Abstract
The architecture of modern automotive electronic systems is composed of multiple distributed mixed-criticality functions. The effective utilization of such systems with heterogeneity is hindered by the scheduling of multifunctions. Minimizing the response time of functions (e.g., makespan) is an important optimization objective, and several scheduling algorithms for heterogeneous distributed architectures that optimize this objective have been proposed. However, the reliability requirements of functions of automotive systems are also an vital objective that needs to be optimized. Ignoring the reliability requirements of the functions during the scheduling process can cause catastrophic consequences, especially in automotive electronic systems. We propose a heuristic scheduling algorithm called real-time aware scheduling under reliability requirement assurance (RTRRA). The proposed algorithm meets the reliability requirement of each function by reliability transfer method technique and reduces the high-criticality functions' deadline miss ratio (DMR) by applying resource reallocation policy. Our results indicate that the RTRRA can reduce the response time of critical functions and meet the reliability requirements of all functions compared with the state-of-the-art algorithms.
Highlights
INTRODUCTIONMany proposed heuristics are concentrated on single directed acyclic graph (DAG) task model multiprocessor scheduling that guarantees global system reliability and satisfies some real-time requirements [8], [9], [12], [13]
We aim to propose a method to reduce high-criticality functions’ deadline miss ratio (DMR) while ensuring reliability requirements of multifunctions
2) We propose a heuristic scheduling algorithm called real-time aware scheduling under reliability requirement assurance (RTRRA) to reduce DMR of high-criticality functions while guaranteeing reliability requirement of multifunctional mixed-criticality automotive electronic systems (AES)
Summary
Many proposed heuristics are concentrated on single directed acyclic graph (DAG) task model multiprocessor scheduling that guarantees global system reliability and satisfies some real-time requirements [8], [9], [12], [13]. In AES, reliability and response time requirements of each distributed scheduled function should be optimized simultaneously. 1) We propose a multifunctional mixed-criticality bicriteria (response time and reliability) scheduling framework for AES. In [9], authors present a fast functional safety verification method for a single distributed automotive application to find a solution satisfying response time and reliability requirements. In recently proposed multifunctional scheduling frameworks [3], [6], only response time requirements of functions are considered in task ordering and clustering phases.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.