Implementation and Verification of the Slave Elementary Cycle Synchronization Mechanism of the Flexible Time-Triggered Replicated Star for Ethernet

Author Ines Alvarez Vadillo
Supervisor/s Julián Proenza Arenas | Manuel Alejandro Barranco González
In Universitat de les Illes Balears, 2014.

A distributed embedded system that must work in dynamic environments, where the working conditions may change in an unpredictable way, must be flexible. Moreover, if such system must operate continuously it must also be reliable. Therefore, its internal communication network must support both attributes. Unfortunately, nowadays it does not exist any communication network that completely fulfils both requirements.

The Flexible Time-Triggered (FTT) communication paradigm provides the system with support for time-triggered and event-triggered communication, as well as adaptability to environment changes. FTT can be deployed on top of any existing network technology. Implementing FTT on top of the Ethernet communication protocol offers a high bandwidth and a low cost of the components of the network. Nevertheless, FTT-Ethernet lacks the necessary fault-tolerance mechanisms to provide adequate dependability levels.

The Fault Tolerance for Flexible Time-Triggered Ethernet (FT4FTT) research project faces the development of the required fault tolerance mechanisms in order to construct a flexible and highly-dependable communication infrastructure based on FTT-Ethernet.

The Flexible Time-Triggered Replicated Star (FTTRS) was proposed as part of the FT4FTT project to provide adequate fault-tolerance mechanisms for the communication infrastructure. Among other features, FTTRS provides tolerance in front of transient faults in the channel. This is done by means of time and information redundancy. The Slave Elementary Cycle Synchronization Mechanism (SECSM) is a proposal to manage such redundancy that pays a special attention to achieve a proper synchronization among the nodes of the system. In this way all nodes have a similar view, even in the presence of faults, of when the different communication cycles start.

This project consisted in the implementation, validation and modification of the SECSM; as well as the later evaluation of the complete prototype that was built. The results of this project have been published in a conference paper that is attached as an appendix.


Uso de cookies

Este sitio web utiliza cookies para que usted tenga la mejor experiencia de usuario. Si continúa navegando está dando su consentimiento para la aceptación de las mencionadas cookies y la aceptación de nuestra política de cookies, pinche el enlace para mayor información.