DocumentCode :
3063343
Title :
Autonomic Resource Management Handling Delayed Configuration Effects
Author :
Niehoerster, O. ; Brinkmann, André
Author_Institution :
Paderborn Center for Parallel Comput., Univ. Paderborn, Paderborn, Germany
fYear :
2011
fDate :
Nov. 29 2011-Dec. 1 2011
Firstpage :
138
Lastpage :
145
Abstract :
Today, cloud providers offer customers access to complex applications running on virtualized hardware. Nevertheless, big virtualized data centers become stochastic environments with performance fluctuations. The growing number of cloud services makes a manual steering impossible. An automatism on the provider side is needed. In this paper, we present a software solution located in the Software as a Service layer with autonomous agents that handle user requests. The agents allocate resources and configure applications to compensate performance fluctuations. They use a combination of Support Vector Machines and Model-Predictive Control to predict and plan future configurations. This allows them to handle configuration delays for requesting new virtual machines and to guarantee time-dependent service level objectives (SLOs). We evaluated our approach on a real cloud system with a high-performance software and a three-tier e-commerce application. The experiments show that the agents accurately configure the application and plan horizontal scalings to enforce SLO fulfillments even in the presence of noise.
Keywords :
cloud computing; multi-agent systems; predictive control; support vector machines; virtual machines; SLO; autonomic resource management; autonomous agent; cloud service; delayed configuration effect; model-predictive control; software as a service; stochastic environment; support vector machine; time-dependent service level objective; virtual machine; virtualized data center; virtualized hardware; Adaptation models; Delay; Knowledge based systems; Quality of service; Runtime; Support vector machines; Vectors;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Cloud Computing Technology and Science (CloudCom), 2011 IEEE Third International Conference on
Conference_Location :
Athens
Print_ISBN :
978-1-4673-0090-2
Type :
conf
DOI :
10.1109/CloudCom.2011.28
Filename :
6133137
Link To Document :
بازگشت