• Journal of Korea Multimedia Society
• /
• v.16 no.1
• /
• pp.56-66
• /
• 2013

In MANET, the frequent movement of nodes causes the dynamic network topology changes. Therefore, it is required that the routing protocol should be very stable to effectively respond the changes of the network changes. Moreover, the existing cluster-based routing protocol, that is the hybrid approach, has routing delay due to the re-electing of the cluster header. In addition, the routing table of CBRP has all only one hop distant neighbor nodes. PCBRP, proposed in this paper, ties two clusters in one paired cluster to make longer radius. Then the headers of the paired cluster manage and operate corresponding member nodes. In the current CBRP, when the cluster header leaves out the cluster, the delay, due to the re-electing a header, should be occurred. However, in PCBRP, another cluster header of the paired cluster plays the role instead of the left cluster header. This method reduces the routing delay. Concurrently, PCBRP reduces the delay when they route nodes in the paired cluster internally.

• Journal of KIISE:Computer Systems and Theory
• /
• v.29 no.1
• /
• pp.35-41
• /
• 2002

It is extremely important to minimize network access time in constructing a high-performance PC cluster system For an SCI based PC cluster it is possilbe to reduce the network access time by maintaining network cache in each cluster node, This paper presents a CC-NUMA card that utilizes network cache for SCI based PC clustering The CC-NUMA card is directly plugged into the PCI solot of each node, and contains shared memory network cache, and interconnection modules. The network cache is maintained for the shared memory on the PCI bus of cluster nodes. The coherency mechanism between the network cache and the shared memory is based on the IEEE SCI standard. A CC-NUMA prototype card is developed to evaluate the performance of the system. According to the experiments. the cluster system with the CC-NUMA card showed considerable improvements compared with an SCI based clustser without network cache.

• The KIPS Transactions:PartA
• /
• v.10A no.6
• /
• pp.635-642
• /
• 2003

The radical development of recent network technology provides the basic foundation which can establish a high speed and cheap cluster system. It is a general trend that conventional cluster systems are built as the system over a fixed level based on stabilized and high speed local networks. A multi-distributed web cluster group is a web cluster model which can obtain high performance, high efficiency and high availability through mutual cooperative works between effective job division and system nodes through parallel performance of a given work and shared memory of SC-Server with low price and low speed system nodes on networks. For this, multi-distributed web cluster group builds a sub-cluster group bound with single imaginary networks of multiple system nodes and uses the web distributed shared memory of system nodes for the effective data transmission within sub-cluster groups. Since the presented model uses a load balancing and parallel computing method of large-scale work required from users, it can maximize the processing efficiency.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.3A
• /
• pp.287-295
• /
• 2010

In wireless sensor networks(WSNs), the studies that support sink mobility without global position information exploit a Backbone-based Virtual Infrastructure (BVI) which considers one-hop clusters and a backbone-based tree. Since the clusters of a sink and a source node are connected via flooding into the infrastructure, it causes high routing cost. Although the network could reduce the number of clusters via multi-level clusters, if the source nodes exist at nearest clusters from the cluster attached by the sink and they are in different branches of the tree, the data should be delivered via detour paths on the tree. Therefore, to reduce the number of clusters, we propose a novel multi-hop cluster based communication protocol supporting sink mobility without global position information. We exploit a rendezvous cluster head for sink location service and data dissemination but the proposed protocol effectively reduces data detour via comparing cluster hops from the source. Simulation shows that the proposed protocol is superior to the existing protocols in terms of the data delivery hop counts.

• Journal of the Korean Academic Society of Industrial Cluster
• /
• v.3 no.1
• /
• pp.11-25
• /
• 2009

Wind power is the most rapidly growing energy source in the world. Increased focus on climate changes and renewable energy is supporting the wind power industry in gaining momentum. Noksan wind cluster in Busan has been a major area in manufacturing the elementary parts of wind turbine. Despite growing recognition of the significance of Noksan, there has been only limited attention paid and in recent years. This paper reviews the literature of the current burning issues in wind turbine industries in the western countries. In addition, it describes the present state of Noksan wind power generation cluster and suggests the future plans to make it more effective complex.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.10a
• /
• pp.510-513
• /
• 2010

In hierarchical wireless sensor network, Sensor nodes forming a cluster with a hierarchy. And there are being study for balanced energy consumption between cluster nodes. When forming network routing path, if there are configured incorrectly then it can be wasting energy. In this paper to solve these problem, We propose that it can consider sensor's communication range to create minimum hop layer when cluster heads configure routing path.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.49 no.1
• /
• pp.8-15
• /
• 2012

In this paper, we propose a new monitor for collecting job information from Hadoop clusters in real time. This monitor is made of two programs called Collector and Agent. Agent collects Hadoop cluster's node information and job information, and Collector analyzes the collected information and saves it in a database. Also, Collector was placed in a new node outside the Hadoop cluster so that it does not affect Hadoop's work and will not cause overload. When the proposed monitor was implemented and applied, the testbed cluster was able to detect the occurrence of dead nodes immediately. In addition, we were able to find Hadoop jobs which were inefficient and when we modified such jobs to further enhance the performance of Hadoop.

• The KIPS Transactions:PartC
• /
• v.14C no.5
• /
• pp.403-410
• /
• 2007

For reliable sensor network communication, secure data transmission mechanisms are necessary. In our work, for secure communication, we cluster the network field in hexagonal shape and deploy nodes according to Gaussian distribution. After node deployment, clusterheads and gateway nodes in each cluster play the role of aggregating and delivering the sensed data with suity information all the way to the base station. Our mechanism decreases the overhead and provides food performance. It also has resilience against various routing attacks.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.04a
• /
• pp.710-711
• /
• 2015

IT 산업의 발전에 따라 생성되는 데이터의 양이 폭발적으로 증가하고 있다. 이러한 빅 데이터는 여러 대의 컴퓨터로 구성한 하둡 클러스터를 이용하면 상당히 빠른 속도로 처리할 수 있으나, 일반적으로 하둡 클러스터를 구성하기 위해 많은 비용과 공간이 소요되는 단점이 있다. 본 논문에서는 저가의 미니 PC로 하둡 클러스터를 구성하여 비용 및 공간적 문제점을 해결하고, 구축한 하둡 클러스터를 이용한 트렌드 분석 서비스를 제안하였다. 실험 결과 미니 PC로 이루어진 하둡 클러스터가 고가의 서버보다 트랜드 분석에 더 좋은 처리 성능을 보였다.

• Journal of KIISE:Computing Practices and Letters
• /
• v.8 no.6
• /
• pp.639-646
• /
• 2002

In this paper, we discuss the system configuration and the design issues of CATS-i, a set of installation and administration tools for Linux cluster systems. CATS-i enables users to manage cluster systems easily, quickly, and safety. It integrates many functions, ranging from installing operating systems and applications to real-time monitoring and management of various important resources. In addition, batch job submission and management are included. These functions support a single system image. Finally, a powerful graphic user interface based on Java lets users quickly understand the cluster status and conveniently use the CATS-i on the Web.