Multi-heuristic dynamic task allocation using genetic algorithms in a heterogeneous distributed system

doi:10.1016/j.jpdc.2010.03.011

Journal of Parallel and Distributed Computing

Volume 70, Issue 7, July 2010, Pages 758-766

https://doi.org/10.1016/j.jpdc.2010.03.011 Get rights and content

Under a Creative Commons license

open access

Abstract

We present a multi-heuristic evolutionary task allocation algorithm to dynamically map tasks to processors in a heterogeneous distributed system. It utilizes a genetic algorithm, combined with eight common heuristics, in an effort to minimize the total execution time. It operates on batches of unmapped tasks and can preemptively remap tasks to processors. The algorithm has been implemented on a Java distributed system and evaluated with a set of six problems from the areas of bioinformatics, biomedical engineering, computer science and cryptography. Experiments using up to 150 heterogeneous processors show that the algorithm achieves better efficiency than other state-of-the-art heuristic algorithms.

Keywords

Scheduling

Genetic algorithms

Heterogeneous

Distributed computing

Cited by (0)

Andrew J. Page received a B.Sc. degree in Computer Science and Software Engineering from the National University of Ireland, Maynooth in 2003. He received a Ph.D. in Computer Science in 2009 from the same university. He is now working in the Wellcome Trust Sanger Institute in Cambridge in sequencing informatics in the field of genomics. His research interests include scheduling, distributed computing and bioinformatics.

Thomas M. Keane received a B.Sc. in Computer Science and Software Engineering in 2002 and an M.Sc. in Computer Science in 2004 from the National University of Ireland, Maynooth. For his Ph.D. Thomas moved to work at the Bioinformatics laboratory at the National University of Ireland, Maynooth, working in the area of phylogenetic methods and high-throughput phylogenomics using distributed computing and completed it in 2006. He is currently a team leader at the Wellcome Trust Sanger Institute in Cambridge. His research interests include distributed computing and bioinformatics.

Thomas J. Naughton received the B.Sc. degree (double honours) in Computer Science and Experimental Physics from the National University of Ireland, Maynooth, Ireland. He has worked at Space Technology (Ireland) Ltd. and has been a visiting researcher at the Department of Radioelectronics, Czech Technical University, Prague, and the Department of Electrical and Computer Engineering, University of Connecticut, Storrs. He is a Senior Lecturer in the Department of Computer Science, National University of Ireland, Maynooth, with a permanent appointment since 2001. Since 2007 he has been a European Commission Marie Curie Fellow at Oulu Southern Institute, University of Oulu, Finland. He leads the EC FP7 three-year eight-partner collaborative project Real 3D. His research interests include optical information processing, computer theory, and distributed computing. He has served as a committee member on 12 international IEEE, ICO, and SPIE conferences. He has co-authored more than 150 publications including 35 journal articles and 20 invited conference papers. He is co-recipient of the 2008 IEEE Donald G. Fink Prize Paper Award.