Tuning Genetic Algorithms for resource provisioning and scheduling in uncertain cloud environments: Challenges and findings

Marco Luigi Della Vedova, Daniele Tessera, Luisa Massari, Maria Carla Calzarossa, Giuseppe Nebbione

Risultato della ricerca: Contributo in libroContributo a convegno

1 Citazioni (Scopus)

Abstract

Cloud computing allows users to devise cost-effectivesolutions for deploying their applications. Nevertheless, the deci-sions about resource provisioning are very challenging becauseworkloads are seriously affected by the uncertainty of cloudperformance and their characteristics vary. In this paper weaddress these issues by explicitly modeling workload and clouduncertainty in the decision process. For this purpose, we adopt aprobabilistic formulation of the optimization problem aimed atminimizing the expected cost for deploying a parallel applicationunder a deadline constraint. To find a sub-optimal solutionof the problem we apply a Genetic Algorithm. By tuning itsparameters we are able to assess their role and their impact onthe effectiveness and efficiency of the algorithm for provisioningand scheduling in uncertain cloud environments.
Lingua originaleEnglish
Titolo della pubblicazione ospiteProc. 27th Euromicro International Conference on Parallel, Distributed, and Network-Based Processing - PDP
Pagine174-180
Numero di pagine7
Volume2019
DOI
Stato di pubblicazionePubblicato - 2019
Evento2019 27th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP) - Italia
Durata: 13 feb 201915 mar 2019

Convegno

Convegno2019 27th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)
CittàItalia
Periodo13/2/1915/3/19

Keywords

  • Cloud Computing
  • Genetic Algorithm

Fingerprint

Entra nei temi di ricerca di 'Tuning Genetic Algorithms for resource provisioning and scheduling in uncertain cloud environments: Challenges and findings'. Insieme formano una fingerprint unica.

Cita questo