Deterministic Network Calculus (DNC) can derive upper bounds on message transfer delay as well as the buffer size requirements of servers – two key metrics of safety-critical real-time systems that cannot tolerate violation of predefined deadlines or data being dropped due to buffer overflows.
This project's goal is to improve DNC, in particular its end-to-end analysis capabilities delivering accurate results, and to focus on applicability enhancements for a wide range of systems. Among these are systems with multicast flows, wireless sensor networks, systems best modeled with complex resource descriptions, or the combination thereof. Key aspects are system modeling and understanding the inherent interdependencies between modeling accuracy, analysis complexity, as well as accuracy of performance bounds obtained by DNC. To facilitate this research, we maintain tool support for DNC in the DiscoDNC project.
This project is funded by the Carl Zeiss Foundation grant of Steffen Bondorf from September 2016 to September 2018 [www].
Dr. Steffen Bondorf (project lead)
Alexander Scheffler (undergraduate student; B.Sc. thesis; graduate student M.Sc. and Ph.D.)
Philipp Schon (graduate student (M.Sc.))
Bruno Oliveira Cattelan (undergraduate exchange student from UFRGS, Brasil; B.Sc. thesis)
Deepak Paramashivam (graduate student (M.Sc.))
Markus Fögen (graduate student (M.Sc.))
Malte Schütze (B.Sc. thesis)
Tobias Jeske (undergraduate student)
Anja Hamscher (B.Sc. thesis)
|||DeepTMA: Predicting Effective Contention Models for Network Calculus using Graph Neural Networks (Fabien Geyer and Steffen Bondorf), In Proceedings of the 38th IEEE International Conference on Computer Communications (INFOCOM 2019), 2019. [bibtex] [pdf]|
|||Deterministic Network Calculus Analysis of Multicast Flows (Steffen Bondorf and Fabien Geyer), In Antonio Puliafito and Kishor S. Trivedi (Eds.), Systems Modeling: Methodologies and Tools, EAI/Springer Innovations in Communication and Computing. Springer International Publishing, 2019. [bibtex] [pdf]|
|||The Deterministic Network Calculus Analysis: Reliability Insights and Performance Improvements (Alexander Scheffler, Markus Fögen and Steffen Bondorf), to appear in the 22nd IEEE International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD 2018), 2018. [bibtex] [pdf]|
|||Demo Abstract: Worst-Case Performance Analysis with the Disco Deterministic Network Calculator (Alexander Scheffler, Steffen Bondorf and Jens B. Schmitt), to appear in the 22nd IEEE International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD 2018), 2018. [bibtex] [pdf]|
|||Cross-Sender Bit-Mixing Coding , In CoRR, volume abs/1807.04449, 2018. [bibtex] [pdf]|
|||Catching Corner Cases in Network Calculus – Flow Segregation Can Improve Accuracy (Steffen Bondorf, Paul Nikolaus and Jens B. Schmitt), In Proceedings of the 19th International GI/ITG Conference on Measurement, Modelling and Evaluation of Computing Systems (MMB 2018), 2018. [bibtex] [pdf]|
|||Verification of the FAIR Control System using Deterministic Network Calculus (Malte Schütze, Steffen Bondorf and Mathias Kreider), In Proceedings of the 16th International Conference on Accelerator and Large Experimental Physics Control Systems (ICALEPCS 2017), 2017. [bibtex] [pdf]|
|||Iterative Design Space Exploration for Networks Requiring Performance Guarantees (Bruno Cattelan and Steffen Bondorf), In Proceedings of the IEEE/AIAA 36th Digital Avionics Systems Conference (DASC 2017), 2017. [bibtex] [pdf]|
|||The Sensor Network Calculus as Key to the Design of Wireless Sensor Networks with Predictable Performance (Jens Schmitt, Steffen Bondorf, Wint Yi Poe), In Journal of Sensor and Actuator Networks, volume 6, 2017. [bibtex] [pdf] [doi]|
|||Towards Unified Tool Support for Real-time Calculus & Deterministic Network Calculus (Philipp Schon and Steffen Bondorf), In Proceedings of the 29th Euromicro Conference on Real-Time Systems (ECRTS 2017), Work-in-Progress Session, 2017. [bibtex] [pdf]|
|||Quality and Cost of Deterministic Network Calculus – Design and Evaluation of an Accurate and Fast Analysis (Steffen Bondorf, Paul Nikolaus and Jens B. Schmitt), In Proceedings of the ACM on Measurement and Analysis of Computing Systems (POMACS), ACM, volume 1, 2017. [bibtex] [pdf]|
|||Quality and Cost of Deterministic Network Calculus – Design and Evaluation of an Accurate and Fast Analysis (Steffen Bondorf, Paul Nikolaus and Jens B. Schmitt), In Proceedings of the ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems (SIGMETRICS 2017), 2017. [bibtex] [pdf]|
|||Better Bounds by Worse Assumptions – Improving Network Calculus Accuracy by Adding Pessimism to the Network Model (Steffen Bondorf), In Proceedings of the IEEE International Conference on Communications (ICC 2017), 2017. [bibtex] [pdf]|
|||Generalized Finitary Real-Time Calculus (Kai Lampka, Steffen Bondorf, Jens B. Schmitt, Nan Guan and Wang Yi), In Proceedings of the 36th IEEE International Conference on Computer Communications (INFOCOM 2017), 2017. [bibtex] [pdf]|
|||Generalizing Network Calculus Analysis to Derive Performance Guarantees for Multicast Flows (Steffen Bondorf and Fabien Geyer), In Proceedings of the 10th International Conference on Performance Evaluation Methodologies and Tools (VALUETOOLS 2016), 2016. [bibtex] [pdf]|
|||Deterministic Network Calculus for Multicasting: A Numerical Comparison Between Explicit Intermediate Bounds and Multicast Feed-Forward Analysis (Bruno Oliveira Cattelan), B.Sc. thesis, Universidade Federal do Rio Grande do Sul, Porto Alegre, Brazil, 2018.|
|||Large-Scale Numerical Evaluation of Network Calculus Analyses (Anja Hamscher), B.Sc thesis, TU Kaiserslautern, 2018.|
|||Deterministic Performance Analysis of FIFO-multiplexing Feed-forward Networks (Alexander Scheffler), B.Sc. thesis, TU Kaiserslautern, 2017.|
|||Modelling and Analysis of Timing Constraints of an Industrial Control System (Malte Schütze), B.Sc. thesis, TU Kaiserslautern, 2017.|
Worst-Case Analysis of Distributed Systems lecture (WoCADS, 4 ECTS): winter term 2016/17.
In winter term 2017/18, the lecture was given by Dr.-Ing. Kai Lampka (see also publication ).
WoNeCa-4 - the 4th Workshop on Network Calculus, 28 February 2018 (collocated with GI/ITG MMB 2018).
NetCal 2018 - the 2018 International Workshop on Network Calculus and Applications, 7 September 2018 (collocated with ITC 30).
DISCO Lab is proud to present the DISCO Deterministic Network Calculator, a network calculus library. This library contains a number of classes written in Java(tm) which may be useful for analyzing communication networks using the Network Calculus. This calculus allows to determine such characteristics of data flows as the maximum latency or the minimum bandwidth, as long as bounds can be specified for these flows in the form of so-called arrival curves.
For feedback, questions, etc., please contact Steffen Bondorf.
If you use the Disco Deterministic Network Calculator for research, please include one of the following entries in any resulting publication.
We offer an archive with the complete source code. For development, you need to get the dependencies listed in the System Requirements section, and set up your environment so that all external libraries are in the classpath.
Although this is a release candidate, unknown issues might occur.
DISCO Deterministic Network Calculator 2.0rc9 (source)
Development towards version 2.0 focusses on eliminating external dependencies, improving precision by using rational numbers, reducing structural complexity by modularization and simplifying the usage of the Network Calculator.
Besides the usual code, performance and stability improvements, this release candidate has the following noteworthy changes to offer:
Beta 4 breaks compatibility with previous beta versions due to the following changes:
The core of this library is the class "Curve" which represents piecewise-linear curves and provides min-plus-algebraic operations on these. Based on these operations, the class "NetworkAnalyser" allows to determine bounds on output, delay, and backlog using various approaches (see also technical report):
For some of these approaches the library offers the choice between FIFO and blind multiplexing assumptions. Furthermore, it supports the use of maximum service curves.
Finally, the library contains some useful methods for converting network graphs to server model graphs, an implementation of the Turn Prohibition algorithm for creating feed-forward networks from general network topologies, and a simple class for graphically viewing piecewise-linear curves.
Flows exiting the actual network at the same server need to share a common explicit sink node. Otherwise the TFA triggers a residual service curve computation for the flow of interest at this last hop before the explicit sink, i.e., the flow of interest is separated from the all other flows (like in the SFA), instead of handling those flows in total (TFA’s actual aggregate handling of flows). This behavious not only differs from the TFA procedure, it can also lead to a loss of tightness.
To run and compile version 1.1, you need at least J2SE 1.5 ("Java 5"). To use the precompiled libraries, earlier versions of the JRE may be sufficient, but the source code uses features introduced with version 1.5.
The sources are given as a Netbeans 6 project.
We offer two packages. One is an archive including the compiled library and all dependencies, the other is an archive with the complete source code. For development, you need to get both packages, and set up your environment so that all external libraries are in the classpath.
The DISCO Network Calculator's preferred file format for reading/storing network topologies is GraphML. One way to generate topologies in this format is to use the Boston University's Representative Internet Topology Generator (BRITE). BRITE can generate different types of flat and hierarchical network topologies and can also read topologies in a number of different file formats.
Below you can find a small patch for BRITE that allows to export graphs to the GraphML file format. If you do not have the "patch" program available, download the drop-in version, which contains the already patched files, and simply unpack it in BRITE's base directory.
Recently, a number of experimental studies showed that concurrent transmissions can boost wireless network performance, despite collisions. While these practical works provide evidence that concurrent transmissions may be received reliably, the underlying mechanisms are not fully understood. This work studies packet collisions starting with their mathematical representations to analyze the effect of factors like power ratio, timing offset, and carrier phase offset. Our results show that the capture effect alone can result in poor reception performance. We extend our model to study the effect of direct sequence spread spectrum (DSSS) with IEEE 802.15.4 as an example. With DSSS, we observe a reception ratio of over 90% in the model, complying with existing studies. We further experimentally validate our model on two widely used receivers (CC2420, AT86RF230), observing a good fit between analysis and experiments. Our model provides insights that help to improve existing and future protocols exploiting concurrent transmissions.
The code for simulations and some figures is available at GitHub: github.com/mwil/collision
DiscoSec is available with source from our download page.
DiscoSec is the first Open-Source WLAN driver that provides protection against the most common attacks on the IEEE 802.11 MAC layer. With an innovative design focusing on performance as well as an efficient implementation we were able to unite the seemingly contradictory goals performance and security. Our system offers reliable protection of wireless communication right from the beginning without sacrificing throughput.
More Information on DiscoSec is provided in the paper Design, Implementation, and Performance Analysis of DiscoSec – Service Pack for Securing WLANs PDF (and a german abstract PDF).
The new major version DiscoSec is now available for download. With a direct integration into the new generic IEEE 802.11 MAC layer mac80211 of the Linux kernel, DiscoSec is now independent from kernel versions and specific chipsets. It provides a hardware-independent protection to IEEE 802.11 networks against common Denial-of-Service attacks. The new version is published under the GPLv2.
DiscoSec is now easily integrable to existing WLAN networks, as most of the devices supported by the Linux kernel are using mac80211. It can be added simply by patching the network source files in the kernel directory. Installation instructions can be found in the README file included in the download package.
A separate patchset for OpenWRT is included for easy use on access point hardware that offers Linux support.
DiscoSec can now be configured using the provided tool ds_config, which can be used to change all parameters that are offered directly from the user space. Instructions for the usage are located in the README file.
A future goal is an adaptive access control mechanism that limits and controls the load of the Access Point, since new authentications can be a heavy burden on the AP if the authentication rate is not controlled.
This section describes the legacy version of DiscoSec that was integrated into the MadWifi device driver.
Source Code: DiscoSec-2.0.zip (updated 2009-10-20)
Old Version: DiscoSec-0.11.zip