The Vienna 4G/5G Drive-Test Dataset

TL;DR

The Vienna 4G/5G Drive-Test Dataset is introduced, a city-scale open dataset of georeferenced Long Term Evolution and 5G New Radio measurements collected across Vienna, Austria, enabling reproducible benchmarking across environment-aware learning, propagation modeling, coverage analysis, and ray-tracing calibration workflows.

Abstract

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.

Figures (12)

• Figure 1: City-wide measurement coverage with dense sampling across suburban and urban areas (indicated by the black and red boxes).
• Figure 2: Overview of the city-model provided with the dataset: building model (left), a zoomed-in building-region of interest (center, indicated by the red box), and terrain model overview (right).
• Figure 3: Example RSRP coverage maps around two BSs with different antenna heights: 38 m (left) and 19 m (right). The red triangle marks the estimated BS position; colors show RSRP.
• Figure 4: Example NR beam-level view for a single cell of the corresponding BS: strongest beam index per location (left) and the corresponding RSRP (right). The BS position is marked by a red triangle.
• Figure 5: Equipment for passive measurements (left) consisting of scanner (i), two OmniLOG PRO antennas (ii), and a GPS receiver (iii). Scanner setup in the car (right)