Innovative Energy Management System for Mobile Processors Power Consumption with Integration of Predictive Neural Network Models

Abstract

At the present stage of information technologies development in the field of portable devices implementation one of the perspective direction is the development of software and hardware to optimise the consumption of energy resources in mobile processors. Modern solutions are aimed at continuous improvement of methods to reduce power consumption along with increasing the performance of devices, but the problem of limited time interval of portable devices active use is still relevant. Existing solutions are aimed at using various energy-dependent methods in the kernel configuration – I/O scheduler governors, TCP overload algorithms, as well as additional entropy distribution systems and memory release algorithms. The solutions considered involve a system of aggressive behaviour based on the use of user-driven methods to terminate energy demanding processes in the system. The purpose of this study is to overcome the problems under consideration by developing a cross-platform algorithmic approach, which is based on the tracking of the energy consumption processes in the kernel, taking into account system calls and background activity in the system. A distinctive feature of the proposed solution is the use of a neural network training sample for the processes of tracking user behaviour, which affects the reduction of the CPU load by completing side processes and increasing the time interval of battery performance. To implement the project, root access to the system was also used, assuming full-function access to the system kernel. Another feature of the implemented algorithm is backwards compatibility of the work with mobile processors, which allows to organise work on mobile devices.