Extending 5G Capacity Planning Through Advanced Subscriber Behavior-Centric Clustering

Gonçalves Gonçalves,Souto Souto,Sebastião Sebastião,Correia Correia

doi:10.3390/electronics8121385

Gonçalves Gonçalves, Souto Souto + Show 2 more

Open Access

https://doi.org/10.3390/electronics8121385

Copy DOI

Journal: Electronics	Publication Date: Nov 21, 2019
Citations: 1	License type: CC BY 4.0

Affiliation: Instituto de Telecomunicações

Abstract

This work focuses on providing enhanced capacity planning and resource management for 5G networks through bridging data science concepts with usual network planning processes. For this purpose, we propose using a subscriber-centric clustering approach, based on subscribers’ behavior, leading to the concept of intelligent 5G networks, ultimately resulting in relevant advantages and improvements to the cellular planning process. Such advanced data-science-related techniques provide powerful insights into subscribers’ characteristics that can be extremely useful for mobile network operators. We demonstrate the advantages of using such techniques, focusing on the particular case of subscribers’ behavior, which has not yet been the subject of relevant studies. In this sense, we extend previously developed work, contributing further by showing that by applying advanced clustering, two new behavioral clusters appear, whose traffic generation and capacity demand profiles are very relevant for network planning and resource management and, therefore, should be taken into account by mobile network operators. As far as we are aware, for network, capacity, and resource management planning processes, it is the first time that such groups have been considered. We also contribute by demonstrating that there are extensive advantages for both operators and subscribers by performing advanced subscriber clustering and analytics.

Highlights

Smartphones and tablets have become very convenient end user devices that can replace several other devices, providing a multitude of multimedia functionalities that are no longer limited to specific people, occupations, or social status
Our main contribution is twofold: first, we demonstrate the advantage of considering subscriber-centric clustering based on behavior both in terms of capacity network planning process and resource management
In main contribution contribution isistwofold: twofold:first, first,we wedemonstrated demonstratedthe the advantage applying subscriber-centric clustering based on behavior, both to capacity network planning process and subscriber-centric clustering based on behavior, both to capacity network planning process and resource resource management

Summary

Introduction

Smartphones and tablets have become very convenient end user devices that can replace several other devices, providing a multitude of multimedia functionalities that are no longer limited to specific people, occupations, or social status. The pervasiveness of smartphones and tablets have transformed them almost into children’s toys, with small children using them mainly to watch videos. The unprecedented availability of new services, new data rates, and applications, with the introduction of 5G, implies that network operators must be prepared and plan their networks according to expected capacity demand. Mobile network operators (MNOs) might not have the chance to exhaustively test the introduction of new services and applications along with any eventual capacity exhaustion that might happen. Especially considering densities that are expected both on network and subscriber planes, it is complex to analyze both planes’ behavior against the capacity that needs to be guaranteed. 5G’s most prevalent “use-cases” are enhanced mobile broadband (eMBB), ultrareliable and low-latency communications (URLLC), and massive machine type communications (mMTC); this work focuses on eMBB.

Objectives

Results

Conclusion