Dynamic robust power allocation games under channel uncertainty and time delays

Tembine Hamidou, Abdellatif Kobbane, Mohamed El Koutbi

Research output: Contribution to journalArticle

Abstract

In this paper, we study dynamic robust power allocation strategies under the imperfectness of the channel state information at the transmitters. Considering unknown payoff functions at the transmitters, we propose an heterogeneous Delayed COmbined fully DIstributed Payoff and Strategy Reinforcement Learning (Delayed-CODIPAS-RL) in which each transmitter learns its payoff function as well as its associated optimal strategies in the long-term. We show that equilibrium power allocations can be obtained using the multiplicative weighted imitative CODIPAS-RLs and Bush-Mosteller based CODIPAS-RL. We also show almost sure convergence to the set of global optima for specific scenarios.

Original languageEnglish (US)
Pages (from-to)1529-1537
Number of pages9
JournalComputer Communications
Volume34
Issue number12
DOIs
StatePublished - Aug 2 2011

Fingerprint

Transmitters
Time delay
Channel state information
Reinforcement learning
Uncertainty

Keywords

  • Combined learning
  • Heterogeneous learning
  • Power allocation

ASJC Scopus subject areas

  • Computer Networks and Communications

Cite this

Dynamic robust power allocation games under channel uncertainty and time delays. / Hamidou, Tembine; Kobbane, Abdellatif; Koutbi, Mohamed El.

In: Computer Communications, Vol. 34, No. 12, 02.08.2011, p. 1529-1537.

Research output: Contribution to journalArticle

Hamidou, Tembine ; Kobbane, Abdellatif ; Koutbi, Mohamed El. / Dynamic robust power allocation games under channel uncertainty and time delays. In: Computer Communications. 2011 ; Vol. 34, No. 12. pp. 1529-1537.
@article{67cd3555faa94b18aed88da838f97586,
title = "Dynamic robust power allocation games under channel uncertainty and time delays",
abstract = "In this paper, we study dynamic robust power allocation strategies under the imperfectness of the channel state information at the transmitters. Considering unknown payoff functions at the transmitters, we propose an heterogeneous Delayed COmbined fully DIstributed Payoff and Strategy Reinforcement Learning (Delayed-CODIPAS-RL) in which each transmitter learns its payoff function as well as its associated optimal strategies in the long-term. We show that equilibrium power allocations can be obtained using the multiplicative weighted imitative CODIPAS-RLs and Bush-Mosteller based CODIPAS-RL. We also show almost sure convergence to the set of global optima for specific scenarios.",
keywords = "Combined learning, Heterogeneous learning, Power allocation",
author = "Tembine Hamidou and Abdellatif Kobbane and Koutbi, {Mohamed El}",
year = "2011",
month = "8",
day = "2",
doi = "10.1016/j.comcom.2011.02.009",
language = "English (US)",
volume = "34",
pages = "1529--1537",
journal = "Computer Communications",
issn = "0140-3664",
publisher = "Elsevier",
number = "12",

}

TY - JOUR

T1 - Dynamic robust power allocation games under channel uncertainty and time delays

AU - Hamidou, Tembine

AU - Kobbane, Abdellatif

AU - Koutbi, Mohamed El

PY - 2011/8/2

Y1 - 2011/8/2

N2 - In this paper, we study dynamic robust power allocation strategies under the imperfectness of the channel state information at the transmitters. Considering unknown payoff functions at the transmitters, we propose an heterogeneous Delayed COmbined fully DIstributed Payoff and Strategy Reinforcement Learning (Delayed-CODIPAS-RL) in which each transmitter learns its payoff function as well as its associated optimal strategies in the long-term. We show that equilibrium power allocations can be obtained using the multiplicative weighted imitative CODIPAS-RLs and Bush-Mosteller based CODIPAS-RL. We also show almost sure convergence to the set of global optima for specific scenarios.

AB - In this paper, we study dynamic robust power allocation strategies under the imperfectness of the channel state information at the transmitters. Considering unknown payoff functions at the transmitters, we propose an heterogeneous Delayed COmbined fully DIstributed Payoff and Strategy Reinforcement Learning (Delayed-CODIPAS-RL) in which each transmitter learns its payoff function as well as its associated optimal strategies in the long-term. We show that equilibrium power allocations can be obtained using the multiplicative weighted imitative CODIPAS-RLs and Bush-Mosteller based CODIPAS-RL. We also show almost sure convergence to the set of global optima for specific scenarios.

KW - Combined learning

KW - Heterogeneous learning

KW - Power allocation

UR - http://www.scopus.com/inward/record.url?scp=79959380843&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79959380843&partnerID=8YFLogxK

U2 - 10.1016/j.comcom.2011.02.009

DO - 10.1016/j.comcom.2011.02.009

M3 - Article

VL - 34

SP - 1529

EP - 1537

JO - Computer Communications

JF - Computer Communications

SN - 0140-3664

IS - 12

ER -