%0 Conference Paper %1 info3-inproceedings-2021-2 %A Grigorjew, Alexej %A Seufert, Michael %A Wehner, Nikolas %A Hofmann, Jan %A Hoßfeld, Tobias %B IFIP/IEEE International Symposium on Integrated Network Management (IM 2021) %C Bordeaux, France (Virtual Conference) %D 2021 %K %T ML-Assisted Latency Assignments in Time-Sensitive Networking %X Recent developments in industrial automation and invehicle communication have raised the requirements of real-time networking. Bus systems that were traditionally deployed in these fields cannot provide sufficient bandwidth and are now shifting towards Ethernet for their real-time communication needs. In this field, standardization efforts from the IEEE and the IETF have developed new data plane mechanisms such as shapers and schedulers, as well as control plane mechanisms such as reservation protocols to support their new requirements. However, their implementation and their optimal configuration remain an important factor for their efficiency. This work presents a machine learning framework that takes on the configuration task. Four different models are trained for the configuration of per-hop latency guarantees in a distributed resource reservation process and compared with respect to their real-time traffic capacity. The evaluation shows that all models provide good configurations for the provided scenarios, but more importantly, they represent a first step for a semi-automated configuration of parameters in Time-Sensitive Networking.

@inproceedings{info3-inproceedings-2021-2, abstract = {Recent developments in industrial automation and invehicle communication have raised the requirements of real-time networking. Bus systems that were traditionally deployed in these fields cannot provide sufficient bandwidth and are now shifting towards Ethernet for their real-time communication needs. In this field, standardization efforts from the IEEE and the IETF have developed new data plane mechanisms such as shapers and schedulers, as well as control plane mechanisms such as reservation protocols to support their new requirements. However, their implementation and their optimal configuration remain an important factor for their efficiency. This work presents a machine learning framework that takes on the configuration task. Four different models are trained for the configuration of per-hop latency guarantees in a distributed resource reservation process and compared with respect to their real-time traffic capacity. The evaluation shows that all models provide good configurations for the provided scenarios, but more importantly, they represent a first step for a semi-automated configuration of parameters in Time-Sensitive Networking.}, added-at = {2023-12-13T06:29:13.000+0100}, address = {Bordeaux, France (Virtual Conference)}, author = {Grigorjew, Alexej and Seufert, Michael and Wehner, Nikolas and Hofmann, Jan and Hoßfeld, Tobias}, biburl = {https://www.bibsonomy.org/bibtex/246e381348674d97d6b9a17c8cac8a7ee/admin}, booktitle = {IFIP/IEEE International Symposium on Integrated Network Management (IM 2021)}, interhash = {ae33d161c488b684ab16f3a9f4c133be}, intrahash = {46e381348674d97d6b9a17c8cac8a7ee}, keywords = {}, month = {5}, timestamp = {2023-12-13T06:29:13.000+0100}, title = {ML-Assisted Latency Assignments in Time-Sensitive Networking}, year = 2021 }