Cell Association via Boundary Detection: A Scalable Approach Based on Data-Driven Random Features

TL;DR

This paper introduces a scalable, data-driven boundary detection method using randomized shallow networks for cell association in 5G networks, reducing computational costs and improving accuracy over traditional approaches.

Contribution

It proposes a novel physical layer solution using randomized shallow networks for cell boundary detection, enhancing scalability and efficiency in 5G and 4G coexistence.

Findings

Outperforms data-independent boundary detection methods.

Reduces computational cost compared to kernel methods.

Demonstrates superior accuracy in cell boundary detection.

Abstract

The problem of cell association is considered for cellular users present in the field. This has become a challenging problem with the deployment of 5G networks which will share the sub-6 GHz bands with the legacy 4G networks. Instead of taking a network-controlled approach, which may not be scalable with the number of users and may introduce extra delays into the system, we propose a scalable solution in the physical layer by utilizing data that can be collected by a large number of spectrum sensors deployed in the field. More specifically, we model the cell association problem as a nonlinear boundary detection problem and focus on solving this problem using randomized shallow networks for determining the boundaries for location of users associated to each cell. We exploit the power of data-driven modeling to reduce the computational cost of training in the proposed solution for the cell association problem. This is equivalent to choosing the right basis functions in the shallow architecture such that the detection is done with minimal error. Our experiments demonstrate the superiority of this method compared to its data-independent counterparts as well as its computational advantage over kernel methods.