Reinforcement Learning Algorithm for Traffic Steering in Heterogeneous Network

TL;DR

This paper introduces a reinforcement learning-based traffic steering algorithm for heterogeneous networks that significantly improves user capacity and efficiency compared to existing methods, as demonstrated through network simulations.

Contribution

It presents a novel reinforcement learning algorithm combined with neural networks for traffic steering in HetNets, enhancing network capacity and user satisfaction.

Findings

The proposed algorithm outperforms reference algorithms in network simulations.

It increases the number of served users with limited radio resources.

The method achieves higher efficiency in traffic management.

Abstract

Heterogeneous radio access networks require efficient traffic steering methods to reach near-optimal results in order to maximize network capacity. This paper aims to propose a novel traffic steering algorithm for usage in HetNets, which utilizes a reinforcement learning algorithm in combination with an artificial neural network to maximize total user satisfaction in the simulated cellular network. The novel algorithm was compared with two reference algorithms using network simulation results. The results prove that the novel algorithm provides noticeably better efficiency in comparison with reference algorithms, especially in terms of the number of served users with limited frequency resources of the radio access network.