Team Deep Mixture of Experts for Distributed Power Control

TL;DR

This paper introduces a Team Deep Mixture of Experts model for distributed power control in wireless networks, enabling robust, universal policies that adapt to changing noise environments without retraining.

Contribution

It proposes a novel Team-DMoE architecture inspired by Mixture of Experts to handle decentralized power control with evolving noise statistics.

Findings

Team-DMoE effectively tracks time-varying statistical scenarios.

The model demonstrates robustness across different noise environments.

Compared to other algorithms, it offers improved adaptability and performance.

Abstract

In the context of wireless networking, it was recently shown that multiple DNNs can be jointly trained to offer a desired collaborative behaviour capable of coping with a broad range of sensing uncertainties. In particular, it was established that DNNs can be used to derive policies that are robust with respect to the information noise statistic affecting the local information (e.g. CSI in a wireless network) used by each agent (e.g. transmitter) to make its decision. While promising, a major challenge in the implementation of such method is that information noise statistics may differ from agent to agent and, more importantly, that such statistics may not be available at the time of training or may evolve over time, making burdensome retraining necessary. This situation makes it desirable to devise a "universal" machine learning model, which can be trained once for all so as to allow for decentralized cooperation in any future feedback noise environment. With this goal in mind, we propose an architecture inspired from the well-known Mixture of Experts (MoE) model, which was previously used for non-linear regression and classification tasks in various contexts, such as computer vision and speech recognition. We consider the decentralized power control problem as an example to showcase the validity of the proposed model and to compare it against other power control algorithms. We show the ability of the so called Team-DMoE model to efficiently track time-varying statistical scenarios.