CyNC: a MATLAB/SimuLink toolbox for network calculus

This paper presents a graphical integrated modelling and performance-analysis tool based on deterministic network calculus (DNC) and implemented as an open source toolbox for the MATLAB/SimuLink environment. The paper introduces briefly the main concepts from network calculus and especially recent results for systems with cyclic dependencies, which appear in cases of cyclic data/work flow or counter directional resource and work flows. A number of network element types are supported including various arbitration/scheduling disciplines such as: Fixed Priorities, FIFO, TDMA, round robin/token passing and EDF along with packetization, flow control and flow convergence. These are all presented in the paper together with auxiliary tools like worst case backlog and delay calculations. Implementation details of general interest are presented along with illustrative examples demonstrating the virtues of the separate modelling elements and the overall tool framework. Discussion is provided concerning issues in system stability and the ability of DNC to provide usefull estimates of stability limits. Likewise current activities to support synchronous communication and flow control within the tool are presented.

[1]  Giuseppe Lipari,et al.  Improved schedulability analysis of EDF on multiprocessor platforms , 2005, 17th Euromicro Conference on Real-Time Systems (ECRTS'05).

[2]  Leandros Tassiulas,et al.  Any work-conserving policy stabilizes the ring with spatial re-use , 1996, TNET.

[3]  Azer Bestavros,et al.  Safe compositional specification of networking systems , 2004, CCRV.

[4]  Jean-Yves Le Boudec,et al.  Network Calculus: A Theory of Deterministic Queuing Systems for the Internet , 2001 .

[5]  Lothar Thiele,et al.  Workload correlations in multi-processor hard real-time systems , 2007, J. Comput. Syst. Sci..

[6]  Paul Ward,et al.  Structured Development for Real-Time Systems , 1986 .

[7]  Kim G. Larsen,et al.  CyNC: A method for real time analysis of systems with cyclic data flows , 2006, J. Embed. Comput..

[8]  James W. Layland,et al.  Scheduling Algorithms for Multiprogramming in a Hard-Real-Time Environment , 1989, JACM.

[9]  Rene L. Cruz,et al.  A calculus for network delay, Part I: Network elements in isolation , 1991, IEEE Trans. Inf. Theory.

[10]  Ivar Jacobson,et al.  The Unified Modeling Language User Guide , 1998, J. Database Manag..

[11]  Lothar Thiele,et al.  Performance evaluation of network processor architectures: combining simulation with analytical estimation , 2003, Comput. Networks.

[12]  Henrik Schiøler,et al.  Traffic Analysis for Real-Time Communication Networks Onboard Ships , 1998 .

[13]  Kim G. Larsen,et al.  Introducing synchronisation in deterministic network models , 2006, ISCA International Conference on Computer Applications in Industry and Engineering.

[14]  Sanjoy K. Baruah,et al.  Algorithms and complexity concerning the preemptive scheduling of periodic, real-time tasks on one processor , 1990, Real-Time Systems.

[15]  ThieleLothar,et al.  Performance evaluation of network processor architectures , 2003 .

[16]  Hassan Gomaa.  Software design methods for concurrent and real-time systems , 1993, SEI series in software engineering.

[17]  Bran Selic,et al.  Real-time object-oriented modeling , 1994, Wiley professional computing.

[18]  John P. Lehoczky,et al.  The rate monotonic scheduling algorithm: exact characterization and average case behavior , 1989, [1989] Proceedings. Real-Time Systems Symposium.

[19]  Rajeev Alur,et al.  A Theory of Timed Automata , 1994, Theor. Comput. Sci..

[20]  Wang Yi,et al.  Uppaal in a nutshell , 1997, International Journal on Software Tools for Technology Transfer.

[21]  M. Diaz,et al.  Modeling and Verification of Time Dependent Systems Using Time Petri Nets , 1991, IEEE Trans. Software Eng..