Vol.41, No.1, 2022, pp.209-224, doi:10.32604/csse.2022.019531
OPEN ACCESS
ARTICLE
Novel Power-Aware Optimization Methodology and Efficient Task Scheduling Algorithm
  • K. Sathis Kumar1,*, K. Paramasivam2
1 Department of Computer Science and Engineering, Bannari Amman Institute of Technology, Sathyamangalam, 638401, Tamilnadu, India
2 Department of Electrical and Electronics Engineering, Kumaraguru College of Technology, Coimbatore, 641049, Tamilnadu, India
* Corresponding Author: K. Sathis Kumar. Email:
Received 16 April 2021; Accepted 12 June 2021; Issue published 08 October 2021
Abstract
The performance of central processing units (CPUs) can be enhanced by integrating multiple cores into a single chip. Cpu performance can be improved by allocating the tasks using intelligent strategy. If Small tasks wait for long time or executes for long time, then CPU consumes more power. Thus, the amount of power consumed by CPUs can be reduced without increasing the frequency. Lines are used to connect cores, which are organized together to form a network called network on chips (NOCs). NOCs are mainly used in the design of processors. However, its performance can still be enhanced by reducing power consumption. The main problem lies with task scheduling, which fully utilizes the network. Here, we propose a novel random fit algorithm for NOCs based on power-aware optimization. In this algorithm, tasks that are under the same application are mapped to the neighborhoods of the same application, whereas tasks belonging to different applications are mapped to the processor cores on the basis of a series of steps. This scheduling process is performed during the run time. Experiment results show that the proposed random fit algorithm reduces the amount of power consumed and increases system performance based on effective scheduling.
Keywords
Random fit algorithm; network on chips; processor cores; power-aware optimization
Cite This Article
Kumar, K. S., Paramasivam, K. (2022). Novel Power-Aware Optimization Methodology and Efficient Task Scheduling Algorithm. Computer Systems Science and Engineering, 41(1), 209–224.
This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.