Data-Driven Optimization of Multi-Generational Cellular Networks: A Performance Classification Framework for Strategic Infrastructure Management

Maryam Sabahat; M. Umar Khan

cs.NIFeb 16, 2026

Data-Driven Optimization of Multi-Generational Cellular Networks: A Performance Classification Framework for Strategic Infrastructure Management

Authors: Maryam Sabahat, M. Umar Khan

Organizations: Department of Mathematics, Ghazi University, Dera Ghazi Khan, Pakistan. · Department of Computer Engineering, COMSATS University, Islamabad, Pakistan.

Abstract

The exponential growth in mobile data demand necessitates intelligent management of telecommunications infrastructure to ensure Quality of Service (QoS) and operational efficiency. This paper presents a comprehensive analysis of a multigenerational cellular network dataset, sourced from the OpenCelliD project, to identify patterns in network deployment, utilization, and infrastructure gaps. The methodology involves geographical, temporal, and performance analysis of 1,818 cell tower entries, predominantly Long Term Evolution (LTE), across three countries with a significant concentration in Pakistan. Key findings reveal the long-term persistence of legacy 2G/3G infrastructure in major urban centers, the existence of a substantial number of under-utilized towers representing opportunities for cost savings, and the identification of specific "non-4G demand zones" where active user bases are served by outdated technologies. By introducing a signal-density metric, we distinguish between absolute over-utilization and localized congestion. The results provide actionable intelligence for Mobile Network Operators (MNOs) to guide strategic LTE upgrades, optimize resource allocation, and bridge the digital divide in underserved regions.

Figures & tables

Algorithm 1 Tower Performance Classifier

Figure 1: Time series of monthly network updates from December 2023 to May 2025, illustrating a pronounced non-stationary pattern with a significant step-change in activity.

Figure 2: Comparative box plots of (a) coverage range (meters) and (b) sample count per tower, disaggregated by GSM, UMTS, and LTE technologies.

Figure 3: Scatter plot of samples versus signal density (samples/meter). The over-utilized clusters are clearly separated in the high-sample, high-density quadrant.

Figure 4: Spatial distribution of tower clusters across geographical coordinates, showing the physical layout and density patterns of different utilization categories.

Figure 5: Comparative analysis of traffic load across different tower classifications, displaying mean samples with standard deviation error bars for each utilization category.

Figure 6: Distribution of tower clusters across five utilization categories, showing the proportional breakdown of over-utilized, under-utilized, balanced, and strategic coverage clusters.

Panel of Figure 7 — Figure 7: Decision logic flow for the Tower Performance Classification.

Aspect	NetDataDrilling
Objective	Identify top $N_{c}$ highest-traffic cells in busiest TAC for congestion relief.
Scope	Limited to hotspot areas with high traffic density.
Output	List of cells requiring immediate tactical management.
Aspect	Tower Performance Classification
Objective	Classify all towers into operational categories for holistic optimization.
Scope	Entire network, considering both congestion and under-utilization.

Table 2: Comparison of NetDataDrilling and Tower Performance Classification Frameworks

Technology	Tower Count	Percentage	Avg. Range (m)
LTE	1,456	80.1%	1365.18
UMTS	204	11.2%	1762.50
GSM	158	8.7%	2119.04
Total	1,818	100%	1475.28

Table 3: Network Technology Distribution and Key Statistics

Priority	Cluster ID	Sample Count
1	T04	3,196
2	T11	1,082
3	T09	923

Table 4: Top Over-Utilized Clusters Requiring Immediate Intervention

Wireless Communications

Wireless communications studies how information is sent over radio links and how networks manage signals, spectrum, and resources reliably.

See all 399 papers

The Vienna 4G/5G Drive-Test Dataset
Mar 3, 2026Wilfried Wiedner, Lukas Eller, Mariam Mussbah +4Wireless Communications Radio Propagation Modeling
Institute of Telecommunications, TU Wien, Gusshausstraße 25, 1040 Vienna, Austria · Christian Doppler Laboratory for Digital Twin assisted AI for sustainable Radio Access Networks, TU Wien
Adaptive Alarm Threshold Prediction in 4G Mobile Networks: A Percentile-Guided Deep Learning Framework with Interpretable Outputs
Apr 4, 2026Ayon Roy, Sadman Sharif, Shiva Prasad SarkarInterpretable ML
Towards Flexible Spectrum Access: Data-Driven Insights into Spectrum Demand
Mar 10, 2026Mohamad Alkadamani, Amir Ghasemi, Halim Yanikomeroglu6G Networks Spatiotemporal Forecasting
Communications Research Centre, Ottawa, Ontario, Canada · Carleton University, Ottawa, Ontario, Canada

Mar 3, 2026J/K move · Enter open · S save

The Vienna 4G/5G Drive-Test Dataset

Wilfried Wiedner, Lukas Eller, Mariam Mussbah, Dominik Rössler+3

Institute of Telecommunications, TU Wien, Gusshausstraße 25, 1040 Vienna, Austria · Christian Doppler Laboratory for Digital Twin assisted AI for sustainable Radio Access Networks, TU Wien

Wireless Communications Radio Propagation Modeling

Open paper AskPDF arXiv

Machine learning for mobile network analysis, planning, and optimization is often limited by the lack of large, comprehensive real-world datasets. This paper introduces the Vienna 4G/5G Drive-Test Dataset, a city-scale open dataset of georeferenced Long Term Evolution (LTE) and 5G New Radio (NR) measurements collected across Vienna, Austria. The dataset combines passive wideband scanner observations with active handset logs, providing complementary network-side and user-side views of deployed radio access networks. The measurements cover diverse urban and suburban settings and are aligned with time and location information to support consistent evaluation. For a representative subset of base stations (BSs), we provide inferred deployment descriptors, including estimated BS locations, sector azimuths, and antenna heights. The release further includes high-resolution building and terrain models, enabling geometry-conditioned learning and calibration of deterministic approaches such as ray tracing. To facilitate practical reuse, the data are organized into scanner, handset, estimated cell information, and city-model components, and the accompanying documentation describes the available fields and intended joins between them. The dataset enables reproducible benchmarking across environment-aware learning, propagation modeling, coverage analysis, and ray-tracing calibration workflows.

Abstract

Wireless Communications

Explore similar work

The Vienna 4G/5G Drive-Test Dataset

Adaptive Alarm Threshold Prediction in 4G Mobile Networks: A Percentile-Guided Deep Learning Framework with Interpretable Outputs

Towards Flexible Spectrum Access: Data-Driven Insights into Spectrum Demand