investigates how cloud computing can support mobile distributed computing, in which users' mobile devices interact with each other to provide a large spectrum of collaborative applications for mobile computing and sensing. A surrogate is a per-user software entity in the cloud that acts on behalf of the user's mobile devices. Surrogates have larger storage capacity, higher compute power, wider bandwidth, and better availability than mobile devices. They are available 24x7, even when their mobile devices are offline because of poor connectivity or simply turned off. The applications enabled by this project have a substantial benefit for society in areas such as healthcare, safety, or social interaction. For example, a mobile distributed application would allow users or health agencies to monitor and stop, in early stages, the spread of epidemic diseases. The user mobile devices and surrogates may collaborate regionally to make localized decisions for improved scalability and privacy. In addition to the larger societal benefits, this project benefits many traditionally under-served student groups on campus which are involved in research, development, and testing. The foundational results of this project are incorporated into a new graduate course on Mobile Cloud Computing. A new course on Mobile Application Programming is offered to high school students by leveraging an existing program for educating high school students in science and technology.

The aim of this project is to design, build, and study a mobile-cloud system architecture that enables effective and efficient collaborative applications for mobile users. The novel research outcomes expected from this project are: (1) a programming model and a middleware that enable effective execution of distributed applications on a combination of mobile devices and surrogates; (2) automatic and dynamic application partitioning techniques to divide the application between the mobile devices and the surrogate; (3) cloud services that perform surrogate management: scalable storage for surrogate virtual machine images, surrogate request co-scheduling, and storage management for mobile data; (4) privacy-preserving protocols that leverage additional cloud providers to guarantee an enhanced level of user data privacy, while maintaining most of the functionality achieved in the non-private protocols; (5) a prototype using an surrogate cloud and Android phones/tablets; and (6) a set of representative applications. The prototype and applications will be tested in a large scale user study. To spur the dissemination of results, the surrogate source code will be made Publicly available. Furthermore, researchers from industry labs are invited to workshops organized on campus to encourage collaboration and seek technology traNational Science Foundation er opportunities.
Effective start/end date10/1/149/30/17


  • National Science Foundation


Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.