محیط محاسبات ابری موبایل مبتنی بر یادگیری ماشین
Abstract
1- Introduction
2- Related work
3- Adaptable MCC environment
4- Performance evaluation
5- Conclusions
References
Abstract
The growing importance of mobile devices has caused the need to develop solutions (such as Mobile Cloud Computing) that make it possible to optimize their operation. The main objective of this article is to investigate the possibilities for using machine learning and the code offloading mechanism in the Mobile Cloud Computing concept which may enable the operation of services to be optimized, among others, on mobile devices. We have proposed a formal model of the solution and created its prototype implementation. The adaptable Mobile Cloud Computing environment developed has been implemented using a cross-platform technology for designing Internet applications (Ionic 2). This technology enables hybrid applications to be built with code transfer that run on different operating systems (such as Android, iOS or Windows), which decreases the amount of work required from developers, as the same code is executed on a mobile device and in the cloud. It also makes this solution significantly more universal. The experiments conducted with respect to our solution showed its effectiveness, especially in the case of services which require complex calculations. Test results (for the Face Recognition and Optical Character Recognition services) showed that service execution time and energy consumption decreased significantly during the performance of tasks on a mobile device.
Introduction
In recent years, we have seen the increased importance of solutions that make it possible to optimize the operation of mobile devices. Among these solutions, the Mobile Cloud Computing (MCC) concept plays an important role, which enables tasks/services to be sent from the mobile device to the cloud and the result to be returned to the mobile device. This makes it possible, among other things, to reduce the time of task/service performance and to reduce the energy consumption of mobile devices.