Prediction of cost and performance of cloud applications
Rak, Massimiliano
Prediction of cost and performance of cloud applications created by Massimiliano Rak, Antonio Cuomo, Umberto Villano and Giuseppe Aversano - International journal of cloud computing Volume 4 , number 1 , .
The pay-per-use business model is one of the key factors for the success of the cloud computing paradigm: resources are acquired only when needed and charged on the basis of their actual usage. The execution of applications in the cloud implies costs that depend on the usage of the leased resources and on the resource pricing model adopted by the providers. This paper presents a technique to evaluate the tradeoff between costs and performance of cloud applications through the use of benchmarks and simulation. Given a mOSAIC cloud application, it is possible to predict performance indexes and resource consumption under generic workloads. This makes it possible to choose the deployment on the resources of the provider that guarantees the desired performance levels and minimises the costs for executing the application.
2043-9989
Discrete-event simulation--Cloud computing--Performance prediction
QA76.S85 INT
Prediction of cost and performance of cloud applications created by Massimiliano Rak, Antonio Cuomo, Umberto Villano and Giuseppe Aversano - International journal of cloud computing Volume 4 , number 1 , .
The pay-per-use business model is one of the key factors for the success of the cloud computing paradigm: resources are acquired only when needed and charged on the basis of their actual usage. The execution of applications in the cloud implies costs that depend on the usage of the leased resources and on the resource pricing model adopted by the providers. This paper presents a technique to evaluate the tradeoff between costs and performance of cloud applications through the use of benchmarks and simulation. Given a mOSAIC cloud application, it is possible to predict performance indexes and resource consumption under generic workloads. This makes it possible to choose the deployment on the resources of the provider that guarantees the desired performance levels and minimises the costs for executing the application.
2043-9989
Discrete-event simulation--Cloud computing--Performance prediction
QA76.S85 INT