Avionics Full Duplex switched Ethernet (AFDX) is the de facto standard for the transmission of critical avionics flows. It is a specific switched Ethernet solution based on First-in First-out (FIFO) scheduling. Worst-case traversal time (WCTT) analysis is mandatory for such flows, since timing constraints have to be guaranteed. A classical approach in this context is Network Calculus (NC). However, NC introduces some pessimism in the WCTT computation. Moreover, the worst-case often corresponds to very rare scenarios. Thus, the network architecture is most of the time lightly loaded. Typically, less than 10 % of the available bandwidth is used for the transmission of avionics flows on an AFDX network embedded in an aircraft. One solution to improve the utilization of the network is to introduce Quality of Service (QoS) mechanisms. Deficit Round Robin (DRR) is such a mechanism and it is envisioned for future avionics networks. A WCTT analysis has been proposed for DRR. It is based on NC. It doesn't make any assumption on the scheduling of flows by end systems. The first contribution of this paper is to identify sources of pessimism of this approach and to propose an improved solution which removes part of this pessimism. The second contribution is to show how the scheduling of flows can be integrated in this optimized DRR approach, thanks to offsets. An evaluation on a realistic case study shows that both contributions bring significantly tighter bounds on worst-case latencies. Index Terms-Deficit Round Robin, Network Calculus, worstcase traversal time, switched Ethernet network, offsets

Avionics Full Duplex switched Ethernet (AFDX) is the de facto standard for the transmission of critical avionics flows. It is a specific switched Ethernet solution based on First-in First-out (FIFO) scheduling. Timing constraints have to be guaranteed for such critical flows. The worst-case traversal time analysis introduces some pessimism, leading to a very lightly loaded network: typically less than 10 % of the bandwidth is used. One solution to improve the utilisation of the network is to introduce Quality of Service (QoS) mechanisms. First, it can decrease worst-case delays for the most constrained avionics flows. Second less/non critical additional flows can be transmitted on the network with bounded impact on avionics ones. Deficit Round Robin (DRR) is such a QoS mechanism and it is envisioned for future avionics networks. An optimised WCTT analysis has been proposed for DRR on AFDX, based on network calculus. With DRR, the flow set is divided into classes and each class is allocated a quantum. In each round, transmissions are managed, based on these quanta. Thus delays are significantly impacted by quanta. The contribution of this paper is to propose an efficient quantum assignment for a set of critical avionics flow classes and at most one additional class with less/non critical flows.

Nowadays, a real-time embedded system often has to cope with flows with different criticality levels. Such a situation is forecasted for next generation avionics networks, in order to better use communication resources. Indeed, the present situation, where the Avionics Full Duplex switched Ethernet (AFDX) network is reserved for critical avionics flows, leads to a very lightly loaded network.Quality of Service (QoS) mechanisms such as service disciplines are mandatory in order to cope with the heterogeneous constraints of the different kinds of flows. Weighted Round Robin (WRR) is envisioned in the context of avionics.Worst-case traversal time (WCTT) analysis is mandatory to ensure that temporal constraints of flows are met. Network Calculus (NC) is a popular solution for this analysis and results exist for WRR. They lead to pessimistic upper bounds.The main contribution of this paper is to show how existing NC results for WRR can be applied and improved in the context of an avionics configuration. The resulting analysis is evaluated on an industrial size configuration.