A Machine Learning Approach for Power Allocation in HetNets Considering QoS

TL;DR

This paper introduces a Q-learning based machine learning method for power allocation in heterogeneous networks, enhancing scalability, QoS, and fairness in dense femtocell deployments.

Contribution

It presents a novel cooperative Q-learning approach for resource management in HetNets, addressing complexity and unplanned femtocell deployment.

Findings

Supports over four times more femtocells than previous methods

Reduces resource allocation overhead significantly

Improves QoS and fairness in dense HetNets

Abstract

There is an increase in usage of smaller cells or femtocells to improve performance and coverage of next-generation heterogeneous wireless networks (HetNets). However, the interference caused by femtocells to neighboring cells is a limiting performance factor in dense HetNets. This interference is being managed via distributed resource allocation methods. However, as the density of the network increases so does the complexity of such resource allocation methods. Yet, unplanned deployment of femtocells requires an adaptable and self-organizing algorithm to make HetNets viable. As such, we propose to use a machine learning approach based on Q-learning to solve the resource allocation problem in such complex networks. By defining each base station as an agent, a cellular network is modelled as a multi-agent network. Subsequently, cooperative Q-learning can be applied as an efficient approach to manage the resources of a multi-agent network. Furthermore, the proposed approach considers the quality of service (QoS) for each user and fairness in the network. In comparison with prior work, the proposed approach can bring more than a four-fold increase in the number of supported femtocells while using cooperative Q-learning to reduce resource allocation overhead.