• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.5
• /
• pp.2379-2397
• /
• 2017

Content distribution technology, which routes content to the cache servers, is considered as an effective method to reduce the response time of the user requests. However, due to the exponential increases of content traffic, traditional content routing methods suffer from high delay and consequent inefficient delivery. In this paper, a content selection policy is proposed, which combines the histories of cache hit and cache hit rate to collaboratively determine the content popularity. Specifically, the CGM policy promotes the probability of possible superior paths considering the storage cost and transmission cost of content network. Then, the content routing table is updated with the proportion of the distribution on the paths. Extensive simulation results show that our proposed scheme improves the content routing and outperforms existing routing schemes in terms of Internet traffic and access latency.

• The Journal of the Korea Contents Association
• /
• v.8 no.11
• /
• pp.57-64
• /
• 2008

The data grid computing provides geographically distributed storage resources to solve computational problems with large-scale data. Unlike cache replacement policies in virtual memory or web-caching replacement, an optimal file replacement policy for data grids is the one of the important problems by the fact that file size is very large. The traditional file replacement policies such as LRU(Least Recently Used), LCB-K(Least Cost Beneficial based on K), EBR(Economic-based cache replacement), LVCT(Least Value-based on Caching Time) have the problem that they have to predict requests or need additional resources to file replacement. To solve theses problems, this paper propose SBR-k(Sized-based replacement-k) that replaces files based on file size. The proposed policy considers file size to reduce the number of files corresponding to a requested file rather than forecasting the uncertain future for replacement. The results of the simulation show that hit ratio was similar when the cache size was small, but the proposed policy was superior to traditional policies when the cache size was large.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.16 no.3
• /
• pp.7-12
• /
• 2016

DRAM is commonly used as a smartphone memory medium, but extending its capacity is challenging due to DRAM's large battery consumption and density limit. Meanwhile, smartphone applications such as social network services need increasingly large memory, resulting in long latency due to additional storage accesses. To alleviate this situation, we adopt emerging nonvolatile memory (NVRAM) as smartphone's buffer cache and propose an efficient management scheme. The proposed scheme stores all dirty data in NVRAM, thereby reducing the number of storage accesses. Moreover, it separately exploits read and write histories of data accesses, leading to more efficient management of volatile and nonvolatile buffer caches, respectively. Trace-driven simulations show that the proposed scheme improves I/O performances significantly.

• Journal of the Korea Society for Simulation
• /
• v.16 no.2
• /
• pp.9-15
• /
• 2007

As the Internet grows and the mass multimedia data become popular, the storage system migrates from DAS, where the storage and the server are directly connected, to SAN and NAS. SAN connects the storages with a separate network, and NAS provides only file services, connects the storages with IP network. However, SAN and NAS can not fulfill the needs for companies if used separately, thus are asked to be integrated. In this research, we propose an efficient data sharing method which employees the concept of GMC, Croup Master Cache for the integrated environment of SAN and NAS. GMC is based on MCI, Metadata server and Cluster system Integration, but tries to solve the high expansion cost problem with MCI. We introduce the basic concept of GMC, compare the performance of GMC with that of MCI using computer simulation.

• The KIPS Transactions:PartA
• /
• v.13A no.6 s.103
• /
• pp.511-516
• /
• 2006

The data grid computing provides geographically distributed storage resources to solve computational problems with large-scale data. Unlike cache replacement policies in virtual memory or web-caching replacement, an optimal file replacement policy for data grids is the one of the important problems by the fact that file size is very large. The traditional file replacement policies such as LRU(Least Recently Used) LCB-K(Least Cost Beneficial based on K), EBR(Economic-based cache replacement), LVCT(Least Value-based on Caching Time) have the problem that they have to predict requests or need additional resources to file replacement. To solve theses problems, this paper propose SBR-k(Sized-based replacement-k) that replaces files based on file size. The results of the simulation show that the proposed policy performs better than traditional policies.

• Journal of KIISE
• /
• v.42 no.8
• /
• pp.954-960
• /
• 2015

It is important to improve the performance of storage in the home cloud environment within the virtualized IoT gateway since the performance of applications deeply depends on storage. Though SSD caching is applied in order to improve the storage, it is only used for read-cache due to the limitations of SSD such as poor write performance and small write endurance. However, it is important to improve performance of the write operation in the home cloud server, in order to improve the end-user experience. This paper propose a novel SSD caching which considers write-data as well as read-data. We validate the enhancement in the performance of random-write by transforming it to the sequential patterns.

• Journal of Communications and Networks
• /
• v.8 no.3
• /
• pp.330-338
• /
• 2006

Many web cache systems and policies concerning them have been proposed. These studies, however, consider large objects less useful than small objects in terms of performance, and evict them as soon as possible. Even if this approach increases the hit rate, the byte hit rate decreases and the connections occurring over congested links to outside networks waste more bandwidth in obtaining large objects. This paper puts forth a client-cluster approach for improving the web cache system. The client-cluster is composed of the residual resources of clients and utilizes them as exclusive storage for large objects. This proposed system achieves not only a high hit rate but also a high byte hit rate, while reducing outgoing traffic. The distributed hash table (DHT) based peer-to-peer lookup protocol is utilized to manage the client-cluster. With the natural characteristics of this protocol, the proposed system with the client-cluster is self-organizing, fault-tolerant, well-balanced, and scalable. Additionally, the large objects are managed with an index based allocation method, which balances the loads of all clients well. The performance of the cache system is examined via a trace driven simulation and an effective enhancement of the proxy cache performance is demonstrated.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.5
• /
• pp.791-800
• /
• 2022

CCN, which has emerged to overcome the limitations of existing network structures, enables efficient networking by changing the IP Address-based network method to the Content-based network method. At this time, the contents are stored on each node(router) rather than on the top server, and considering the limitation of storage capacity, it is very important to determine which contents to store and release through the cache policy, and there are several cache policies that have been studied so far. In this paper, two of the existing cache policies, producer popularity-based and distance-based, were mixed. In addition, the mixing ratio was set differently to experiment, and we proved which experiement was the most efficient one.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10c
• /
• pp.4-6
• /
• 2001

본 논문에서는 SAN(Storage Area Network) 기반의 공유파일시스템인 Asphodel 파일 시스템을 이용하여 를러스터 웹 서버를 구성하였다. 그리고 Asphodel 공유 파일 시스템이 가지는 락(lock) 서버를 이용하여 효율적인 웹 분배 정책인 CARD(Cache-Aware Request Dispatch)를 제안하고 이를 설계 구현하였다. 그 결과 후위 서버의 메모리 캐쉬의 적중률을 높임으로써 보통의 분배 정책인 라운드로빈(Round-Robin) 방식에 비해 웹 서버의 throughput과 latency에서의 성능 향상을 보였다.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.8
• /
• pp.868-872
• /
• 2010

Many embedded Java systems are equipped with limited memory, which can constrain the code cache size provided for Java just-in-time compilation, affecting the Java performance. This paper proposes expanding the limited code cache when it is full, by saving the machine code for some methods in the code cache into the file system of the permanent storage and reloading it to the code cache when they are re-invoked later. This is applying the client ahead-of-time compilation during the execution time for the purpose of enlarging the code cache. Our experimental results indicate that the proposed execution method can improve the performance by as much as 1.6 times compared to the conventional method, when the code cache size is reduced by half.