Autonomous Context-Based Service Optimization in Mobile Cloud Computing

Abstract

As the concept of merging the capabilities of mobile devices and cloud computing is becoming increasingly popular, an important question arises: how to optimally schedule services/tasks between the device and the cloud. The main objective of this paper is to investigate the possibilities for using a decision module on mobile devices in order to autonomously optimize the execution of services within the framework of Mobile Cloud Computing while taking context into account. A novel model of the decision module with learning capabilities, service-oriented architecture, and service selection optimization algorithm are proposed to solve this problem. To achieve autonomous, online learning on mobile devices, we apply supervised learning. Information about the context, task description, the decision made and its results such as calculation time or power consumption are stored and form training data for a supervised learning algorithm, which updates the knowledge used by the decision module to determine the optimal place for the execution of a given type of task. To verify the solution proposed, service-oriented mobile processing systems

VM Reservation Plan Adaptation Using Machine Learning in Cloud Computing

“…For example, in [22] the authors are trying to predict, using weather forecasts, how much energy can be potentially harvested and on that basis make decisions which device peripherals can be used without overdrawing the power budget predicted. We have also applied an approach similar to the one described in [23,24], where machine learning algorithms are used to create models predicting battery usage and computation time for tasks executed on mobile devices.…”

“…However, these algorithms usually exhibit better accuracy. Based on our research [23] in which Neural Networks were successfully applied to task allocation adaptation in Mobile Cloud, we decided to start with this machine learning model for experiments. Subsequently, we have also applied linear regression and decision trees to compare quality of results.…”

Review on Compute Augmentation Techniques in Mobile Cloud Computing

“…Piotr Nawrocki et al, [54] The objective of this paper is to reduce the makespan and energy using context information. The profiling information are obtained from program profiler, device profiler and network monitor.…”