Beyond the Accuracy-Complexity Tradeoffs of CompositionalAnalyses using Network Calculus for Complex Networks

Achieving the accuracy-complexity tradeoffs for compositional timing analyses using Network Calculus is still a hot research topic. In this specific area, we propose in this paper an improved version of the Total Flow Analysis (TFA) algorithm, called TFA++, when taking into account the impact of the finite transmission capacity of the network links on the input and output traffic models at each network node. First, we review the existing analysis algorithms by identifying their main limitations in terms of accuracy and complexity, through a simple but representative network example. Afterwards, we define the TFA++ algorithm and we detail the main steps of the followed methodology to compute the delay upper bounds. Moreover, we conduct comparative analyses of the derived delay bounds and analysis times with the different algorithms, with respect to the network size and load. In doing this, we highlight noticeable enhancements of both metrics under TFA++, in comparison to the existing algorithms; thus the high accuracy and low complexity of TFA++. Finally, this statement has been asserted through a representative avionics case.

[1]  Cheng-Shang Chang,et al.  Performance guarantees in communication networks , 2000, Eur. Trans. Telecommun..

[2]  J.-B. Grieu,et al.  Analyse et évaluation de techniques de commutation Ethernet pour l'interconnexion des systèmes avioniques , 2004 .

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

[4]  Ahlem Mifdaoui,et al.  Worst-case timing analysis of ring networks with cyclic dependencies using network calculus , 2017, 2017 IEEE 23rd International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA).

[5]  J. Loeser,et al.  Low-latency hard real-time communication over switched Ethernet , 2004 .

[6]  Giovanni Stea,et al.  Exact Worst-Case Delay in FIFO-Multiplexing Feed-Forward Networks , 2015, IEEE/ACM Transactions on Networking.

[7]  Luciano Lenzini,et al.  A methodology for computing end-to-end delay bounds in FIFO-multiplexing tandems , 2008, Perform. Evaluation.

[8]  Wenhua Dou,et al.  Analysis of Worst-Case Delay Bounds for On-Chip Packet-Switching Networks , 2010, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[9]  Jens B. Schmitt,et al.  The DISCO network calculator: a toolbox for worst case analysis , 2006, valuetools '06.

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

[11]  Jens B. Schmitt,et al.  Delay Bounds under Arbitrary Multiplexing: When Network Calculus Leaves You in the Lurch... , 2008, IEEE INFOCOM 2008 - The 27th Conference on Computer Communications.

[12]  Eric Thierry,et al.  Service curves in Network Calculus: dos and don'ts , 2009 .

[13]  Ivan Martinovic,et al.  Improving Performance Bounds in Feed-Forward Networks by Paying Multiplexing Only Once , 2008, MMB.

[14]  Lothar Thiele,et al.  Influence of different abstractions on the performance analysis of distributed hard real-time systems , 2009, Des. Autom. Embed. Syst..