Berlin V2X: A Machine Learning Dataset from Multiple Vehicles and Radio Access Technologies

Hernangómez, Rodrigo; Geuer, Philipp; Palaios, Alexandros; Daniel, Schäufele,; Watermann, Cara; Khawla, Taleb-Bouhemadi,; Parvini, Mohammad; Krause, Anton; Partani, Sanket; Vielhaus, Christian; Kasparick, Martin; Kulzer, Daniel Fabian; Burmeister, Friedrich; Fitzek, Frank H. P.; Schotten, Hans D.; Fettweis, Gerhard; Stańczak, Sławomir

doi:10.1109/vtc2023-spring57618.2023.10200750

Cited by 8 publications

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In fact, we are on the brink where intelligent algorithms and machine learning techniques can be utilized to predict resource requirements and make real-time resource allocation decisions. The availability of recent datasets such as [24] makes researching this approach feasible, where the goal would be to optimize the allocation of resources across diverse applications and traffic scenarios, ensuring efficient utilization and minimizing resource wastage. Additionally, ensuring the seamless integration of NR V2X with existing and future communication technologies is critical for longterm system viability.…”

Section: Multi-rat V2x and Future Researchesmentioning

confidence: 99%

Performance Evaluation and Optimal Management of Mode 2 V2X Communications in 5G Networks

González,

Estrada,

Garcia-Roger

et al. 2023

IEEE Access

View full text Add to dashboard Cite

New Radio (NR) Vehicle-to-Everything (V2X) communications, a subject of the Third Generation Partnership Project (3GPP) specifications for 5G networks, enable vehicle communications akin to Long Term Evolution (LTE). These communications can be implemented either centrally, by connecting to 5G nodes, or autonomously, by establishing sidelink through the PC5 interface. Particularly noteworthy is the latter connection mode, referred to as Mode 2, which is independent of cellular network coverage. Instead, communication is established using pre-configured parameters and a sensing mechanism for resource selection and allocation in time and frequency. This paper delineates the resource selection procedures for NR VV2X Mode 2 and evaluates their performance across various scenarios. The findings suggest superior performance of high numerologies compared to smaller subcarrier spacings. Even though the standard prescribes a random method for V2X resource selection, it was observed that the sensing procedures yield higher Packet Reception Ratio (PRR) levels. Moreover, factors such as a smaller sidelink channel size and an extended duration of the candidate resource sensing window were found to enhance the frequency diversification of resources, thereby improving PRR levels. A qualitative examination of key considerations for the performance evaluation of Radio Access Technologies (RAT) V2X communications is also provided, delving into aspects such as RAT interplay, resource utilization, interoperability, performance trade-offs, and Quality of Service (QoS) for optimal management of multi-RAT V2X scenarios.

show abstract

Section: Multi-rat V2x and Future Researchesmentioning

confidence: 99%

Performance Evaluation and Optimal Management of Mode 2 V2X Communications in 5G Networks

González,

Estrada,

Garcia-Roger

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

Brain-Inspired Traffic Incident Detection for Effective Communication

Saravanan,

Potluri

2024

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

Machine Learning for QoS Prediction in Vehicular Communication: Challenges and Solution Approaches

et al. 2023

Self Cite

View full text Add to dashboard Cite

As cellular networks evolve towards the 6th generation, machine learning is seen as a key enabling technology to improve the capabilities of the network. Machine learning provides a methodology for predictive systems, which, in turn, can make networks become proactive. This proactive behavior of the network can be leveraged to sustain, for example, a specific quality of service requirement. With predictive quality of service, a wide variety of new use cases, both safety-and entertainment-related, are emerging, especially in the automotive sector. Therefore, in this work, we consider maximum throughput prediction enhancing, for example, streaming or highdefinition mapping applications. We discuss the entire machine learning workflow highlighting less regarded aspects such as the detailed sampling procedures, the in-depth analysis of the dataset characteristics, the effects of splits in the provided results, and the data availability. Reliable machine learning models need to face a lot of challenges during their lifecycle. We highlight how confidence can be built on machine learning technologies by better understanding the underlying characteristics of the collected data. We discuss feature engineering and the effects of different splits for the training processes, showcasing that random splits might overestimate performance by more than twofold. Moreover, we investigate diverse sets of input features, where network information proved to be most effective, cutting the error by half. Part of our contribution is the validation of multiple machine learning models within diverse scenarios. We also use explainable AI to show that machine learning can learn underlying principles of wireless networks without being explicitly programmed. Our data is collected from a deployed network that was under full control of the measurement team and covered different vehicular scenarios and radio environments.INDEX TERMS Intelligent transportation systems, machine learning, quality of service, throughput prediction, vehicular communication, wireless networks.

show abstract

Berlin V2X: A Machine Learning Dataset from Multiple Vehicles and Radio Access Technologies

Cited by 8 publications

References 13 publications

Performance Evaluation and Optimal Management of Mode 2 V2X Communications in 5G Networks

Performance Evaluation and Optimal Management of Mode 2 V2X Communications in 5G Networks

Brain-Inspired Traffic Incident Detection for Effective Communication

Machine Learning for QoS Prediction in Vehicular Communication: Challenges and Solution Approaches

Contact Info

Product

Resources

About