An Experimental Study of Factor Analysis over Cellular Network Data

Abstract

Mobile Network Operators (MNOs) are evolving towards becoming data-driven, while delivering capacity to collect and analyze data. This can help in enhancing user experiences while empowering the operation workforce and building new business models. Mobile traffic demands of users can give insights to MNOs to plan, decide and act depending on network conditions. In this paper, we investigate the behaviour of Istanbul residents using the cellular network traffic activity over spatial and temporal dimensions via exploratory factor analysis (EFA) using a major MNO's cellular network traffic data in Turkey. Our results reveal various time and spatial patterns for Istanbul residents such as morning and evening commuting factors, business and residential factors as well as nightlife and weekend afternoon factors as the most prominent cultural behaviour. The analysis results also demonstrate interesting findings such as tunnels and transportation paths selected by Istanbul residents may differ during morning rush work hour compared to evening rush after-work hour.

Recent Advances in Data Engineering for Networking

“…events, festivals), etc. For example, the spatio-temporal behaviour of residents may differ significantly depending on the time of day or week [210]. Some of the devices (e.g., mobile devices) also have limited hardware capacities and cannot train complex ML/DL models with large datasets.…”

“…In complex and large architectures and environments such as 5G, powerful hardware and software are required to support both training and inference (as data volume and quality become increasingly important) if intelligence is to be built on top of the network infrastructure, as described in survey paper [10] and the articles referenced therein. Therefore, computational and time resources for training processes need to be considered when learning with large datasets especially in wireless applications where patterns change over time [210], [211]. When model training is performed with large distributed datasets on central servers, additional communication and storage costs are incurred and the solution does not scale.…”

Understanding the City Behaviour through Data Analysis: A Case Study of Barcelona

“…Data analytics on dataset that are collected city-wide large scale regions can yield important and useful insights into the behaviour of the residents of the city. For example, the paper in [2] has run empirical results on mobile cellular data to find interesting conclusions on tunnels and transportation paths selected by residents of city of Istanbul in Turkey. In the mean time, the amount of available dataset for researchers provided by city officials have also recently gained momentum, e.g.…”

A Predictive Approach for Managing Network Port Resources of Service Providers

“…Prediction of number of user equipments (UEs) during the time of the day with Bayesian Neural Networks using a real-world Base Station (BS) dataset in Turkey is studied in [3]. Clustering [7] and factor analysis [8] approaches are also utilized using real network datasets to observe the behaviour of network resources within Mobile Network Operators (MNOs). With respect to DSLAM based research, different DSLAM metrics are monitored in [9] to provide high quality IPTV delivery service.…”