2026-07-23T05:17:59Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:23598 2025-10-27T10:21:56Z ddc:004 open_access

Detecting Low-Density Mixtures in High-Quantile Tails for pWCET Estimation Manau, Blau Vilardell, Sergi Serra, Isabel Mezzetti, Enrico Abella, Jaume Cazorla, Francisco J. WCET EVT The variability arising from sophisticated hardware and software solutions in cutting-edge embedded products causes software to exhibit complex execution time distributions. Mixture distributions can happen, with different density (weight), as a result of inherent different features in the execution platform and multiple operational scenarios. In the context of probabilistic WCET (pWCET) analysis based on Extreme Value Theory (EVT), where identical distribution is a pre-requisite, mixtures are typically intercepted by applying stationarity tests on the full sample. Those tests, however, are instructed to detect only mixtures with sufficiently high probability (weight) and disregard low-density mixtures (which are unlikely to be preserved in the high-quantile tail of the sample) as they would prevent any form of stationarity. Nonetheless, low-density mixture distributions can persist and even exacerbate in the tail, and, when not considered, they can impair pWCET estimation in EVT-based approaches, leading to overly pessimistic or optimistic bounds. In this work, we propose TailID, an iterative point-wise approach that builds on the asymptotic convergence of the Maximum Likelihood Estimator (MLE) of the Extreme Value Index (EVI) parameter ξ to detect low-density mixture distributions on high-quantile tails and use this information to steer EVT tail selection. The benefits of the proposed method are assessed on synthetic mixture distributions and real data collected on an industrially representative embedded platform. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Blau Manau and Sergi Vilardell and Isabel Serra and Enrico Mezzetti and Jaume Abella and Francisco J. Cazorla 2025 Is Part Of LIPIcs, Volume 335, 37th Euromicro Conference on Real-Time Systems (ECRTS 2025) InProceedings Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/LIPIcs.ECRTS.2025.20 urn:nbn:de:0030-drops-235982 https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ECRTS.2025.20 eng https://creativecommons.org/licenses/by/4.0/legalcode