Jean-Luc Scharbarg

Methods for bounding end-to-end delays on an AFDX network

Architectures of avionics networks, such as that of the Airbus A380, currently know important evolutions. This is principally due to the increase in the complexity of the embedded systems, in term of rise in number of integrated functions and their connectivity. The evolution of switched Ethernet technologies allows their implementation as an avionics architecture (AFDX: avionics full duplex switched Ethernet). The problem is then to prove that no frame is lost by the network (no switch queue will overflow) and to evaluate the end-to-end transfer delay through the network. The objective of this paper is to present and shortly compare three methods for the evaluation of end-to-end delays: network calculus, queuing networks simulation and model checking

Improving the Worst-Case Delay Analysis of an AFDX Network Using an Optimized Trajectory Approach

Avionics Full Duplex Switched Ethernet (AFDX) standardized as ARINC 664 is a major upgrade for avionics systems. The mandatory certification implies a worst-case delay analysis of all the flows transmitted on the AFDX network. Up to now, this analysis is done thanks to a tool based on a Network Calculus approach. The more recent Trajectory approach has been proposed for the computation of worst-case response time in distributed systems. This paper shows how the worst-case delay analysis of the AFDX can be improved using an optimized Trajectory approach. The Network Calculus and the Trajectory approaches are compared on a real avionics AFDX configuration. Moreover, an evaluation of an upper bound of the pessimism of each approach is proposed.

A Probabilistic Analysis of End-To-End Delays on an AFDX Avionic Network

AFDX (Avionics Full DupleX Switched Ethernet, ARINC 664) developed for the Airbus A380 represents a major upgrade in both bandwidth and capability. Its reliance on Ethernet technology helps to lower some implementation costs, but guaranteed service presents challenges for system designers. An analysis of end-to-end transfer delays through the network is required in order to determine upper bounds. In this paper, we propose to compute probabilistic upper bounds for end-to-end delays on avionic flows. Such upper bounds can be exceeded with a given probability p, and are relevant in the context of avionics, where functions are designed to give accurate results even if they miss some frames. The stochastic network calculus approach analytically determines a probabilistic upper bound, whereas the simulation approach gives an experimental upper bound. The former may be used for new certification needs since it assures that the probability of exceeding the computed upper bound is not greater than p. The latter closely approximates actual network behavior and can help to give some idea of the pessimism of the stochastic network calculus upper bound. The two approaches have been developed in the context of an industrial AFDX network configuration.

Applying and optimizing trajectory approach for performance evaluation of AFDX avionics network

AFDX (Avionics Full Duplex Switched Ethernet) standardized as ARINC 664 is a major upgrade for avionics systems. But network delay analysis is required to evaluate end-to-end delays upper bounds. The Network Calculus approach, that has been used to evaluate such end-to-end delay upper bounds for certification purposes, is shortly described. In this paper we present how the Trajectory approach can be applied to an AFDX avionics network. Moreover we explain how this approach can be optimized in this context. We show that, on an industrial configuration, it outperforms existing end-to-end delays upper bounds.

Applying Trajectory approach with static priority queuing for improving the use of available AFDX resources

AFDX (Avionics Full Duplex Switched Ethernet) standardized as ARINC 664 is a major upgrade for avionics systems. The mandatory certification implies a worst-case delay analysis of all the flows transmitted on the AFDX network. Up to now, this analysis is done thanks to a tool based on a Network Calculus approach. The more recent Trajectory approach has been proposed for the computation of worst-case response time in distributed systems. It has been shown that the worst-case delay analysis of an AFDX network can be improved using an optimized Trajectory approach. This paper extends this optimized approach with the integration of static priority QoS policies. This extension makes possible to compute the bounds needed for deterministic avionics flows (high priority) when (lower priority) non avionics flows are added. Moreover, the paper provides an analysis of the pessimism of the obtained bounds.

Improving end-to-end delay upper bounds on an AFDX network by integrating offsets in worst-case analysis

AFDX (Avionics Full Duplex Switched Ethernet) standardized as ARINC 664 is a major upgrade for avionics systems. The mandatory certification implies a worst-case delay analysis of all the flows transmitted on the AFDX network. Up to now, this analysis is done thanks to a tool based on the Network Calculus approach. This existing approach considers that all the flows transmitted on the network are asynchronous and it does not take into account the scheduling of output flows done by each end system. The main contribution of this paper is to extend the existing Network Calculus approach by introducing the offsets associated to the different periodic flows into the computation. The resulting approach is evaluated on an industrial AFDX configuration with an existing offset assignment algorithm. The obtained upper bounds are significantly reduced.

CAN-Ethernet architectures for real-time applications

Embedded systems have specific real-time requirements that led to the development of dedicated communication protocols. Such systems must face increasing communication needs and the evolution of switched Ethernet architecture. But moving from existing dedicated field-busses architectures to new Ethernet based architectures is not always feasible, due to industrial constraints. In this paper, we compare different solutions for integrating existing data busses (such as CAN, which is an important standard in automotive context) on a global architecture that respects increasing bandwidth requirements. In a first step, we study classical CAN/CAN bridging strategies. In a second step, we propose CAN/Ethernet bridging strategies that respect the real time behavior of CAN End System when communicating through an Ethernet network that can be shared by (non CAN) applications

Designing specific systolic arrays with the API15C chip

The API15C processor, a building block for different systolic structures, is designed exclusively for single-instruction-multiple data (SIMD) execution mode. To support this mode, the instruction set includes special control instructions. Three parallel I/O ports are available for different interconnection schemes. The API15C chip is designed in a CMOS 2- mu m technology. It contains 45000 transistors on a 6-mm

Worst-case end-to-end delay analysis of an avionics AFDX network

M6.2-mm silicon area. The functionality of the circuit was tested successfully after the first run. It executes one instruction per clock phase of 100 ns, giving a global rate of 10 MIPS. To validate this processing element as a building block for systolic structures, a programmable interface and two single board machines were developed. The first is an 18 processor linear structure able to support a wide range of applications. The second is a 28 processor bidimensional structure for a specific application of string comparison. The instruction set is particularly well-suited for SIMD operation.<<ETX>>

Probabilistic upper bounds for heterogeneous flows using a static priority queueing on an AFDX network

AFDX (Avionics Full Duplex Switched Ethernet) standardized as ARINC 664 is a major upgrade for avionics systems. But network delay analysis is required to evaluate end-to-end delays upper bounds. The Network Calculus approach, that has been used to evaluate such end-to-end delay upper bounds for certification purposes, is shortly described. The Trajectory approach is an alternative method that can be applied to an AFDX avionics network. We show on an industrial configuration, in which cases the Trajectory approach outperforms the existing end-to-end delays upper bounds and how the combination of the two methods can lead to an improvement of the existing analysis.