DFT4FTT - Dynamic Fault Tolerance for increasing the adaptivity of highly-reliable distributed embedded systems based on Flexible Time-Triggered Ethernet

Design, evaluation, validation, implementation and verification of two types of fault tolerance mechanisms for systems based on FTT-Ethernet. On the one hand, some specifically designed for increasing the reliability of the part of the functionality of the network that is related to its flexibility and, on the other hand, some dynamic ones intended to increase the flexibility of the fault tolerance added to the system.

This work is supported in part by the Spanish Agencia Estatal de Investigación (AEI) and in part by FEDER funding through grant TEC2015-70313-R (AEI/FEDER, UE). Adaptive embedded systems should be able to automatically adjust their internal strategies in response to requirement changes. They require services supporting flexibility, real time and dependability at different levels of the system architecture, which in the case of distributed embedded systems (DESs) includes the network level. In this sense, there is still significant research pending to bring adaptivity to one of the most ubiquitous network technologies available, namely Ethernet, which is being used more and more as the underlying network technology for DESs. Specifically, there is a need for making Ethernet-based DESs capable not only of adapting to changing real-time requirements, but also of changing dependability, and especially reliability, requirements. This would allow an Ethernet-based DES to reallocate resources to make a certain more critical service more reliable if this is required. An example might be a car exposed to increased electromagnetic interference when traveling near power lines. Making a system more adaptive in terms of reliability can be achieved through so called dynamic fault tolerance. Thus, making an Ethernet-based DES both adaptive in terms of real-time and reliability can be achieved by providing dynamic fault tolerance to Ethernet technologies that already provide services for flexible real-time requirements. One such technology is FTT-Ethernet, since it provides communication services that allow the nodes of the system to change the real-time attributes of the exchanged messages without interrupting the service provided by the system. The goal of the predecessor project, FT4FTT-Ethernet (DPI2011-22992), was to make FTT-Ethernet highly reliable by using static, as opposed to dynamic, fault tolerance mechanisms. In contrast, this new project aims at improving FTT-Ethernet by providing it with dynamic fault tolerance mechanisms. This would allow FTT-Ethernet to be used as the underlying network for adaptive DESs that not only need to adapt to changing real-time requirements, but also to changing reliability ones.

R. Rotaeche, A. Ballesteros, J. Proenza. Exploring the use of Deep Reinforcement Learning to allocate tasks in Critical Adaptive Distributed Embedded Systems. Universitat de les Illes Balears, Palma de Mallorca, 2022.

R. Rotaeche, A. Ballesteros, J. Proenza. Speeding Task Allocation Search for Reconfigurations in Adaptive Distributed Embedded Systems Using Deep Reinforcement Learning. In Sensors, MDPI, vol. 23, no. 1, January, 2023 .

M. Costa, A. Ballesteros. Implementación y verificación de mecanismos para tolerar fallos en el canal de comunicaciones de manera dinámica en sistemas distribuidos empotrados de tiempo real críticos basados en Ethernet. Universitat de les Illes Balears, Palma de Mallorca, 2021.

A. Ballesteros, M. A. Barranco, J. Proenza, L. Almeida, F. Pozo, P. Palmer-Rodríguez. An Infrastructure for Enabling Dynamic Fault Tolerance in Highly-Reliable Adaptive Distributed Embedded Systems Based on Switched Ethernet. In Sensors, MDPI, vol. 22, no. 18, December, 2022 .

I. Álvarez, M. A. Barranco, J. Proenza. Reliability Analysis of the Proactive Transmission of Replicated Frames Mechanism over Time-Sensitive Networking. In Sensors, MDPI, vol. 21, no. 24, December, 2021 .

I. Álvarez, M. A. Barranco, J. Proenza. Dataset: Reliability Sensitivity Analyses of TSN and PTRF in the presence of temporary faults.

I. Álvarez, J. Proenza, M. A. Barranco. Time Redundancy Mechanisms for Tolerating Temporary Faults in the Communication Subsystem of Systems based on Time-Sensitive Networking Standards. University of the Balearic Islands, Ph. D. Thesis, 2021.

A. Servera, I. Álvarez, J. Proenza. Development of a Centralized Network Controller for Networks based on the Time-Sensitive Networking (TSN) Ethernet Standards. Universitat de les Illes Balears, M. Sc. Thesis, 2021.

R. Rotaeche, A. Ballesteros, J. Proenza. Exploring the use of Deep Reinforcement Learning to allocate tasks in Critical Adaptive Distributed Embedded Systems. In Proceedings of the IEEE 26th International Conference on Emerging Technologies and Factory Automation (ETFA 2021), Västerås (Sweden), 2021.

I. Álvarez, I. Furió, J. Proenza, M. A. Barranco. Design and Experimental Evaluation of the Proactive Transmission of Replicated Frames Mechanism over Time-Sensitive Networking. In Sensors, MDPI, vol. 21, no. 3, January, 2021 .

D. Bujosa, I. Álvarez, J. Proenza. CSRP: an Enhanced Protocol for Consistent Reservation of Resources in AVB/TSN. In IEEE Transactions on Industrial Informatics , vol. 17, no. 5, pp. 3640-3650, May, 2021 .

D. Bujosa, I. Álvarez, J. Proenza. Description of the UPPAAL Models for SRP and CSRP and Verification of their Termination and Consistency Properties. arXiv:2007.15712 [cs.NI], July, 2020 .

D. Bujosa, D. Hallmans, M. Ashjaei, A. Papadopoulos, J. Proenza, T. Nolte. Clock Synchronization in Integrated TSN-EtherCAT Networks. In 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA 2020), Vienna, 2020.

M. A. Barranco, S. Derasevic, J. Proenza. An Architecture for Highly Reliable Fault-Tolerant Adaptive Distributed Embedded Systems. In Computer, vol. 53, no. 3, pp. 38-46, March, 2020 .

I. Álvarez, L. Moutinho, P. Pedreiras, D. Bujosa, J. Proenza, L. Almeida. Comparing Admission Control Architectures for Real-Time Ethernet. In IEEEAccess, IEEE, vol. 8, pp. 105521-105534, June, 2020 .

T. Jorda, I. Álvarez, M. A. Barranco. Design, Implementation and Validation of a System to Automatically Configure the Scheduling of Real-Time Traffic in Time Sensitive Networking (TSN) Switches. Universitat de les Illes Balears, 2019.

D. Bujosa, I. Álvarez, J. Proenza. Estudio de la idoneidad del Stream Reservation Protocol para dar soporte a Sistemas Empotrados Distribuidos Críticos Adaptativos. Universitat de les Illes Balears, 2019.

A. Servera, A. Ballesteros. Design and Implementation of a Domotics System based on the Sentilo IoT Platform. Universitat de les Illes Balears, Palma de Mallorca, 2019.

J. Proenza, Y. González, P. Arguimbau. First exploration of the potential of diverse training and voting for increasing the accuracy of CNNs. In Proceedings of the IEEE 24th International Conference on Emerging Technologies and Factory Automation (ETFA 2019), Zaragoza, 2019.

A. Ballesteros, M. A. Barranco, S. Arguimbau, M. Costa, J. Proenza. Temporal Replication of Messages for Adaptive Systems using a Holistic Approach. In Proceedings of the IEEE 24th International Conference on Emerging Technologies and Factory Automation (ETFA 2019), Zaragoza, 2019.

D. Bujosa, S. Arguimbau, P. Arguimbau, J. Proenza, M. A. Barranco. Formal Verification of the FTTRS Mechanisms for the Consistent Update of the Traffic Schedule. In Proceedings of the IEEE 24th International Conference on Emerging Technologies and Factory Automation (ETFA 2019), Zaragoza, 2019.

D. Bujosa, I. Álvarez, D. Cavka, J. Proenza. Analysing Termination and Consistency in the AVB’s Stream Reservation Protocol. In Proceedings of the IEEE 24th International Conference on Emerging Technologies and Factory Automation (ETFA 2019), Zaragoza, 2019.

I. Álvarez, D. Cavka, J. Proenza, M. A. Barranco. Simulation of the Proactive Transmission of Replicated Frames Mechanism over TSN. In Proceedings of the IEEE 24th International Conference on Emerging Technologies and Factory Automation (ETFA 2019), Zaragoza, 2019.

A. Ballesteros, M. A. Barranco, S. Arguimbau, M. Costa, J. Proenza. Towards a Dynamic Replication of Messages in a Network with Flexible Real-Time Guarantees. In 17th International Workshop on Real-Time Networks (RTN 2019), Stuttgart, 2019.

D. Bujosa, D. Cavka, I. Álvarez, J. Proenza. First Analysis of the AVB’s Stream Reservation Protocol in the Context of TSN. In 17th International Workshop on Real-Time Networks (RTN 2019), 2019.

I. Álvarez, M. A. Barranco, J. Proenza. Towards a Fault-Tolerant Architecture based on Time-Sensitive Networking. In 4ª Edición de las Jornadas de ACM Celebrations: Informática para tod@s, A Coruña, Spain, 2019.

A. Ballesteros, J. Proenza, M. A. Barranco, L. Almeida, P. Palmer-Rodríguez. First Description of a Self-Reconfigurable Infrastructure for Critical Adaptive Distributed Embedded Systems. May, 2019.

D. Bujosa, D. Cavka, I. Álvarez, J. Proenza. First Analysis of the AVB’s Stream Reservation Protocol in the Context of TSN (Technical Report). May, 2019.

I. Álvarez, A. Ballesteros, M. A. Barranco, D. Gessner, S. Derasevic, J. Proenza. Fault Tolerance in Highly-Reliable Ethernet-based Industrial Systems. In Proceedings of the IEEE, vol. 107, no. 6, pp. 977-1010, June, 2019 .

S. Derasevic, M. A. Barranco, J. Proenza. Node Fault Tolerance for Distributed Embedded Systems based on FTT-Ethernet. University of the Balearic Islands, 2018.

I. Álvarez, M. A. Barranco, J. Proenza. Towards a Fault-Tolerant Architecture based on Time Sensitive Networking. In Proceedings of the IEEE 23rd International Conference on Emerging Technologies and Factory Automation (ETFA 2018), Torino, 2018.

D. Navarro, I. Furió, A. Ballesteros. Disseny i implementació d’una xarxa domòtica basada en Ethernet Industrial. Universitat de les Illes Balears, Palma de Mallorca, 2018.

D. Bujosa, S. Arguimbau, P. Arguimbau, J. Proenza, M. A. Barranco. Verification of the Schedule Consistent Update Mechanisms of FTTRS with UPPAAL. In 16th International Workshop on Real-Time Networks (RTN2018), Barcelona, 2018.

D. Cavka, I. Álvarez, J. Proenza. An OMNeT++ Simulation Model for the Proactive Transmission of Replicated Frames Mechanism over TSN. Illes Balears, 2018.

A. Ballesteros, J. Proenza, M. A. Barranco, L. Almeida, P. Palmer-Rodríguez. Towards a Self-Reconfigurable Infrastructure for Critical Adaptive Distributed Embedded Systems. In 16th International Workshop on Real-Time Networks (RTN 2018), Barcelona, 2018.

I. Álvarez, D. Cavka, J. Proenza, M. A. Barranco. First Study of the Proactive Transmission of Replicated Frames Mechanism over TSN. In 16th International Workshop on Real-Time Networks (RTN 2018), Barcelona, 2018.

I. Álvarez, J. Proenza, M. A. Barranco. Mixing Time and Spatial Redundancy over Time Sensitive Networking. In Proceedings of the 48th Annual IEEE/IFIP International Conference on Dependable Systems and Networks, Luxemburg, 2018.

A. Ballesteros, J. Proenza, M. A. Barranco, L. Almeida. Reconfiguration Strategies for Critical Adaptive Distributed Embedded Systems. In Proceedings of the 48th Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN 2018), Luxembourg, 2018.

I. Álvarez. Current Research on Dependability Aspects of TSN at UIB. .

S. Arguimbau, A. Ballesteros. Implementation and Validation of the Fundamental Mechanisms of the Flexible Time-Triggered Communication Paradigm for Ethernet-based Highly-Reliable Systems. Universitat de les Illes Balears, Palma de Mallorca, 2017.

D. Gessner, J. Proenza, M. A. Barranco. Adding Fault Tolerance To a Flexible Real-Time Ethernet Network for Embedded Systems. University of the Balearic Islands, 2017.

A. Ballesteros, J. Proenza, P. Palmer-Rodríguez. Towards a Dynamic Task Allocation Scheme for Highly-Reliable Adaptive Distributed Embedded Systems. In Proceedings of the 22th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA 2017), Limassol, 2017.

I. Álvarez, J. Proenza, M. A. Barranco, M. Knezic. Towards a Time Redundancy Mechanism for Critical Frames in Time-Sensitive Networking. In Proceedings of the 22nd IEEE International Conference on Emerging Technologies And Factory Automation (ETFA 2017), Cyprus, 2017.

I. Álvarez, J. Proenza, L. Almeida, M. Knezic. Estudio del Control de Admisión en los Protocolos de Comunicación Flexible Time-Triggered y Audio Video Bridging. In 2ª Edición de las Jornadas de ACM Celebrations: Informática para tod@s, Palma, Spain, 2017.

I. Álvarez, J. Proenza, L. Almeida. Study of the Admission Control in the Flexible Time-Triggered and the Audio Video Bridging Communication Protocols. Universitat de les Illes Balears, 2016.

M. A. Barranco, A. Zendouh, A. Ballesteros, J. Proenza. Improving Maintenance of FT4FTT: Extending it to Monitor and Log its Available Redundancy via Internet. In Proceedings of the 21th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA 2016), 2016.

I. Álvarez, M. Knezic, L. Almeida, J. Proenza. A First Performance Analysis of the Admission Control in the HaRTES Ethernet Switch. In Proceedings of the 21th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA 2016), 2016.

A. Ballesteros, S. Derasevic, M. A. Barranco, J. Proenza. First Implementation and Test of Reintegration Mechanisms for Node Replicas in the FT4FTT Architecture. In Proceedings of the 21th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA 2016), Berlin, 2016.

S. Derasevic, M. A. Barranco, J. Proenza. Designing fault-diagnosis and reintegration to prevent node redundancy attrition in highly reliable control systems based on FTT-Ethernet. In Proceedings of the 12th IEEE World Conference on Factory Communication Systems (WFCS 2016), Aveiro, 2016.

I. Álvarez, L. Almeida, J. Proenza. A First Qualitative Comparison of the Admission Control in FTT-SE, HaRTES and AVB. In Proceedings of the 12th IEEE World Conference on Factory Communication Systems (WFCS 2016), Aveiro, 2016.

A. Ballesteros, S. Derasevic, D. Gessner, F. Font, I. Álvarez, M. A. Barranco, J. Proenza. First Implementation and Test of a Node Replication Scheme on top of the Flexible Time-Triggered Replicated Star for Ethernet. In Proceedings of the 12th IEEE World Conference on Factory Communication Systems (WFCS 2016), Aveiro, 2016.