A New Alternative for Traffic Hotspot Localization in Wireless Networks Using O&M Metrics

TL;DR

This paper introduces a novel, low-cost traffic hotspot localization method in wireless networks using five KPIs from O&M data, improving accuracy for network management and small cell deployment.

Contribution

The paper proposes a new hotspot localization technique combining five KPIs from O&M data, enhancing accuracy and cost-effectiveness over existing probing methods.

Findings

High localization precision achieved with combined KPIs

Method is cost-effective and easily implementable

Potential for further optimization with commercial hotspot data

Abstract

In recent years, there has been an increasing awareness to traffic localization techniques driven by the problematic of hotspot offloading solutions, the emergence of heterogeneous networks (HetNet) with small cells' deployment and the green networks. The localization of traffic hotspots with a high accuracy is indeed of great interest to know how the congested zones can be offloaded, where small cells should be deployed and how they can be managed for sleep mode concept. We propose, in this paper, a new hotspot localization technique based on the direct exploitation of five Key Performance Indicators (KPIs) extracted from the Operation and Maintenance (O&M) database of the network. These KPIs are the Timing Advance (TA), the angle of arrival (AoA), the neighboring cell level, the load time and two mean throughputs: arithmetic (AMT) and harmonic (HMT). The combined use of these KPIs, projected over a coverage map, yields a promising localization precision and can be further optimized by exploiting commercial data on potential hotspots. This solution can be implemented in the network at an appreciable low cost when compared with widely used probing methods.