Wireless Datasets for Aerial Networks

Abstract: The integration of unmanned aerial vehicles (UAVs) into 5G-Advanced and future 6G networks presents a transformative opportunity for wireless connectivity, enabling agile deployment and improved LoS communications. However, the effective design and optimization of these aerial networks depend critically on high-quality, empirical data. This paper provides a comprehensive survey of publicly available wireless datasets collected from an airborne platform called Aerial Experimentation and Research Platform on Advanced Wireless (AERPAW). We highlight the unique challenges associated with generating reproducible aerial wireless datasets, and review the existing related works in the literature. Subsequently, for each dataset considered, we explain the hardware and software used, present the dataset format, provide representative results, and discuss how these datasets can be used to conduct additional research. The specific aerial wireless datasets presented include raw I/Q samples from a cellular network over different UAV trajectories, spectrum measurements at different altitudes, flying 4G base station (BS), a 5G-NSA Ericsson network, a LoRaWAN network, an radio frequency (RF) sensor network for source localization, wireless propagation data for various scenarios, and comparison of ray tracing and real-world propagation scenarios. References to all datasets and post-processing scripts are provided to enable full reproducibility of the results. Ultimately, we aim to guide the community toward effective dataset utilization for validating propagation models, developing machine learning algorithms, and advancing the next generation of aerial wireless systems.

• The paper presents extensive aerial wireless datasets from AERPAW, enabling reproducible studies and validation of propagation models.
• It details the use of programmable radios, digital twins, and large UAV platforms to overcome technical and regulatory challenges in dataset collection.
• The datasets support applications in machine learning, 3D coverage, waveform design, and network simulation for next-generation wireless systems.

Wireless Datasets for Aerial Networks

The paper "Wireless Datasets for Aerial Networks" (2510.08752) provides an extensive survey of publicly available wireless datasets collected from the Aerial Experimentation and Research Platform on Advanced Wireless (AERPAW). These datasets are critical for the design and optimization of aerial networks, which play a vital role in 5G-Advanced and future 6G networks by enabling improved line-of-sight (LoS) communications and agile deployment. The paper focuses on the technical, logistical, and regulatory challenges involved in creating reproducible aerial wireless datasets and reviews existing related works. Additionally, it details the hardware, software used, dataset format, representative results, and potential applications for each dataset, aiming to guide researchers in validating propagation models, developing machine learning algorithms, and advancing aerial wireless systems.

Introduction

Aerial platforms, particularly unmanned aerial vehicles (UAVs), are increasingly recognized as valuable complements to terrestrial infrastructure in wireless networks. UAVs offer unique advantages such as agile deployment, rapid coverage extension, and spectrum monitoring capabilities, especially in challenging environments like disaster-stricken areas. Recent efforts by regulatory bodies like the FCC and 3GPP have sought to integrate UAVs into cellular networks, addressing challenges like interference mitigation and mobility management. These initiatives highlight the need for open and reproducible datasets to validate theoretical models and guide system design.

Figure 1: Campaign environment and UAV trajectory for the I/Q measurement dataset.

Challenges for Generating Datasets

The paper outlines several key challenges in collecting high-quality datasets for aerial wireless systems:

1. Programmable Radios: While commercial off-the-shelf (COTS) equipment is commonly used for data collection, it often lacks flexibility. AERPAW uses USRP devices, allowing custom waveform generation and enhanced programmability, albeit with increased complexity and size.
2. Outdoor Infrastructure and Spectrum: Secure outdoor experiments require dedicated radio infrastructure and access to experimental spectrum bands. AERPAW's Innovation Zones enable such experimentation, overcoming regulatory hurdles related to spectrum usage in UAV operations.
3. Large Drones for Payloads: Large drones are deployed to carry the necessary equipment, including USRP devices. AERPAW designs these drones using open-source software, maximizing customization while ensuring reproducibility in drone design.
4. Digital Twins: A digital twin of the testbed facilitates remote development and testing, enabling rapid deployment of experiments while ensuring safety and reliability in autonomous UAV operations.

Aerial Wireless Datasets

A comprehensive set of datasets collected through AERPAW are presented, spanning different technologies and measurement parameters:

• Wireless I/Q Datasets: Captures raw I/Q samples over LTE networks at various UAV altitudes, enabling studies in A2G propagation modeling and UAV receiver algorithm design.

  Figure 2: Illustration of the AERPAW large multirotor-type UAV setup for the experiment, where the UAV carries a portable node.

• Wireless Spectrum Dataset: Includes wideband aerial spectrum monitoring data for propagation analysis and spectrum allocation.
• 5G NSA Wireless KPI Datasets: Offers aerial KPI measurements on a 5G NSA network, essential for analyzing network performance in UAV deployments.
• LoRa Propagation Datasets: Provides data on LoRaWAN propagation characteristics, useful for IoT coverage analysis.
• Multipath Propagation Datasets: Characterizes A2G multipath channels, assisting in waveform design and channel modeling efforts.

Figure 3: Representative results from the A2G channel sounding campaign using a UAV-mounted transmitter.

Possible Applications

The datasets support numerous applications in wireless communications research, such as:

• Validating propagation models and enhancing 3D coverage estimation.
• Machine learning algorithm development for spectrum sensing and channel estimation.
• Benchmarking network simulation tools with empirical data.
• Designing trajectory-aware network protocols, improving QoS in aerial networks.
• Spectrum management and allocation studies in dynamic UAV environments.

Conclusion

The collection of datasets from AERPAW represents a significant contribution to the aerial wireless research community, providing the empirical basis needed for future advancements in 5G and 6G networks. These open datasets encourage collaboration and innovation in UAV-assisted network design, system integration, and performance optimization. As UAV technologies continue to evolve, ongoing dataset expansion and integration with emerging standards will be crucial for addressing new challenges and opportunities in aerial computing and connectivity.

Figure 4: Measurement setup and procedure for spectrum data collection using the helikite-mounted portable node.