Network under Control: Multi-Vehicle E2E Measurements for AI-based QoS Prediction

Palaios, Alexandros; Geuer, Philipp; Fink, Jochen; Kulzer, Daniel Fabian; Göttsch, Fabian; Kasparick, Martin; Schaufele, Daniel; Hernangómez, Rodrigo; Partani, Sanket; Sattiraju, Raja; Kumar, Atul; Burmeister, Friedrich; Weinand, Andreas; Vielhaus, Christian; Fitzek, Frank H. P.; Fettweis, Gerhard; Schotten, Hans D.; Stańczak, Sławomir

doi:10.1109/pimrc50174.2021.9569490

Cited by 15 publications

(10 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We also used several protocols and created traffic in both UL and DL to the server and to other vehicles. For a complete in-depth description of all parameters for the measurement campaign, we refer to [41].…”

Section: B the Conducted Studiesmentioning

confidence: 99%

See 1 more Smart Citation

The Story of QoS Prediction in Vehicular Communication: From Radio Environment Statistics to Network-Access Throughput Prediction

Palaios¹,

Vielhaus²,

Kulzer³

et al. 2023

Preprint

View full text Add to dashboard Cite

As cellular networks evolve towards the 6th Generation (6G), Machine Learning (ML) is seen as a key enabling technology to improve the capabilities of the network. ML 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 (QoS) requirement. With predictive Quality of Service (pQoS), 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 HD mapping applications. We discuss the entire ML 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 ML models need to face a lot of challenges during their lifecycle. We highlight how confidence can be built on ML 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 ML models within diverse scenarios. We also use Explainable AI (XAI) to show that ML 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.

show abstract

Section: B the Conducted Studiesmentioning

confidence: 99%

“…All clocks are synchronized and all generated data is marked accordingly and captured at separate entities. Figure adapted from [41].…”

Section: A Sampling the Radio Environmentmentioning

confidence: 99%

The Story of QoS Prediction in Vehicular Communication: From Radio Environment Statistics to Network-Access Throughput Prediction

Palaios¹,

Vielhaus²,

Kulzer³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…One example [12] measured the parameters of a wireless network with dedicated measurement equipment (DME) and commercial off-the-shelf (COTS) mobile phones. They cooperated with the mobile network provider and ran a dedicated measurement campaign to collect the data.…”

Section: Related Workmentioning

confidence: 99%

An Open Mobile Communications Drive Test Data Set and Its Use for Machine Learning

Farthofer¹,

Herlich²,

Maier³

et al. 2022

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

The capability to provide guarantees for network metrics, such as latency, data rate, and reliability will be an important factor for widespread adoption of next generation mobile networks and hence, such metrics play a central role in standards for new wireless communication technologies. However, due to the inherently stochastic nature of mobile communications, any guarantees can only be of statistical nature and are highly dependent on the actual physical environment. To analyze the stochastic behavior, this paper presents a tool chain for measurement, collection, evaluation, and prediction of controlled mobile communications drive test data. We also publish the underlying data set of measurements covering two years' worth of highway traffic on a 25 km long section comprising 267 198 data points. We statistically evaluate the data set and validate it with a corresponding data set from another source. Applying machine learning to the data set illustrates possible use cases: Feed-forward neural networks to predict the data rate in five application scenarios, LIME to explain the behavior of the model, and an autoencoder to describe the interaction of five signal strength parameters. The data set and the tool chain show how machine learning can be applied to wireless networks and provide fellow researchers with the means to make further experiments.

show abstract

“…The conducted This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/ measurement campaigns are part of a bigger data-collection framework covering also automotive scenarios [3,12]. The common measurement procedure is described in detail in [12] and the resulting data is analyzed in [13].…”

Section: Introductionmentioning

confidence: 99%

“…For more information, see https://creativecommons.org/licenses/by/4.0/ measurement campaigns are part of a bigger data-collection framework covering also automotive scenarios [3,12]. The common measurement procedure is described in detail in [12] and the resulting data is analyzed in [13]. The datasets are publicly available and documented at https:// dx.doi.org/10.21227/04ta-v128.…”

Section: Introductionmentioning

confidence: 99%

Toward an AI-Enabled Connected Industry: AGV Communication and Sensor Measurement Datasets

Hernangómez,

Palaios,

Watermann

et al. 2024

IEEE Commun. Mag.

Self Cite

View full text Add to dashboard Cite

This article presents two wireless measurement campaigns in industrial testbeds: industrial vehicle-to-vehicle (iV2V) and industrial vehicle-to-infrastructure plus sensor (iV2I+), with detailed information about the two captured datasets. iV2V covers sidelink communication scenarios between moving and stationary robots, while iV2I+ is conducted at an industrial setting where an autonomous cleaning robot is connected to a private cellular network. The combination of different communication technologies within a common measurement methodology provides insights that can be exploited by ML for tasks, such as fingerprinting, line-of-sight detection, prediction of quality of service, or link selection. Moreover, the datasets are publicly available, labeled, and pre-filtered for fast on-boarding and applicability.

show abstract

Network under Control: Multi-Vehicle E2E Measurements for AI-based QoS Prediction

Cited by 15 publications

References 20 publications

The Story of QoS Prediction in Vehicular Communication: From Radio Environment Statistics to Network-Access Throughput Prediction

The Story of QoS Prediction in Vehicular Communication: From Radio Environment Statistics to Network-Access Throughput Prediction

An Open Mobile Communications Drive Test Data Set and Its Use for Machine Learning

Toward an AI-Enabled Connected Industry: AGV Communication and Sensor Measurement Datasets

Contact Info

Product

Resources

About