• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37C no.11
• /
• pp.1162-1169
• /
• 2012

One of the important operational requirements for mission critical Ethernet networked system is having the fault tolerant capability. Such capability can be obtained by equipping multiport Network Interface Card (NIC) in each node in the system. Conventional NIC uses two or more Media Access Controls (MACs) and a co-processor for the MAC switching whenever an active port fails. Since firmware is needed for the co-processor, longer fail-over switching and degraded throughput can be generally expected. Furthermore the system upgrading requiring the firmware revision in each tactical node demands high cost. In this paper we propose a novel single MAC based NIC that does not use a co-processor, but just use general discrete building blocks such as MAC chip and switching chip, which results in better performances than conventional method. Experimental results validate our scheme.

• ICROS
• /
• v.17 no.4
• /
• pp.35-41
• /
• 2011

비동기적으로 동작하는 디지털 회로는 동기 순차 회로에 비해서 고속, 저전력 소비 등 여러 가지 장점을 지니기 때문에 현대 디지털 시스템에서 여전히 중요한 요소로 사용되고 있다. 본 기고에서는 비동기 순차 회로에서 발생하는 고장을 진단하고 극복하는 최신 기술을 소개한다. 본 기고에서 주로 다루는 기술은 '교정 제어'로서 피드백 제어의 원리를 이용하여 비동기 순차 회로의 안정 상태를 바꾸는 기법이다. 크리티컬 레이스(critical race), 무한 순환 등 비동기 회로 설계상의 오류를 포함하여 SEU(Single Event Upset), 총이론화선량(TID)에 의한 고장 등 외부 환경에 의해서 발생하는 비동기 회로의 고장을 교정 제어를 이용하여 진단하고 극복하는 기술에 대해서 알아본다.

• Proceedings of the KIEE Conference
• /
• 2000.07d
• /
• pp.2974-2976
• /
• 2000

최근에 인터넷의 급격한 수요증가로 인하여 웹서버의 고가용성(high availability)이 절실히 요구되고 있다. 이를 위한 방안으로 클러스터링 가상 서버가 핫이슈로 대두되고 있는 상황에서 이의 가장 핵심부분인 로드밸런스(load balancer)의 고가용성을 위해 고장극복(fault-tolerant) 기법 연구는 필수적이라 할 수 있다. 본 연구에서는 클러스터링 웹서버의 구성과 로드밸런서의 운영방안을 제시하고 특히, 로드밸런서가 고장났을 경우 로드밸런서의 작업을 신속하게 대체하는 방안을 모색한다. 로드밸런서의 구성이 마스터 로드밸런서와 백업 로드밸러서로 구성된다는 가정 하에 백업 로드 밸런서가 마스터 로드밸런서의 작업을 신속히 대체하는 방안을 위해 체크포인트(checkpoint) 기법을 적용한다.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.47 no.5
• /
• pp.9-17
• /
• 2010

Corrective control compensates the stable-state behavior of asynchronous sequential machines so that the closed-loop system can be changed in a desirable way. Using corrective control, we present a novel fault tolerance scheme that overcomes permanent faults for asynchronous sequential machines. When a permanent fault occurs to an asynchronous machine, the fault is not recovered forever while the machine is irreversibly stuck in a set of failure states. But, if the machine has control redundancy in the limited behavior range, corrective control can be applied to solve the fault tolerance problem against permanent faults. We present the condition on detecting permanent faults and the existence condition of an appropriate corrective controller. The design procedure for the proposed controller is described in a case study.

• Annual Conference of KIPS
• /
• 2008.11a
• /
• pp.1355-1358
• /
• 2008

긴급 업무를 위한 네트워크 시스템에서는 네트워크 구성요소의 고장을 즉시 극복할 수 있는 메커니즘이 제공되어야 한다. 고장 극복을 위해서 네트워크 경로를 이중화하고 경로를 주기적으로 감시하여 고장 발생 시에 대체 경로를 사용하는 방법이 연구되어 왔다. 이를 위해서 서브넷 상의 경로를 감시하는 마스터 노드가 필요한데 마스터 노드의 고장 시 이를 극복할 방법이 필요하다. 본 논문에서는 마스터 노드가 있는 단일 서브넷에서 마스터의 고장 시에 모든 노드가 참여하여 자율적으로 새로운 마스터를 선출하는 알고리즘을 연구하였다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.1
• /
• pp.49-55
• /
• 2012

Asynchronous counters, where the counter value is changed not by a synchronizing clock but by outer inputs, are used in various modern digital systems such as spaceborne electronics. In this paper, we propose a scheme of fault tolerance for asynchronous counters with critical races caused by total ionizing dose (TID) in space. As a typical design flaw of asynchronous digital circuits, critical races cause an asynchronous circuit to show non-deterministic behavior, i.e., the next stable state of a state transition is not a fixed value but may be any value of a state set. Using the corrective control scheme for asynchronous sequential machines, this paper provides an existence condition and design procedure for a state feedback controller that can invalidate the effect of critical races. We implement the proposed control system in VHDL code and conduct experiments to demonstrate that the proposed control system can overcome critical races.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.48 no.3
• /
• pp.40-47
• /
• 2011

This paper addresses the problem of fault detection and tolerance for asynchronous sequential machines using state feedback control. The considered asynchronous machine is affected by intermittent faults. When intermittent faults occur, the machine undergoes unauthorized state transitions and, for a finite duration, remains at the fault state, not responding to the change of the external input. In this paper, we postulate the scheme of detecting intermittent faults and present the existence condition and design algorithm for a robust state feedback controller that overcomes the adversarial effect of intermittent faults. We also undertake a comparative study between the previous control scheme for transient faults and the present strategy for intermittent faults. The design procedure for the proposed controller is described in a case study.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.1 no.1
• /
• pp.82-91
• /
• 1998

This paper presents a neural networks based approach for the problem of sensor failure detection and accommodation for ship without physical redundancy in the sensors. The designed model consists of two neural networks. The first neural network is responsible for the failure detection and the second neural network is responsible for the failure identification and accommodation. On the yaw rate sensor of ship, simulation results indicates that the proposed method can be useful as failure detector and sensor estimator.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.7
• /
• pp.103-109
• /
• 2016

Corrective control for asynchronous sequential machines is a novel automatic control theory that compensates illegal behavior or adverse effects of faults in the operation of existent asynchronous machines. In this paper, we propose a scheme of diagnosing and tolerating faults occurring to input channels of corrective control systems. The corrective controller can detect faults occurring in the input channel to the controlled machine, whereas those faults happening in the external input channel cannot be detected. The proposed scheme involves an outer operator which, upon receiving the state feedback, diagnoses a fault and sends an appropriate command signal to the controller for tolerating faults in the external input channel.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.10 no.2
• /
• pp.107-114
• /
• 2007

This paper describes the Petri Net(PN) model for reliability analysis of fault-tolerant dual Ethernet which Is applied in Naval Combat System. The network for Naval Combat System performs failure detection and auto path recovery by handling redundant path in case of temporary link failure. After studying the behavior of this kind of network, the reliability analysis model is proposed using stochastic Petri Net and continuous-time Markov chains. Finally, the numerical result is analyzed according to changing the failure rate and the recover rate of link.