Full text

Turn on search term navigation

© 2023. This work is licensed under https://creativecommons.org/licenses/by/4.0 (the “License”). Notwithstanding the ProQuest Terms and conditions, you may use this content in accordance with the terms of the License.

Abstract

Partition operating system conforming to ARINC653 is widely used in airborne to support application software integration. Under the two-level scheduling model for partition operating system, the demanding real-time requirements of airborne software are usually difficult to obtain effective deterministic guarantee, so it is very important to analyze the schedulability of the system. Judging whether the scheduling table can meet the real-time requirements of the process in the partition through the schedulability analysis algorithm is an effective means to ensure that all processes in the system complete the computing task within the specified time. Based on the method of operations research and the introduction of virtual process, a schedulability analysis algorithm for multi partition system is designed, and the numerical verification is carried out. The verification results show that the algorithm can accurately judge whether the scheduling table matches the process time attribute, give the qualitative analysis conclusion of whether the system can be scheduled, help the system integrator to verify the rationality of the scheduling table before the actual operation of the system, and reduce the risk of test and flight test.

Alternate abstract:

机载领域普遍采用符合ARINC653标准的分区操作系统支撑应用软件综合化。在分区操作系统的两级调度模型下,机载软件苛刻的实时性要求通常难以得到有效的确定性保证,因此对系统进行可调度性分析显得至关重要。通过可调度性分析算法判断调度表是否能满足分区内进程的实时性要求,是保障系统中所有的进程在规定的时间内完成运算任务的有效手段。基于运筹学方法,通过引入虚拟进程,设计了一种多分区系统可调度性分析算法,并进行了数值验证。验证结果表明,该算法能够准确判断调度表与进程时间属性是否匹配,给出系统是否可调度的定性分析结论,帮助系统集成人员在系统实际运行前对调度表的合理性进行先期验证,降低试验和试飞风险。

Details

Title
Research on schedulability analysis algorithm of airborne multi partition system
Author
ZHANG, Min; WU, Junsheng; CUI, Xining; SUN, Jingchang
Pages
557-567
Publication year
2023
Publication date
Jun 2023
Publisher
EDP Sciences
ISSN
10002758
e-ISSN
26097125
Source type
Scholarly Journal
Language of publication
Chinese
ProQuest document ID
3180969748
Copyright
© 2023. This work is licensed under https://creativecommons.org/licenses/by/4.0 (the “License”). Notwithstanding the ProQuest Terms and conditions, you may use this content in accordance with the terms of the License.