The Safe and Effective Use of Low-Assurance Predictions in Safety-Critical Systems

Autor:	Agrawal, Kunal, Baruah, Sanjoy, Bender, Michael A., Marchetti-Spaccamela, Alberto
Jazyk:	angličtina
Rok vydání:	2023
Předmět:	Algorithms using predictions on-line scheduling Software and its engineering → Scheduling classification energy minimization Computer systems organization → Real-time systems robust scheduling
DOI:	10.4230/lipics.ecrts.2023.3
Popis:	The algorithm-design paradigm of algorithms using predictions is explored as a means of incorporating the computations of lower-assurance components (such as machine-learning based ones) into safety-critical systems that must have their correctness validated to very high levels of assurance. The paradigm is applied to two simple example applications that are relevant to the real-time systems community: energy-aware scheduling, and classification using ML-based classifiers in conjunction with more reliable but slower deterministic classifiers. It is shown how algorithms using predictions achieve much-improved performance when the low-assurance computations are correct, at a cost of no more than a slight performance degradation even when they turn out to be completely wrong. LIPIcs, Vol. 262, 35th Euromicro Conference on Real-Time Systems (ECRTS 2023), pages 3:1-3:19
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::014f069e017b81562e26a30e490a191a Zobrazit plný text záznamu