Cloud Application Resource Mapping and Scaling Based on Monitoring of QoS Constraints

Abstract—Infrastructure as a Service (IaaS) clouds promise unlimited raw computing resources on-demand. However, the performance and granularity of these resources can vary widely between providers. Cloud computing users, such as Web de-velopers, can benefit from a service which automatically maps performance non-functional requirements to these resources. We propose a SOA API, in which users provide a cloud application model and get back possible resource allocations in an IaaS provider. The solution emphasizes the assurance of quality of service (QoS) metrics embedded in the application model. An initial mapping is done based on heuristics, and then the application performance is monitored to provide scaling sugges-tions. Underneath the API, the solution is designed to accept different resource usage prediction models and can map QoS constraints to resources from various IaaS providers. To validate our approach, we report on a regression-based prediction model that produces mappings for a CPU-bound cloud application running on Amazon EC2 resources with an average relative error of 17.49%. Index Terms—cloud computing; QoS; resource allocation