Federated Deep Reinforcement Learning for the Distributed Control of NextG Wireless Networks

TL;DR

This paper introduces federated deep reinforcement learning (F-DRL) for NextG wireless networks, enabling distributed control by collaboratively training models without sharing raw data, thus improving adaptability and performance.

Contribution

It proposes a novel federated DRL framework for distributed network control, addressing data exchange and convergence issues in traditional centralized and distributed DRL methods.

Findings

F-DRL outperforms distributed DRL in convergence speed and accuracy.

Federated approach reduces data exchange requirements.

Both value and policy-based F-DRL show superior performance.

Abstract

Next Generation (NextG) networks are expected to support demanding tactile internet applications such as augmented reality and connected autonomous vehicles. Whereas recent innovations bring the promise of larger link capacity, their sensitivity to the environment and erratic performance defy traditional model-based control rationales. Zero-touch data-driven approaches can improve the ability of the network to adapt to the current operating conditions. Tools such as reinforcement learning (RL) algorithms can build optimal control policy solely based on a history of observations. Specifically, deep RL (DRL), which uses a deep neural network (DNN) as a predictor, has been shown to achieve good performance even in complex environments and with high dimensional inputs. However, the training of DRL models require a large amount of data, which may limit its adaptability to ever-evolving statistics of the underlying environment. Moreover, wireless networks are inherently distributed systems, where centralized DRL approaches would require excessive data exchange, while fully distributed approaches may result in slower convergence rates and performance degradation. In this paper, to address these challenges, we propose a federated learning (FL) approach to DRL, which we refer to federated DRL (F-DRL), where base stations (BS) collaboratively train the embedded DNN by only sharing models' weights rather than training data. We evaluate two distinct versions of F-DRL, value and policy based, and show the superior performance they achieve compared to distributed and centralized DRL.