Load balancing vs. distributed rate limiting: An unifying framework for cloud control

Rade Stanojevic, Robert Shorten

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

16 Citations (Scopus)

Abstract

With the expansion of cloud-based services, the question as to how to control usage of such large distributed systems has become increasingly important. Load balancing (LB), and recently proposed distributed rate limiting (DRL) have been used independently to reduce costs and to fairly allocate distributed resources. In this paper we propose a new mechanism for cloud control that unifies the use of LB and DRL: LB is used to minimize the associated costs and DRL makes sure that the resource allocation is fair. From an analytical standpoint, modelling the dynamics of DRL in dynamic workloads (resulting from LB cost-minimization scheme) is a challenging problem. Our theoretical analysis yields a condition that ensures convergence to the desired working regime. Analytical results are then validated empirically through several illustrative simulations. The closed-form nature of our result also allows simple design rules which, together with extremely low computational and communication overhead, makes the presented algorithm practical and easy to deploy.

Original languageEnglish
Title of host publicationProceedings - 2009 IEEE International Conference on Communications, ICC 2009
DOIs
Publication statusPublished - 2009
Externally publishedYes
Event2009 IEEE International Conference on Communications, ICC 2009 - Dresden, Germany
Duration: 14 Jun 200918 Jun 2009

Other

Other2009 IEEE International Conference on Communications, ICC 2009
CountryGermany
CityDresden
Period14/6/0918/6/09

Fingerprint

Resource allocation
Costs
Communication

Keywords

  • CDN
  • Cloud control
  • Load balancing
  • Rate limiting

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Electrical and Electronic Engineering

Cite this

Stanojevic, R., & Shorten, R. (2009). Load balancing vs. distributed rate limiting: An unifying framework for cloud control. In Proceedings - 2009 IEEE International Conference on Communications, ICC 2009 [5199141] https://doi.org/10.1109/ICC.2009.5199141

Load balancing vs. distributed rate limiting : An unifying framework for cloud control. / Stanojevic, Rade; Shorten, Robert.

Proceedings - 2009 IEEE International Conference on Communications, ICC 2009. 2009. 5199141.

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

Stanojevic, R & Shorten, R 2009, Load balancing vs. distributed rate limiting: An unifying framework for cloud control. in Proceedings - 2009 IEEE International Conference on Communications, ICC 2009., 5199141, 2009 IEEE International Conference on Communications, ICC 2009, Dresden, Germany, 14/6/09. https://doi.org/10.1109/ICC.2009.5199141
Stanojevic R, Shorten R. Load balancing vs. distributed rate limiting: An unifying framework for cloud control. In Proceedings - 2009 IEEE International Conference on Communications, ICC 2009. 2009. 5199141 https://doi.org/10.1109/ICC.2009.5199141
Stanojevic, Rade ; Shorten, Robert. / Load balancing vs. distributed rate limiting : An unifying framework for cloud control. Proceedings - 2009 IEEE International Conference on Communications, ICC 2009. 2009.
@inproceedings{b38fae980636484cb06fceb92dfdb55c,
title = "Load balancing vs. distributed rate limiting: An unifying framework for cloud control",
abstract = "With the expansion of cloud-based services, the question as to how to control usage of such large distributed systems has become increasingly important. Load balancing (LB), and recently proposed distributed rate limiting (DRL) have been used independently to reduce costs and to fairly allocate distributed resources. In this paper we propose a new mechanism for cloud control that unifies the use of LB and DRL: LB is used to minimize the associated costs and DRL makes sure that the resource allocation is fair. From an analytical standpoint, modelling the dynamics of DRL in dynamic workloads (resulting from LB cost-minimization scheme) is a challenging problem. Our theoretical analysis yields a condition that ensures convergence to the desired working regime. Analytical results are then validated empirically through several illustrative simulations. The closed-form nature of our result also allows simple design rules which, together with extremely low computational and communication overhead, makes the presented algorithm practical and easy to deploy.",
keywords = "CDN, Cloud control, Load balancing, Rate limiting",
author = "Rade Stanojevic and Robert Shorten",
year = "2009",
doi = "10.1109/ICC.2009.5199141",
language = "English",
isbn = "9781424434350",
booktitle = "Proceedings - 2009 IEEE International Conference on Communications, ICC 2009",

}

TY - GEN

T1 - Load balancing vs. distributed rate limiting

T2 - An unifying framework for cloud control

AU - Stanojevic, Rade

AU - Shorten, Robert

PY - 2009

Y1 - 2009

N2 - With the expansion of cloud-based services, the question as to how to control usage of such large distributed systems has become increasingly important. Load balancing (LB), and recently proposed distributed rate limiting (DRL) have been used independently to reduce costs and to fairly allocate distributed resources. In this paper we propose a new mechanism for cloud control that unifies the use of LB and DRL: LB is used to minimize the associated costs and DRL makes sure that the resource allocation is fair. From an analytical standpoint, modelling the dynamics of DRL in dynamic workloads (resulting from LB cost-minimization scheme) is a challenging problem. Our theoretical analysis yields a condition that ensures convergence to the desired working regime. Analytical results are then validated empirically through several illustrative simulations. The closed-form nature of our result also allows simple design rules which, together with extremely low computational and communication overhead, makes the presented algorithm practical and easy to deploy.

AB - With the expansion of cloud-based services, the question as to how to control usage of such large distributed systems has become increasingly important. Load balancing (LB), and recently proposed distributed rate limiting (DRL) have been used independently to reduce costs and to fairly allocate distributed resources. In this paper we propose a new mechanism for cloud control that unifies the use of LB and DRL: LB is used to minimize the associated costs and DRL makes sure that the resource allocation is fair. From an analytical standpoint, modelling the dynamics of DRL in dynamic workloads (resulting from LB cost-minimization scheme) is a challenging problem. Our theoretical analysis yields a condition that ensures convergence to the desired working regime. Analytical results are then validated empirically through several illustrative simulations. The closed-form nature of our result also allows simple design rules which, together with extremely low computational and communication overhead, makes the presented algorithm practical and easy to deploy.

KW - CDN

KW - Cloud control

KW - Load balancing

KW - Rate limiting

UR - http://www.scopus.com/inward/record.url?scp=70449475583&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70449475583&partnerID=8YFLogxK

U2 - 10.1109/ICC.2009.5199141

DO - 10.1109/ICC.2009.5199141

M3 - Conference contribution

AN - SCOPUS:70449475583

SN - 9781424434350

BT - Proceedings - 2009 IEEE International Conference on Communications, ICC 2009

ER -