In this paper we study a general energy minimization problem for mixed-criticality systems on multi-cores, considering different system operation modes, and static & dynamic energy consumption. While making global scheduling decisions, trade-offs in energy consumption between different modes and also between static and dynamic energy consumption are required. Thus, such a problem is challenging. To this end, we first develop an optimal solution analytically for unicore and a corresponding low-complexity heuristic. Leveraging this, we further propose energy-aware mapping techniques and explore energy savings for multi-cores. To the best of our knowledge, we are the first to investigate mixed-criticality energy minimization in such a general setting. The effectiveness of our approaches in energy reduction is demonstrated through both extensive simulations and a realistic industrial application.
Original languageEnglish
Title of host publication2016 IEEE Real-Time and Embedded Technology and Applications Symposium, RTAS 2016
EditorsR Davis
Place of PublicationPiscataway, NJ, USA
Number of pages12
ISBN (Electronic)978-1-4673-8641-8
ISBN (Print)978-1-4673-8639-5
Publication statusPublished - 2016
Event22th IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS'16) - Vienna, Austria
Duration: 11 Apr 201614 Apr 2016


Conference22th IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS'16)

    Research areas

  • Energy consumption, Job shop scheduling, Minimization, Power demand, Processor scheduling, Program processors, Vehicle dynamics

ID: 7745078