• Journal of the Korean Association of Geographic Information Studies
• /
• v.12 no.4
• /
• pp.113-124
• /
• 2009

A research of grid computing that is the combination of computer resources from multiple distributed administrative domains to get large amount of computing power is underway. This research is an application of grid technology on a urban facilities management system based on u-GIS. The sensors are set up in the urban facilities to make it monitoring. If an amount of sensors and gateways is increased, the server needs more computing resources to process the data. In this study we developed the skills that can distribute jobs to idle gateway, in case of the server capacity had approached threshold. It will be possible to develop of economic and efficient system that will apply to large amount of data processing about u-City.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.3B
• /
• pp.105-113
• /
• 2005

In this paper, through the implementation of the application service, we evaluated the feasibility and availability of the staged application service platform, which is based on the sharing of the PVM cluster. Application service platform provides three managers for dividing the request processing steps into two stages, such as a request processing stage and a service providing stage. Three managers and its relation to the divided stages are as follows, service manager and load manager to distribute the request in front-end server for a request processing stage, job manager in clustered(back-end) servers for a service providing stage. The experiment shows that the staged application service platform provides more stable and scalable characteristics and better performance improvement on the dynamic load changes than the single server system. And also it shows that real application service system can be implemented easily without modification of the proposed service platform.

• The KIPS Transactions:PartA
• /
• v.10A no.5
• /
• pp.439-452
• /
• 2003

Mobile agent is one of the good technologies for overcoming network load and latency in distributed applications, and it may be a promising way of base technology of distributed applications because of its high adaptability for various network environments. In this paper, a mobile agent programming system, called HUMAN, is designed and implemented efficient use in various distributed applications based on mobile agents. HUMAN supports such high level utilities as file searhing, addressing by groups of nodes, storing path information, storing search information, and thus it gives us high easiness in agent-based programming. And it provides various itinerary modes and flexible reply modes for easy adaptation to given network environment. It also provides a management server for registering and active agents. Thus it can be efficiently applied for such varous distributed applications as searching distributed information, remote control, and file sharing in networks. A simple electronic commerce system is designed is designed and implemented as a HUMAN based illustrative application.

• The KIPS Transactions:PartA
• /
• v.10A no.2
• /
• pp.123-130
• /
• 2003

This paper presents a new striped checkpointing scheme for serverless cluster computers, where the local disks are attached to the cluster nodes collectively form a distributed RAID with a single I/O space. Striping enables parallel I/O on the distributed disks and staggering avoids network bottleneck in the distributed RAID. We demonstrate how to reduce the checkpointing overhead and increase the availability by striping and staggering dynamically for communication intensive applications. Linpack HPC Benchamark and MPI programs are applied to these checkpointing schemes for performance evaluation on the 16-nodes cluster system. Benchmark results prove the benefits of the striped checkpointing scheme compare to the existing schemes, and these results are useful to design the efficient checkpointing scheme for fast rollback recovery from any single node failure in a cluster system.

• Journal of KIISE:Computing Practices and Letters
• /
• v.6 no.5
• /
• pp.543-554
• /
• 2000

In the conventional distance education systems, all functions for the distance education were processed by a server. Therefore, the system of high capacity was required and there were various restrictions to provide many classes in real-time simultaneously. The group-based distance education system proposed in this study reduces a load of the main server by distributing its functions to client PCs. In the group-based education system, the establishment of lecture or discussion rooms is executed by main server, but on the other hand, the functions of the conventional server are executed by a lecturer's PC or a discussion administrator's PC The test results of the system implemented in this study show that a lecturer's PC can afford to provide fifty trainees a lecture, though they depend on the specification of systems. Therefore, the proposed system in this study can afford to simultaneously provide with the various distance discussions and lectures by reducing a load concentrated to the server.

• KIPS Transactions on Computer and Communication Systems
• /
• v.2 no.7
• /
• pp.283-292
• /
• 2013

In order to ensure high performance, all the servers in an existing server cluster are always On regardless of number of real-time requests. They ensure QoS, but waste server power if some of them are idle. To save energy consumed by servers, the server power mode control was developed by shutdowning a server when a server is not needed. There are two types of server power mode control depending on when a server is actually turned off if the server is selected to be off: static or dynamic. In a static mode, the server power is actually turned off after a fixed time delay from the time of the server selection. In a dynamic mode, server power is actually turned off if all the services served in the server are done. This corresponds to a turn off after a variable time delay. The static mdoe has disadvantages. It takes much time to find an optimal shutdown time manually through repeated experiments. In this paper, we propose a dynamic shutdown method to overcome the disadvantages of static shutdown. The proposed method allows to guarantee user QoS with good power-saving because it automatically approaches an optimal shutdown time. We performed experiments using 30 PCs cluster. Experimental results show that the proposed dynamic shutdown method is almost same as the best static shutdown in terms of power saving, but better than the best static shutdown in terms of QoS.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.5
• /
• pp.143-150
• /
• 2019

Cloud computing has recently become an attractive solution for massively multiplayer online games(MMOGs), as it lifts operators from the burden of buying and maintaining hardware. Peer-to-peer(P2P) -based solutions present several advantages, including the inherent scalability, self-repairing, and natural load distribution capabilities. We propose a hybrid architecture for MMOGs that combines technological advantages of two different paradigms, P2P and cloud computing. An efficient and effective provisioning of resources and mapping of load are mandatory to realize an architecture that scales in economical cost and quality of service to large communities of users. As the number of simultaneous players keeps growing, the hybrid architecture relieves a lot of computational power and network traffic, the load on the servers in the cloud by exploiting the capacity of the peers. For MMOGs, besides server time, bandwidth costs represent a major expense when renting on-demand resources. Simulation results show that by controlling the amount of cloud and user-provided resource, the proposed hybrid architecture can reduce the bandwidth at the server while utilizing enough bandwidth of players.

• Annual Conference of KIPS
• /
• 2001.04a
• /
• pp.577-580
• /
• 2001

최근 정보통신 기술 발전 및 초고속 통신망의 발달로 인한 인터넷 망(network)상에서의 방송과 통신이 융합되는 추세가 가속화되고 있다. 이에 스트리밍(Streaming) 기술을 기반으로 한 멀티미디어 데이터의 서비스와 데이터 정보의 푸시(push) 기술을 결합하여 인터넷과 고속망상에서의 원활한 실시간 전송 서비스를 위하여 다중 서버를 지원하는 3-tier 방식의 스트리밍 시스템을 구현하였다. 구현된 시스템은 실시간 전송 프로토콜인 RTP(Real-time Transport Protocol)를 이용하여 송신자에게 멀티미디어 스트리밍 서비스를 제공하며, VOD(Video on Demand) 및 실시간 방송 서비스를 제공하는 분산 멀티미디어 스트리밍 전송 시스템이다. 전체 시스템은 인터넷 방송 서비스 제공을 위한 VOD 서버, 실시간 방송 서버 및 푸시 서버와 멀티미디어의 실시간 재생을 위한 클라이언트 인터페이스 등으로 구성되어 있으며, 안정적인 서비스를 위한 미들웨어에서의 부하분배 및 채널 정보의 관리를 가능하게 하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.74-77
• /
• 2019

Many enterprises and public institutions are building their own server stabilization system. Nevertheless, many web servers including some public institutions have frequent obstacles due to the unexpected causes such as traffic concentration. Data loss during each of these situations and business interruption can cause a huge loss. In this study, we propose high-availability Web system that uses load balancing and session clustering. Each deals with the failure due to the over traffic by distributing incoming requests in the multiplexed web server and provides the continuous services by maintaining session information of the users in case of the failure of some servers.

• Annual Conference of KIPS
• /
• 2001.10a
• /
• pp.289-292
• /
• 2001

에이전트 위임모델 기반 워크플로우 시스템은 기존 클라이언트 서버기반 워크플로우 시스템과 이동에이전트 기반 워크플로우 시스템보다 워크플로우 수가 증가하고 워크플로우 구조가 복잡해짐에 따라 보다 좋은 성능 및 확장성을 제공한다. 이는 에이전트 위임모델이 워크플로우 엔진에서 발생하는 병목현상을 제거하여 작업수행자(Task Performer)라 명명된 호스트들로 워크플로우 엔진의 부하를 자연스럽게 분산시키기 때문이다. 에이전트 위임모텔은 워크플로우 엔진의 부하를 제거하지만, 작업수행자의 부하를 고려하지 않고 작업을 할당하기 때문에, 작업수행자에 병목현상을 발생시킬 수 있다. 이는 에이전트 위임모델의 목적인 워크플로우 시스템의 성능 및 확장성 향상을 저해하는 요인이다. 따라서, 워크플로우 시스템의 성능 및 확장성을 향상시키기 위해서는 작업수행자에 발생하는 병목현상을 제거해야 한다. 본 논문에서는 작업수행자의 병목현상을 제거하기 위해 응답리스트(Response List)를 제안하며 응답리스트 관리방법을 제시한다. 이러한 응답리스트가 에이전트 위임모델 기반 워크플로우 시스템의 성능 및 확장성 향상에 어떠한 영향을 미치는지 성능평가를 수행한다.