Abstract
With the increased usage of cloud computing in production environments, both for scientific workflows and industrial applications, the focus of application providers shifts towards service cost optimisation. One of the ways to achieve minimised service execution cost is to optimise the placement of the service in the resource pool of the cloud data centres. An increasing number of research approaches is focusing on using machine learning algorithms to deal with dynamic cloud workloads by allocating resources to services in an adaptive way. Many of such solutions are intended for cloud infrastructure providers and deal only with specific types of cloud services. In this paper, we present a model-based approach aimed at the providers of applications hosted in the cloud, which is applicable in early phases of the service lifecycle and can be used for any cloud application service. Using several machine learning methods, we create models to predict cloud service cost and response times of two cloud applications. We also explore how to extract knowledge about the effect that the cloud application context has on both service cost and quality of service so that the gained knowledge can be used in the service placement decision process. The experimental results demonstrate the ability of providing relevant information about the impact of cloud application context parameters on service cost and quality of service. The results also indicate the relevance of our approach for applications in preproduction phase since application providers can gain useful insights regarding service placement decision without acquiring extensive training datasets.
Highlights
In recent years, a significant number of application service providers migrated their workloads to cloud environments [1], offering their services to customers as software as a service (SaaS) solutions
In this work, we are aiming for an approach that would allow cloud application providers to decide on the best cloud service placement option based on application load, resource utilisation, and other cloud application context parameters in order to minimise service execution cost and maintain an appropriate quality of service (QoS) level
We present the prediction error of the response time model for the medical record system (MRS) service implemented using the Multivariate Adaptive Regression Splines (MARS) method in Figure 15. e Artificial Neural Network (ANN) cost models of both use cases have somewhat lower model accuracy, compared to the QoS models, which can be explained by the different prices and pricing models offered by cloud infrastructure providers that affect service execution cost
Summary
A significant number of application service providers migrated their workloads to cloud environments [1], offering their services to customers as software as a service (SaaS) solutions. An approach that can reduce resource waste and cloud service cost should determine the optimised service placement in a cloud environment, both in terms of infrastructure provider selection and instance right-sizing. Finding such service placement can be a complicated task for a SaaS provider, due to a large number of cloud infrastructure providers and pricing models on the market [5], as well as the potential complexity of the service. E experimental results demonstrate that it is feasible to use machine learning models and techniques to detect which parameters affect the service execution cost and quality of service, as well as to predict them Such knowledge can be used by the providers of applications hosted in cloud environments in the decision process of determining optimised cloud service placement to reduce the service cost.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
