Transforming reactive auto-scaling into proactive auto-scaling

Abstract

Elasticity is a key characteristic of cloud platforms enabling resource to be acquired on-demand in response to time-varying workloads. We introduce a new elasticity management framework that takes as input commonly used reactive rule-based scaling strategies but offers in return proactive auto-scaling. The elasticity framework combines reactive and predictive auto-scaling techniques, and we discuss the specification and performance of these individual components. We present a case study, based on real datasets, to demonstrate that our framework is capable of making appropriate auto-scaling decisions that can improve resource utilization compared to that obtained from a purely reactive approach.