Dynamic energy aware task scheduling using run-queue peek

Sachin Pawaskar, Hesham H Ali

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Scheduling dependent tasks is one of the most challenging problems in parallel and distributed systems. It is known to be computationally intractable in its general form as well as several restricted cases. An interesting application of scheduling is in the area of energy awareness for mobile battery operated devices where minimizing the energy utilized is the most important scheduling policy consideration. A number of heuristics have been developed for this consideration. In this paper, we study the scheduling problem for a particular battery model. In the proposed work, we show how to enhance a well know approach of accounting for the slack generated at runtime due to the difference between WCET (Worst Case Execution Time) and AET (Actual Execution Time). Our solution exploits the fact that even though some tasks become available based on the actual periodicity of a task they are not executed because the run queue is determined by the schedule generated in the offline phase I of the algorithm using the conservative EDF (Earliest Deadline First) algorithm. We peek at the task run-queue to find such tasks to eliminate wastage of the slack generated. Based on the outcome of the conducted experiments, the proposed algorithm outperformed or matched the performance of the 2-Phase dynamic task scheduling algorithm all the time.

Original languageEnglish (US)
Title of host publicationProceedings of the IASTED International Conference on Parallel and Distributed Computing and Networks, PDCN 2007
Pages164-169
Number of pages6
StatePublished - Dec 1 2007
EventIASTED International Conference on Parallel and Distributed Computing and Networks, PDCN 2007 - Innsbruck, Austria
Duration: Feb 13 2007Feb 15 2007

Publication series

NameProceedings of the IASTED International Conference on Parallel and Distributed Computing and Systems
ISSN (Print)1027-2658

Conference

ConferenceIASTED International Conference on Parallel and Distributed Computing and Networks, PDCN 2007
CountryAustria
CityInnsbruck
Period2/13/072/15/07

Fingerprint

Scheduling
Scheduling algorithms
Experiments

Keywords

  • Energy awareness
  • Heuristics
  • Optimal algorithms
  • Parallel processing
  • Scheduling

ASJC Scopus subject areas

  • Software
  • Hardware and Architecture
  • Computer Networks and Communications

Cite this

Pawaskar, S., & Ali, H. H. (2007). Dynamic energy aware task scheduling using run-queue peek. In Proceedings of the IASTED International Conference on Parallel and Distributed Computing and Networks, PDCN 2007 (pp. 164-169). (Proceedings of the IASTED International Conference on Parallel and Distributed Computing and Systems).

Dynamic energy aware task scheduling using run-queue peek. / Pawaskar, Sachin; Ali, Hesham H.

Proceedings of the IASTED International Conference on Parallel and Distributed Computing and Networks, PDCN 2007. 2007. p. 164-169 (Proceedings of the IASTED International Conference on Parallel and Distributed Computing and Systems).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Pawaskar, S & Ali, HH 2007, Dynamic energy aware task scheduling using run-queue peek. in Proceedings of the IASTED International Conference on Parallel and Distributed Computing and Networks, PDCN 2007. Proceedings of the IASTED International Conference on Parallel and Distributed Computing and Systems, pp. 164-169, IASTED International Conference on Parallel and Distributed Computing and Networks, PDCN 2007, Innsbruck, Austria, 2/13/07.
Pawaskar S, Ali HH. Dynamic energy aware task scheduling using run-queue peek. In Proceedings of the IASTED International Conference on Parallel and Distributed Computing and Networks, PDCN 2007. 2007. p. 164-169. (Proceedings of the IASTED International Conference on Parallel and Distributed Computing and Systems).
Pawaskar, Sachin ; Ali, Hesham H. / Dynamic energy aware task scheduling using run-queue peek. Proceedings of the IASTED International Conference on Parallel and Distributed Computing and Networks, PDCN 2007. 2007. pp. 164-169 (Proceedings of the IASTED International Conference on Parallel and Distributed Computing and Systems).
@inproceedings{0fc2ddeaa5bd4fb483b61ecea1ed140d,
title = "Dynamic energy aware task scheduling using run-queue peek",
abstract = "Scheduling dependent tasks is one of the most challenging problems in parallel and distributed systems. It is known to be computationally intractable in its general form as well as several restricted cases. An interesting application of scheduling is in the area of energy awareness for mobile battery operated devices where minimizing the energy utilized is the most important scheduling policy consideration. A number of heuristics have been developed for this consideration. In this paper, we study the scheduling problem for a particular battery model. In the proposed work, we show how to enhance a well know approach of accounting for the slack generated at runtime due to the difference between WCET (Worst Case Execution Time) and AET (Actual Execution Time). Our solution exploits the fact that even though some tasks become available based on the actual periodicity of a task they are not executed because the run queue is determined by the schedule generated in the offline phase I of the algorithm using the conservative EDF (Earliest Deadline First) algorithm. We peek at the task run-queue to find such tasks to eliminate wastage of the slack generated. Based on the outcome of the conducted experiments, the proposed algorithm outperformed or matched the performance of the 2-Phase dynamic task scheduling algorithm all the time.",
keywords = "Energy awareness, Heuristics, Optimal algorithms, Parallel processing, Scheduling",
author = "Sachin Pawaskar and Ali, {Hesham H}",
year = "2007",
month = "12",
day = "1",
language = "English (US)",
isbn = "9780889866379",
series = "Proceedings of the IASTED International Conference on Parallel and Distributed Computing and Systems",
pages = "164--169",
booktitle = "Proceedings of the IASTED International Conference on Parallel and Distributed Computing and Networks, PDCN 2007",

}

TY - GEN

T1 - Dynamic energy aware task scheduling using run-queue peek

AU - Pawaskar, Sachin

AU - Ali, Hesham H

PY - 2007/12/1

Y1 - 2007/12/1

N2 - Scheduling dependent tasks is one of the most challenging problems in parallel and distributed systems. It is known to be computationally intractable in its general form as well as several restricted cases. An interesting application of scheduling is in the area of energy awareness for mobile battery operated devices where minimizing the energy utilized is the most important scheduling policy consideration. A number of heuristics have been developed for this consideration. In this paper, we study the scheduling problem for a particular battery model. In the proposed work, we show how to enhance a well know approach of accounting for the slack generated at runtime due to the difference between WCET (Worst Case Execution Time) and AET (Actual Execution Time). Our solution exploits the fact that even though some tasks become available based on the actual periodicity of a task they are not executed because the run queue is determined by the schedule generated in the offline phase I of the algorithm using the conservative EDF (Earliest Deadline First) algorithm. We peek at the task run-queue to find such tasks to eliminate wastage of the slack generated. Based on the outcome of the conducted experiments, the proposed algorithm outperformed or matched the performance of the 2-Phase dynamic task scheduling algorithm all the time.

AB - Scheduling dependent tasks is one of the most challenging problems in parallel and distributed systems. It is known to be computationally intractable in its general form as well as several restricted cases. An interesting application of scheduling is in the area of energy awareness for mobile battery operated devices where minimizing the energy utilized is the most important scheduling policy consideration. A number of heuristics have been developed for this consideration. In this paper, we study the scheduling problem for a particular battery model. In the proposed work, we show how to enhance a well know approach of accounting for the slack generated at runtime due to the difference between WCET (Worst Case Execution Time) and AET (Actual Execution Time). Our solution exploits the fact that even though some tasks become available based on the actual periodicity of a task they are not executed because the run queue is determined by the schedule generated in the offline phase I of the algorithm using the conservative EDF (Earliest Deadline First) algorithm. We peek at the task run-queue to find such tasks to eliminate wastage of the slack generated. Based on the outcome of the conducted experiments, the proposed algorithm outperformed or matched the performance of the 2-Phase dynamic task scheduling algorithm all the time.

KW - Energy awareness

KW - Heuristics

KW - Optimal algorithms

KW - Parallel processing

KW - Scheduling

UR - http://www.scopus.com/inward/record.url?scp=56149090076&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=56149090076&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9780889866379

T3 - Proceedings of the IASTED International Conference on Parallel and Distributed Computing and Systems

SP - 164

EP - 169

BT - Proceedings of the IASTED International Conference on Parallel and Distributed Computing and Networks, PDCN 2007

ER -