Dynamic resource allocation for spot markets in cloud computing environments

Qi Zhang, Quanyan Zhu, Raouf Boutaba

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The advent of cloud computing promises to provide computational resources to customers like public utilities such as water and electricity. To deal with dynamically fluctuating resource demands, market-driven resource allocation has been proposed and recently implemented by public Infrastructure-as-a-Service (IaaS) providers like Amazon EC2. In this environment, cloud resources are offered in distinct types of virtual machines (VMs) and the cloud provider runs an auction-based market for each VM type with the goal of achieving maximum revenue over time. However, as demand for each type of VMs can fluctuate over time, it is necessary to adjust the capacity allocated to each VM type to match the demand in order to maximize total revenue while minimizing the energy cost. In this paper, we consider the case of a single cloud provider and address the question how to best match customer demand in terms of both supply and price in order to maximize the providers revenue and customer satisfactions while minimizing energy cost. In particular, we model this problem as a constrained discrete-time optimal control problem and use Model Predictive Control (MPC) to find its solution. Simulation studies using real cloud workloads indicate that under dynamic workload conditions, our proposed solution achieves higher net income than static allocation strategies and minimizes the average request waiting time.

Original languageEnglish (US)
Title of host publicationProceedings - 2011 4th IEEE International Conference on Utility and Cloud Computing, UCC 2011
Pages178-185
Number of pages8
DOIs
StatePublished - 2011
Event4th IEEE/ACM International Conference on Cloud and Utility Computing, UCC 2011 - Melbourne, VIC, Australia
Duration: Dec 5 2011Dec 8 2011

Other

Other4th IEEE/ACM International Conference on Cloud and Utility Computing, UCC 2011
CountryAustralia
CityMelbourne, VIC
Period12/5/1112/8/11

Fingerprint

Cloud computing
Resource allocation
Public utilities
Customer satisfaction
Model predictive control
Costs
Electricity
Virtual machine
Water

Keywords

  • Cloud Computing
  • Model Predictive Control
  • Resource Management

ASJC Scopus subject areas

  • Software

Cite this

Zhang, Q., Zhu, Q., & Boutaba, R. (2011). Dynamic resource allocation for spot markets in cloud computing environments. In Proceedings - 2011 4th IEEE International Conference on Utility and Cloud Computing, UCC 2011 (pp. 178-185). [6123496] https://doi.org/10.1109/UCC.2011.33

Dynamic resource allocation for spot markets in cloud computing environments. / Zhang, Qi; Zhu, Quanyan; Boutaba, Raouf.

Proceedings - 2011 4th IEEE International Conference on Utility and Cloud Computing, UCC 2011. 2011. p. 178-185 6123496.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zhang, Q, Zhu, Q & Boutaba, R 2011, Dynamic resource allocation for spot markets in cloud computing environments. in Proceedings - 2011 4th IEEE International Conference on Utility and Cloud Computing, UCC 2011., 6123496, pp. 178-185, 4th IEEE/ACM International Conference on Cloud and Utility Computing, UCC 2011, Melbourne, VIC, Australia, 12/5/11. https://doi.org/10.1109/UCC.2011.33
Zhang Q, Zhu Q, Boutaba R. Dynamic resource allocation for spot markets in cloud computing environments. In Proceedings - 2011 4th IEEE International Conference on Utility and Cloud Computing, UCC 2011. 2011. p. 178-185. 6123496 https://doi.org/10.1109/UCC.2011.33
Zhang, Qi ; Zhu, Quanyan ; Boutaba, Raouf. / Dynamic resource allocation for spot markets in cloud computing environments. Proceedings - 2011 4th IEEE International Conference on Utility and Cloud Computing, UCC 2011. 2011. pp. 178-185
@inproceedings{60bf8481c1c04695bc8e5e974b645667,
title = "Dynamic resource allocation for spot markets in cloud computing environments",
abstract = "The advent of cloud computing promises to provide computational resources to customers like public utilities such as water and electricity. To deal with dynamically fluctuating resource demands, market-driven resource allocation has been proposed and recently implemented by public Infrastructure-as-a-Service (IaaS) providers like Amazon EC2. In this environment, cloud resources are offered in distinct types of virtual machines (VMs) and the cloud provider runs an auction-based market for each VM type with the goal of achieving maximum revenue over time. However, as demand for each type of VMs can fluctuate over time, it is necessary to adjust the capacity allocated to each VM type to match the demand in order to maximize total revenue while minimizing the energy cost. In this paper, we consider the case of a single cloud provider and address the question how to best match customer demand in terms of both supply and price in order to maximize the providers revenue and customer satisfactions while minimizing energy cost. In particular, we model this problem as a constrained discrete-time optimal control problem and use Model Predictive Control (MPC) to find its solution. Simulation studies using real cloud workloads indicate that under dynamic workload conditions, our proposed solution achieves higher net income than static allocation strategies and minimizes the average request waiting time.",
keywords = "Cloud Computing, Model Predictive Control, Resource Management",
author = "Qi Zhang and Quanyan Zhu and Raouf Boutaba",
year = "2011",
doi = "10.1109/UCC.2011.33",
language = "English (US)",
isbn = "9780769545929",
pages = "178--185",
booktitle = "Proceedings - 2011 4th IEEE International Conference on Utility and Cloud Computing, UCC 2011",

}

TY - GEN

T1 - Dynamic resource allocation for spot markets in cloud computing environments

AU - Zhang, Qi

AU - Zhu, Quanyan

AU - Boutaba, Raouf

PY - 2011

Y1 - 2011

N2 - The advent of cloud computing promises to provide computational resources to customers like public utilities such as water and electricity. To deal with dynamically fluctuating resource demands, market-driven resource allocation has been proposed and recently implemented by public Infrastructure-as-a-Service (IaaS) providers like Amazon EC2. In this environment, cloud resources are offered in distinct types of virtual machines (VMs) and the cloud provider runs an auction-based market for each VM type with the goal of achieving maximum revenue over time. However, as demand for each type of VMs can fluctuate over time, it is necessary to adjust the capacity allocated to each VM type to match the demand in order to maximize total revenue while minimizing the energy cost. In this paper, we consider the case of a single cloud provider and address the question how to best match customer demand in terms of both supply and price in order to maximize the providers revenue and customer satisfactions while minimizing energy cost. In particular, we model this problem as a constrained discrete-time optimal control problem and use Model Predictive Control (MPC) to find its solution. Simulation studies using real cloud workloads indicate that under dynamic workload conditions, our proposed solution achieves higher net income than static allocation strategies and minimizes the average request waiting time.

AB - The advent of cloud computing promises to provide computational resources to customers like public utilities such as water and electricity. To deal with dynamically fluctuating resource demands, market-driven resource allocation has been proposed and recently implemented by public Infrastructure-as-a-Service (IaaS) providers like Amazon EC2. In this environment, cloud resources are offered in distinct types of virtual machines (VMs) and the cloud provider runs an auction-based market for each VM type with the goal of achieving maximum revenue over time. However, as demand for each type of VMs can fluctuate over time, it is necessary to adjust the capacity allocated to each VM type to match the demand in order to maximize total revenue while minimizing the energy cost. In this paper, we consider the case of a single cloud provider and address the question how to best match customer demand in terms of both supply and price in order to maximize the providers revenue and customer satisfactions while minimizing energy cost. In particular, we model this problem as a constrained discrete-time optimal control problem and use Model Predictive Control (MPC) to find its solution. Simulation studies using real cloud workloads indicate that under dynamic workload conditions, our proposed solution achieves higher net income than static allocation strategies and minimizes the average request waiting time.

KW - Cloud Computing

KW - Model Predictive Control

KW - Resource Management

UR - http://www.scopus.com/inward/record.url?scp=84863064969&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84863064969&partnerID=8YFLogxK

U2 - 10.1109/UCC.2011.33

DO - 10.1109/UCC.2011.33

M3 - Conference contribution

AN - SCOPUS:84863064969

SN - 9780769545929

SP - 178

EP - 185

BT - Proceedings - 2011 4th IEEE International Conference on Utility and Cloud Computing, UCC 2011

ER -