Masters Theses

Samsil Arefin

Keywords and Phrases

Graceful Degradation; Mixed-Criticality Scheduling; Probabilistic Scheduling; Real-Time Scheduling

Abstract

”The mixed-criticality real-time systems implement functionalities of different degrees of importance (or criticalities) upon a shared platform. In traditional mixed-criticality systems, under a hi mode switch, no guaranteed service is provided to lo-criticality tasks. After a mode switch, only hi-criticality tasks are considered for execution while no guarantee is made to the lo-criticality tasks. However, with careful optimistic design, a certain degree of service guarantee can be provided to lo-criticality tasks upon a mode switch. This concept is broadly known as graceful degradation. Guaranteed graceful degradation provides a better quality of service as well as it utilizes the system resource more efficiently. In this thesis, we study two efficient techniques of graceful degradation.

First, we study a mixed-criticality scheduling technique where graceful degradation is provided in the form of minimum cumulative completion rates. We present two easy-to-implement admission-control algorithms to determine which lo-criticality jobs to complete in hi mode. The scheduling is done by following deadline virtualization, and two heuristics are shown for virtual deadline settings. We further study the schedulability analysis and the backward mode switch conditions, which are proposed and proved in (Guo et al., 2018).

Next, we present a probabilistic scheduling technique for mixed-criticality tasks on multiprocessor systems where a system-wide permitted failure probability is known. The schedulability conditions are derived along with the processor allocation scheme. The work is extended from (Guo et al., 2015), where the probabilistic model is first introduced for independent task scheduling on a uniprocessor platform. We further consider the failure dependency between tasks while scheduling on multiprocessor platforms.

We provide related theoretical analysis to show the correctness of our work. To show the effectiveness of our proposed techniques, we conduct a detailed experimental evaluation under different circumstances”--Abstract, page iii.

Advisor(s)

Guo, Zhishan

Committee Member(s)

Wunsch, Donald C.
Taylor, Patrick

Department(s)

Computer Science

Degree Name

M.S. in Computer Science

Publisher

Missouri University of Science and Technology

Publication Date

Fall 2018

Pagination

xi, 66 pages

Note about bibliography

Includes bibliographic references (pages 59-65).

Rights

© 2018 Samsil Arefin, All rights reserved.

Document Type

Thesis - Open Access

File Type

text

Language

English

Thesis Number

T 12000

Electronic OCLC #

1313117332

Download

Share

 
COinS