Genetic Fuzzy Scheduling - Development of Rule-based Scheduling Strategies for Parallel Machines

Joachim Lepping 1
1 MOAIS - PrograMming and scheduling design fOr Applications in Interactive Simulation
Inria Grenoble - Rhône-Alpes, LIG - Laboratoire d'Informatique de Grenoble
Abstract : In this book, we present novel methodologies for automatically generating online scheduling strategies with the help of real life workload data. The scheduling problem includes independent parallel jobs, multiple identical machines, and a complex scheduling objective. This objective is defined by the machine provider and considers different priorities of user groups. In order to allow a wide range of objective functions, we use a rule based scheduling strategy. There, a rule system classifies all possible scheduling states and assigns an appropriate scheduling strategy to the actual state. The rule bases are developed in three different ways. We evaluate our new scheduling strategies again on real workload data and provide a com­prehensive comparison of the different approaches among each other. Further, we show the benefit of the developed rule based scheduling systems by comparing them to the main standard algorithms currently in use. To this end, we select several exemplary objective functions that prioritize some user groups over others.
Type de document :
Ouvrage (y compris édition critique et traduction)
AV Akademikerverlag, pp.96, 2012, 3639437624
Liste complète des métadonnées

https://hal.inria.fr/hal-00796263
Contributeur : Grégory Mounié <>
Soumis le : samedi 2 mars 2013 - 14:13:54
Dernière modification le : jeudi 11 janvier 2018 - 01:48:46

Identifiants

  • HAL Id : hal-00796263, version 1

Collections

Citation

Joachim Lepping. Genetic Fuzzy Scheduling - Development of Rule-based Scheduling Strategies for Parallel Machines. AV Akademikerverlag, pp.96, 2012, 3639437624. 〈hal-00796263〉

Partager

Métriques

Consultations de la notice

222