A Tabu search algorithm for scheduling independent jobs in computational grids

The efficient allocation of jobs to grid resources is indispensable for high performance grid-based applications, and it is a computationally hard problem even when there are no dependencies among jobs. We present in this paper a new tabu search (TS) algorithm for the problem of batch job scheduling...

Descripción completa

Detalles Bibliográficos
Autores: Xhafa Xhafa, Fatos|||0000-0001-6569-5497, Carretero Casado, Javier Sebastián, Dorronsoro, Bernabé, Alba, Enrique
Tipo de recurso: artículo
Fecha de publicación:2009
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/130002
Acceso en línea:https://hdl.handle.net/2117/130002
Access Level:acceso abierto
Palabra clave:Computational grids (Computer systems)
Computer algorithms
Job scheduling
Computational grid
Tabu search
Computació distribuïda
Algorismes computacionals
Àrees temàtiques de la UPC::Informàtica::Arquitectura de computadors::Arquitectures distribuïdes
Descripción
Sumario:The efficient allocation of jobs to grid resources is indispensable for high performance grid-based applications, and it is a computationally hard problem even when there are no dependencies among jobs. We present in this paper a new tabu search (TS) algorithm for the problem of batch job scheduling on computational grids. We define it as a bi-objective optimization problem, consisting of the minimization of the makespan and flowtime. Our TS is validated versus three other algorithms in the literature for a classical benchmark. We additionally consider some more realistic benchmarks with larger size instances in static and dynamic environments. We show that our TS clearly outperforms the compared algorithms.