TY - JOUR
T1 - Exploiting CloudSim in a multiformalism modeling approach for cloud based systems
AU - Barbierato, Enrico
AU - Gribaudo, Marco
AU - Iacono, Mauro
AU - Jakóbik, Agnieszka
PY - 2018
Y1 - 2018
N2 - Cloud based architectures present many challenges, ranging from poorly dimensioned\r\nhardware to lengthy wait times and resource balancing issues. Most of\r\nthese problems can be mitigated by using proper performance evaluation techniques,\r\ndepending on the accuracy of the model abstracting the real system. The\r\nadoption of a formalism over another to describe the considered infrastructure\r\nplays a crucial role in achieving this goal. In this sense, multiformalism proves\r\nitself to be a powerful modeling approach describing each system component according\r\nto the most suitable representation. This paper presents a novel modeling\r\nmethod oriented to the prediction of cloud architectures performance, suitable for\r\njoining the advantages of high level modeling abstractions and of the detail of\r\na specialized simulator. Generalized Stochastic Petri Nets are used to describe\r\nthe workload and the behavior of users and applications, while Cloudsim, a well\r\nknown cloud infrastructure simulator, is adopted for the cloud part. A case study\r\nof a simplified Edge Computing application is presented to demonstrate the effectiveness\r\nof the proposed approach.
AB - Cloud based architectures present many challenges, ranging from poorly dimensioned\r\nhardware to lengthy wait times and resource balancing issues. Most of\r\nthese problems can be mitigated by using proper performance evaluation techniques,\r\ndepending on the accuracy of the model abstracting the real system. The\r\nadoption of a formalism over another to describe the considered infrastructure\r\nplays a crucial role in achieving this goal. In this sense, multiformalism proves\r\nitself to be a powerful modeling approach describing each system component according\r\nto the most suitable representation. This paper presents a novel modeling\r\nmethod oriented to the prediction of cloud architectures performance, suitable for\r\njoining the advantages of high level modeling abstractions and of the detail of\r\na specialized simulator. Generalized Stochastic Petri Nets are used to describe\r\nthe workload and the behavior of users and applications, while Cloudsim, a well\r\nknown cloud infrastructure simulator, is adopted for the cloud part. A case study\r\nof a simplified Edge Computing application is presented to demonstrate the effectiveness\r\nof the proposed approach.
KW - Cloud computing
KW - Cloudsim
KW - Domain Specific Language
KW - Multiformalism modeling
KW - Performance evaluation
KW - Simulation
KW - Cloud computing
KW - Cloudsim
KW - Domain Specific Language
KW - Multiformalism modeling
KW - Performance evaluation
KW - Simulation
UR - https://publicatt.unicatt.it/handle/10807/154419
UR - https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=85054447089&origin=inward
UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85054447089&origin=inward
U2 - 10.1016/j.simpat.2018.09.018
DO - 10.1016/j.simpat.2018.09.018
M3 - Article
SN - 1569-190X
SP - 133
EP - 147
JO - Simulation Modelling Practice and Theory
JF - Simulation Modelling Practice and Theory
IS - 93
ER -