Mobility pattern analysis in LTE networks

My role

Team of 3 · challenge winners

Topics

communications4G/LTEmachine learningclusteringtime series

Share of static, pedestrian and vehicular users over a week at three LTE base stations (5-hour rolling average)

In 2019 I teamed up with my good friends Pau Batlle Franch and Antoni Eritja for the SCAVENGE Data Challenge: analysing the downlink control data (LTE PDCCH traces) of three 4G base stations to discover underlying patterns in communication quality and user mobility, using machine learning, clustering and time-series analysis.

Our work was selected as the winner of the challenge, and I presented it in September 2019 at the 27th International Conference on Software, Telecommunications and Computer Networks (SoftCOM 2019) in Split, Croatia, organised with the IEEE Communications Society. A paper followed at the IEEE 93rd Vehicular Technology Conference (VTC2021-Spring) [1].

Related publications

[1]

PUB-21-01

User mobility inference and clustering through LTE PDCCH data analysis

P. Batlle Franch, A. J. Eritja Olivella, R. M. García Alarcia and P. Dini

conference2021 IEEE 93rd Vehicular Technology Conference (VTC2021-Spring), 2021

pdf bibtex doi

The high penetration of mobile services provides an ample set of data generated by users and network elements. The analysis of such data yields insights on the behaviour of users and their experienced quality, and can be used by mobile operators to improve their mobile networks. In this paper, we design methods to infer user mobility patterns, estimate their channel quality and cluster them based on their Modulation and Coding Scheme (MCS) time evolution. In detail, we propose: i) a mapping between MCS and SNR, useful to assess the quality of the transmissions, ii) a method for deriving users' approximate velocities and categorising user mobility, and iii) a hierarchical clustering algorithm using Dynamic Time Warping, able to generate meaningful user clusters according to communication length and quality. We apply those proposed methods to real traces collected from more than one week of observations of three operative base stations in Spain. We observe that our solutions successfully provide relevant information about users' mobility and their channel quality, making them suitable for improvements in the understanding and planning of LTE resources by mobile network operators.Keywords: Channel Quality Analysis, Channel Quality Time Evolution, Clustering, Data Analysis, Dynamic Time Warping, PDCCH, Time Series Analysis, Time Series Clustering, Users Mobility, Wireless Traffic Analysis, Wireless Traffic Characterization