Reference : On the use of supervised machine learning for assessing schedulability: application t...

	Document type :	Scientific congresses, symposiums and conference proceedings : Paper published in a book
	Discipline(s) :	Engineering, computing & technology : Computer science
	Focus Areas :	Security, Reliability and Trust
	To cite this reference:	http://hdl.handle.net/10993/40154

Title :	On the use of supervised machine learning for assessing schedulability: application to Ethernet TSN
Language :	English
Author, co-author :	Mai, Tieu Long [University of Luxembourg > Faculty of Science, Technology and Communication (FSTC) > Computer Science and Communications Research Unit (CSC) >]
	Navet, Nicolas [University of Luxembourg > Faculty of Science, Technology and Communication (FSTC) > Computer Science and Communications Research Unit (CSC) >]
	Migge, Jörn [RealTime-at-Work (RTaW)]
Publication date :	2019
Main document title :	27th International Conference on Real-Time Networks and Systems (RTNS 2019)
Peer reviewed :	Yes
Audience :	International
Event name :	27th International Conference on Real-Time Networks and System (RTNS 2019)
Event date :	from 06-11-2019 to 08-11-2019
Keywords :	[en] Real-time systems ; timing verification ; machine learning ; Time-Sensitive Networking (TSN) ; schedulability analysis ; in-vehicle networks
Abstract :	[en] In this work, we ask if Machine Learning (ML) can provide a viable alternative to conventional schedulability analysis to determine whether a real-time Ethernet network meets a set of timing constraints. Otherwise said, can an algorithm learn what makes it difficult for a system to be feasible and predict whether a configuration will be feasible without executing a schedulability analysis? To get insights into this question, we apply a standard supervised ML technique, k-nearest neighbors (k-NN), and compare its accuracy and running times against precise and approximate schedulability analyses developed in Network-Calculus. The experiments consider different TSN scheduling solutions based on priority levels combined for one of them with traffic shaping. The results obtained on an automotive network topology suggest that k-NN is efficient at predicting the feasibility of realistic TSN networks, with an accuracy ranging from 91.8% to 95.9% depending on the exact TSN scheduling mechanism and a speedup of 190 over schedulability analysis for 10^6 configurations. Unlike schedulability analysis, ML leads however to a certain rate "false positives'' (i.e., configurations deemed feasible while they are not). Nonetheless ML-based feasibility assessment techniques offer new trade-offs between accuracy and computation time that are especially interesting in contexts such as design-space exploration where false positives can be tolerated during the exploration process.
Target :	Researchers ; Professionals
Permalink :	http://hdl.handle.net/10993/40154
DOI :	10.1145/3356401.3356409

	File(s) associated to this reference
	Fulltext file(s): File Commentary Version Size Access Open access Supervised-Learning-RTNS2019.pdf Author preprint 1.49 MB View/Open

All documents in ORBi^lu are protected by a user license.

 

University of Luxembourg Library |  Feedback |  Legal notices Site Map