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

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

doi:10.1109/EMPDP.2019.8671564

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

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

^*Corresponding author

University of Pavia

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (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.

Original language	English
Title of host publication	Proc. 27th Euromicro International Conference on Parallel, Distributed, and Network-Based Processing - PDP
Pages	174-180
Number of pages	7
Volume	2019
DOIs	https://doi.org/10.1109/EMPDP.2019.8671564
Publication status	Published - 2019
Event	2019 27th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP) - Italia Duration: 13 Feb 2019 → 15 Mar 2019

Conference

Conference	2019 27th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)
City	Italia
Period	13/2/19 → 15/3/19

Keywords

Cloud Computing
Genetic Algorithm

Access to Document

10.1109/EMPDP.2019.8671564

Cite this

Calzarossa, M. C., Massari, L., Della Vedova, M. L., Nebbione, G., & Tessera, D. (2019). Tuning Genetic Algorithms for resource provisioning and scheduling in uncertain cloud environments: Challenges and findings. In Proc. 27th Euromicro International Conference on Parallel, Distributed, and Network-Based Processing - PDP (Vol. 2019, pp. 174-180) https://doi.org/10.1109/EMPDP.2019.8671564

@inproceedings{5a3078fe889b44e29b8e7be781504eaf,

title = "Tuning Genetic Algorithms for resource provisioning and scheduling in uncertain cloud environments: Challenges and findings",

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.",

keywords = "Cloud Computing, Genetic Algorithm, Cloud Computing, Genetic Algorithm",

author = "Calzarossa, \{Maria Carla\} and Luisa Massari and \{Della Vedova\}, \{Marco Luigi\} and Giuseppe Nebbione and Daniele Tessera",

year = "2019",

doi = "10.1109/EMPDP.2019.8671564",

language = "English",

isbn = "978-1-7281-1644-0",

volume = "2019",

pages = "174--180",

booktitle = "Proc. 27th Euromicro International Conference on Parallel, Distributed, and Network-Based Processing - PDP",

note = "2019 27th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP) ; Conference date: 13-02-2019 Through 15-03-2019",

}

Calzarossa, MC, Massari, L, Della Vedova, ML, Nebbione, G & Tessera, D 2019, Tuning Genetic Algorithms for resource provisioning and scheduling in uncertain cloud environments: Challenges and findings. in Proc. 27th Euromicro International Conference on Parallel, Distributed, and Network-Based Processing - PDP. vol. 2019, pp. 174-180, 2019 27th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP), Italia, 13/2/19. https://doi.org/10.1109/EMPDP.2019.8671564

Tuning Genetic Algorithms for resource provisioning and scheduling in uncertain cloud environments: Challenges and findings. / Calzarossa, Maria Carla; Massari, Luisa; Della Vedova, Marco Luigi et al.
Proc. 27th Euromicro International Conference on Parallel, Distributed, and Network-Based Processing - PDP. Vol. 2019 2019. p. 174-180.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Tuning Genetic Algorithms for resource provisioning and scheduling in uncertain cloud environments: Challenges and findings

AU - Calzarossa, Maria Carla

AU - Massari, Luisa

AU - Della Vedova, Marco Luigi

AU - Nebbione, Giuseppe

AU - Tessera, Daniele

PY - 2019

Y1 - 2019

N2 - 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.

AB - 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.

KW - Cloud Computing

KW - Genetic Algorithm

KW - Cloud Computing

KW - Genetic Algorithm

UR - http://hdl.handle.net/10807/132271

U2 - 10.1109/EMPDP.2019.8671564

DO - 10.1109/EMPDP.2019.8671564

M3 - Conference contribution

SN - 978-1-7281-1644-0

VL - 2019

SP - 174

EP - 180

BT - Proc. 27th Euromicro International Conference on Parallel, Distributed, and Network-Based Processing - PDP

T2 - 2019 27th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)

Y2 - 13 February 2019 through 15 March 2019

ER -

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

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this