We introduce an open live multi-technology cellular network dataset derived from real, operational base stations of a commercial mobile operator in Slovakia. It provides a rare look inside live 2G, 4G and 5G Radio Access Networks (RANs) through Performance Management (PM) counters collected at 15-minute intervals and mapped to cell-level granularity. Each baseband processes multiple radio configurations, enabling multi-band and multi-generation correlation studies across real network deployments. Unlike any previously released resource, this dataset exposes real energy consumption values alongside radio and user-level performance indicators such as utilisation, Channel Quality Indicator (CQI), number of Radio Resource Control (RRC) connected and active users, uplink and downlink data volume and Multiple-Input Multiple-Output (MIMO) rank for all network cells where applicable. It supports research in energy-aware RAN optimisation, data-driven network management and cross-layer performance modelling. The dataset has been validated for internal consistency and is released under the Creative Commons Attribution (CC BY) license to foster reproducible and open telecommunications research.
Commercial fifth-generation (5G) networks are increasingly considered for latency-sensitive applications such as remote monitoring, teleoperation, and autonomous mobility. However, public datasets that jointly expose packet-level latency, packet loss, radio-layer measurements, mobility information, and dual-operator multi-connectivity (MC) traces remain limited. This article describes a processed dataset collected over commercial 5G Non-Standalone networks in Aalborg, Denmark, using a vehicle-mounted dual-modem measurement platform. The dataset contains synchronized per-packet uplink and downlink latency measurements, application-level packet-loss indicators, Global Positioning System (GPS) information, Long-Term Evolution (LTE) and New Radio (NR) radio key performance indicators (KPIs), serving- and neighboring-cell metadata, and uplink transmit-power measurements. The records cover urban, suburban, and rural routes under controlled constant-bit-rate User Datagram Protocol (UDP) traffic, with particular emphasis on rural uplink operation across multiple target data rates. The dataset is intended to support reproducible research on uplink reliability, radio-to-application-layer correlation, packet duplication, link aggregation, interface switching, and adaptive MC mechanisms in operational cellular networks. A companion source-code repository provides scripts for loading, processing, analyzing, and reproducing the main dataset-derived metrics. IEEE SOCIETY/COUNCIL IEEE Communications Society DATA TYPE/LOCATION Time-series; per-packet latency traces; radio KPI telemetry; mobile 5G NSA measurements; Aalborg, Denmark DATA DOI/PID 10.21227/xp31-0x80
C. S. Álvarez-Merino, Miguel Villanueva-Fernández, Alejandro Ramírez-Arroyo et al.· IEEE Data Descriptions· 0 citations
Efficient long-term network evolution is becoming increasingly critical in dense 5G-Advanced and beyond cellular systems, where persistent traffic imbalances and localized congestion pose significant challenges that conventional short-term radio resource management alone cannot fully mitigate. This paper proposes a digital twin (DT)-enabled non-real-time (NRT) network evolution framework integrated with a large language model (LLM). Within this architecture, the digital twin provides a high-fidelity, controllable environment for evaluating infrastructure actions, while the LLM serves as a strategic orchestration engine that recommends cost-efficient network upgrades based on observed network states. Unlike traditional optimization methods that require exhaustive mathematical reformulations for each specific scenario, the proposed framework leverages the reasoning capabilities of LLMs to interpret operator objectives and constraints in natural language, generating structured evolution plans. The considered NRT action space encompasses antenna upgrades, bandwidth expansion, and new base station (BS) deployment. A techno-economic formulation is introduced to jointly evaluate load reduction performance and overall economic expenditure. Numerical results in a dense cellular scenario demonstrate that the framework effectively reduces peak resource utilization and provides diverse, coordinated evolution strategies tailored to varying network conditions.
Yukai Wang, Janghee Woo, G. Hahm et al.· International Conference on...· 0 citations
Conventional LTE-to-5G NR Non-Standalone (NSA) planning remains predominantly coverage-oriented and often fails to capture user-experienced throughput degradation under realistic traffic conditions. This limitation is critical in NSA architectures, where LTE acts as the anchor layer for control and mobility while 5G NR provides additional capacity. This study proposes a measurement-driven, throughput-centric spatial framework to identify LTE Capacity Bottleneck Zones (CBZ) as a basis for more realistic LTE-to-5G NR NSA deployment planning. The main novelty is the integration of a KPI-weighted RF Index with Kernel Density Estimation (KDE), DBSCAN spatial clustering, and fuzzy spatial zoning to generate throughput-aware capacity maps rather than purely coverage-based assessments. Drive-test measurements were conducted in Lubuk Alung District, Indonesia, under live LTE network conditions, yielding 8,355 radio KPI samples (RSRP, SINR) and 25,613 HTTP downlink throughput samples with geolocation. Statistical analysis using Pearson/Spearman correlation, polynomial regression, and Random Forest regression reveals consistently weak relationships between RSRP/SINR and throughput, indicating that radio-layer indicators alone provide limited explanatory power for user-experienced performance. The proposed framework classifies the study area into three spatial zones: LTE Stability Zone (28.99%), LTE Degradation Zone (63.02%), and LTE Capacity Bottleneck Zone (7.99%), where CBZs are characterized by acceptable radio conditions but localized throughput degradation. These findings enable a shift from coverage-centric evaluation toward targeted, throughput-aware capacity optimization for LTE-to-5G NR NSA deployment planning
Afrizal Yuhanef, Muhammad Putra Pamungkas, Herry Setiawan et al.· SinkrOn· 0 citations
LoRa-LQE, a link quality estimation scheme specifically designed for mobile environments, outperforms state-of-the-art solutions and achieves packet delivery ratio improvements and energy efficiency improvements, thereby enabling more reliable communication for mobile IoT assets.
G. S. Neto, T. S. D. Silva, Instituto Federal do Maranhão et al.· Journal of Internet Services...· 0 citations
Bridging the rural digital divide remains a persistent global challenge despite the widespread deployment of 4G and 5G cellular networks. This paper presents a comprehensive survey and quantitative analysis of network architectures for enabling future sixth-generation (6G) services in rural and underserved regions. Drawing on a structured review of peer-reviewed studies, 3GPP and ITU-R standards, O-RAN Alliance specifications, and documented field deployments, we classify and evaluate four architectural categories: terrestrial networks (TNs), non-terrestrial networks (NTNs), hybrid TN–NTN systems, and Open Radio Access Network (O-RAN)-based deployments. Each architecture is assessed against International Mobile Telecommunications for 2030 (IMT-2030) performance targets for throughput, end-to-end round-trip latency, energy efficiency (expressed as energy consumed per bit), coverage, and reliability. Unlike prior surveys that address individual components in isolation, such as satellite backhaul, microwave transport, or O-RAN frameworks, this paper provides a unified, deployment-driven, and quantitatively grounded treatment of all four architectural classes under rural 6G constraints. The survey analyzes key enabling technologies including Integrated Access and Backhaul (IAB), High-Altitude Platform Stations (HAPSs), Low-Earth Orbit (LEO) satellite systems, Reconfigurable Intelligent Surfaces (RIS), and AI-native orchestration frameworks. Analytical models are presented for RIS-assisted link enhancement and AI-native RAN Intelligent Controller (RIC) control utility. A quantitative, normalized key performance indicator (KPI) comparison across cost efficiency, spectral utilization, power consumption, and deployment scalability is grounded in a transparent scoring methodology, extended with a multi-criteria (AHP) architecture ranking, a weight-sensitivity analysis, and a parametric techno-economic cost-per-user comparison, and supported by an extensive review of technical, industrial, and policy literature. Beyond current deployments, this work identifies emerging technologies, including direct-to-device non-terrestrial access, programmable radio environments, and intelligent RAN control, that are expected to play a central role in extending sustainable rural 6G connectivity. A practical deployment decision framework and scenario-driven architectural guidance are provided for researchers, network operators, and policymakers pursuing inclusive, future-ready rural connectivity.
Souradeep Deb, Nishith D. Tripathi, Jeffrey H. Reed· IEEE Open Journal of the Com...· 0 citations
This research Paper focuses on an Ultra-Dense Network (UDN) is a core enabling technology for 5G and 6G wireless systems, proposed to meet escalating capacity demands and support new high-rate, low-latency services. The fundamental principle is network densification, achieved by deploying a massive number of low-power Access Points (APs) and communication links per unit area, dramatically shortening the distance between transmitters and receivers to improve signal quality and spatial frequency reuse. Ultimately, the successful operation of UDNs relies heavily on advanced, AI-driven management systems to dynamically optimize resources, manage interference, and ensure seamless, high-performance connectivity in an inherently complex environment: Our key objectives are improving the Massive Capacity and Data Rates, Enhanced Coverage and Reliability, Ultra-Low Latency, Massive Connectivity Internet of Things (IoT) to maintaining the advanced resilient communication system all the time and every times.
P. Pradhan, Pramod D Gangejar· Journal of Ad-hoc Network an...· 0 citations
