Distributed stochastic learning for continuous power control in wireless networks

Ahmed Farhan Hanif; Hamidou Tembine; Mohamad Assaad; Djamal Zeghlache

doi:10.1109/SPAWC.2012.6292887

Distributed stochastic learning for continuous power control in wireless networks

Ahmed Farhan Hanif, Hamidou Tembine, Mohamad Assaad, Djamal Zeghlache

Electrical Engineering

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

Abstract

In this paper, we develop a distributed stochastic learning framework for seeking Nash equilibria under state dependent payoff functions. Most of the existing works assumes that a closed form expression of the reward is available at the nodes. We consider here a realistic assumption that the nodes have only a numerical realization of the reward at each time and develop a discrete time stochastic learning using sinus perturbation. We examine the convergence of our discrete time algorithm to a limiting trajectory defined by an Ordinary Differential Equation (ODE). Finally, we conduct a stability analysis and apply the proposed scheme in a generic power control problem in wireless networks.

Original language	English (US)
Title of host publication	2012 IEEE 13th International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2012
Pages	199-203
Number of pages	5
DOIs	https://doi.org/10.1109/SPAWC.2012.6292887
State	Published - 2012
Event	2012 IEEE 13th International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2012 - Cesme, Turkey Duration: Jun 17 2012 → Jun 20 2012

Publication series

Name	IEEE Workshop on Signal Processing Advances in Wireless Communications, SPAWC

Other

Other	2012 IEEE 13th International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2012
Country/Territory	Turkey
City	Cesme
Period	6/17/12 → 6/20/12

ASJC Scopus subject areas

Electrical and Electronic Engineering
Computer Science Applications
Information Systems

Access to Document

10.1109/SPAWC.2012.6292887

Cite this

Hanif, A. F., Tembine, H., Assaad, M., & Zeghlache, D. (2012). Distributed stochastic learning for continuous power control in wireless networks. In 2012 IEEE 13th International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2012 (pp. 199-203). Article 6292887 (IEEE Workshop on Signal Processing Advances in Wireless Communications, SPAWC). https://doi.org/10.1109/SPAWC.2012.6292887

Distributed stochastic learning for continuous power control in wireless networks. / Hanif, Ahmed Farhan; Tembine, Hamidou; Assaad, Mohamad et al.
2012 IEEE 13th International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2012. 2012. p. 199-203 6292887 (IEEE Workshop on Signal Processing Advances in Wireless Communications, SPAWC).

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

Hanif, AF, Tembine, H, Assaad, M & Zeghlache, D 2012, Distributed stochastic learning for continuous power control in wireless networks. in 2012 IEEE 13th International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2012., 6292887, IEEE Workshop on Signal Processing Advances in Wireless Communications, SPAWC, pp. 199-203, 2012 IEEE 13th International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2012, Cesme, Turkey, 6/17/12. https://doi.org/10.1109/SPAWC.2012.6292887

Hanif AF, Tembine H, Assaad M, Zeghlache D. Distributed stochastic learning for continuous power control in wireless networks. In 2012 IEEE 13th International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2012. 2012. p. 199-203. 6292887. (IEEE Workshop on Signal Processing Advances in Wireless Communications, SPAWC). doi: 10.1109/SPAWC.2012.6292887

@inproceedings{6e4d240b07ba4f44ad7e76cd7ed20850,

title = "Distributed stochastic learning for continuous power control in wireless networks",

abstract = "In this paper, we develop a distributed stochastic learning framework for seeking Nash equilibria under state dependent payoff functions. Most of the existing works assumes that a closed form expression of the reward is available at the nodes. We consider here a realistic assumption that the nodes have only a numerical realization of the reward at each time and develop a discrete time stochastic learning using sinus perturbation. We examine the convergence of our discrete time algorithm to a limiting trajectory defined by an Ordinary Differential Equation (ODE). Finally, we conduct a stability analysis and apply the proposed scheme in a generic power control problem in wireless networks.",

author = "Hanif, {Ahmed Farhan} and Hamidou Tembine and Mohamad Assaad and Djamal Zeghlache",

year = "2012",

doi = "10.1109/SPAWC.2012.6292887",

language = "English (US)",

isbn = "9781467309714",

series = "IEEE Workshop on Signal Processing Advances in Wireless Communications, SPAWC",

pages = "199--203",

booktitle = "2012 IEEE 13th International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2012",

note = "2012 IEEE 13th International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2012 ; Conference date: 17-06-2012 Through 20-06-2012",

}

TY - GEN

T1 - Distributed stochastic learning for continuous power control in wireless networks

AU - Hanif, Ahmed Farhan

AU - Tembine, Hamidou

AU - Assaad, Mohamad

AU - Zeghlache, Djamal

PY - 2012

Y1 - 2012

N2 - In this paper, we develop a distributed stochastic learning framework for seeking Nash equilibria under state dependent payoff functions. Most of the existing works assumes that a closed form expression of the reward is available at the nodes. We consider here a realistic assumption that the nodes have only a numerical realization of the reward at each time and develop a discrete time stochastic learning using sinus perturbation. We examine the convergence of our discrete time algorithm to a limiting trajectory defined by an Ordinary Differential Equation (ODE). Finally, we conduct a stability analysis and apply the proposed scheme in a generic power control problem in wireless networks.

AB - In this paper, we develop a distributed stochastic learning framework for seeking Nash equilibria under state dependent payoff functions. Most of the existing works assumes that a closed form expression of the reward is available at the nodes. We consider here a realistic assumption that the nodes have only a numerical realization of the reward at each time and develop a discrete time stochastic learning using sinus perturbation. We examine the convergence of our discrete time algorithm to a limiting trajectory defined by an Ordinary Differential Equation (ODE). Finally, we conduct a stability analysis and apply the proposed scheme in a generic power control problem in wireless networks.

UR - http://www.scopus.com/inward/record.url?scp=84868031227&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84868031227&partnerID=8YFLogxK

U2 - 10.1109/SPAWC.2012.6292887

DO - 10.1109/SPAWC.2012.6292887

M3 - Conference contribution

AN - SCOPUS:84868031227

SN - 9781467309714

T3 - IEEE Workshop on Signal Processing Advances in Wireless Communications, SPAWC

SP - 199

EP - 203

BT - 2012 IEEE 13th International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2012

T2 - 2012 IEEE 13th International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2012

Y2 - 17 June 2012 through 20 June 2012

ER -

Distributed stochastic learning for continuous power control in wireless networks

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this