QoS-aware AFDX: benefits of an efficient priority assignment for avionics flows

نویسندگان

  • Tasnim Hamza
  • Jean-Luc Scharbarg
  • Christian Fraboul
چکیده

AFDX (Avionics Full Duplex Switched Ethernet) standardised as ARINC 664 is a major upgrade for avionics systems. The certification imposes to guarantee that the end-toend delay of any frame transmitted on the network is upperbounded and that no frame is lost due to buffer overflow. This guarantee is obtained thanks to a worst-case analysis assuming a FIFO scheduling policy of flows on each output port. For future aircraft, it is envisioned to modify AFDX switch and to use a Fixed Priority scheduling policy of flows (QoS AFDX using IEEE 802.p mechanisms). A worst-case analysis of such a network has been proposed, based on the Trajectory approach. But the remaining issue is to efficiently assign available priorities to the avionics flows inside the network without modifying the application knowledge. The objective is then to minimise overall the worst case end to end delay of flows and consequently to minimise needed buffer size at switch level. The main contribution of this paper deals with the assignment of priorities to the flows using the well-know Optimal Priority Assignment algorithm (OPA) which was first defined for monoprocessor preemptive systems. The schedulability test is then based on the worst case delay analysis of each flow allocated on the AFDX QoS network computed by the trajectory approach. The proposed mechanisms have been applied on an industrial AFDX case study using two priority levels and the overall worstcase delay could be reduced by 20 %.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Impact Analysis of Flow Shaping in Ethernet-AVB/TSN and AFDX from Network Calculus and Simulation Perspective

Ethernet-AVB/TSN (Audio Video Bridging/Time-Sensitive Networking) and AFDX (Avionics Full DupleX switched Ethernet) are switched Ethernet technologies, which are both candidates for real-time communication in the context of transportation systems. AFDX implements a fixed priority scheduling strategy with two priority levels. Ethernet-AVB/TSN supports a similar fixed priority scheduling with an ...

متن کامل

Towards Quality of Service Provision with Avionics Full Duplex Switching

Avionics Full-Duplex Switched Ethernet (AFDX) has been designed to carry exclusively time-critical flows dictated by the severe real-time constraints of avionics. Certification methods ensure end-to-end communication delays are upper bounded at the cost of an over-provision of network bandwidth. This paper investigates the issues related to the efficient use of such wasted communication capacit...

متن کامل

Worst-case backlog for AFDX network with n-priorities

In most recent avionics systems, AFDX (Avionics Full Duplex Switched Ethernet) is the network used to replace the previously employed point-to-point networks. AFDX guarantees bandwidth reservations by means of virtual links which can be classified with two priority levels. AFDX compliant switches implement output buffers at each switch output port. The stored frames leave each output port accor...

متن کامل

Incorporating TSN/BLS in AFDX for Mixed-Criticality Avionics Applications: Specification and Analysis

In this paper, we propose an extension of the AFDX standard, incorporating a TSN/BLS shaper, to homogenize the avionics communication architecture, and enable the interconnection of different avionics domains with mixed-criticality levels, e.g., legacy AFDX traffic, Flight Control and In-Flight Entertainment. First, we present the main specifications of such a proposed solution. Then, we detail...

متن کامل

Combining static priority and weighted round-robin like packet scheduling in AFDX for incremental certification and mixed criticality support

Avionics Full DupleX (AFDX) is an aeronautic-specific switched Ethernet technology that provides data exchanges among avionics sub-systems with bounded latencies, without requiring the sub-systems to share a common global clock like in TDMA networks. These predictable latencies can be achieved because the workload submitted to the network by each sub-system is upper bounded and known in advance...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2015