Process Batch Offloading Method for Mobile-Cloud Computing Platform

Abstract

Mobile cloud applications transfers the computational power and data storage outside the mobile device and into the mobile cloud, getting mobile computing and mobile applications to not handheld devices users but a wider choice of mobile subscribers. Process offloading is the technique in which some part of the application is transferred into the mobile cloud for execution. Many applications like GPS, face recognition, video editing etc. consumes more battery of the mobile devices. By offloading the power hunger part to the cloud is one of the approach to elongate the battery lifetime of mobile devices. The major goal of the proposed model is to combine the similar processes into single batch and offload the batch into cloud rather than offloading a single process into cloud. A MPCEPGM (Multilevel Process Cost Evaluation with Process Group Merging) algorithm is proposed for application partitioning and offloading to the cloud. MPCEPGM will predict the overall execution cost of the whole batch or process tree as single entity. This will help the mobile offloading procedure to organize the processes according to their delivery time. Proposed model is energy efficient to deliver the data effectively to the mobile cloud. The performance of the proposed system is assessed on the basis of total execution time and communication cost using Matlab simulations.