Towards the optimization of power and bandwidth consumption in mobile-cloud hybrid applications

Abstract

Mobile devices can now support a wide range of applications, many of which demand high computational power. Backed by the virtually unbounded resources of cloud computing, today's mobile-cloud (MC) computing can meet the demands of even the most computationally and resource intensive applications. However, many existing MC hybrid applications are inefficient in terms of achieving objectives like minimizing battery power consumption and network bandwidth usage, which form a tradeoff. To counter this problem we propose a technique that: 1) measures, at run time, how well the MC application meets these two objectives; and 2) allows arbitrary configurations to be applied to the MC application in order to optimize the efficiency tradeoff. Our experimental evaluation considers two MC hybrid applications. We modularized them first, based on computationally-intensive tasks, and then executed them using a simple MC framework while measuring the power and bandwidth consumption at run-time. Analysis of results shows that efficient configurations of the apps can be obtained in terms of minimizing the two objectives. However, there remain challenges such as scalability and automation of the process, which we discuss.

The importance of granularity in multiobjective optimization of mobile cloud hybrid applications

“…The integration might be done through a middleware that provides an abstraction between a mobile device and the cloud and controls every aspect of the communication in between. In our previous work, we used a simple middleware‐based framework, which was based on Firebase . Using Firebase or another such kind of system as middleware comes with a number of problems that we had highlighted.…”

“…In this paper, we consider minimizing battery power consumption and network bandwidth usage as two objectives. To achieve efficient MC hybrid applications, we presented previously a multiobjective optimization technique to find and apply the optimal configurations of Android‐based MC hybrid application. We evaluated the technique using offline profiling of Android‐based MC hybrid applications but only with a class‐level granularity.…”

“…In our previous work, we have shown that the MC hybrid applications have an efficiency trade‐off between battery power consumption and network bandwidth usage. This exists because (1) performing computationally intensive tasks on a mobile device can be inefficient in terms of battery power consumption and (2) sending data to and receiving from the cloud can also be inefficient in terms of bandwidth usage cost and battery power consumption by the transmitter chip on board (ie, WiFi) inside the mobile device.…”

“…We use a binary string to represent a configuration. Previously, we presented initial steps toward establishing this technique. In this paper, we extend that work to consider method‐level and hybrid‐level configurations and provide a more in‐depth analysis of its behavior and performance.…”

A Self-Aware and Scalable Solution for Efficient Mobile-Cloud Hybrid Robotics

“…In MCC, an efficiency trade-off exists between the battery power consumption and network usage (Akbar and Lewis, 2017 , 2018a ). Due to which, the performance of Mobile-cloud hybrid (MCH) applications can be inefficient in terms of battery power consumption.…”