A New Hybrid Approach on WCET Analysis for Real-Time Systems Using Machine Learning

Authors Thomas Huybrechts, Siegfried Mercelis, Peter Hellinckx

Thumbnail PDF


  • Filesize: 1.13 MB
  • 12 pages

Document Identifiers

Author Details

Thomas Huybrechts
  • University of Antwerp - imec, IDLab - Faculty of Applied Engineering, Belgium
Siegfried Mercelis
  • University of Antwerp - imec, IDLab - Faculty of Applied Engineering, Belgium
Peter Hellinckx
  • University of Antwerp - imec, IDLab - Faculty of Applied Engineering, Belgium

Cite AsGet BibTex

Thomas Huybrechts, Siegfried Mercelis, and Peter Hellinckx. A New Hybrid Approach on WCET Analysis for Real-Time Systems Using Machine Learning. In 18th International Workshop on Worst-Case Execution Time Analysis (WCET 2018). Open Access Series in Informatics (OASIcs), Volume 63, pp. 5:1-5:12, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2018)


The notion of the Worst-Case Execution Time (WCET) allows system engineers to create safe real-time systems. This value is used to schedule all software tasks before their deadlines. Failing these deadlines will cause catastrophic events, e.g. vehicle crashes, failing to detect dangerous anomalies, etc. Different analysis methodologies exist to determine the WCET. However, these methods do not provide early insight in the WCET during development. Therefore, pessimistic assumptions are made by system designers resulting in more expensive, overqualified hardware. In this paper, an extension on the hybrid methodology is proposed which implements a predictor model using Machine Learning (ML). This new approach estimates the WCET on smaller entities of the code, so-called hybrid blocks, based on software and hardware features. As a result, the ML-based hybrid analysis provides insight of the WCET early-on in the development process and refines its estimate when more detailed features are available. In order to facilitate the extraction of code-related features, a new tool for the COBRA framework is proposed. This paper proves the potential of the ML-based hybrid approach by conducting multiple experiments based on the TACLeBench on a first prototype. A set of annotated code features were used to train and validate eight different regression models. The results already show promising estimates without tuning any hyperparameters, proving the potential of the methodology.

Subject Classification

ACM Subject Classification
  • Computer systems organization → Embedded and cyber-physical systems
  • Worst-Case Execution Time
  • Machine Learning
  • Hybrid Analysis
  • Feature Selection
  • COde Behaviour fRamework


  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    PDF Downloads


  1. Peter Altenbernd et al. Early execution time-estimation through automatically generated timing models. Real-Time Systems, 52(6):731-760, Nov 2016. URL: http://dx.doi.org/10.1007/s11241-016-9250-7.
  2. B. W. Boehm et al. Software Engineering Economics. Prentice-Hall PTR, Englewood Cliffs, NJ, 1981. Google Scholar
  3. Armelle Bonenfant et al. Early WCET Prediction Using Machine Learning. In Jan Reineke, editor, 17th International Workshop on Worst-Case Execution Time Analysis (WCET 2017), volume 57, pages 5:1-5:9, 2017. URL: http://dx.doi.org/10.4230/OASIcs.WCET.2017.5.
  4. Yorick De Bock et al. Task-Set Generator for Schedulability Analysis using the TACLeBench benchmark suite. In Proceedings of the Embedded Operating Systems Workshop : EWiLi 2016, pages 1-6, 2016. URL: http://ceur-ws.org/Vol-1697/.
  5. H. Falk et al. TACLeBench: a benchmark collection to support worst-case execution time research. Proceedings of the 16th International Workshop on Worst-Case Execution Time Analysis (WCET'16), 2016. Google Scholar
  6. A. Géron. Hands-On Machine Learning with Scikit-Learn and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems. O'Reilly Media, 2017. Google Scholar
  7. David Griffin et al. Forecast-based Interference: Modelling Multicore Interference from Observable Factors. In Proceedings of the 25th International Conference on Real-Time Networks and Systems, RTNS '17, pages 198-207, 2017. URL: http://dx.doi.org/10.1145/3139258.3139275.
  8. Jan Gustafsson et al. Approximate Worst-Case Execution Time Analysis for Early Stage Embedded Systems Development, pages 308-319. Springer Berlin Heidelberg, Berlin, Heidelberg, 2009. URL: http://dx.doi.org/10.1007/978-3-642-10265-3_28.
  9. Isabelle Guyon and André Elisseeff. An Introduction to Variable and Feature Selection. J. Mach. Learn. Res., 3:1157-1182, 2003. Google Scholar
  10. Mark A. Hall. Correlation-based Feature Selection for Discrete and Numeric Class Machine Learning. In Proceedings of the 17th International Conference on Machine Learning, ICML '00, pages 359-366, San Francisco, CA, USA, 2000. Morgan Kaufmann Publishers Inc. Google Scholar
  11. T. Huybrechts et al. Hybrid Approach on Cache Aware Real-Time Scheduling for Multi-Core Systems. In Fatos Xhafa, Leonard Barolli, and Flora Amato, editors, Advances on P2P, Parallel, Grid, Cloud and Internet Computing, pages 759-768, Cham, 2017. Springer International Publishing. Google Scholar
  12. T. Huybrechts et al. COBRA-HPA: a Block Generating Tool to Perform Hybrid Program Analysis. Int. J. of Grid and Utility Computing, in press 2018. Google Scholar
  13. P. Lokuciejewski and P. Marwedel. Worst-Case Execution Time Aware Compilation Techniques for Real-Time Systems. Springer Netherlands, 2011. URL: http://dx.doi.org/10.1007/978-90-481-9929-7.
  14. Enrico Mezzetti and Tullio Vardanega. On the Industrial Fitness of WCET Analysis. In The 11th International Workshop on Worst-Case Execution Time Analysis (WCET), 2011. Google Scholar
  15. Terence Parr. The Definitive ANTLR 4 Reference. The Pragmatic Bookshelf, 2013. Google Scholar
  16. F. Pedregosa et al. Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research, 12:2825-2830, 2011. Google Scholar
  17. P. Puschner and Ch. Koza. Calculating the Maximum, Execution Time of Real-time Programs. Real-Time Systems, 1(2):159-176, 1989. URL: http://dx.doi.org/10.1007/BF00571421.
  18. Jan Reineke. Caches in WCET Analysis. PhD thesis, University of Saarlandes, 2008. Google Scholar
  19. Rob van der Meulen. Gartner Says 8.4 Billion Connected "Things" Will Be in Use in 2017, Up 31 Percent From 2016, 2017. URL: http://www.gartner.com/newsroom/id/3598917.
  20. Reinhard Wilhelm et al. The Worst-case Execution-time Problem - Overview of Methods and Survey of Tools. ACM Trans. Embed. Comput. Syst., 7(3):36:1-36:53, 2008. URL: http://dx.doi.org/10.1145/1347375.1347389.
  21. Dani Yogatama and Gideon Mann. Efficient Transfer Learning Method for Automatic Hyperparameter Tuning. In Proceedings of the 17th International Conference on Artificial Intelligence and Statistics, volume 33, pages 1077-1085, 2014. Google Scholar
Questions / Remarks / Feedback

Feedback for Dagstuhl Publishing

Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail