DQN-Based Multi-User Power Allocation for Hybrid RF/VLC Networks

TL;DR

This paper introduces a DQN-based multi-agent algorithm for power allocation in hybrid RF/VLC networks, significantly improving convergence speed and accuracy over traditional Q-Learning methods.

Contribution

It presents a novel multi-agent DQN approach for online power allocation in hybrid RF/VLC networks, enhancing convergence efficiency and data rate accuracy.

Findings

DQN converges 90% faster than Q-Learning.

DQN achieves 96.1% convergence rate, outperforming QL's 72.3%.

DQN provides data rates closer to targets than QL.

Abstract

In this paper, a Deep Q-Network (DQN) based multi-agent multi-user power allocation algorithm is proposed for hybrid networks composed of radio frequency (RF) and visible light communication (VLC) access points (APs). The users are capable of multihoming, which can bridge RF and VLC links for accommodating their bandwidth requirements. By leveraging a non-cooperative multi-agent DQN algorithm, where each AP is an agent, an online power allocation strategy is developed to optimize the transmit power for providing users' required data rate. Our simulation results demonstrate that DQN's median convergence time training is 90% shorter than the Q-Learning (QL) based algorithm. The DQN-based algorithm converges to the desired user rate in half duration on average while converging with the rate of 96.1% compared to the QL-based algorithm's convergence rate of 72.3% Additionally, thanks to its continuous state-space definition, the DQN-based power allocation algorithm provides average user data rates closer to the target rates than the QL-based algorithm when it converges.