Robust power allocation games under channel uncertainty and time delays

Tembine Hamidou, Abdellatif Kobbane, Mohammed El Koutbi

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

Abstract

In this paper, we focus on robust power allocation strategies, against the imperfectness of the channel state information at the transmitters in discrete power allocation games. Considering imperfectness in term of payoff measurement and time delays at the transmitters, we propose a 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. Under the Delayed-CODIPAS-RL, the transmitter can use different learning patterns (heterogeneous learning) and different learning rates. Exploiting the specific structure of the power allocation game under channel uncertainty, a global convergence of the ordinary differential equation to one the equilibrium is obtained for small time delays and for almost all initial conditions.

Original languageEnglish (US)
Title of host publication2010 IFIP Wireless Days, WD 2010
DOIs
StatePublished - Dec 1 2010
Event2010 IFIP Wireless Days, WD 2010 - Venice, Italy
Duration: Oct 20 2010Oct 22 2010

Other

Other2010 IFIP Wireless Days, WD 2010
CountryItaly
CityVenice
Period10/20/1010/22/10

Fingerprint

Transmitters
Time delay
Channel state information
Reinforcement learning
Ordinary differential equations
Uncertainty

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Electrical and Electronic Engineering

Cite this

Hamidou, T., Kobbane, A., & El Koutbi, M. (2010). Robust power allocation games under channel uncertainty and time delays. In 2010 IFIP Wireless Days, WD 2010 [5657740] https://doi.org/10.1109/WD.2010.5657740

Robust power allocation games under channel uncertainty and time delays. / Hamidou, Tembine; Kobbane, Abdellatif; El Koutbi, Mohammed.

2010 IFIP Wireless Days, WD 2010. 2010. 5657740.

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

Hamidou, T, Kobbane, A & El Koutbi, M 2010, Robust power allocation games under channel uncertainty and time delays. in 2010 IFIP Wireless Days, WD 2010., 5657740, 2010 IFIP Wireless Days, WD 2010, Venice, Italy, 10/20/10. https://doi.org/10.1109/WD.2010.5657740
Hamidou, Tembine ; Kobbane, Abdellatif ; El Koutbi, Mohammed. / Robust power allocation games under channel uncertainty and time delays. 2010 IFIP Wireless Days, WD 2010. 2010.
@inproceedings{d1a22ba4441749339b0f1b07a1893fe2,
title = "Robust power allocation games under channel uncertainty and time delays",
abstract = "In this paper, we focus on robust power allocation strategies, against the imperfectness of the channel state information at the transmitters in discrete power allocation games. Considering imperfectness in term of payoff measurement and time delays at the transmitters, we propose a 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. Under the Delayed-CODIPAS-RL, the transmitter can use different learning patterns (heterogeneous learning) and different learning rates. Exploiting the specific structure of the power allocation game under channel uncertainty, a global convergence of the ordinary differential equation to one the equilibrium is obtained for small time delays and for almost all initial conditions.",
author = "Tembine Hamidou and Abdellatif Kobbane and {El Koutbi}, Mohammed",
year = "2010",
month = "12",
day = "1",
doi = "10.1109/WD.2010.5657740",
language = "English (US)",
isbn = "9781424492299",
booktitle = "2010 IFIP Wireless Days, WD 2010",

}

TY - GEN

T1 - Robust power allocation games under channel uncertainty and time delays

AU - Hamidou, Tembine

AU - Kobbane, Abdellatif

AU - El Koutbi, Mohammed

PY - 2010/12/1

Y1 - 2010/12/1

N2 - In this paper, we focus on robust power allocation strategies, against the imperfectness of the channel state information at the transmitters in discrete power allocation games. Considering imperfectness in term of payoff measurement and time delays at the transmitters, we propose a 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. Under the Delayed-CODIPAS-RL, the transmitter can use different learning patterns (heterogeneous learning) and different learning rates. Exploiting the specific structure of the power allocation game under channel uncertainty, a global convergence of the ordinary differential equation to one the equilibrium is obtained for small time delays and for almost all initial conditions.

AB - In this paper, we focus on robust power allocation strategies, against the imperfectness of the channel state information at the transmitters in discrete power allocation games. Considering imperfectness in term of payoff measurement and time delays at the transmitters, we propose a 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. Under the Delayed-CODIPAS-RL, the transmitter can use different learning patterns (heterogeneous learning) and different learning rates. Exploiting the specific structure of the power allocation game under channel uncertainty, a global convergence of the ordinary differential equation to one the equilibrium is obtained for small time delays and for almost all initial conditions.

UR - http://www.scopus.com/inward/record.url?scp=78751549432&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78751549432&partnerID=8YFLogxK

U2 - 10.1109/WD.2010.5657740

DO - 10.1109/WD.2010.5657740

M3 - Conference contribution

SN - 9781424492299

BT - 2010 IFIP Wireless Days, WD 2010

ER -