PRESS: PRedictive Elastic ReSource Scaling for cloud systems

Cloud systems require elastic resource allocation to minimize resource provisioning costs while meeting service level objectives (SLOs). In this paper, we present a novel PRedictive Elastic reSource Scaling (PRESS) scheme for cloud systems. PRESS unobtrusively extracts fine-grained dynamic patterns in application resource demands and adjust their resource allocations automatically. Our approach leverages light-weight signal processing and statistical learning algorithms to achieve online predictions of dynamic application resource requirements. We have implemented the PRESS system on Xen and tested it using RUBiS and an application load trace from Google. Our experiments show that our light-weight resource demand prediction schemes can achieve better resource prediction accuracy with both lower over-estimation and under-estimation errors than previous approaches. Our elastic resource scaling can effectively reduce both resource waste and SLO violations.

• Type: Journal
• Year: 2010
• Where: CNSM
• Authors: Zhenhuan Gong, Xiaohui Gu, John Wilkes
• Keywords: CNSM 2010, Computer Networks, Elastic Resource, Resource, Resource Allocations