ACM SIGCOMM 2019 Tutorial on Modeling and Analysis of Network Infrastructure in Cyber-Physical Systems

Tutorial Program (subject to changes)

Call For Participation

This tutorial will provide participants with challenges, solutions, and tools with hands-on exercises to modeling and analysis of network infrastructure in delay-constrained cyber-physical systems. Attendee will learn network calculus with cases studies of its applications in designing and analyzing wireless sensor networks and smart-grid substation networks.

Attendees will also learn details of DNC (NetworkCalculus.org), a comprehensive tool for network calculus analysis, and how to use it for analyzing the delay performance of tandem networks, tree networks, and feed-forward networks for CPS with hands-on labs.

Travel Support

There may be opportunities for attendees of this tutorial who are current students of U.S. universities to receive nominal support for travel with the fund provided by the U.S. National Science Foundation as it wishes to increase participation of under-represented groups such as female and/or minority students. Please contact Prof. Liang Cheng cheng@lehigh.edu for details and an application.

Important Dates

• August 23, 2019

  Tutorial

Outline

Part I: Background and network calculus theory. Introduction to CPS; network infrastructure evolution in CPS; min-plus calculus; network calculus; review exercise. [Le Boudec and Thiran 2001]

Part II: Case studies of modeling and analysis of network infrastructure in CPS.
Case study #1: designing wireless sensor networks with predictable performance using sensor network calculus. [Bondorf and Schmitt 2015]
Case study #2: analyzing worst-case delay performance of smart-grid substation networks using measurements and network calculus. [Yang, Cheng, and Ma 2017]

Part III: Hands-on lab activities of using a network calculus tool, the NetworkCalculus.org Deterministic Network Calculator (DNC). Introduction to DNC, a comprehensive tool for network calculus analysis; hands-on labs on analyzing the delay performance of tandem networks, tree networks, and feed-forward networks for CPS. [Bondorf and Schmitt 2014]

Background

Modern societies are witnessing the prevalence of a wide assortment of distributed cyber-physical systems (CPS) built upon network infrastructure for mission-critical applications, such as industrial process control systems and avionics. Such applications demand strict and deterministic delay performance of their CPS network infrastructure for system safety, stability and resilience. Thus there is an increasing interest in modeling and analysis of delay-constrained CPS.

Industrial process control systems and avionics had been developing networking solutions for decades and we can currently observe a convergence to a common standard. As an example take fieldbus technologies such as Profibus that had been developed for use in factory automation. With increasing demands on data rates and interoperability with existing off-the-shelf components, Ethernet-based solutions such as Profinet have started replacing the bus technologies. The same trend can be observed in the avionics sector where Airbus developed the Ethernet-based on-board communication system AFDX (Avionics Full-Duplex Ethernet) that has subsequently been adopted by its competitors Boeing and Bombardier. In addition to these industry-led developments for real-time-capable Ethernet, the IEEE has been working on official standards to address these use-cases of Ethernet. Its efforts first led to IEEE AVB (audio-video bridging) that defines traffic shaping, scheduling and path reservation for time-synchronized low latency streaming services. The continued development is led by the IEEE TSN (Time-Sensitive Networking) working group and TSN technologies are already discussed to be incorporated into Profinet and AFDX. Moreover, the Internet Engineering Task Force (IETF) has established a working group for Deterministic Networking (DetNet) that is closely collaborating with IEEE TSN in order to bring its concepts to the Internet.

Given that there is a technological convergence, the search for a common methodology for verification of real-time capabilities under any operation condition is complementary. During the development of AFDX, the Network Calculus was adopted and subsequently used for certification. Both the IEEE and the IETF have already discussed the applicability of Network Calculus to their respective problem spaces and standardization efforts. Recent development in network performance analyses especially network calculus and network modeling and measurements makes it possible for an organically integrated approach to modeling and analysis of delay-constrained networked cyber-physical systems. Researchers may be able to take advantage of the contents of this tutorial for their work when which may be utilized for analysis, identification and mitigation of delay performance bottlenecks of network infrastructure in cyber-physical systems.

Audience Expectations and Prerequisites

Attendees are required to bring their own laptops with a Java 10 JDK and an editor for the hands-on lab. We recommend using the Eclipse Java IDE as dnc.networkcalculus.org provides documentation for configuring Eclipse.

Organizers

• Liang Cheng

  New York, USA

  • Bio: Prof. Liang Cheng of the Department of Computer Science and Engineering at Lehigh University focuses his research on enabling intelligent infrastructure based on real-time sensing, model-driven data analytics, and machine learning. He is an expert in cyber-physical systems and ad hoc networks. His research has been funded by U.S. federal funding agencies such as NSF, DOE, DOT, and DARPA, Pennsylvania government, and companies including ABB, Agere Systems, East Penn Manufacturing, and PPL. He has advised 6 Ph.D. students to their graduation, supervised 2 postdocs, advised 22 Master's degree theses, and co-authored more than 100 papers. Prof. Cheng was a keynote speaker at 2015 IEEE International Conference on the Edges of Innovation for Smarter Cities. He served as a Program Co-Chair for IEEE SustainCom 2016 and MobiSPC 2014. He received Christian R. & Mary F. Lindback Foundation Minority Junior Faculty Award in 2004. Previously he offered tutorials on Network Systems Design with Network Processor Technology and MAC Schemes for Message Dissemination in Vehicular Ad Hoc Networks.

• Steffen Bondorf

  Trondheim, Norway

  • Bio: Steffen Bondorf received his B.Sc. (2009), M.Sc. (2012) and Ph.D. (2016) in Computer Science from TU Kaiserslautern, Germany. After graduation, he was a postdoctoral researcher and Carl-Zeiss Fellow at TU Kaiserslautern, Research Fellow at the National University of Singapore as well as visiting the University of Toronto, Canada. He is currently an ERCIM (European Research Consortium for Informatics and Mathematics) Alain-Bensoussan Fellow and postdoc the NTNU – the Norwegian University of Science and Technology in Trondheim, Norway. His research interests are in performance modeling and analysis of communication networks and in particular in advancing the Network Calculus methodology.

References

[Bondorf and Schmitt 2014] Steffen Bondorf and Jens B. Schmitt. 2014. The DiscoDNC v2 – a comprehensive tool for deterministic network calculus. In Proceedings of the 8th International Conference on Performance Evaluation Methodologies and Tools (VALUETOOLS '14). ICST (Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering), ICST, Brussels, Belgium, Belgium, 44-49.

• For the source code visit dnc.networkcalculus.org

[Bondorf and Schmitt 2015] Steffen Bondorf and Jens B. Schmitt, Boosting sensor network calculus by thoroughly bounding cross-traffic, 2015 IEEE Conference on Computer Communications (INFOCOM), Kowloon, 2015, pp. 235-243.
[Le Boudec and Thiran 2001] Jean-Yves Le Boudec and Patrick Thiran. 2001. Network Calculus: A Theory of Deterministic Queuing Systems for the Internet. Springer-Verlag, Berlin, Heidelberg.
[Yang, Cheng, and Ma 2017] Huan Yang, Liang Cheng, and Xiaoguang Ma, Analyzing worst-case delay performance of IEC 61850-9-2 process bus networks using measurements and network calculus, in the Proceeding of The Eighth International Conference on Future Energy Systems (ACM e-Energy), Hong Kong, May 17-19, 2017