More Web Proxy on the site http://driver.im/

research-article

Open access

Improvements to Deep-Learning-based Feasibility Prediction of Switched Ethernet Network Configurations

Authors:

Nicolas NavetAuthors Info & Claims

RTNS '21: Proceedings of the 29th International Conference on Real-Time Networks and Systems

Pages 89 - 99

https://doi.org/10.1145/3453417.3453429

Published: 22 July 2021 Publication History

All formats PDF

Abstract

Graph neural network (GNN) is an advanced machine learning model, which has been recently applied to encode Ethernet configurations as graphs and predict their feasibility in terms of meeting deadlines constraints. Ensembles of GNN models have proven to be robust to changes in the topology and traffic patterns with respect to the training set. However, the moderate prediction accuracy of the model, 79.3% at the lowest, hinders the application of GNN to real-world problems.

This study proposes improvements to the base GNN model in the construction of the training set and the structure of the model itself. We first introduce new training sets that are more diverse in terms of topologies and traffic patterns and focus on configurations that are difficult to predict. We then enhance the GNN model with more powerful activation functions, multiple channels and implement a technique called global pooling. The prediction accuracy of ensemble of GNNs with a combination of the suggested improvements increases significantly, up to 11.9% on the same 13 testing sets. Importantly, these improvements increase only marginally the time it takes to predict unseen configurations, i.e., the speedup factor is still from 50 to 1125 compared to schedulability analysis, which allows a far more extensive exploration of the design space.

References

[1]

RealTime at Work. [n.d.]. RTaW-Pegase: Modeling, Simulation and automated Configuration of communication networks. Retrieved 2019/01/24, https://www.realtimeatwork.com/software/rtaw-pegase.

[2]

N.C. Audsley. 2001. On priority assignment in fixed priority scheduling. Inform. Process. Lett. 79, 1 (2001), 39–44.

Digital Library

[3]

P.W. Battaglia, J.B. Hamrick, V. Bapst, A. Sanchez-Gonzalez, V. Zambaldi, M. Malinowski, A. Tacchetti, D. Raposo, A. Santoro, R. Faulkner, 2018. Relational inductive biases, deep learning, and graph networks. arXiv preprint arXiv:1806.01261(2018).

[4]

O. Creighton, N. Navet, P. Keller, and J. Migge. 2020. Towards Computer-Aided, Iterative TSN-and Ethernet-based E/E Architecture Design. In 2020 IEEE Standards Association (IEEE-SA) Ethernet & IP @ Automotive Technology Day. Munich. http://hdl.handle.net/10993/44490

[5]

R.I. Davis, L. Cucu-Grosjean, M. Bertogna, and A. Burns. 2016. A Review of Priority Assignment in Real-Time Systems. J. Syst. Archit. 65, C (April 2016), 64–82. https://doi.org/10.1016/j.sysarc.2016.04.002

Digital Library

[6]

R.I. Davis and N. Navet. 2012. Controller area network (CAN) schedulability analysis for messages with arbitrary deadlines in FIFO and work-conserving queues. In 9th IEEE International Workshop on Factory Communication Systems. 33–42.

[7]

F. Geyer. 2017. Performance evaluation of network topologies using graph-based deep learning. In Proceedings of the 11th EAI International Conference on Performance Evaluation Methodologies and Tools. 20–27.

Digital Library

[8]

F. Geyer and S. Bondorf. 2019. DeepTMA: predicting effective contention models for network calculus using graph neural networks. In IEEE INFOCOM 2019-IEEE Conference on Computer Communications. IEEE, 1009–1017.

[9]

F. Geyer and G. Carle. 2018. Learning and generating distributed routing protocols using graph-based deep learning. In Proceedings of the 2018 Workshop on Big Data Analytics and Machine Learning for Data Communication Networks. 40–45.

[10]

I. Goodfellow, Y. Bengio, and A. Courville. 2016. Deep learning. MIT press.

[11]

T. Hastie, R. Tibshirani, and J. Friedman. 2009. The elements of statistical learning: data mining, inference, and prediction. Springer Science & Business Media.

[12]

IEEE. 2009. IEEE Standard for Local and Metropolitan Area Networks – Virtual Bridged Local Area Networks Amendment 12 Forwarding and Queuing Enhancements for Time-Sensitive Streams (Std 802.1Qav-2009 ed.).

[13]

IEEE. 2016. IEEE Standard for Local and Metropolitan Area Networks – Bridges and Bridged Networks - Amendment 25: Enhancements for Scheduled Traffic (IEEE Std 802.1Qbv-2015ed.).

[14]

IEEE. 2016. IEEE Standard for Local and Metropolitan Area Networks – Bridges and Bridged Networks – Amendment 26: Frame Preemption (IEEE Std 802.1Qbu-2016 ed.).

[15]

T.L. Mai, N.N. Dao, and M. Park. 2018. Real-time task assignment approach leveraging reinforcement learning with evolution strategies for long-term latency minimization in fog computing. Sensors 18, 9 (2018), 2830.

[16]

T.L. Mai, N. Navet, and J. Migge. 2019. A hybrid machine learning and schedulability analysis method for the verification of TSN networks. In 2019 15th IEEE International Workshop on Factory Communication Systems (WFCS). IEEE, 1–8.

[17]

T.L. Mai, N. Navet, and J. Migge. 2019. On the use of supervised machine learning for assessing schedulability: application to Ethernet TSN. In Proceedings of the 27th International Conference on Real-Time Networks and Systems. 143–153.

[18]

Tieu Long Mai and Nicolas Navet. 2020. Deep Learning to Predict the Feasibility of Priority-Based Ethernet Network Configurations. Technical Report. University of Luxembourg. submitted to ACM TECS.

[19]

B. Mao, Z.M. Fadlullah, F. Tang, N. Kato, O. Akashi, T. Inoue, and K. Mizutani. 2017. Routing or computing? The paradigm shift towards intelligent computer network packet transmission based on deep learning. IEEE Trans. Comput. 66, 11 (2017), 1946–1960.

Digital Library

[20]

Jishnu Mukhoti, Viveka Kulharia, Amartya Sanyal, Stuart Golodetz, Philip HS Torr, and Puneet K Dokania. 2020. Calibrating Deep Neural Networks using Focal Loss. arXiv preprint arXiv:2002.09437(2020).

[21]

N. Navet, H.H. Bengtsson, and J. Migge. 2020. Early-stage Bottleneck Identification and Removal in TSN Networks. In Automotive Ethernet Congress. Munich. http://hdl.handle.net/10993/46282

[22]

N. Navet, T.L. Mai, and J. Migge. 2019. Using machine learning to speed up the design space exploration of Ethernet TSN networks. Technical Report. University of Luxembourg. http://hdl.handle.net/10993/38604

[23]

N. Navet, J. Migge, J. Villanueva, and M. Boyer. 2018. Pre-shaping Bursty Transmissions under IEEE802.1Q as a Simple and Efficient QoS Mechanism. SAE Int. J. Passeng. Cars – Electron. Electr. Syst. 11 (04 2018). https://doi.org/10.4271/2018-01-0756

[24]

N. Navet, J. Seyler, and J. Migge. 2015. Timing verification of real-time automotive Ethernet networks: what can we expect from simulation?. In the SAE World Congress 2015, ”Safety-Critical Systems” Session. Detroit, USA.

[25]

N. Navet, J. Villanueva, and J. Migge. 2018. Automating QoS protocols selection and configuration for automotive Ethernet networks. In SAE World Congress Experience (WCX018), session “Vehicle Networks and Communication (Part 2 of 2)”. Detroit, USA.

[26]

N. Navet, J. Villanueva, and J. Migge. 2019. Early-stage topological and technological choices for TSN-based communication architectures. In 2019 IEEE Standards Association (IEEE-SA) Ethernet & IP @ Automotive Technology Day. Detroit, Mi. http://hdl.handle.net/10993/40623

[27]

B.A.A. Nunes, K. Veenstra, W. Ballenthin, S. Lukin, and K. Obraczka. 2014. A machine learning framework for TCP round-trip time estimation. EURASIP Journal on Wireless Communications and Networking 2014, 1(2014), 47.

[28]

Plexxi. 2016. Latency in Ethernet Switches. Retrieved 2019/04/25, http://www.plexxi.com/wp-content/uploads/2016/01/Latency-in-Ethernet-Switches.pdf.

[29]

K. Rusek, J. Suárez-Varela, A. Mestres, P. Barlet-Ros, and A. Cabellos-Aparicio. 2019. Unveiling the potential of Graph Neural Networks for network modeling and optimization in SDN. In Proceedings of the 2019 ACM Symposium on SDN Research. 140–151.

[30]

Sébastien Varrette, Pascal Bouvry, Hyacinthe Cartiaux, and Fotis Georgatos. 2014. Management of an academic HPC cluster: The UL experience. In 2014 International Conference on High Performance Computing & Simulation (HPCS). IEEE, 959–967.

[31]

M. Wang, Y. Cui, X. Wang, S. Xiao, and J. Jiang. 2018. Machine Learning for Networking: Workflow, Advances and Opportunities. IEEE Network 32, 2 (March 2018), 92–99. https://doi.org/10.1109/MNET.2017.1700200

[32]

K. Winstein and H. Balakrishnan. 2013. TCP Ex Machina: Computer-generated congestion control. ACM SIGCOMM Computer Communication Review 43, 4, 123–134.

Digital Library

[33]

Marvin Zhang, Henrik Marklund, Abhishek Gupta, Sergey Levine, and Chelsea Finn. 2020. Adaptive Risk Minimization: A Meta-Learning Approach for Tackling Group Shift. arXiv preprint arXiv:2007.02931(2020).

Cited By

Keller PNavet N(2024)Approximation of Worst-Case Traversal Times in Real-Time Ethernet Networks: Exploring the Potential of Many-Objective Optimization for Simulation Aggregation2024 IEEE 20th International Conference on Factory Communication Systems (WFCS)10.1109/WFCS60972.2024.10540870(1-8)Online publication date: 17-Apr-2024
https://doi.org/10.1109/WFCS60972.2024.10540870
Wang CChen LTang CWang YXian YZhao YXue HHuan Z(2024)Enhanced time-sensitive networking configuration detection using optimized BPNN with feature selection for industry 4.0Cluster Computing10.1007/s10586-024-04493-5Online publication date: 29-Apr-2024
https://doi.org/10.1007/s10586-024-04493-5
Gonzalez de Oliveira RNavet NHenkel A(2023)Multi-Objective Optimization for Safety-Related Available E/E Architectures Scoping Highly Automated Driving VehiclesACM Transactions on Design Automation of Electronic Systems10.1145/358200428:3(1-37)Online publication date: 22-Mar-2023
https://dl.acm.org/doi/10.1145/3582004
Show More Cited By

Recommendations

Deep Learning to Predict the Feasibility of Priority-Based Ethernet Network Configurations
Machine learning has been recently applied in real-time systems to predict whether Ethernet network configurations are feasible in terms of meeting deadline constraints without executing conventional schedulability analysis. However, the existing ...
Edge Based Graph Neural Network to Recognize Semigraph Representation of English Alphabets
MIKE 2013: Proceedings of the First International Conference on Mining Intelligence and Knowledge Exploration - Volume 8284

Graph Neural Network based on edges is introduced in this paper and is used to recognize the English uppercase alphabets treating their corresponding graphs as semigraphs. Graph Neural Network(GNN) is a connectionist model comprising of two feedforward ...
New Results for Prediction of Chaotic Systems Using Deep Recurrent Neural Networks
Abstract
Prediction of nonlinear and dynamic systems is a challenging task, however with the aid of machine learning techniques, particularly neural networks, is now possible to accomplish this objective. Most common neural networks used are the multilayer ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Other conferences

RTNS '21: Proceedings of the 29th International Conference on Real-Time Networks and Systems

April 2021

236 pages

ISBN:9781450390019

DOI:10.1145/3453417

Editors:
Audrey Queudet
University of Nantes, France
,
Iain Bate
University of York, UK
,
Giuseppe Lipari
University of Lille, France

Copyright © 2021 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 22 July 2021

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Conference

RTNS'2021

RTNS'2021: 29th International Conference on Real-Time Networks and Systems

April 7 - 9, 2021

NANTES, France

Acceptance Rates

Overall Acceptance Rate 119 of 255 submissions, 47%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

7
Total Citations
View Citations
576
Total Downloads

Downloads (Last 12 months)222
Downloads (Last 6 weeks)37

Reflects downloads up to 17 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Keller PNavet N(2024)Approximation of Worst-Case Traversal Times in Real-Time Ethernet Networks: Exploring the Potential of Many-Objective Optimization for Simulation Aggregation2024 IEEE 20th International Conference on Factory Communication Systems (WFCS)10.1109/WFCS60972.2024.10540870(1-8)Online publication date: 17-Apr-2024
https://doi.org/10.1109/WFCS60972.2024.10540870
Wang CChen LTang CWang YXian YZhao YXue HHuan Z(2024)Enhanced time-sensitive networking configuration detection using optimized BPNN with feature selection for industry 4.0Cluster Computing10.1007/s10586-024-04493-5Online publication date: 29-Apr-2024
https://doi.org/10.1007/s10586-024-04493-5
Gonzalez de Oliveira RNavet NHenkel A(2023)Multi-Objective Optimization for Safety-Related Available E/E Architectures Scoping Highly Automated Driving VehiclesACM Transactions on Design Automation of Electronic Systems10.1145/358200428:3(1-37)Online publication date: 22-Mar-2023
https://dl.acm.org/doi/10.1145/3582004
Han MKwak BKim H(2023)TOW-IDS: Intrusion Detection System Based on Three Overlapped Wavelets for Automotive EthernetIEEE Transactions on Information Forensics and Security10.1109/TIFS.2022.322189318(411-422)Online publication date: 2023
https://doi.org/10.1109/TIFS.2022.3221893
Shibly KHossain MInoue HTaenaka YKadobayashi Y(2023)A Feature-Aware Semi-Supervised Learning Approach for Automotive Ethernet2023 IEEE International Conference on Cyber Security and Resilience (CSR)10.1109/CSR57506.2023.10224976(426-431)Online publication date: 31-Jul-2023
https://doi.org/10.1109/CSR57506.2023.10224976
Bezerra DOliveira Filho ARodrigues IDantas MBarbosa GSouza RKelner JSadok D(undefined)A Machine Learning-Based Optimization for End-to-End Latency in Tsn NetworksSSRN Electronic Journal10.2139/ssrn.4117312
https://doi.org/10.2139/ssrn.4117312
Bezerra DOliveira Filho ARodrigues IDantas MBarbosa GSouza RKelner JSadok D(undefined)A Machine Learning-Based Optimization for End-to-End Latency in Tsn NetworksSSRN Electronic Journal10.2139/ssrn.4117311
https://doi.org/10.2139/ssrn.4117311

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

HTML Format

View this article in HTML Format.

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Table of Contents