• 한국컴퓨터정보학회논문지
• /
• 제16권8호
• /
• pp.11-18
• /
• 2011

웹 사용자의 급증은 과중한 전송량과 시스템의 부하문제를 야기 시켰으며 이를 해결하기 위한 방안으로 클러스터시스템이 연구되고 있다. 기존 웹 클러스터 시스템에서는 웹 서버 간 부하가 균등하더라도 멀티미디어나CGI 등으로 요청 데이터 크기가 크면 특정 웹 서버의 부하와 응답 시간이 증가되는 경향이 있다. 본 논문에서는 웹 클러스터 시스템의 효율적인 자원사용 방법에 관하여 연구하였다. 메모리 사용을 균형적으로 하는 웹 클러스터 시스템을 구현하기 위한 부하 분산 알고리즘을 제안하여 검토하고 다양한 클러스터링 모델에서 반응시간을 성능 측정의 지수로 제시하였다. 또한 웹 클러스터 시스템의 동시사용자 수를 기반으로 반응시간은 사용자 수를 증가시키면서 실험하였으며, 성능 실험을 통해 기존의 방식보다 제안한 기법이 처리율과 응답시간에서 보다 향상된 것으로 나타났다.

• 대한의용생체공학회:의공학회지
• /
• 제25권6호
• /
• pp.617-621
• /
• 2004

최근 들어 유전자 서열의 생산량 증가에 비례하여 유전자 발현 마이크로 칩과 같은 새로운 분석방법과 기술들이 도입되면서 연구자들이 매일 수천개의 서열을 효율적으로 분석해야 할 필요성이 증대되고 있다. 이러한 생명공학분야의 급속한 발전은 대용량 유전자 서열에 대한 빠른 분석이 가능한 컴퓨팅 자원을 요구하고 있으나 IT 인프라에 대한 막대한 투자비용으로 인해 관련 연구기관에서 쉽게 이들 컴퓨팅 자원을 도입하지 못하고 있는 실정이다. 본 연구에서는 저가의 PC서버를 고속의 네트워크로 연결한 PC 클러스터를 활용하여 시스템의 안정성과 신뢰성을 보장함과 동시에 범용성을 지닌 병렬형 유전자 서열 검색 시스템을 구축하였다. 이러한 효율적인 시스템 구축을 통해 생물정보 데이터베이스 및 서열 검색 시스템을 제공하고, 대용량 서열 데이터베이스의 검색 시간을 단축하였다.

• 한국지열·수열에너지학회논문집
• /
• 제15권3호
• /
• pp.14-20
• /
• 2019

In this study, the technologies and regulations for distributing standing column well(SCW) ground source heat pump systems to the residential cluster homes were investigated. They have only been installed in the public or commercial building having different load pattern and site structure compared with the residential cluster homes. Some of SCWs for the residential cluster homes should be installed under the basement due to a lack of site area. There are pressure differences between the SCWs installed under ground surface and basement. It is needed to develop the technology or devices to prevent overflow caused by pressure difference among the SCWs. In addition, heat balance algorithm between SCWs should be adopted to maximize the system efficiency. A heat pump having heating, cooling, hot water, heating-hot water, and cooling-hot water modes should be developed for adopting an individual air-conditioning system to the residential cluster homes.

• International Journal of Internet, Broadcasting and Communication
• /
• 제9권4호
• /
• pp.51-58
• /
• 2017

This paper deals with the improvement of cluster head selection method in L-SEP for heterogeneous nodes among hierarchical routing protocols of wireless sensor network. Wireless sensor networks are classified into homogeneous and heterogeneous network. In heterogeneous network, SEP, L-SEP are mainly used because cluster head selection probability is different depending on node type. But, since protocol based on SEP has different cluster head selection probabilities depending on the node type, clusters that transmit data inefficiently can be formed. to improve this, it is necessary to select the cluster head that minimizes the transmission distance of member node and the cluster head. Therefore, we propose a protocol that improve the cluster head selection method.

• 전기학회논문지
• /
• 제57권7호
• /
• pp.1150-1156
• /
• 2008

This paper introduces the PC clustering of the SIMD structure for a distributed processing of on-line contingency to assess a static security of a power system. To execute on-line contingency analysis of a large-scale power system, we need to use high-speed execution device. Therefore, we constructed PC-cluster system using PC clustering method of the SIMD structure and applied to a power system, which relatively shows high quality on the high-speed execution and has a low price. SIMD(single instruction stream, multiple data stream) is a structure that processes are controlled by one signal. The PC cluster system is consisting of 8 PCs. Each PC employs the 2 GHz Pentium 4 CPU and is connected with the others through ethernet switch based fast ethernet. Also, we consider N-1 line contingency that have high potentiality of occurrence realistically. We propose the distributed process algorithm of the SIMD structure for reducing too much execution time on the on-line N-1 line contingency analysis in the large-scale power system. And we have verified a usefulness of the proposed algorithm and the constructed PC cluster system through IEEE 39 and 118 bus system.

• 한국전산유체공학회:학술대회논문집
• /
• 한국전산유체공학회 2001년도 추계 학술대회논문집
• /
• pp.182-189
• /
• 2001

A project has been initiated at KISTI Supercomputing Center at year 1999 to build a Tflops cluster in order to support newly emerging demands for larger scale parallel computing resources. As a supportive substitute of traditional supercompters, the cluster systems are expected to play important role in supporting diversified computational needs. In this paper, KISTI Supercomputing Center's working status of building Tflops cluster system and future plans.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권6호
• /
• pp.2513-2533
• /
• 2018

In cognitive radio technology, the overall efficiency of communications systems can be improved without allocating additional bands by allowing a secondary system to utilize the licensed band when the primary system, which has the right to use the band, does not use it. In this paper, we propose a fast and reliable common channel initialization protocol without any exchange of initialization messages between the cluster head and the member nodes in cognitive ad-hoc networks. In the proposed method, the cluster and member nodes perform channel-based spectrum sensing. After sensing, the cluster head transmits a system activation signal through its available channels with a predetermined angle difference pattern. To detect the cluster head's transmission channels and to join the cluster, each member node implements fast Fourier transform (FFT) and computes autocorrelation for the angle difference sequence of the received signal patterns. This is compared to the predetermined reference angle difference pattern. The join-request and channel-decision procedures are presented in this paper. Performance evaluation of the proposed method is presented in the simulation results.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권9호
• /
• pp.4342-4366
• /
• 2016

Congestion control in Cluster Wireless Sensor Networks (CWSNs) has drawn widespread attention and research interests. The increasing number of nodes and scale of networks cause more complex congestion control and management. Active Queue Management (AQM) is one of the major congestion control approaches in CWSNs, and Random Early Detection (RED) algorithm is commonly used to achieve high utilization in AQM. However, traditional RED algorithm depends exclusively on source-side control, which is insufficient to maintain efficiency and state stability. Specifically, when congestion occurs, deficiency of feedback will hinder the instability of the system. In this paper, we adopt the Additive-Increase Multiplicative-Decrease (AIMD) adjustment scheme and propose an improved RED algorithm by using neighbor feedback and scheduling scheme. The congestion control model is presented, which is a linear system with a non-linear feedback, and modeled by Lur'e type system. In the context of delayed Lur'e dynamical network, we adopt the concept of cluster synchronization and show that the congestion controlled system is able to achieve cluster synchronization. Sufficient conditions are derived by applying Lyapunov-Krasovskii functionals. Numerical examples are investigated to validate the effectiveness of the congestion control algorithm and the stability of the network.

• 천문학회지
• /
• 제40권4호
• /
• pp.153-155
• /
• 2007

We have analyzed H and $K_s$-band images of the Arches cluster obtained using the NIRC2 instrument on Keck with the laser guide star adaptive optics (LGS AO) system. With the help of the LGS AO system, we were able to obtain the deepest ever photometry for this cluster and its neighborhood, and derive the background-subtracted present-day mass function (PDMF) down to $1.3M_{\bigodot}$ for the 5"-9" annulus of the cluster. We find that the previously reported turnover at $6M_{\bigodot}$ is simply due to a local bump in the mass function (MF), and that the MF continues to increase down to our 50 % completeness limit ($1.3M_{\bigodot}$) with a power-law exponent of ${\Gamma}$ = -0.91 for the mass range of 1.3 < M/$M_{\bigodot}$ < 50. Our numerical calculations for the evolution of the Arches cluster show that the ${\Gamma}$ values for our annulus increase by 0.1-0.2 during the lifetime of the cluster, and thus suggest that the Arches cluster initially had ${\Gamma}$ of $-1.0{\sim}-1.1$, which is only slightly shallower than the Salpeter value.

• 대한임베디드공학회논문지
• /
• 제9권6호
• /
• pp.361-367
• /
• 2014

This paper introduces balancing energy and memory consumption for lifetime increase of wireless sensor network. In cluster-based wireless sensor network, sensor nodes adjacent of cluster heads have a tendency to deplete their own battery energy and cluster heads occupy memory space significantly. If the nodes close to region where events occur frequently consume their energy and memory fully, network might be destroyed even though most of nodes are still alive. Therefore, it needs to balance network energy and memory with consideration of event occurrence probability so that network lifetime is increased. We show a method of balancing wireless sensor network energy and memory to organize cluster groups and elect cluster heads in terms of event occurrence probability.