Quality of service modeling for green scheduling in Clouds

Tom Guérout (1) , Samir Medjiah (1) , Georges da Costa (2, 3) , Thierry Monteil (1)

1 LAAS-SARA - Équipe Services et Architectures pour Réseaux Avancés
2 IRIT-SEPIA - Système d’exploitation, systèmes répartis, de l’intergiciel à l’architecture
3 UT3 - Université Toulouse III - Paul Sabatier

Best known Cloud providers propose services under constraints of Service Level Agreement (SLA) definitions.The SLAs are composed of different Quality of Service (QoS) rules promised by the provider. Thus, the QoSin Clouds becomes more and more important. Precise definitions and metrics have to be explained. Thisarticle proposes an overview of Cloud QoS parameters as well as their classification, but also it defines usablemetrics to evaluate QoS parameters. Moreover, the defined QoS metrics are measurable and reusable in anyscheduling approach for Clouds. Energy consumption is an inherent objective in Cloud Computing, thus, it isalso considered. For evaluation purposes, two uncommon QoS parameters: Dynamism and Robustness are takeninto account in different Cloud virtual machines scheduling approaches. Validation is done through comparisonof common scheduling algorithms, including a genetic algorithm (GA), in terms of QoS parameters evolutionin time. Simulation results have shown that including various QoS parameters allows a deeper schedulingalgorithms analysis

Mots clés: Cloud computing; Multi-objectives optimization; Energy-Efficiency; Genetic Algorithm; Dynamic Voltage and Frequency Scaling (DVFS); Quality of Service; Simulation

Domaines: Informatique [cs]

Tom Guérout, Samir Medjiah, Georges da Costa, Thierry Monteil. Quality of service modeling for green scheduling in Clouds. Sustainable Computing : Informatics and Systems, 2014, 4 (4), pp.225-240. ⟨10.1016/j.suscom.2014.08.006⟩. ⟨hal-01228273⟩