High performance real-time scheduling of multiple mixed-criticality functions in heterogeneous distributed embedded systems
High performance real-time scheduling of multiple mixed-criticality functions in heterogeneous distributed embedded systems
复制标题
DOI：
10.1016/j.sysarc.2016.04.008
复制
发表时间：
2016-10-01
影响因子：
4.5
通讯作者：
Li, Keqin
中科院分区：
文献类型：
--
作者：
Xie, Guoqi;Zeng, Gang;Li, Keqin
高端嵌入式系统的体系结构已演变为异质分布式集成体系结构。由于系统和功能的要求不同，因此在异质分布式嵌入式系统中的多个分布式混合临界功能的调度是一个巨大的挑战。总体调度长度（即MakePAN）是系统性能的主要关注点，而截止日期则代表了功能的主要时间限制。大多数算法都使用公平政策来减少异质分布式系统中的MakePan。但是，这些公平政策无法满足大多数功能的截止日期。每个功能都有不同的临界水平（例如严重性），并且在这种情况下，某些高批判性功能的截止日期可能会对人们造成致命伤害。这项研究首先构建了异质分布式嵌入式系统相关的模型。此后，提出了多个异质完成时间（F_MHEFT）算法的批判性认证，调度框架和公平性，用于异构分布式嵌入式系统。最后，这项研究提出了一种新型算法，称为多个最早完成时间（D_MHEFT）的截止日期，该算法是多种混合临界功能的调度算法。 F_MHEFT算法旨在提高系统性能，而D_MHEFT算法试图通过牺牲某个性能来满足更高临界功能的截止日期。实验结果表明，D_MHEFT算法可以显着降低截止日期比率（DMR），并在现有方法上保持令人满意的性能。 （c）2016 Elsevier B.V.保留所有权利。
The architectures of high-end embedded system have evolved into heterogeneous distributed integrated architectures. The scheduling of multiple distributed mixed-criticality functions in heterogeneous distributed embedded systems is a considerable challenge because of the different requirements of systems and functions. Overall scheduling length (i.e., makespan) is the main concern in system performance, whereas deadlines represent the major timing constraints of functions. Most algorithms use the fairness policies to reduce the makespan in heterogeneous distributed systems. However, these fairness policies cannot meet the deadlines of most functions. Each function has different criticality levels (e.g., severity), and missing the deadlines of certain high-criticality functions may cause fatal injuries to people under this situation. This study first constructs related models for heterogeneous distributed embedded systems. Thereafter, the criticality certification, scheduling framework, and fairness of multiple heterogeneous earliest finish time (F_MHEFT) algorithm for heterogeneous distributed embedded systems are presented. Finally,,this study proposes a novel algorithm called the deadline-span of multiple heterogeneous earliest finish time (D_MHEFT), which is a scheduling algorithm for multiple mixed-criticality functions. The F_MHEFT algorithm aims at improving the performance of systems, while the D_MHEFT algorithm tries to meet the deadlines of more high-criticality functions by sacrificing a certain performance. The experimental results demonstrate that the D_MHEFT algorithm can significantly reduce the deadline miss ratio (DMR) and keep satisfactory performance over existing methods. (C) 2016 Elsevier B.V. All rights reserved.