• The KIPS Transactions:PartA
• /
• v.11A no.5
• /
• pp.355-364
• /
• 2004

These days, various clustering technologies have been adopted to construct web sites. High performance hardware switches have good performance, but have disadvantage of high cost for constructing small and middle-sized web sites. Now a days, many sites have been constructed with the LVS (Linux Virtual Server), which is free of charge and has good performance. Having a centralized load balancing with one front-end, the LVS causes a bottleneck when it receives all at once. In the paper, we suggest a way to remove the LVS bottleneck by providing multiple front-ends. In this architecture, all of cluster nodes act as both a front-end and a back-end. When the load of a node receiving requests is not large enough, the node responds to the client directly. When the load of a node is large enough, the node send the request to a node which is selected by a scheduling algorithm. The scheduling algorithm is discussed to balance loads between servers. While single front-end cluster raises the throughput curvedly, the multiple front-end cluster raises the throughput linearly.

• Journal of Korea Multimedia Society
• /
• v.3 no.3
• /
• pp.320-332
• /
• 2000

Web consists of the grand virtual system which is made of all connected computers network. We can solve the huge problem which requires high quality in cost performance and powerful computing power to use a numerous idle state system on internet as process it parallel. However, we have to consider heterogeneous computing resources, accessibility, and reliability to carry out parallel system on global environment, not network but whole Internet. In this paper, We the WebImg system which has the power of web computing, and show the flexible task allocation strategy in heterogeneous hosts. Also, we evaluate its performance, moreover the proposed task allocation strategy supplies fault tolerance by controlling host situation at any time.

• Journal of KIISE:Information Networking
• /
• v.28 no.4
• /
• pp.508-516
• /
• 2001

This paper proposes multicast routing algorithm that operates for non-interactive multimedia applications such as VOD(Video On Demand) and real-time data broadcasting. It is possible that there exist multiple senders in non-interactive multimedia applications. This paper designs multicast routing algorithm in this environment. The simulation of algorithm proposed in this paper shows much better performancetcost, delay) than that of only one source. To guarantee the performance of algorithm, Broadband ATM network is modelled in simulation.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.2A
• /
• pp.168-175
• /
• 2006

To cope with channel variation, wireless networks such as IEEE 802.11 WLAN provide multiple transmission rates by employing different channel modulation and coding schemes. However, the coexistence of different transmission rates degrades the total system performance of the network. In order to eliminate this performance abnormality and improve protocol capacity, we propose a new Packet transmission algorithm, the RAT(Rate-Adapted Transmission) scheme. The RAT scheme distributes the wireless channel fairly based on the channel occupancy time. Moreover, it efficiently transmits packets even in a single station using rate-based queue management. Therefore, the RAT scheme obtains not only the inter-rate contention gain among stations but also the intra-rate contention gain among connections in a single station.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2007.05a
• /
• pp.1005-1008
• /
• 2007

모바일 네트워크 환경은 언제 어디서나 네트워크를 사용하는 모바일 서비스를 편리하게 사용할 수 있도록 해준다. 그러나 언제 어디서나 서비스를 제공받을 수 있다는 것은 언제 어디서든지 정보가 누출되거나 왜곡될 위험성 또한 존재하기 마련이다. 특히, 프라이버시 문제가 해결되지 않고서는 우리 일상생활과 융합되어 편리함을 제공해주는 모바일 네트워크 환경이 오히려 모바일 네트워크 감시 체제를 구축하는 심각한 역기능을 초래하게 될 것이다. 모바일 단말기들은 크기와 모양이 다양하고 컴퓨팅 연산 능력이 적은 저성능 휴대 장치들이 많기 때문에, 컴퓨팅 연산이 많이 요구되는 공개키 암호 기술을 저성능 모바일 단말기에 적용하기는 힘든 상황이다. 이에 본 논문에서는 프라이버시 문제를 해결하면서, 컴퓨팅 연산 능력이 적은 저성능 모바일 단말기에 적용할 수 있는 자바 기반의 암호 모듈 및 PKI 기반의 사용자 인증을 제안하고자 한다. 국내 표준 암호 알고리즘(SEED)과 인증서를 기반으로 세션키와 공개키를 조합함으로서 최소한의 암복호화 연산을 통해 인증 및 전자 서명을 제공하며, 이를 대표적인 모바일 단말기인 PDA 환경에서 세션키 분배 및 사용자 인증이 안전하게 이루어짐을 확인할 수 있었다.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.44 no.3 s.357
• /
• pp.41-50
• /
• 2007

In this paper, a new Dual Round-Robin (DRR) based iterative SLIP (iSLIP) scheduling scheme, called DiSLIP is proposed for IP switching systems. By using DRR followed by iSLIP, DiSLIP can exploit desynchronization effect of DRR and high performance of iSLIP, while the drawbacks of two schemes are minimized. 'Through computer simulation, we verify the switch throughput and total waiting time of the proposed scheme under nonuniform and correlated self-similar traffic. Moreover, the proposed scheme can considerably reduce the complexity of parallel matching logics compared to iSLIP. From the result, we observe that the proposed scheme outperforms DRR on throughput as well as iSLIP schemes on complextiy.

• Korean Journal of Construction Engineering and Management
• /
• v.8 no.3
• /
• pp.159-167
• /
• 2007

In this study, the concepts of integrated VE analysis assessment is introduced in order to achieve "Design for Deterioration performance" in design VE phase. For this purpose, a framework for fuzzy reliability based LCC and value analysis model using fuzzy logic based approach for breakwaters Projects is suggested. It is anticipated that the methodology Proposed in this paper can also be utilized in the design and maintenance phase of other facilities where decision making is made for the fuzzy reliability based life cycle cost and value analysis.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.11 no.8
• /
• pp.1329-1336
• /
• 2000

A new fractal geometry of the traveling wave type cross antenna is newly presented. In the conventional type of the traveling wave antenna, the electrical length of the radiating conductor increases as the order of fractal expansion increases. But, increased length of the current path degrades the performance of the antenna from the various loss mechanism of the traveling wave type antenna. To reduce the antenna performance degradation, the new hybrid fractal antenna, which divides the entire fractal structure into some smaller ones and connects each smaller fractal group with a power divider is presented. The secondly, thirdly and fourthly expanded hybrid fractal cross antennas are fabricated and their performances are examined by measurements. Influences of the fractal order to the antenna performance are examined.

• KIPS Transactions on Computer and Communication Systems
• /
• v.4 no.5
• /
• pp.153-160
• /
• 2015

The effectiveness of multicores depends on how well a scheduler can assign tasks onto the cores efficiently. In a heterogeneous multicore platform, the execution time of an application depends on which core it executes on. That is to say, the effectiveness of task assignment is one of the important components for a multicore systems' performance. This work proposes a load scheduling technique that analyzes execution time of each task by profiling. The profiling result provides a basic information to predict which task-to-core mapping is likely to provide the best performance. By using such information, the proposed technique is about 26% performance gain.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.11a
• /
• pp.118-121
• /
• 2014

격자 양자 색역학(Lattice Quantum ChromoDynamics; Lattice QCD)은 자연계에 존재하는 중력, 전자 기력, 약한 핵력, 그리고 강한 핵력 등의 기본적인 상호작용 중 강한 핵력의 상호작용을 이해하기 위한 핵물리 분야의 이론이다. 이 물리 역학은 몬테 카를로(Monte Carlo) 기법을 이용하여 대규모 수치 연산을 필요로 하고, 수행시간 단축을 위하여 병렬처리가 필요하다. 본 논문에서는 격자 양자 색역학에서 요구되는 대규모 수치 연산에 대하여 마이크로프로세서와 성능가속기에 최적의 작업부하 분배를 통한 이기종 병렬처리 방법을 제안하고 성능가속기반을 사용한 방법과 제안 방법의 성능을 비교한다.