Mobile offloading in the wild: Findings and lessons learned through a real-life experiment with a new cloud-aware system | IEEE Conference Publication | IEEE Xplore

Mobile offloading in the wild: Findings and lessons learned through a real-life experiment with a new cloud-aware system


Abstract:

Mobile-cloud offloading mechanisms delegate heavy mobile computation to the cloud. In real life use, the energy tradeoff of computing the task locally or sending the inpu...Show More

Abstract:

Mobile-cloud offloading mechanisms delegate heavy mobile computation to the cloud. In real life use, the energy tradeoff of computing the task locally or sending the input data and the code of the task to the cloud is often negative, especially with popular communication intensive jobs like social-networking, gaming, and emailing. We design and build a working implementation of CDroid, a system that tightly couples the device OS to its cloud counterpart. The cloud-side handles data traffic through the device efficiently and, at the same time, caches code and data optimally for possible future offloading. In our system, when offloading decision takes place, input and code are likely to be already on the cloud. CDroid makes mobile cloud offloading more practical enabling offloading of lightweight jobs and communication intensive apps. Our experiments with real users in everyday life show excellent results in terms of energy savings and user experience.
Date of Conference: 27 April 2014 - 02 May 2014
Date Added to IEEE Xplore: 08 July 2014
Electronic ISBN:978-1-4799-3360-0
Print ISSN: 0743-166X
Conference Location: Toronto, ON, Canada

Contact IEEE to Subscribe

References

References is not available for this document.