Performance Modelling and Verification of Cloud-based Auto-Scaling Policies

Alexandros Evangelidis; David Parker; Rami Bahsoon

doi:10.1109/CCGRID.2017.39

Performance Modelling and Verification of Cloud-based Auto-Scaling Policies

Alexandros Evangelidis, David Parker, Rami Bahsoon

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

10 Citations (Scopus)

386 Downloads (Pure)

Abstract

Auto-scaling, a key property of cloud computing, allows application owners to acquire and release resources on demand. However, the shared environment, along with the exponentially large configuration space of available parameters, makes configuration of auto-scaling policies a challenging task. In particular, it is difficult to quantify, a priori, the impact of a policy on Quality of Service (QoS) provision. To address this problem, we propose a novel approach based on performance modelling and formal verification to produce performance guarantees on particular rule-based auto-scaling policies. We demonstrate the usefulness and efficiency of our model through a detailed validation process on the Amazon EC2 cloud, using two types of load patterns. Our experimental results show that it can be very effective in helping a cloud application owner configure an
auto-scaling policy in order to minimise the QoS violations.

Original language	English
Title of host publication	Proceedings of 2017 IEEE/ACM 17th International Symposium on Cluster, Cloud and Grid Computing (CCGrid'17)
Publisher	IEEE Xplore
Pages	355-364
ISBN (Electronic)	978-1-5090-6611-7
ISBN (Print)	978-1-5090-6610-0
DOIs	https://doi.org/10.1109/CCGRID.2017.39
Publication status	Published - 13 Jul 2017
Event	IEEE/ACM 17th International Symposium on Cluster, Cloud and Grid Computing - Madrid, Spain Duration: 14 May 2017 → 17 May 2017 https://www.arcos.inf.uc3m.es/wp/ccgrid2017/

Conference

Conference	IEEE/ACM 17th International Symposium on Cluster, Cloud and Grid Computing
Abbreviated title	CCGrid 17
Country/Territory	Spain
City	Madrid
Period	14/05/17 → 17/05/17
Internet address	https://www.arcos.inf.uc3m.es/wp/ccgrid2017/

Keywords

cloud computing
probabilistic logic
computational modeling
quality of service
measurement
model checking
Markov processes

Access to Document

10.1109/CCGRID.2017.39

Evangelidis_et_al_Performance_modelling_and_verification_CCGrid_17_2017
(c) 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works
Accepted author manuscript, 828 KBLicence: None: All rights reserved

http://ieeexplore.ieee.org/document/7973721/Licence: None: All rights reserved

Cite this

@inproceedings{1e37fd4cabd84acbad886b49c4adbaed,

title = "Performance Modelling and Verification of Cloud-based Auto-Scaling Policies",

abstract = "Auto-scaling, a key property of cloud computing, allows application owners to acquire and release resources on demand. However, the shared environment, along with the exponentially large configuration space of available parameters, makes configuration of auto-scaling policies a challenging task. In particular, it is difficult to quantify, a priori, the impact of a policy on Quality of Service (QoS) provision. To address this problem, we propose a novel approach based on performance modelling and formal verification to produce performance guarantees on particular rule-based auto-scaling policies. We demonstrate the usefulness and efficiency of our model through a detailed validation process on the Amazon EC2 cloud, using two types of load patterns. Our experimental results show that it can be very effective in helping a cloud application owner configure anauto-scaling policy in order to minimise the QoS violations.",

keywords = "cloud computing , probabilistic logic , computational modeling , quality of service , measurement , model checking , Markov processes",

author = "Alexandros Evangelidis and David Parker and Rami Bahsoon",

year = "2017",

month = jul,

day = "13",

doi = "10.1109/CCGRID.2017.39",

language = "English",

isbn = "978-1-5090-6610-0",

pages = "355--364",

booktitle = "Proceedings of 2017 IEEE/ACM 17th International Symposium on Cluster, Cloud and Grid Computing (CCGrid'17)",

publisher = "IEEE Xplore",

note = "IEEE/ACM 17th International Symposium on Cluster, Cloud and Grid Computing, CCGrid 17 ; Conference date: 14-05-2017 Through 17-05-2017",

url = "https://www.arcos.inf.uc3m.es/wp/ccgrid2017/",

}

Evangelidis, A, Parker, D & Bahsoon, R 2017, Performance Modelling and Verification of Cloud-based Auto-Scaling Policies. in Proceedings of 2017 IEEE/ACM 17th International Symposium on Cluster, Cloud and Grid Computing (CCGrid'17). IEEE Xplore, pp. 355-364, IEEE/ACM 17th International Symposium on Cluster, Cloud and Grid Computing, Madrid, Spain, 14/05/17. https://doi.org/10.1109/CCGRID.2017.39

TY - GEN

T1 - Performance Modelling and Verification of Cloud-based Auto-Scaling Policies

AU - Evangelidis, Alexandros

AU - Parker, David

AU - Bahsoon, Rami

PY - 2017/7/13

Y1 - 2017/7/13

N2 - Auto-scaling, a key property of cloud computing, allows application owners to acquire and release resources on demand. However, the shared environment, along with the exponentially large configuration space of available parameters, makes configuration of auto-scaling policies a challenging task. In particular, it is difficult to quantify, a priori, the impact of a policy on Quality of Service (QoS) provision. To address this problem, we propose a novel approach based on performance modelling and formal verification to produce performance guarantees on particular rule-based auto-scaling policies. We demonstrate the usefulness and efficiency of our model through a detailed validation process on the Amazon EC2 cloud, using two types of load patterns. Our experimental results show that it can be very effective in helping a cloud application owner configure anauto-scaling policy in order to minimise the QoS violations.

AB - Auto-scaling, a key property of cloud computing, allows application owners to acquire and release resources on demand. However, the shared environment, along with the exponentially large configuration space of available parameters, makes configuration of auto-scaling policies a challenging task. In particular, it is difficult to quantify, a priori, the impact of a policy on Quality of Service (QoS) provision. To address this problem, we propose a novel approach based on performance modelling and formal verification to produce performance guarantees on particular rule-based auto-scaling policies. We demonstrate the usefulness and efficiency of our model through a detailed validation process on the Amazon EC2 cloud, using two types of load patterns. Our experimental results show that it can be very effective in helping a cloud application owner configure anauto-scaling policy in order to minimise the QoS violations.

KW - cloud computing

KW - probabilistic logic

KW - computational modeling

KW - quality of service

KW - measurement

KW - model checking

KW - Markov processes

U2 - 10.1109/CCGRID.2017.39

DO - 10.1109/CCGRID.2017.39

M3 - Conference contribution

SN - 978-1-5090-6610-0

SP - 355

EP - 364

BT - Proceedings of 2017 IEEE/ACM 17th International Symposium on Cluster, Cloud and Grid Computing (CCGrid'17)

PB - IEEE Xplore

T2 - IEEE/ACM 17th International Symposium on Cluster, Cloud and Grid Computing

Y2 - 14 May 2017 through 17 May 2017

ER -

Performance Modelling and Verification of Cloud-based Auto-Scaling Policies

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this