An auction mechanism for cloud spot markets

Adel Nadjaran Toosi, Kurt Vanmechelen, Farzad Khodadadi, Rajkumar Buyya

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Dynamic forms of resource pricing have recently been introduced by cloud providers that offer Infrastructure as a Service (IaaS) capabilities in order to maximize profits and balance resource supply and demand. The design of a mechanism that efficiently prices perishable cloud resources in line with a provider's profit maximization goal remains an open research challenge, however. In this article, we propose the Online Extended Consensus Revenue Estimate mechanism in the setting of a recurrent, multiunit and single price auction for IaaS cloud resources. The mechanism is envy-free, has a high probability of being truthful, and generates a near optimal profit for the provider. We combine the proposed auction design with a scheme for dynamically calculating reserve prices based on data center Power Usage Effectiveness (PUE) and electricity costs. Our simulation-based evaluation of the mechanism demonstrates its effectiveness under a broad variety of market conditions. In particular, we show how it improves on the classical uniform price auction, and we investigate the value of prior knowledge on the execution time of virtual machines for maximizing profit. We also developed a system prototype and conducted a small-scale experimental study with a group of 10 users that confirms the truthfulness property of the mechanism in a real test environment.

Original languageEnglish
Article number2
Number of pages33
JournalACM Transactions on Autonomous and Adaptive Systems
Volume11
Issue number1
DOIs
Publication statusPublished - 1 Feb 2016
Externally publishedYes

Keywords

  • Auction
  • Cloud computing
  • Mechanism design
  • Multi-unit
  • Online
  • PUE
  • Reserve price

Cite this

Toosi, Adel Nadjaran ; Vanmechelen, Kurt ; Khodadadi, Farzad ; Buyya, Rajkumar. / An auction mechanism for cloud spot markets. In: ACM Transactions on Autonomous and Adaptive Systems. 2016 ; Vol. 11, No. 1.
@article{45246d920e3d4355982c7bb3b03eb577,
title = "An auction mechanism for cloud spot markets",
abstract = "Dynamic forms of resource pricing have recently been introduced by cloud providers that offer Infrastructure as a Service (IaaS) capabilities in order to maximize profits and balance resource supply and demand. The design of a mechanism that efficiently prices perishable cloud resources in line with a provider's profit maximization goal remains an open research challenge, however. In this article, we propose the Online Extended Consensus Revenue Estimate mechanism in the setting of a recurrent, multiunit and single price auction for IaaS cloud resources. The mechanism is envy-free, has a high probability of being truthful, and generates a near optimal profit for the provider. We combine the proposed auction design with a scheme for dynamically calculating reserve prices based on data center Power Usage Effectiveness (PUE) and electricity costs. Our simulation-based evaluation of the mechanism demonstrates its effectiveness under a broad variety of market conditions. In particular, we show how it improves on the classical uniform price auction, and we investigate the value of prior knowledge on the execution time of virtual machines for maximizing profit. We also developed a system prototype and conducted a small-scale experimental study with a group of 10 users that confirms the truthfulness property of the mechanism in a real test environment.",
keywords = "Auction, Cloud computing, Mechanism design, Multi-unit, Online, PUE, Reserve price",
author = "Toosi, {Adel Nadjaran} and Kurt Vanmechelen and Farzad Khodadadi and Rajkumar Buyya",
year = "2016",
month = "2",
day = "1",
doi = "10.1145/2843945",
language = "English",
volume = "11",
journal = "ACM Transactions on Autonomous and Adaptive Systems",
issn = "1556-4665",
publisher = "Association for Computing Machinery (ACM)",
number = "1",

}

An auction mechanism for cloud spot markets. / Toosi, Adel Nadjaran; Vanmechelen, Kurt; Khodadadi, Farzad; Buyya, Rajkumar.

In: ACM Transactions on Autonomous and Adaptive Systems, Vol. 11, No. 1, 2, 01.02.2016.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - An auction mechanism for cloud spot markets

AU - Toosi, Adel Nadjaran

AU - Vanmechelen, Kurt

AU - Khodadadi, Farzad

AU - Buyya, Rajkumar

PY - 2016/2/1

Y1 - 2016/2/1

N2 - Dynamic forms of resource pricing have recently been introduced by cloud providers that offer Infrastructure as a Service (IaaS) capabilities in order to maximize profits and balance resource supply and demand. The design of a mechanism that efficiently prices perishable cloud resources in line with a provider's profit maximization goal remains an open research challenge, however. In this article, we propose the Online Extended Consensus Revenue Estimate mechanism in the setting of a recurrent, multiunit and single price auction for IaaS cloud resources. The mechanism is envy-free, has a high probability of being truthful, and generates a near optimal profit for the provider. We combine the proposed auction design with a scheme for dynamically calculating reserve prices based on data center Power Usage Effectiveness (PUE) and electricity costs. Our simulation-based evaluation of the mechanism demonstrates its effectiveness under a broad variety of market conditions. In particular, we show how it improves on the classical uniform price auction, and we investigate the value of prior knowledge on the execution time of virtual machines for maximizing profit. We also developed a system prototype and conducted a small-scale experimental study with a group of 10 users that confirms the truthfulness property of the mechanism in a real test environment.

AB - Dynamic forms of resource pricing have recently been introduced by cloud providers that offer Infrastructure as a Service (IaaS) capabilities in order to maximize profits and balance resource supply and demand. The design of a mechanism that efficiently prices perishable cloud resources in line with a provider's profit maximization goal remains an open research challenge, however. In this article, we propose the Online Extended Consensus Revenue Estimate mechanism in the setting of a recurrent, multiunit and single price auction for IaaS cloud resources. The mechanism is envy-free, has a high probability of being truthful, and generates a near optimal profit for the provider. We combine the proposed auction design with a scheme for dynamically calculating reserve prices based on data center Power Usage Effectiveness (PUE) and electricity costs. Our simulation-based evaluation of the mechanism demonstrates its effectiveness under a broad variety of market conditions. In particular, we show how it improves on the classical uniform price auction, and we investigate the value of prior knowledge on the execution time of virtual machines for maximizing profit. We also developed a system prototype and conducted a small-scale experimental study with a group of 10 users that confirms the truthfulness property of the mechanism in a real test environment.

KW - Auction

KW - Cloud computing

KW - Mechanism design

KW - Multi-unit

KW - Online

KW - PUE

KW - Reserve price

UR - http://www.scopus.com/inward/record.url?scp=84958255785&partnerID=8YFLogxK

U2 - 10.1145/2843945

DO - 10.1145/2843945

M3 - Article

VL - 11

JO - ACM Transactions on Autonomous and Adaptive Systems

JF - ACM Transactions on Autonomous and Adaptive Systems

SN - 1556-4665

IS - 1

M1 - 2

ER -