• Proceedings of the Korean Information Science Society Conference
• /
• 2007.06b
• /
• pp.350-353
• /
• 2007

기존의 시스템 개발 환경은 동질성, 신뢰성 그리고 보안성 등을 중요시하는 중앙 집중 형태로 운영되어 왔다. 그러나 최근의 컴퓨팅 환경은 분산된 자원들 사이에서의 협업이나 자원 고유를 위한 상호 운영 방향으로 변모되어가고 있다. 이러한 상호 연결 시스템으로는 그리드 컴퓨팅이 활발하게 연구가 진행되고 있다. 그리드 환경에서 고려해야 할 사항은 필요 자원의 사용 대기시간을 줄이는 작업 분배 알고리즘과 고장 감내이며 이들을 중요한 연구 대상으로 하고 있다. 특히, 한정된 지역 정보만을 사용하는 n-Cycle 오버레이 네트워크는 효율적이고 고른 작업 분배 알고리즘을 제공하지만 고장 감내에 대한 대처를 하지 못하는 단점을 지니고 있다. 본 논문에서 부분 복구 기법을 제안함으로써 고장 노드에 의해 발생되는 작업 메시지의 누락율을 줄이고 전체 네트워크 토폴로지의 성능을 향상 시킨다. 또한 고장 노드가 발생하면 전체의 오버레이 네트워크를 재구성해야 하는 문제점을 해결한다. 실험을 통해 부분 복구 기법으로 노드의 고장에 따른 성능 저하율이 현저히 낮아짐을 보인다.

• The Journal of the Korea Contents Association
• /
• v.6 no.10
• /
• pp.126-133
• /
• 2006

Application software streaming is a virtualization technology that enables users to use applications without installation on her/his computer. With application streaming service, a client immediately starts and uses the application as if it were installed. The application can be executed while executable codes for the application may still be streamed. Since the software streaming is based on networks, its service is affected by network failures. Network failures may cause the streamed application to stop, and to make it worse, also the system may crash because executable codes for the application can't be streamed from the streaming server. Using the Pareto principle (80 vs. 20 rule), users can be served continuously with the minimum functions that are frequently used, pre-fetched and cached if we provide a more intelligent and fault-tolerant streaming technique. This paper proposes the concept and technique named Evergreen. Using the Evergreen technique, users can continue using the streamed application while a network failure occurs, although user can access only the streamed code. We also discuss the implementation of Evergreen technique in details.

• Journal of KIISE:Computer Systems and Theory
• /
• v.29 no.9
• /
• pp.493-502
• /
• 2002

The connectivity and edge-connectivity have been the prime deterministic measure of fault tolerance in multicomputer networks. These parameters have a problem that they do not differentiate the different types of disconnected graphs which result from removing the disconnecting vertices or disconnecting edges. To compensate for this shortcoming, one can utilize generalized measures of connectedness such as superconnectivity, toughness, scattering number, vertex-integrity, binding number, and restricted connectivity. In this paper, we analyze such deterministic measures of fault tolerance in recursive circulants and hypercubes, and compare them in terms of fault tolerance.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.9B
• /
• pp.1295-1304
• /
• 2010

This paper proposes a fault-tolerant data aggregation which provides energy efficient and reliable data collection in wireless sensor networks. The traditional aggregation scheme does not provide the countermeasure to packet loss or the countermeasure scheme requires a large amount of energy. The proposed scheme applies caching and re-transmission based on the track topology to the adaptive timeout scheduling. The proposed scheme uses a single-path routing based on the traditional tree topology at normal, which reduces the dissipated energy in sensor nodes without any countermeasure against packet loss. The proposed scheme, however, retransmits the lost packet using track topology under event occurrences in order to fulfill more accurate data aggregation. Extensive simulation work under various workloads has revealed that the proposed scheme decrease by 8% in terms of the dissipated energy and enhances data accuracy 41% when the potential of event occurrence exists as compared with TAG data aggregation. And the proposed scheme decrease by 53% in terms of the dissipated energy and shows a similar performance in data accuracy when the potential of event occurrence exists as compared with PERLA data aggregation.

• Journal of KIISE:Computer Systems and Theory
• /
• v.31 no.1_2
• /
• pp.19-26
• /
• 2004

In this paper, we investigate the longest fault-free paths joining every pair of vertices in a double loop network with faulty vertices and/or edges, and show that a bipartite double loop network G(mn；1, m) is strongly hamiltonian-laceable when the number of faulty elements is two or less. G(mn；1, m) is bipartite if and only if m is odd and n is even.

• Proceedings of the Korea Contents Association Conference
• /
• 2004.11a
• /
• pp.437-441
• /
• 2004

As the development of networks and computer systems, users want various services. To meet user's various needs, new technologies is developed and a software streaming technology, uses software with streaming technology, is newly coming out. If network trouble occurs, the software is not available because the streaming server can't send the binary code that software needs to be executed in the streaming service based on network environment. In this paper, we propose the management technology of software binary code in client that managing the binary codes classfied by the function kept in the local storage device, provides the service continuously after the network trouble with the given binary code previously not the binary code from the server.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2003.05b
• /
• pp.19-22
• /
• 2003

현대 사회는 인터넷과 네트워크의 발전과 더불어 많은 성장을 거듭해 왔고, 인터넷을 이용한 많은 서비스들은 계속해서 생기고 있다. 이러한 사회적인 배경에서 인터넷을 이용한 서비스에 대한 의존도도 또한 급격하게 증가하고 있다. 서비스를 언제, 어디서나 접근이 가능하게 함으로써 사용자들이 편리한 서비스를 제공받을 수 있게 되었지만, 이러한 서비스들이 안정적으로 제공되어야 한다. 고로 본 논문에서는 컴퓨터 시스템에 대한 신뢰성을 확보하기 위해 사용되는 기법 중 소프트웨어적인 고장 감내 시스템에 대해 알아보고 그에 따른 기법들을 조사하여 단일 시스템에서 구현해 볼 수 있는 방법 중 감시 프로세스를 이용하여 서비스를 안정적으로 서비스를 할 수 있는지에 대해 알아보았다.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.8
• /
• pp.66-75
• /
• 2016

Due to aggressive scaling of device sizes and reduced noise margins, physical defects caused by aging and process variation are continuously increasing. Additionally, with scaling limitation of metal wire and the increasing of communication volume, fault tolerant method in manycore network-on-chip (NoC) has been actively researched. However, there are few researches investigating reliability in NoC with voltage-frequency-island (VFI) regime. In this paper, we propose a table-based routing technique that can communicate, even if link failures occur in the VFI NoC. The output port is alternatively selected between best and the detour routing path in order to improve reliability with minimized hardware cost. Experimental results show that the proposed method achieves full coverage within 1% faulty links. Compared to $d^2$-LBDR that also considers a routing method for searching a detour path in real time, the proposed method, on average, produces 0.8% savings in execution time and 15.9% savings in energy consumption.

• Journal of KIISE:Databases
• /
• v.32 no.6
• /
• pp.616-627
• /
• 2005

In the shared storage file system, systems can directly access the shared storage device through specialized data-only subnetwork unlike in the network attached file server system. In this shared-storage architecture, data consistency is maintained by some designated set of lock servers which use control network to send and receive the lock information. Furthermore, lease mechanism is introduced to cope with the control network failure. But when the control network is partitioned, participating systems can no longer make progress after the lease term expires until the network recovers. This paper addresses this limitation and proposes a method that allows partitioned systems to make progress under the partition of control network. The proposed method works in a manner that each participating system is rotationally given a predefined lease term periodically. It is also shown that the proposed mechanism always preserves data consistency.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2011.11a
• /
• pp.599-601
• /
• 2011

무선 센서 네트워크를 구성하는 센서노드들이 클러스터를 구성하고 선출된 클러스터 헤드가 클러스터 내의 센서노드들로부터 데이터를 받아서 병합한 다음, 기지국으로 데이터를 전달하는 클러스터 기반 라우팅 방법이 연구되어 왔다. 이 클러스터 기반 라우팅 방법에서 클러스터 헤드에 고장이 발생한다면, 해당 클러스터의 데이터는 기지국으로 전달할 수 없어 데이터 신뢰성에 문제가 생긴다. 이러한 문제를 해결하기 위해, 본 논문에서는 고장감내를 지원하는 클러스터 기반 라우팅 방법을 제안한다. 제안한 방법은 각 클러스터마다 백업 클러스터 헤드를 지정하여 원래의 클러스터 헤드에 고장이 발생한다면 백업 클러스터 헤드가 그 역할을 대신하도록 함으로써 데이터 전달의 신뢰성을 보장한다.