Title :
Cloud Resource Auto-scaling System Based on Hidden Markov Model (HMM)
Author :
Nikravesh, Ali Yadavar ; Ajila, S.A. ; Lung, Chung-Horng
Author_Institution :
Dept. of Syst. & Comput. Eng., Carleton Univ., Ottawa, ON, Canada
Abstract :
The elasticity characteristic of cloud computing enables clients to acquire and release resources on demand. This characteristic reduces clients´ cost by making them pay for the resources they actually have used. On the other hand, clients are obligated to maintain Service Level Agreement (SLA) with their users. One approach to deal with this cost-performance trade-off is employing an auto-scaling system which automatically adjusts application´s resources based on its load. In this paper we have proposed an auto-scaling system based on Hidden Markov Model (HMM). We have conducted an experiment on Amazon EC2 infrastructure to evaluate our model. Our results show HMM can generate correct scaling actions in 97% of time. CPU utilization, throughput, and response time are being considered as performance metrics in our experiment.
Keywords :
cloud computing; hidden Markov models; resource allocation; Amazon EC2 infrastructure; CPU utilization metric; HMM; SLA; auto-scaling system; cloud computing elasticity characteristic; cloud resource auto-scaling system; hidden Markov model; response time metric; scaling actions; service level agreement; throughput metric; Accuracy; Cloud computing; Computational modeling; Databases; Hidden Markov models; Learning (artificial intelligence); Measurement; Cloud computing; Hidden Markov model; proactive auto-scaling; resource provisioning;
Conference_Titel :
Semantic Computing (ICSC), 2014 IEEE International Conference on
Conference_Location :
Newport Beach, CA
Print_ISBN :
978-1-4799-4002-8
DOI :
10.1109/ICSC.2014.43
