Dynamic Scheduling of Tasks for Multi-core Real Time Systems based on Optimum Energy and Throughput

What is it about?

One of the critical design issues in real-time systems is energy consumption, especially in battery-operated systems. Generally higher processor voltage generates higher throughput of the system while decreasing voltage can perform energy minimization. Instead of lowering processor voltage, this paper presents an optimum energy efficient realtime scheduling to adjust voltage dynamically to achieve optimum throughput. Earlier research works have considered random new tasks, which have been divided into jobs using pfair scheduling to fit into idle times of different cores of the system. In this paper, we consider each job has different power levels and execution time at each power level can be found using normalized execution time. Based on the power levels and their corresponding execution time, we find different combinations of energy signature of the system and derive the optimum state of the system using weighted average of the energy of the system and corresponding throughput. We verify the model using generated task sets and the results show that our model performs excellently in all the cases and significantly reduce the total energy consumption of the system with respect to some popular and relatively new scheduling schemes

Featured Image

Photo by Thomas Jensen on Unsplash

Photo by Thomas Jensen on Unsplash

Why is it important?

The main contributions of our proposed model are as follows: 1) For the first time a new kind of task scheduling model for multicore real time system has been implemented by extending the existing work. It gives better performance than the previous model. Further the proposed scheduling scheme significantly reduces the total energy consumption of the system with respect to some popular scheduling algorithms namely EDF by 18%, DM by 17.5% and relatively new scheduling scheme Optimal Job to a Fast Processor First (OJFPF) by 6%. 2) The proposed model finds an optimum state of the system where throughput (i.e CPU utilization) and energy of the system are optimum. 3) A Ranking methodology of the system has been established considering energy budgets and corresponding throughputs of the system. 4) The user of the model has the flexibility to choose any of the ranking states depending upon the requirements of the throughput and energy without missing the deadline of the task. 5) To the best of our knowledge, there is no previous research work exists to find an optimum state of the real-time system using ranking methodology considering energy budgets and corresponding throughputs of the system.