Distributed stochastic learning for continuous power control in wireless networks

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

Research output: Chapter in Book/Report/Conference proceedingConference 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 languageEnglish (US)
Title of host publication2012 IEEE 13th International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2012
Pages199-203
Number of pages5
DOIs
StatePublished - 2012
Event2012 IEEE 13th International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2012 - Cesme, Turkey
Duration: Jun 17 2012Jun 20 2012

Publication series

NameIEEE Workshop on Signal Processing Advances in Wireless Communications, SPAWC

Other

Other2012 IEEE 13th International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2012
CountryTurkey
CityCesme
Period6/17/126/20/12

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Science Applications
  • Information Systems

Fingerprint Dive into the research topics of 'Distributed stochastic learning for continuous power control in wireless networks'. Together they form a unique fingerprint.

Cite this