Community detection applications in cellular networks /Ayman gaber mohamed mohamed

Supervisor:
Nashwa Abdelbaki

Thesis (M.A.)—Nile University, Egypt, 2024 .

"Includes bibliographical references"

Contents:
DEDICATION................................................................................................................ i
ACKNOWLEDGEMENTS........................................................................................... ii
TABLE OF CONTENTS.............................................................................................. vi
LIST OF FIGURES ...................................................................................................... vi
LIST OF TABLES....................................................................................................... vii
ACRONYMS.............................................................................................................. viii
PUBLICATIONS......................................................................................................... vii
ABSTRACT.................................................................................................................. iii
Chapter 1 INTRODUCTION.........................................................................................1
1.1 Thesis Outlines.....................................................................................................3
1.2 Thesis Contributions...........................................................................................4
Chapter 2 OPPRTUNITIES AND USE CASES ...........................................................5
Chapter 3 MOBILE NETWORK ARCHETICTURE AND TRACKING AREA
DESIGN.........................................................................................................................9
Chapter 4 PREVIOUSE WORK..................................................................................17
Chapter 5 CLUSTERING, CONSTRAINED CLUSTERING AND COMMUNITY
DETECTION ...............................................................................................................19
5.1 Clustering Algorithms........................................................................................19
5.2 Edge Betweenness Calculation:.........................................................................23
5.3 Edge Removal:....................................................................................................23
5.4 Final Communities: ............................................................................................24
CHAPTER 6 PHASE1: DATASET AND CLUSTERING ALGORITHMS RESULTS
......................................................................................................................................25
vii
6.1 Dataset Creation................................................................................................25
6.2 Results of Clustering Algorithms and Constrained Clustering..........................27
Chapter 7 Phase 2 Dataset and Community Detection Algorithm..............................32
7.1 Dataset Creation.................................................................................................32
7.2 Community Detection Algorithm ......................................................................33
7.3 Benchmarking Results.......................................................................................42
Chapter 8 CONCLUSION AND FUTURE WORK....................................................46
8.1 Conclusion..........................................................................................................46
8.2 Future Work.......................................................................................................46
REFERENCES ............................................................................................................49

Abstract:
The explosive growth of mobile internet services and demand for data connectivity
boosts the innovation and development in Radio Access Network (RAN) to define how
next generation mobile networks will look like. Continuous improvement in existing
RAN is crucial to meet very strict speed and latency requirements by different mobile
applications with minimum investments. The existing Radio Access Network (RAN)
is facing many challenges to meet Quality of Service (QoS) requirements by different
mobile applications in addition to the increasing pressure to reduce operating cost.
Innovation and development in RAN have been accelerated to tackle these challenges
and to define how next generation mobile networks should look like. The role of
Machine Learning (ML) and Artificial Intelligence (AI) driven innovations within the
RAN domain is strengthening and attracting lots of attention to tackle many of the
challenging problems. In this research we surveyed RAN network base stations
clustering and its applications in the literature. The research also demonstrates how to
leverage community detection algorithms to understand underlying community
structures within RAN. Tracking Areas (TA) planning novel framework was developed
by adapting existing community detection algorithm to solve the problem of statically
partitioning a set of base stations into TA according to mobility patterns. Finally, live
network dataset in dense urban part of Cairo is used to assess how the developed
framework is used to partition this part of the network more efficiently compared to
other clustering techniques. Results obtained showed that the new methodology saved
up to 37.8% of inter TA signalling overhead and surpassing other conventional
iv
clustering algorithms. The main contributions of the thesis can be summarized as
follows.
1. Formulating the Tracking Area optimization problem using live network dataset
using real network measurements to estimate density of mobile subscriber’s mobility
between different base stations to benchmarking different partitioning approaches.
2. Developing a heuristic approach for solving the tracking area optimization problem
using constrained clustering techniques.
3. Developing a heuristic approach for solving the tracking area optimization problem
using graph theory by defining each base station as a vertex and define weighted edges
between different vertices.
4. A performance comparison for the quality of the constrained partitioning. The
assessment is based on the mobility density between different cuts in each of the used
algorithms using real network statistics.
5. The thesis propose a new framework to tackle other mobile network problems using
graph theory by defining weighted edges between different base stations using the
relevant network statistics according to the problem being studied.
Keywords:
RAN Mobility Optimization, Tracking Area Planning, RAN Intelligence,
Community Detection, Machine Learning

Text in English, abstracts in English and Arabic