Computational offloading mechanism for native and android runtime based mobile applications

Abstract

Mobile cloud computing is a promising approach to augment the computational capabilities of mobile devices for emerging resource-hungry mobile applications. Android-based smartphones have opened real-world venues for mobile cloud applications mainly because of the open source nature of Android. Computational offloading mechanism enables the augmentation of smartphone capabilities. The problem is majority of existing computational offloading solutions for Android-based smartphones heavily depends on Dalvik VM (an application-level VM). Apart from being a discontinued product, Dalvik VM consumes extra time and energy because of the just-in-time (JIT) compilation of bytecode into machine instructions. With regard to this problem, Google has introduced Android Runtime (ART) featuring ahead-of-time (AHOT) compilation to native instructions in place of Dalvik VM. However, current state-of-the-art offloading solutions do not consider AHOT compilations to native binaries in the ART environment. To address the issue in offloading ART-based mobile applications, we propose a computational offloading framework. The proposed framework requires infrastructural support from cloud data centers to provide offloading as a service for heterogeneous mobile devices. Numerical results from proof-of-concept implementation revealed that the proposed framework improves the execution time of the experimental application by 76% and reduces its energy consumption by 70%.