Context-aware Graceful Degradation for Mixed-Criticality Scheduling in Autonomous Systems

Jie Zou; Xiaotian Dai; John Alexander McDermid

doi:10.1109/TCAD.2023.3330113

Context-aware Graceful Degradation for Mixed-Criticality Scheduling in Autonomous Systems

Jie Zou, Xiaotian Dai, John Alexander McDermid

Research output: Contribution to journal › Article › peer-review

Abstract

Autonomous systems are of high complexity and often regarded as mixed-criticality systems (MCS) in which functions are allocated criticality levels according to risk assessment based on safety standards. Typically, tasks have different realtime requirements across criticality levels, and the estimated worst-case execution times (WCETs) are distinct. Further, limitations in computational resources increase the difficulty of integrating tasks onto one shared hardware platform. Conventionally, all non-safety critical tasks must be discarded or suspended to guarantee the execution of safety-critical tasks when facing a timing fault. This typically leads to a considerable decrease in the system’s Quality-of-Service (QoS). Achieving more graceful degradation is critical to minimising QoS reduction. This work focuses on tackling timing faults and proposes a novel graceful degradation strategy for use in a mixed-criticality context. Thus, when a system has multiple operational modes depending on the environment or an operational task, our approach can give an effective way of managing degradation to maximise QoS, which is currently not sufficiently recognised in MCS. Furthermore, the proposed causality analysis-based degradation process “bridges the gap” so functional dependencies are considered in scheduling design and thus leads to a graceful degradation that is both feasible and reasonable in functional and non-functional terms. The evaluations show that QoS can be better preserved using the proposed context-aware degradation process when compared with more conventional MCS scheduling approaches.

Original language	English
Journal	IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
DOIs	https://doi.org/10.1109/TCAD.2023.3330113
Publication status	Published - 7 Nov 2023

Keywords

Task analysis , Degradation , Quality of service , Timing , Safety , Sensors , Standards

Access to Document

10.1109/TCAD.2023.3330113Licence: Unspecified

Cite this

@article{d02c458f722a4da896b57d293e83fcc7,

title = "Context-aware Graceful Degradation for Mixed-Criticality Scheduling in Autonomous Systems",

abstract = "Autonomous systems are of high complexity and often regarded as mixed-criticality systems (MCS) in which functions are allocated criticality levels according to risk assessment based on safety standards. Typically, tasks have different realtime requirements across criticality levels, and the estimated worst-case execution times (WCETs) are distinct. Further, limitations in computational resources increase the difficulty of integrating tasks onto one shared hardware platform. Conventionally, all non-safety critical tasks must be discarded or suspended to guarantee the execution of safety-critical tasks when facing a timing fault. This typically leads to a considerable decrease in the system{\textquoteright}s Quality-of-Service (QoS). Achieving more graceful degradation is critical to minimising QoS reduction. This work focuses on tackling timing faults and proposes a novel graceful degradation strategy for use in a mixed-criticality context. Thus, when a system has multiple operational modes depending on the environment or an operational task, our approach can give an effective way of managing degradation to maximise QoS, which is currently not sufficiently recognised in MCS. Furthermore, the proposed causality analysis-based degradation process “bridges the gap” so functional dependencies are considered in scheduling design and thus leads to a graceful degradation that is both feasible and reasonable in functional and non-functional terms. The evaluations show that QoS can be better preserved using the proposed context-aware degradation process when compared with more conventional MCS scheduling approaches.",

keywords = "Task analysis , Degradation , Quality of service , Timing , Safety , Sensors , Standards",

author = "Jie Zou and Xiaotian Dai and McDermid, {John Alexander}",

year = "2023",

month = nov,

day = "7",

doi = "10.1109/TCAD.2023.3330113",

language = "English",

journal = "IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems",

issn = "0278-0070",

publisher = "IEEE",

}

TY - JOUR

T1 - Context-aware Graceful Degradation for Mixed-Criticality Scheduling in Autonomous Systems

AU - Zou, Jie

AU - Dai, Xiaotian

AU - McDermid, John Alexander

PY - 2023/11/7

Y1 - 2023/11/7

N2 - Autonomous systems are of high complexity and often regarded as mixed-criticality systems (MCS) in which functions are allocated criticality levels according to risk assessment based on safety standards. Typically, tasks have different realtime requirements across criticality levels, and the estimated worst-case execution times (WCETs) are distinct. Further, limitations in computational resources increase the difficulty of integrating tasks onto one shared hardware platform. Conventionally, all non-safety critical tasks must be discarded or suspended to guarantee the execution of safety-critical tasks when facing a timing fault. This typically leads to a considerable decrease in the system’s Quality-of-Service (QoS). Achieving more graceful degradation is critical to minimising QoS reduction. This work focuses on tackling timing faults and proposes a novel graceful degradation strategy for use in a mixed-criticality context. Thus, when a system has multiple operational modes depending on the environment or an operational task, our approach can give an effective way of managing degradation to maximise QoS, which is currently not sufficiently recognised in MCS. Furthermore, the proposed causality analysis-based degradation process “bridges the gap” so functional dependencies are considered in scheduling design and thus leads to a graceful degradation that is both feasible and reasonable in functional and non-functional terms. The evaluations show that QoS can be better preserved using the proposed context-aware degradation process when compared with more conventional MCS scheduling approaches.

AB - Autonomous systems are of high complexity and often regarded as mixed-criticality systems (MCS) in which functions are allocated criticality levels according to risk assessment based on safety standards. Typically, tasks have different realtime requirements across criticality levels, and the estimated worst-case execution times (WCETs) are distinct. Further, limitations in computational resources increase the difficulty of integrating tasks onto one shared hardware platform. Conventionally, all non-safety critical tasks must be discarded or suspended to guarantee the execution of safety-critical tasks when facing a timing fault. This typically leads to a considerable decrease in the system’s Quality-of-Service (QoS). Achieving more graceful degradation is critical to minimising QoS reduction. This work focuses on tackling timing faults and proposes a novel graceful degradation strategy for use in a mixed-criticality context. Thus, when a system has multiple operational modes depending on the environment or an operational task, our approach can give an effective way of managing degradation to maximise QoS, which is currently not sufficiently recognised in MCS. Furthermore, the proposed causality analysis-based degradation process “bridges the gap” so functional dependencies are considered in scheduling design and thus leads to a graceful degradation that is both feasible and reasonable in functional and non-functional terms. The evaluations show that QoS can be better preserved using the proposed context-aware degradation process when compared with more conventional MCS scheduling approaches.

KW - Task analysis , Degradation , Quality of service , Timing , Safety , Sensors , Standards

U2 - 10.1109/TCAD.2023.3330113

DO - 10.1109/TCAD.2023.3330113

M3 - Article

SN - 0278-0070

JO - IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems

JF - IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems

ER -