Brokering algorithms for optimizing the availability and cost of cloud storage services

Yaser Mansouri, Adel Nadjaran Toosi, Rajkumar Buyya

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

Abstract

In recent years, cloud storage providers have gained popularity for personal and organizational data, and provided highly reliable, scalable and flexible resources to cloud users. Although cloud providers bring advantages to their users, most cloud providers suffer outages from time-to-time. Therefore, relying on a single cloud storage services threatens service availability of cloud users. We believe that using multi-cloud broker is a plausible solution to remove single point of failure and to achieve very high availability. Since highly reliable cloud storage services impose enormous cost to the user, and also as the size of data objects in the cloud storage reaches magnitude of exabyte, optimal selection among a set of cloud storage providers is a crucial decision for users. To solve this problem, we propose an algorithm that determines the minimum replication cost of objects such that the expected availability for users is guaranteed. We also propose an algorithm to optimally select data centers for striped objects such that the expected availability under a given budget is maximized. Simulation experiments are conducted to evaluate our algorithms, using failure probability and storage cost taken from real cloud storage providers.

Original languageEnglish
Title of host publicationProceedings - IEEE Fifth International Conference on Cloud Computing Technology and Science
Subtitle of host publication2–5 December 2013 Bristol, United Kingdom
EditorsChing-Hsien (Robert) Hsu, Siani Pearson
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages581-589
Number of pages9
Volume1
ISBN (Print)9780768550954
DOIs
Publication statusPublished - 1 Jan 2013
Externally publishedYes
EventIEEE International Conference on Cloud Computing Technology and Science 2013 - Bristol, United Kingdom
Duration: 2 Dec 20135 Dec 2013
Conference number: 5th

Conference

ConferenceIEEE International Conference on Cloud Computing Technology and Science 2013
Abbreviated titleCloudCom 2013
CountryUnited Kingdom
CityBristol
Period2/12/135/12/13

Keywords

  • Availability
  • Broker
  • Cloud Computing
  • Cloud Storage
  • Cost minimization
  • Data replication
  • Data striping
  • Dynamic Programming

Cite this

Mansouri, Y., Toosi, A. N., & Buyya, R. (2013). Brokering algorithms for optimizing the availability and cost of cloud storage services. In C-H. R. Hsu, & S. Pearson (Eds.), Proceedings - IEEE Fifth International Conference on Cloud Computing Technology and Science: 2–5 December 2013 Bristol, United Kingdom (Vol. 1, pp. 581-589). Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/CloudCom.2013.83
Mansouri, Yaser ; Toosi, Adel Nadjaran ; Buyya, Rajkumar. / Brokering algorithms for optimizing the availability and cost of cloud storage services. Proceedings - IEEE Fifth International Conference on Cloud Computing Technology and Science: 2–5 December 2013 Bristol, United Kingdom. editor / Ching-Hsien (Robert) Hsu ; Siani Pearson. Vol. 1 Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2013. pp. 581-589
@inproceedings{2f572584271b491aa2e759a7da6c4a4b,
title = "Brokering algorithms for optimizing the availability and cost of cloud storage services",
abstract = "In recent years, cloud storage providers have gained popularity for personal and organizational data, and provided highly reliable, scalable and flexible resources to cloud users. Although cloud providers bring advantages to their users, most cloud providers suffer outages from time-to-time. Therefore, relying on a single cloud storage services threatens service availability of cloud users. We believe that using multi-cloud broker is a plausible solution to remove single point of failure and to achieve very high availability. Since highly reliable cloud storage services impose enormous cost to the user, and also as the size of data objects in the cloud storage reaches magnitude of exabyte, optimal selection among a set of cloud storage providers is a crucial decision for users. To solve this problem, we propose an algorithm that determines the minimum replication cost of objects such that the expected availability for users is guaranteed. We also propose an algorithm to optimally select data centers for striped objects such that the expected availability under a given budget is maximized. Simulation experiments are conducted to evaluate our algorithms, using failure probability and storage cost taken from real cloud storage providers.",
keywords = "Availability, Broker, Cloud Computing, Cloud Storage, Cost minimization, Data replication, Data striping, Dynamic Programming",
author = "Yaser Mansouri and Toosi, {Adel Nadjaran} and Rajkumar Buyya",
year = "2013",
month = "1",
day = "1",
doi = "10.1109/CloudCom.2013.83",
language = "English",
isbn = "9780768550954",
volume = "1",
pages = "581--589",
editor = "Hsu, {Ching-Hsien (Robert)} and Siani Pearson",
booktitle = "Proceedings - IEEE Fifth International Conference on Cloud Computing Technology and Science",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States of America",

}

Mansouri, Y, Toosi, AN & Buyya, R 2013, Brokering algorithms for optimizing the availability and cost of cloud storage services. in C-HR Hsu & S Pearson (eds), Proceedings - IEEE Fifth International Conference on Cloud Computing Technology and Science: 2–5 December 2013 Bristol, United Kingdom. vol. 1, IEEE, Institute of Electrical and Electronics Engineers, Piscataway NJ USA, pp. 581-589, IEEE International Conference on Cloud Computing Technology and Science 2013, Bristol, United Kingdom, 2/12/13. https://doi.org/10.1109/CloudCom.2013.83

Brokering algorithms for optimizing the availability and cost of cloud storage services. / Mansouri, Yaser; Toosi, Adel Nadjaran; Buyya, Rajkumar.

Proceedings - IEEE Fifth International Conference on Cloud Computing Technology and Science: 2–5 December 2013 Bristol, United Kingdom. ed. / Ching-Hsien (Robert) Hsu; Siani Pearson. Vol. 1 Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2013. p. 581-589.

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

TY - GEN

T1 - Brokering algorithms for optimizing the availability and cost of cloud storage services

AU - Mansouri, Yaser

AU - Toosi, Adel Nadjaran

AU - Buyya, Rajkumar

PY - 2013/1/1

Y1 - 2013/1/1

N2 - In recent years, cloud storage providers have gained popularity for personal and organizational data, and provided highly reliable, scalable and flexible resources to cloud users. Although cloud providers bring advantages to their users, most cloud providers suffer outages from time-to-time. Therefore, relying on a single cloud storage services threatens service availability of cloud users. We believe that using multi-cloud broker is a plausible solution to remove single point of failure and to achieve very high availability. Since highly reliable cloud storage services impose enormous cost to the user, and also as the size of data objects in the cloud storage reaches magnitude of exabyte, optimal selection among a set of cloud storage providers is a crucial decision for users. To solve this problem, we propose an algorithm that determines the minimum replication cost of objects such that the expected availability for users is guaranteed. We also propose an algorithm to optimally select data centers for striped objects such that the expected availability under a given budget is maximized. Simulation experiments are conducted to evaluate our algorithms, using failure probability and storage cost taken from real cloud storage providers.

AB - In recent years, cloud storage providers have gained popularity for personal and organizational data, and provided highly reliable, scalable and flexible resources to cloud users. Although cloud providers bring advantages to their users, most cloud providers suffer outages from time-to-time. Therefore, relying on a single cloud storage services threatens service availability of cloud users. We believe that using multi-cloud broker is a plausible solution to remove single point of failure and to achieve very high availability. Since highly reliable cloud storage services impose enormous cost to the user, and also as the size of data objects in the cloud storage reaches magnitude of exabyte, optimal selection among a set of cloud storage providers is a crucial decision for users. To solve this problem, we propose an algorithm that determines the minimum replication cost of objects such that the expected availability for users is guaranteed. We also propose an algorithm to optimally select data centers for striped objects such that the expected availability under a given budget is maximized. Simulation experiments are conducted to evaluate our algorithms, using failure probability and storage cost taken from real cloud storage providers.

KW - Availability

KW - Broker

KW - Cloud Computing

KW - Cloud Storage

KW - Cost minimization

KW - Data replication

KW - Data striping

KW - Dynamic Programming

UR - http://www.scopus.com/inward/record.url?scp=84899726381&partnerID=8YFLogxK

U2 - 10.1109/CloudCom.2013.83

DO - 10.1109/CloudCom.2013.83

M3 - Conference Paper

SN - 9780768550954

VL - 1

SP - 581

EP - 589

BT - Proceedings - IEEE Fifth International Conference on Cloud Computing Technology and Science

A2 - Hsu, Ching-Hsien (Robert)

A2 - Pearson, Siani

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Piscataway NJ USA

ER -

Mansouri Y, Toosi AN, Buyya R. Brokering algorithms for optimizing the availability and cost of cloud storage services. In Hsu C-HR, Pearson S, editors, Proceedings - IEEE Fifth International Conference on Cloud Computing Technology and Science: 2–5 December 2013 Bristol, United Kingdom. Vol. 1. Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. 2013. p. 581-589 https://doi.org/10.1109/CloudCom.2013.83