• Proceedings of the Korea Multimedia Society Conference
• /
• 2003.11a
• /
• pp.379-382
• /
• 2003

본 논문에서는 멀티미디어 웹 서버에 나타나는 통신량을 추적하여 사용자의 액세스 패턴을 분석하고 그에 따른 캐싱 모델을 수립하였다. 적중률과 바이트적중률을 동시에 향상시키기 위한 파일 타입 캐시 정책을 제안하였으며, 성능을 평가한 결과 캐시의 유용성을 개선하였다.

• The KIPS Transactions:PartA
• /
• v.14A no.4
• /
• pp.235-244
• /
• 2007

Caching and prefetching policies have been used in most of computer systems to compensate speed differences between primary memory and secondary storage devices. In this paper, we design and implement a Flash Cache Core Module(FCCM) on the YAFFS which operates on a file system layer for NAND flash memory. The FCCM is independent of the underlying kernel in order to support its stability and compatibility. Also, we implement the Dirty-Last memory replacement technique considering the characteristics of flash memory, and the waiting queue for pages to be prefetched according to page hit. The FCCM reduced the number of I/Os and the amount of prefetched pages by maximum 55%(20% on average) and maximum 55%(24% on average), respectively, comparing with caching and prefetching policies of Linux.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2014.07a
• /
• pp.337-340
• /
• 2014

클라우드 시스템이 큰 이슈로 떠오르면서 그 기반이 되는 분산 파일 시스템에 관한 연구가 계속되고 있다. 최근 제안된 분산파일 시스템은 대부분 확장 가능하며 신뢰성이 있는 시스템으로 구성되어 있으며 내고장성(Fault tolerance)과 높은 가용성을 위해 데이터 복제 기법을 사용하며 하둡 분산 파일 시스템에서는 블락의 복제수를 기본3개로 지정한다. 그러나 이 정책은 복제수가 많아지면 많아질수록 가용성은 높아지지만 스토리지 또한 증가한다는 단점이 있다. 본 논문에선 이러한 문제점을 해결하기 위해 최소한의 블락 복제수와 복제된 블락을 효율적으로 배치하여 더 좋은 성능과 부하분산(Load Balancing)하기 위한 기법을 제안한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10c
• /
• pp.47-49
• /
• 2000

버퍼 캐쉬의 관리를 위해 많은 교체 정책들과 선반입 정책들이 연구되어져 왔다. 그러나, GNU/Linux를 포함한 많은 실제의 운영체제들은 일반적으로 Least Recently Used (LRU) 교체 정책을 사용한다. 본 논문에서는 끊임없이 적극적인 선반입이 이루어지는 가운데 버퍼관리와 선반입을 효율적으로 통합하는 SA-W2R 정책을 제안한다. 이 정책은 구현이 단순하여 실제 시스템에서 채택하기 용이하다. 이 정책은 기본적으로 버퍼 교체를 위하여 LRU 정책을 사용한다. 그러나 정책의 모듈성으로 인해 어떤 교체 정책도 이 정책에 적용될 수 있다. SA-W2R 정책에서는 선반입을 위해 오버헤드가 적어 일반적으로 많이 사용되는 LRU-One Block Lookahead(OBL) 정책을 사용한다. GNU/Linux 커널 버전 2.2.14에 구현된 SA-W2R 정책은 응용 프로그램의 실행 시간에 있어 현재 버전의 GNU/Linux 보다 최고 23%의 성능 향상을 보였다.

• The KIPS Transactions:PartA
• /
• v.9A no.2
• /
• pp.163-170
• /
• 2002

Previous buffer cache schemes for continuous media file system only exploited the sequentiality of continuous media accesses and didn't consider looping references. However, in some video applications like foreign language learning, users mark the scene as loop area and then application automatically playbacks the scene several times. In this paper, we propose a novel buffer cache scheme for continuous media file system that sequential and looping references exist together. Proposed scheme increases the cache hit ratio by detecting reference pattern of files and appling an appropriate replacement policy to each file.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.46 no.3
• /
• pp.41-50
• /
• 2009

The flash memory has many advantages such as low power consumption, strong shock resistance, fast I/O and non-volatility. And it is increasingly used in the mobile storage device. Many researchers are studying the YAFFS, NAND flash file system, which is widely used in the embedded device. However, the existing YAFFS has two problems. First, it takes long time to mount the YAFFS file system because it scans whole spare areas in all pages. Second, the cleaning policy of the YAFFS does not consider the wear-leveling so that it cannot guarantee the duration of data completely. In order to solve these problems, this paper proposes a new content-based YAFFS that consists of a mounting time reduction technique and a content-cleaning policy by using content-based block management. The proposed method only scans partial spare areas of some special pages and provides the block swapping which enables the wear-leveling of data blocks. We performed experiments to compare the performance of the proposed method with those of the JFFS2 system and YAFFS system. Experimental results show that the proposed method reduces the average mounting time by 82.2% comparing with JFFS2 and 42.9% comparing with YAFFS. Besides, it increases the life time of the flash memory by 35% comparing with the existing YAFFS whereas no overheat is added.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.33 no.1
• /
• pp.321-343
• /
• 2022

This study presents the direction of services and policies for digital file management in universities by identifying undergraduate students' digital file management behavior. The research defined the Life Cycle of Digital Objects. In addition, This research collected data from 154 undergraduate students using an online survey on their file Creation, Storing, Naming, Organizing, and Backup based on the Digital File Management Workflow. Also, an in-depth interview was conducted for 8 students, two for each major in engineering, arts, social science, and humanities. The result showed that students mostly used personal computers as storage media and USB drive as backup media and had their own file Naming and Organizing methods. Furthermore, students' satisfaction with digital file management was high when universities supported software and cloud storage. Therefore, this study suggests that universities need to provide services reflecting the students' digital file management behavior.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10c
• /
• pp.38-40
• /
• 2000

대용량 데이터 베이스, 멀티미디어 서버, 복잡한 과학 기술계산 등의 대용량의 데이터를 처리해야 하는 응용이 증가하고 있다. 이에 따라 파일 서비스의 속도를 높이기 위한 연구가 다방면에서 진행되고 있다. 파일 서비스 속도를 결정하는 중요한 두 부분 중의 하나인 액세스 시간개선을 위해서 좀더 효율적인 캐시, 선반입을 수행하기 위한 선수작업으로써 액세스 패턴을 실시간으로 분석하여 특징을 추출하고 관리하는 방법을 연구하였다.

• The Journal of the Korea Contents Association
• /
• v.3 no.3
• /
• pp.63-73
• /
• 2003

Today, in exponential growth of internet, the importance of file caching which could reduce the sun load, the volume of network traffic, and the latency of response has emerged. Actually, in one network, the traffic has reduced by using the cache and this means that file caching can improve the internet environment by cost a fraction of link upgrades. In this paper, we address a dynamic cache group configuration policy, to solve the scalable problem. The simulation result shows that the cache group using our proposal policy reduces the latency of response time and it means that out cache group configuration is more scalable than the static cache configuration.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.6
• /
• pp.194-210
• /
• 2022

The user-centered EV charging infrastructure construction policy the government is aiming for can increase convenience for electric vehicle users and bring new electric vehicle users into the market. This study was conducted to provide an in-depth understanding of the charging behaviors of actual electric vehicle users, which can be used as basic information for the electric vehicle charging infrastructure. Based on charging diary data collected for a week, the charging of electric vehicles was analyzed on a daily and weekly basis, and sequence analysis and latent class analysis were used. As a result, five daily charging profiles and four weekly charging profiles were identified, which are expected to contribute to revitalizing the electric vehicle market by providing key information for decision-making by potential electric vehicle users as well for establishing user-centered charging infrastructure policies in the future.