Offset scheduling for AFDX: definition, response time computation, and evaluation

Date

2025-8-14

Author

Elgin, Muhammed Fatih

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

12990
views

0
downloads

Cite This

Modern aircrafts require the integration of diverse and high-volume data, both internal and external, to support advanced functionalities and safety-critical operations. Traditional avionic network standards such as ARINC-429 and MIL-STD-1553B are no longer adequate to meet the increasing data transmission demands. Avionics Full Duplex Switched Ethernet (AFDX) has emerged as a promising solution due to its high bandwidth, scalability, and robustness. However, ensuring deterministic communication and bounding end-to-end latency are essential, especially in the context of certification and real-time constraints. This thesis introduces a novel method to reduce the worst-case end-to-end delay in AFDX networks by employing offset scheduling at the end systems. Through detailed analysis, queuing delay variability is identified as a major contributor to overall latency. By assigning time offsets to virtual links within the same end system, burstiness is minimized, thereby reducing contention and delay at switch output ports. An analytical method is also proposed to compute worst-case end-to-end delays for frames under offset scheduling. The method incorporates technological delays, transmission times, and queuing effects at each switch using extended arrival patterns based on Maximum Interference Functions (MIF), Interference MIF (IMIF), and serialization effects. Internal clock drift is accounted for by evaluating multiple source pattern offsets. The overall delay is obtained by adding delays across the path of the frame. Moreover, the proposed method is validated on two representative configurations and its performance is compared against existing methods across three distinct network scenarios, including a realistic avionic network.

Subject Keywords

AFDX, Avionics, Worst-case delay, Offset scheduling, Real-time network

URI

https://hdl.handle.net/11511/115594

Collections

Graduate School of Natural and Applied Sciences, Thesis