Simcan2Cloud: a discrete-event-based simulator for modelling and simulating cloud computing infrastructures

Abstract

Cloud computing is an evolving paradigm whose adoption has been increasing over the last few years. This fact has led to the growth of the cloud computing market, together with fierce competition for the leading market share, with an increase in the number of cloud service providers. Novel techniques are continuously being proposed to increase the cloud service provider’s profitability. However, only those techniques that are proven not to hinder the service agreements are considered for production clouds. Analysing the expected behaviour and performance of the cloud infrastructure is challenging, as the repeatability and reproducibility of experiments on these systems are made difficult by the large number of users concurrently accessing the infrastructure. To this, must be added the complications of using different provisioning policies, managing several workloads, and applying different resource configurations. Therefore, in order to alleviate these issues, we present Simcan2Cloud, a discrete-event-based simulator for modelling and simulating cloud computing environments. Simcan2Cloud focuses on modelling and simulating the behaviour of the cloud provider with a high level of detail, where both the cloud infrastructure and the interactions of the users with the cloud are integrated in the simulated scenarios. For this purpose, Simcan2Cloud supports different resource allocation policies, service level agreements (SLAs), and an intuitive and complete API for including new management policies. Finally, a thorough experimental study to measure the suitability and applicability of Simcan2Cloud, using both real-world traces and synthetic workloads, is presented.