Loading...

Energy-aware Task Mapping and Scheduling in Mixed-criticality Multi-core Embedded Systems

Sobhani, Hoora | 2019

661 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 51757 (19)
  4. University: Sharif University of Technology
  5. Department: Computer Engineering
  6. Advisor(s): Hessabi, Shaahin
  7. Abstract:
  8. Mixed-criticality embedded systems, as the next-generation of safety-critical systems, are increasingly employed in industry due to consolidating functionalities with varying criticality levels onto the same computing platform. Also, cost reduction and performance improvement encourage adoption of multicore platforms in these systems. Technology scaling, battery-supplied design and heavy computation in mixed-criticality systems necessitates employing energy management techniques. Due to the degrading effects of these techniques on the system’s reliability, reducing energy consumption without sacrificing the reliability requirement is a vital challenge in mixed-criticality systems, in addition to guaranteeing task deadlines. In this thesis, we propose a novel preference-oriented task mapping and scheduling approach in multicore mixed-criticality systems with three levels of criticality with a reliability-aware energy management method. To guarantee the desired QoS of lower levels of criticality, our approach exploits the degraded WCET for these imprecise mixed-criticality tasks in critical modes. In design time, tasks are mapped on cores based on dynamic switching between different system utilizations in different modes. In each core, task instances are scheduled according to their virtual deadlines, which are calculated based on the system’s overrun tolerance limit (TL) and the desired QoS, by time reservation. Then, our heuristic DVFS techniques are applied, which reduce the processors frequencies down to f_th which is the minimum required frequency to carry out reliability-aware energy management. In runtime, besides minimizing energy consumption and guaranteeing real-time requirement and reliability levels in the normal mode, our gradual scenario is applied in critical modes according to simultaneous management of reliability and real-time requirements. Our experiments show that the proposed mapping and scheduling approach is more powerful than previous approaches, and the proposed reliability-aware energy management method is more compatible with this approach rather than others. Our method provides on average by 41.5% energy savings compared to other with 100% QoS degradation in lower levels of criticality. With guaranteeing the system’s desired QoS, our method provides on average by 38% energy savings compared to other approaches
  9. Keywords:
  10. Mixed-Criticality Emdedded Systems ; Multi-Core Platforms ; Preference-Oriented Scheduling ; Preference-Oriented Scheduling ; Reliability Aware Energy Management

 Digital Object List

 Bookmark

No TOC