• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2000년도 봄 학술발표논문집 Vol.27 No.1 (A)
• /
• pp.394-396
• /
• 2000

Currently, lots of research s going on in the field of the load distribution within HTTP. RR-DNS and SWEB are the most representative load distribution research. But, there are still many problems: unbalancing of load, load increase of web server and cost increase. Also, clients that require lots of data like multimedia happens to increase network load. To solve these, research about client/agent/server architecture is going on. But, the clients must know the agent's address and there are complexity and migration problems for design of such as protocol. This paper proposes TBSMS that is capable of choosing the optimal server considering the service capacity of the server as well as the network load. This paper demonstrates that TBSMS uses the web to solve the problem that client must know the agent's address and uses SNMP to solve the complexity and migration problem.

• 대한산업공학회지
• /
• 제27권1호
• /
• pp.89-94
• /
• 2001

There are many queueing systems where customers wait for service up to a certain amount of time and leave the system if they are not served during that time. This paper considers a finite capacity multi-server queueing system with Poisson input and Erlang service time, where a customer becomes a lost customer when his service has not begun within an exponential patient time after his arrival. Performance measures such as average queue length, the average number of customers in service, and the proportion of lost customers can be obtained exactly through the proposed numerical solution procedure.

• 한국멀티미디어학회논문지
• /
• 제21권3호
• /
• pp.358-368
• /
• 2018

The mobile characteristics of the smart phone are well suited to on-the-site oriented services and are being utilized in a variety of ways. However, since most applications operate on a central server basis, Internet access is inevitable, and there are various problems such as an increase in server maintenance cost and security deterioration. Although researches have been proposed to utilize the smart phone itself as a server to improve it, these methods are based on downsizing the PC-based web server or modifying the smart phone kernel. These methods have the problems that a end user has to use the rooting, and they are not able to effectively utilize various communication means of a smart phone. In this paper, we propose a design and implementation of an application level smart phone web server. The server receives the document request from the remote via the Internet and in the local area using the WPAN. At this time, the web document is stored as an internal file structure of the smart phone application. We proposed the phttp protocol which uses server's phone number as ID for document request. Through the implementation, we analyzed the capacity and latency of stored data and its effectiveness is evaluated.

• 한국시뮬레이션학회논문지
• /
• 제13권1호
• /
• pp.41-50
• /
• 2004

The purpose of this paper is to analyse the manager's policy to maximize the profit in a multiple-server queueing facility with a limited queue capacity. We assume that the level of advertizing effects on the arrival rate of customers to the facility. The model without ‘word of mouth effect’ is assumed that the arrival rate is independent on the qualify of service level. We estimate the service quality by the balking rate of customers from system. We extend this to the model with ‘word of mouth effect’. To achieve the maximum profit, the most important factor is the considerably high utilization of facility for both models. Given service rate, we should maintain an effective arrival rate to some extent. To this end, among the available options, an increase of advertizing effort is more desirable than reducing the fee if the service value of customers remains unchanged. We also investigate whether the variability of service time has a significant impact on determining the optimal policy. The cost of service variability is not so expensive as that in a single server model due to the reduced variability of service times in a multiple-server model.

• 디지털콘텐츠학회 논문지
• /
• 제2권1호
• /
• pp.73-79
• /
• 2001

VOD 서비스를 제공하는 서버는 클라이언트에게 좋은 서비스를 제공하기 위하여 요청을 처리할 수 있는 여러 개의 부본서버를 이용한다. 또한 시공간적으로 다양한 환경으로부터 요청된 클라이언트의 요구를 가장 효과적으로 처리할 수 있는 서버를 선택하기 위한 다양한 서버 선택 알고리즘들이 제안되었다. 선택 알고리즘은 각 부본서버의 성능을 평가할 수 있는 척도에 의하여 클라이언트의 요청을 적절하게 분산시켜야 서버 부하의 균형이 이루어지고 서비스의 질이 향상된다. 이때 척도를 어떻게 결정하느냐 하는 것이 선택알고리즘의 성능을 결정짓는 중요한 요소이다. 본 논문에서는 서버의 성능에 따라 서비스 요청을 분산시킴으로써 QoS를 향상시키는 데 중점을 둔 에이전트 시스템을 제안하고자 한다. 이 시스템은 부본서버 성능 분석자, 지식베이스, PCI 알고리즘기반 오토마타로 구성하였다. 학습자들의 요청에 응답한 각각의 서버로부터 수집한 로그를 분석하고, 조사하여 지식베이스를 생성하고 이로부터 추출한 규칙에 의하여 서비스를 제공할 서버를 선택한다. 여러 개의 부본서버 중 사용자 요청에 대하여 가장 좋은 서비스를 제공할 것으로 기대되는 서버를 동적으로 선택한다.

• 한국컴퓨터산업학회논문지
• /
• 제2권3호
• /
• pp.329-340
• /
• 2001

비디오 데이터베이스는 비디오 정보를 저장하고 있다가 사용자가 요구한 비디오 정보를 검색해 주는 기능을 갖는다. 따라서, 비디오 데이터베이스의 목적은 비디오정보를 저장하고 검색하기 위한 편리하고도 효율적인 환경을 제공해야 할 뿐만 아니라 보다 많은 사용자들에게 보다 신속하게 요구한 정보들을 검색해 줄 수 있어야 한다. 본 논문에서는 비디오 데이터베이스에서 빠른 응답을 유지하면서 지원할 수 있는 사용자들의 수를 증가시킬 수 있는 저장시스템을 제안한다. 다중 디스크환경하의 저장시스템에서 다중 비디오 스트림들을 읽을 때, 각 디스크헤드들의 이동을 비동기화 시킴으로써 빠른 응답을 유지할 수 있고, 한쪽 방향으로만 이동하게 함으로써 디스크 대역폭을 절약할 수 있다. 또한, 더블버퍼링을 기반으로 비디오 스트림의 시간제약 특성을 만족시키고 더블버퍼링의 단점을 최소화할 수 있는 기법을 제안한다. 새로운 저장시스템에 대한 타당성은 이론적으로 해석 및 증명되고 시뮬레이션을 통하여 평가된다.

• 한국정보처리학회논문지
• /
• 제7권2S호
• /
• pp.656-665
• /
• 2000

A critical issue in the performance of a video-on-demand system is the I/O bandwidth required in order to satisfy client requests. Several approaches: batching, bridging, piggybacking are used ot reduce the I/O demand on the video server through sharing. Piggybacking is the policy for altering display rates of requests in progress fro the same object, for the purpose of merging their corresponding I/O streams into a single stream, which can serve the entire group of merged requests. In this paper, we propose a new policy called an adaptive reservation-based piggybacking that dynamically reserves the I/O stream capacity of video server for popular videos according to video server loads to immediately schedule the requests for popular videos. The performance of the proposed policy is evaluated through simulations, and is compared with that of simple piggybacking. As the result, we know that the adaptive reservation-based piggybacking provides better service probability, average waiting time and percentages saving in frames than simple piggybacking.

• 한국항해학회지
• /
• 제21권2호
• /
• pp.19-40
• /
• 1997

When designing new marine traffic routes, it is desirable that the congestion due to traffic volume is evaluated by theoretical traffic capacity or by traffic simulation. Most of these techniques are applied to single server which is not considered channel width. Over-taking or paralle sailing of two or more vessels is allowalbe in Dover, Uraga, Gaduk-sudo, etc under their traffic capacity. In this paper, the Bumper Model is introduced to multiple severs in narrow channel and applied to Uraga Channel in Japan. The minimum width of Uraga Channel is 1, 400 m and its design traffic capacity is evaluated 19.26 ~ 19.52% of the basic traffic capacity. The traffic capacity on Gaduk Channel according to Busan New Port Development in 2011 will be estimated 3.59 % of maximum density and equal to 18.6% of that on Uraga Channel in 1992. The channel width Gaduk-sudo is designed 1, 600~2, 460 m and evaluated safe enough.

• 디지털산업정보학회논문지
• /
• 제4권2호
• /
• pp.101-108
• /
• 2008

In this paper, we develop system to backup automatically personal data by real time based on ECA model. This system backups data that is changed in user PC using CDP technology based on ECA model. Proposed ECA model defines file's change such as file creation, update, remove etc. in user PC to event for synchronization between server and user PC. If event is detected about file, proposed system examines condition that is defined and backup the file to server. Backup data that is stored to server can recovery on point of time that user wants. The proposed system can be applied to data management system for business, personal data management system, high-capacity contents management system etc.

• 한국정보처리학회논문지
• /
• 제6권10호
• /
• pp.2790-2796
• /
• 1999

In video-on-demand systems, the I.O bandwidth of video servers is the critical resource which contributes to increase in latency. Several approaches: bridging, piggybacking are used to reduce the I/O demand on the video server through sharing. Batching delays the requests for the different videos for a batching window so that more requests for the same video arriving during the current batching window may be served using the same stream. In this paper, we propose an adaptive reservation-based batching policy which dynamically reserves video server capacity for popoular videos according to video server loads. The performance of the proposed policy is evaluated through a simulation, and is compared with simple batching and static reservation-based batching policies. As the result, we know that the adaptive reservation-based batching policy more improves service ratio and average waiting time than simple batching and simple reservation-based batching policy more improves service ratio and average waiting time than simple batching and simple reservation-based batching polices.