ENERGY-EFFICIENT SCHEDULING FOR DISTRIBUTED REAL-TIME EMBEDDED SYSTEMS

Abstract

Energy consumption is a critical design issue in embedded systems, especially in battery-operated systems. Dynamic Voltage Scaling and Dynamic Frequency Scaling allow us to adjust supply voltage and processor frequency to adapt to the workload demand for better energy management instead of lowering processor voltage and frequency as much as possible. Power-Aware Real-time Scheduling adjusts voltage and frequency according to some optimization criteria, such as low energy consumption or high throughput, while meets the timing constraints of real-time tasks. The problem of variable voltage scheduling of multi-rate periodic task graphs i.e., tasks with precedence relationship in heterogeneous distributed real-time embedded systems is addressed. Such an embedded system may contain general purpose processors, field programmable gate arrays and application specification integrated circuits. The implications of the distribution of power consumption of tasks and characteristics of voltage-scalable processing elements (PEs) are studied. Then a energy-efficient variable voltage scheduling algorithm to address these implications is presented. The scheduling algorithm performs execution order optimization of scheduling events to increase the chances of scaling down voltage and frequencies of these voltage-scalable PEs in the distributed embedded systems and it also performs power-profile and timing constraint driven, slack allocation to maximize power reduction via voltage scaling, based on the observation that the energy consumption of task on voltage-scalable PE is normally a convex function of the clock speed. This project aims to provide Energy Efficient Real-Time Scheduling in heterogeneous distributed real-time embedded systems.

Authors and Affiliations

Alka , Dr. Subham Gandhi , Dr. Jitender Khurana

Keywords

Related Articles

TO APPLY DATA ANALYSIS METHODOLOGY TO EXPLAIN THE TBF FACTOR OF LHD MACHINES IN MINING BY MAXIMIZATION ESTIMATION METHOD

In this paper the different mine techniques are discussed in detail. Also the concept of LHD machines is explained. The time between successive failure (TBF) is calculated and TTT plots are explained in detail. Here the...

THE PERFORMANCE OF DATA TRANSMISSION ON CLOUD TECHNOLOGY

This paper presents the necessary utility on network in order to implement the performance of Data Transmission on Cloud. To improve those data transmission we have built Data Storages located at different countries over...

Strategic Analysis of Competitiveness for Global Manufacturing

Manufacturing organizations recognise that the business environment has varying levels of unpredictability. To serve such unpredictability, they utilise forecasting and decision modeling techniques at all levels (strateg...

ANALYSIS OF DYNAMIC INTERCONNECTION NETWORKS

To solve the problem of providing fast, reliable and efficient communication at a reasonable cost in large parallel processing systems, many different networks have been proposed. In this paper dynamic interconnection ne...

THE EXPERIMENTAL STUDY OF THE ELASTICITY OF MATERIALS (IN TERMS OF STRESS, STRAIN) AND TO FIND STRENGTH OF MATERIALS LIKE ALUMINUM AT DIFFERENT TEMPERATURES

The strength of a material is very concerned topic in mechanical engineering, so the main objective of this paper is to discuss about strength of materials like aluminum and find the elasticity of materials in terms of t...

Download PDF file
  • EP ID EP108907
  • DOI -
  • Views 127
  • Downloads 0

How To Cite

Alka, Dr. Subham Gandhi, Dr. Jitender Khurana (2012). ENERGY-EFFICIENT SCHEDULING FOR DISTRIBUTED REAL-TIME EMBEDDED SYSTEMS. International Journal of Electrical, Electronics and Mechanical Fundamentals (www.ijeemf.com), 2(1), 26-32. https://europub.co.uk/articles/-A-108907