• Proceedings of the IEEK Conference
• /
• 2003.11b
• /
• pp.231-234
• /
• 2003

This paper designs and implements fault-tolerant server of meta server for shared filesystem (SANfs) in SAN environment. SANfs is the filesystem that many clients can share data in Network-attached storage in SAN environment and meta server is the server that processes file operation in SANfs. The focus of this paper is the implementation of fault-tolerant server of meta server in SANfs. In the event of a meta server, meta server failovers to a fault-tolerant server where its processing continues seamlessly. If meta server doesn't restore, fault-tolerant server searches reliable client and makes another fault-tolerant server and work as meta server. Heartbeat monitors meta server and shadow server and controls them.

• Proceedings of the KSR Conference
• /
• 1999.05a
• /
• pp.299-306
• /
• 1999

The ${\mu}$-processor based-controlled system is widely used in railway signaling system. The railway signaling systems are highly required safety and reliability. It is necessary to have a fault-tolerant and fail safe concept in ${\mu}$-processor based railway signaling system. In this paper, several architectures and circuits of fault-tolerant computer system is reviewed. The basic concept of the fault-tolerant computer system will be adapted total self checking, strong fail safe, fault display circuit, logic testing circuit and system switching concepts.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2000.10b
• /
• pp.1199-1202
• /
• 2000

CORBA 환경에서 지속적이고 안정적인 객체 서비스틀 제공하기 위해 기존 CORBA에 고장 감내 기능을 부여한 Fault-Tolerant CORBA가 필요하게 되었다. Orbix+ISIS, Eletra 등이 CORBA에서 고장 감내 기능을 제공하고 있으며 OMG에서도 Fault-Tolerant CORBA 규격에 관한 작업을 진행 중이다. CORBA 환경에서 고장 감내 기능을 ORB 에 추가하는 방법은 통합 방식(Integration Approach), 서비스 방식(Service Approach), 인터셉트 방식(Intercept Approach) 등이 있다. 본 논문에서는 OMG에서 작업 중인 Fault-Tolerant CORBA 규격을 기본으로 하여 통합 방식과 서비스 방식을 결합하여 클라이언트 응용에게 투명하게 고장 감내 기능을 제공하는 Fault-Tolerant CORBA 구조를 설계하였다.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.10
• /
• pp.1-5
• /
• 2015

Based on the dual hardware and software with distributed recovery blocks, the centralized type fault tolerant store management system(SMS) was proposed. As a result of trade off study related to mutiplex hardware system design, dual single board computer(SBC) was adapted. To verify redundancy function of the proposed structure, the prototype SMS and weapon simulator were used. The proposed SMS operated normally without being affected by a primary SBC failure. The switching time from primary SBC to shadow SBC was within 200 ms. The reliability of the proposed SMS was predicted and compared with the non fault tolerant SMS, thereby it was proved that the proposed SMS has a higher reliability than the non fault tolerant system within effective range.

• 한국전산유체공학회:학술대회논문집
• /
• 2006.05a
• /
• pp.178-181
• /
• 2006

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.11a
• /
• pp.79-80
• /
• 2009

최근 UAV(Unmanned Aerial Vehicle)의 OFP(Operation Flight Program)에 대한 많은 연구가 진행되고 있다. UAV의 OFP는 경성 소프트웨어 일종으로 Time deadline과 수많은 요인으로 인한 Fault에 대하여 소프트웨어의 높은 신뢰성이 요구가 된다. 본 논문에서는 UAV의 OFP에 대하여 STR(Primary-Shadow TMO replication)기반의 fault tolerant Architecture에 대하여 제안을 한다.

• Journal of Auto-vehicle Safety Association
• /
• v.15 no.2
• /
• pp.13-20
• /
• 2023

This paper presents a fault tolerant control strategy for Steer-by-Wire (SbW) systems. Among many problems to be solved before commercialization of SbW systems, maintaining reliability and fault tolerance in such systems are the most pressing issues. In most previous studies, dual steering motors are used to achieve actuation redundancy. However, relatively few studies have been conducted to introduce fault tolerant control strategies using rear wheel steering system. In this work, an actuator fault in front wheel steering is compensated by active rear wheel steering. The proposed fault tolerant control algorithm consists of disturbance observer and sliding mode control. The fault tolerant control performance of the proposed approach is validated via computer simulation studies with Carsim vehicle dynamics software and MATLAB/Simulink.

• Journal of Power Electronics
• /
• v.10 no.1
• /
• pp.34-42
• /
• 2010

Reliability is an important issue in cascaded H-bridge converters (CHB converters) because they use a high number of power semiconductors. A faulty power cell in a CHB converter can potentially lead to expensive downtime and great losses on the consumer side. With a fault-tolerant control strategy, operation can continue with the undamaged cells; thus increasing the reliability of the system. In this paper, the operating principles and the control method for a CHB multilevel rectifier are introduced. The influence of various faults on the CHB converter is investigated. The method of fault diagnosis and the bypassing of failed cells are explained. A fault-tolerant protection strategy is proposed to achieve redundancy in the CHB rectifier. The redundant H-bridge concept helps to deal with device failures and to increase system reliability. Simulation results verify the performance of the proposed strategy.

• Journal of Internet Computing and Services
• /
• v.17 no.4
• /
• pp.1-9
• /
• 2016

Algorithms implementing distributed shared memory (DSM) were developed for ensuring consistency. The performance of DSM algorithms is dependent on system and usage parameters. However, ensuring these algorithms to tolerate faults is a problem that needs to be researched. In this study, we proposed fault-tolerant scheme for DSM system and analyzed reliability and fault-tolerant overhead. Using our analysis, we can choose a proper algorithm for DSM on error prone environment.

• Journal of Information Processing Systems
• /
• v.2 no.1
• /
• pp.6-12
• /
• 2006

Peer-to-Peer (P2P) networks are attracting considerable research interest because of their scalability and high performance relative to cost. One of the important services on a P2P network is the streaming service. However, because each node in the P2P network is autonomous, it is difficult to provide a stable streaming service on the network. Therefore, for a stable streaming service on the P2P network, a fault-tolerant scheme must be provided. In this paper, we propose two new node selection schemes, Playback Node First (PNF) and Playback Node first with Prefetching (PNF-P) that can be used for a service migration-based fault-tolerant streaming service. The proposed schemes exploit the fact that the failure probability of a node currently being served is lower than that of a node not being served. Simulation results show that the proposed schemes outperform traditional node selection schemes.