Traffic class assignment for mixed-criticality frames in TTEthernet

In this paper we are interested in mixed-criticality applications, which have functions with different timing requirements, i.e., hard real-time (HRT), soft real-time (SRT) and functions that are not time-critical (NC). The applications are implemented on distributed architectures that use the TTEthernet protocol for communication. TTEthernet supports three traffic classes: Time-Triggered (TT), where frames are transmitted based on static schedule tables; Rate Constrained (RC), for dynamic frames with a guaranteed bandwidth and bounded delays; and Best Effort (BE), for which no timing guarantees are provided. HRT messages have deadlines, whereas for SRT messages we capture the quality-of-service using "utility functions". Given the network topology, the set of application messages and their routing, we are interested to determine the traffic class of each message, such that all HRT messages are schedulable and the total utility for SRT messages is maximized. For the TT frames we decide their schedule tables, and for the RC frames we decide their bandwidth allocation. We propose aTabu Search-based metaheuristic to solve this optimization problem. The proposed approach has been evaluated using several benchmarks, including two realistic test cases.

[1]  Hans A. Hansson,et al.  A decomposition approach for SMT-based schedule synthesis for time-triggered networks , 2015, 2015 IEEE 20th Conference on Emerging Technologies & Factory Automation (ETFA).

[2]  Petru Eles,et al.  Analysis and Optimisation of Hierarchically Scheduled Multiprocessor Embedded Systems , 2008, International Journal of Parallel Programming.

[3]  Christian Fraboul,et al.  Priority assignment on an avionics switched Ethernet Network (QoS AFDX) , 2014, 2014 10th IEEE Workshop on Factory Communication Systems (WFCS 2014).

[4]  Paul Pop,et al.  Timing Analysis of Rate Constrained Traffic for the TTEthernet Communication Protocol , 2015, 2015 IEEE 18th International Symposium on Real-Time Distributed Computing.

[5]  Jeffrey D. Ullman,et al.  NP-Complete Scheduling Problems , 1975, J. Comput. Syst. Sci..

[6]  Paul Pop,et al.  Design optimization of TTEthernet-based distributed real-time systems , 2014, Real-Time Systems.

[7]  Graham Kendall,et al.  Search Methodologies: Introductory Tutorials in Optimization and Decision Support Techniques , 2013 .

[8]  Martin Schoeberl,et al.  Time-division multiplexing vs network calculus: a comparison , 2015, RTNS.

[9]  Jean-Dominique Decotignie,et al.  Ethernet-Based Real-Time and Industrial Communications , 2005, Proceedings of the IEEE.

[10]  Giuseppe Lipari,et al.  Soft Real-Time Systems: Predictability vs. Efficiency (Series in Computer Science) , 2005 .

[11]  Silviu S. Craciunas,et al.  Combined task- and network-level scheduling for distributed time-triggered systems , 2016, Real-Time Systems.

[12]  John M. Rushby,et al.  Bus Architectures for Safety-Critical Embedded Systems , 2001, EMSOFT.

[13]  P.博布雷克 Avionics full-duplex switched ethernet network , 2013 .

[14]  Giorgio C. Buttazzo,et al.  FTT-Ethernet: a flexible real-time communication protocol that supports dynamic QoS management on Ethernet-based systems , 2005, IEEE Transactions on Industrial Informatics.

[15]  PopPaul,et al.  Traffic class assignment for mixed-criticality frames in TTEthernet , 2016 .