SLA-aware load balancing in a web-based cloud system over openstack

Abstract

This paper focuses on the scalability problem in cloud-based systems when changing the computing requirements, this is, when there is a high degree of requesting service variability in cloud-computing environments. We study a specific scenario for web-based application deployed in a cloud system, where the number of requests can change with time. This paper deals with guaranteeing the SLA (Service-Level Agreement) in scalable clouds with web-based load variability. We present an architecture able to balance the load (mainly web-browser applications) between different computing virtual machines. This is accomplished by monitoring the system in order to determine when to create or terminate virtual machines. A novel scheduling policy to manage the requested cloud services based on the presented architecture is also proposed. The good results obtained by implementing the proposed architecture in a real cloud framework prove the applicability of our proposal for guaranteeing SLA. © Springer International Publishing Switzerland 2014.