|
|
|
|
| Bachelorprojekt - Softwareteknologi | Project No. 0239: |
| Aktuelle | Tidligere |
Time-Sensitive Networking (TSN) [1] is an upcoming set of Ethernet standards designed for real-time and safety-critical applications, used in domains such as automotive, industrial automation, avionics and aerospace. It must comply with strong real-time requirements, thus validating end-to-end latency bounds of streams is particular important.
Network Calculus (NC) [2] is a mature min-plus algebra-based theory proposed for deterministic performance analysis, such as the computation of the worst-case latency of a flow transmitted over a network. The approach in network calculus is to construct appropriate arrival and service curve models for the investigated flows and network nodes. On one aspect, it is a good method for the timing verification; on the other aspect, it can be used as the feedback for the configuration of the network, if the timing requirements are violated.
Constraint Programming (CP) [3] is an approach for formulating and solving discrete variable constraint satisfaction or constrained optimization problems that allows for a wide variety of constraints. It is a good method used for scheduling and configuration problem in TSN networks.
There are several existing NC-based timing analysis tools and configuration scheduling tools for TSN networks. However, they are independent from each other. Thus when configuring, it needs to constantly call the timing analysis tool, which is very time consuming.
The purpose of this project is to construct constraints related to the Network Calculus formula into the Constraint Programming, to reduce the search space in order to improve the speed for network configuration.
[1]: TSN Task Group. Time-Sensitive Networking. 2017 www.ieee802.org/1/pages/tsn.html
[2]: [2]: J. Y. Le Boudec, and P. Thiran, "Network Calculus: A Theory of Deterministic Queuing Systems for the Internet," Springer-Verlag Lecture Notes in Computer Science, 5th ed., ISBN: 3-540-42184-X, 2001.
[3]: Google OR-tools. https://developers.google.com/optimization
Supervisor(s) Paul Pop
| Sidst opdateret: Nov 6, 2020 af Hans Henrik Løvengreen |