Design-Space Reduction for Architectural Optimization of Automotive Embedded Systems
2015 (English)In: High Performance Computing and Communications (HPCC), 2015 IEEE 7th International Symposium on Cyberspace Safety and Security (CSS), 2015 IEEE 12th International Conferen on Embedded Software and Systems (ICESS), 2015 IEEE 17th International Conference on, IEEE Computer Society, 2015, , 7 p.1103-1109 p.Conference paper (Refereed)
A key decision for the synthesis of automotiveembedded systems is the allocation of application softwarecomponents to ECUs. Design Space Exploration (DSE) supportsthe decision by automatically characterizing and evaluating alarge number of possible design alternatives, and thereby suggestingthe optimal ones. A primary challenge for applying DSEmethods to support this decision is to reduce the computationtime of the DSE process while maintaining the generality andoptimality. This paper exploits legacy system architectures andthe AUTOSAR standard to preemptively reduce the design space,because both artifacts limit the flexibility of certain designvariables. A new DES formulation incorporating the constraintsof the legacy system architectures and the AUTOSAR standardis proposed in this paper. Computation result shows a largereduction of the computation time comparing to traditionalmodeling and formulations. The scalability of our method is alsoanalyzed by testing it on a set of random problem instances.
Place, publisher, year, edition, pages
IEEE Computer Society, 2015. , 7 p.1103-1109 p.
Research subject Industrial Engineering and Management
IdentifiersURN: urn:nbn:se:kth:diva-177585DOI: 10.1109/HPCC-CSS-ICESS.2015.298ISI: 000380408100182ScopusID: 2-s2.0-84961717465OAI: oai:DiVA.org:kth-177585DiVA: diva2:873466
IEEE 12th International Conference on Embedded Softwareand Systems (ICESS), New York, August 24-26
QC 201512012015-11-242015-11-242016-09-05Bibliographically approved