The rise and adoption of the Cloud computing paradigm had a strong impact on the ICT world in the last few years; this technology has now reached maturity and Cloud providers offer a variety of solutions and services to their customers. However, beside the advantages, Cloud computing introduced new issues and challenges. In particular, the heterogeneity of the Cloud services offered and their relative pricing models makes the identification of a deployment solution that minimizes costs and guarantees QoS very complex. Performance assessment of Cloud based application needs for new models and tools to take into consideration the dynamism and multi-tenancy intrinsic of the Cloud environment. The aim of this work is to provide a novel mixed integer linear program (MILP) approach to find a minimum cost feasible cloud configuration for a given cloud based application. The feasibility of the solution is considered with respect to some non-functional requirements that are analyzed through multiple performance models with different levels of accuracy. The initial solution is further improved by a local search based procedure. The quality of the initial feasible solution is compared against first principle heuristics currently adopted by practitioners and Cloud providers. © 2014 Springer International Publishing Switzerland.

Ardagna, D., Gibilisco, G., Ciavotta, M., Lavrentev, A. (2014). A multi-model optimization framework for the model driven design of cloud applications. In 6th International Symposium on Search-Based Software Engineering, SSBSE 2014; Fortaleza; Brazil; 26 August 2014 through 29 August 2014 (pp.61-76). Springer Verlag [10.1007/978-3-319-09940-8_5].

A multi-model optimization framework for the model driven design of cloud applications

CIAVOTTA, MICHELE;
2014

Abstract

The rise and adoption of the Cloud computing paradigm had a strong impact on the ICT world in the last few years; this technology has now reached maturity and Cloud providers offer a variety of solutions and services to their customers. However, beside the advantages, Cloud computing introduced new issues and challenges. In particular, the heterogeneity of the Cloud services offered and their relative pricing models makes the identification of a deployment solution that minimizes costs and guarantees QoS very complex. Performance assessment of Cloud based application needs for new models and tools to take into consideration the dynamism and multi-tenancy intrinsic of the Cloud environment. The aim of this work is to provide a novel mixed integer linear program (MILP) approach to find a minimum cost feasible cloud configuration for a given cloud based application. The feasibility of the solution is considered with respect to some non-functional requirements that are analyzed through multiple performance models with different levels of accuracy. The initial solution is further improved by a local search based procedure. The quality of the initial feasible solution is compared against first principle heuristics currently adopted by practitioners and Cloud providers. © 2014 Springer International Publishing Switzerland.
Si
paper
Multi-Cloud Capacity Allocation, Optimization, MILP.
English
International Symposium on Search-Based Software Engineering, SSBSE 2014 26-29 August
9783319099392
https://link.springer.com/book/10.1007/978-3-319-09940-8
Ardagna, D., Gibilisco, G., Ciavotta, M., Lavrentev, A. (2014). A multi-model optimization framework for the model driven design of cloud applications. In 6th International Symposium on Search-Based Software Engineering, SSBSE 2014; Fortaleza; Brazil; 26 August 2014 through 29 August 2014 (pp.61-76). Springer Verlag [10.1007/978-3-319-09940-8_5].
Ardagna, D; Gibilisco, G; Ciavotta, M; Lavrentev, A
File in questo prodotto:
File Dimensione Formato  
SBSE.pdf

Solo gestori archivio

Dimensione 390.9 kB
Formato Adobe PDF
390.9 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/186589
Citazioni
  • Scopus 11
  • ???jsp.display-item.citation.isi??? 7
Social impact