Spectral Clustering Scheduling Techniques for Tasks with Strict QoS Requirements

Authors:
Nikos Doulamis;Panagiotis Kokkinos;Emmanouel Varvarigos
Affiliations:
Department of Computer Engineering and Informatics, University of Patras and, Research Academic Computer Technology Institute, Patras, Greece;Department of Computer Engineering and Informatics, University of Patras and, Research Academic Computer Technology Institute, Patras, Greece;Department of Computer Engineering and Informatics, University of Patras and, Research Academic Computer Technology Institute, Patras, Greece
Venue:
Euro-Par '08 Proceedings of the 14th international Euro-Par conference on Parallel Processing
Year:
2008

Citing 11
Cited 2

A taxonomy and survey of grid resource management systems for distributed computing

Software—Practice & Experience
Performance-Effective and Low-Complexity Task Scheduling for Heterogeneous Computing

IEEE Transactions on Parallel and Distributed Systems
G-commerce: Market Formulations Controlling Resource Allocation on the Computational Grid

IPDPS '01 Proceedings of the 15th International Parallel & Distributed Processing Symposium
Core Algorithms of the Maui Scheduler

JSSPP '01 Revised Papers from the 7th International Workshop on Job Scheduling Strategies for Parallel Processing
High Performance Parametric Modeling with Nimrod/G: Killer Application for the Global Grid?

IPDPS '00 Proceedings of the 14th International Symposium on Parallel and Distributed Processing
Scalable Grid Application Scheduling via Decoupled Resource Selection and Scheduling

CCGRID '06 Proceedings of the Sixth IEEE International Symposium on Cluster Computing and the Grid
A Multiobjective Resources Scheduling Approach Based on Genetic Algorithms in Grid Environment

GCCW '06 Proceedings of the Fifth International Conference on Grid and Cooperative Computing Workshops
Relative Performance of Scheduling Algorithms in Grid Environments

CCGRID '07 Proceedings of the Seventh IEEE International Symposium on Cluster Computing and the Grid
The portable batch scheduler and the maui scheduler on linux clusters

ALS'00 Proceedings of the 4th annual Linux Showcase & Conference - Volume 4
Fair Scheduling Algorithms in Grids

IEEE Transactions on Parallel and Distributed Systems
Scheduling strategies for mapping application workflows onto the grid

HPDC '05 Proceedings of the High Performance Distributed Computing, 2005. HPDC-14. Proceedings. 14th IEEE International Symposium

Editorial: Infrastructure and Network-aware Grids and Service Oriented Architectures

Future Generation Computer Systems
Scheduling efficiency of resource information aggregation in grid networks

Future Generation Computer Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

Efficient task scheduling is fundamental for the success of the Grids, since it directly affects the Quality of Service (QoS) offered to the users. Efficient scheduling policies should be evaluated based not only on performance metrics that are of interest to the infrastructure side, such as the Grid resources utilization efficiency, but also on user satisfaction metrics, such as the percentage of tasks served by the Grid without violating their QoS requirements. In this paper, we propose a scheduling algorithm for tasks with strict timing requirements, given in the form of a desired start and finish time. Our algorithm aims at minimizing the violations of the time constraints, while at the same time minimizing the number of processors used. The proposed scheduling method exploits concepts derived from spectral clustering, and groups together for assignment to a computing resource the tasks so to a) minimize the time overlapping of the tasks assigned to a given processor and b) maximize the degree of time overlapping among tasks assigned to different processors. Experimental results show that our proposed strategy outperforms greedy scheduling algorithms for different values of the task load submitted.