Skip to Main content Skip to Navigation
Journal articles

Distributed learning policies for power allocation in multiple access channels

Abstract : We analyze the power allocation problem for orthogonal multiple access channels by means of a non-cooperative potential game in which each user distributes his power over the channels available to him. When the channels are static, we show that this game possesses a unique equilibrium; moreover, if the network's users follow a distributed learning scheme based on the replicator dynamics of evolutionary game theory, then they converge to equilibrium exponentially fast. On the other hand, if the channels fluctuate stochastically over time, the associated game still admits a unique equilibrium, but the learning process is not deterministic; just the same, by employing the theory of stochastic approximation, we find that users still converge to equilibrium. Our theoretical analysis hinges on a novel result which is of independent interest: in finite-player games which admit a (possibly nonlinear) convex potential, the replicator dynamics converge to an ε-neighborhood of an equilibrium in time O(log(1/ε)).
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-00648840
Contributor : Elena Veronica Belmega <>
Submitted on : Tuesday, December 6, 2011 - 2:55:49 PM
Last modification on : Wednesday, April 8, 2020 - 3:58:35 PM

Identifiers

  • HAL Id : hal-00648840, version 1

Citation

Panayotis Mertikopoulos, Elena Veronica Belmega, Aris Moustakas, Samson Lasaulce. Distributed learning policies for power allocation in multiple access channels. IEEE Journal on Selected Areas in Communications, Institute of Electrical and Electronics Engineers, 2012, 30 (1), pp 1-11. ⟨hal-00648840⟩

Share

Metrics

Record views

1264