• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04a
• /
• pp.109-111
• /
• 2004

본 논문에서는 LCD 디바이스의 프레임버퍼 모니터링에 기반한 소프트웨어 단계의 저전력 LCD 관리 기법을 제시한다. 제안하는 기법은 Refresh-rate를 조절하여 기존 하드웨어에서 추가설비 없이 사용 가능하며, 커널 레벨로 동작하여 어플리케이션의 수정이 필요 없으며, 프레임 버퍼 모니터링을 통해 디스플레이의 퀼리티 보장이 가능한 특징을 가진다. 본 시스템은 Linux 운영체제 하에서 실제 구현되고, 실험을 통해 제안하는 기법이 사용자의 디스플레이 퀼리티 요구를 만족시키면서 저전력 관리를 수행할 수 있음을 밝힌다.

• The Journal of the Korea Contents Association
• /
• v.2 no.2
• /
• pp.73-84
• /
• 2002

In this paper, we propose a enhanced ERICA switch algorithm using the buffer management scheme which can reduce the queue length, support the efficiency link utilization and the fair share. It has three different buffer thresholds which are low threshold, congestion notification threshold and high threshold. According to the each buffer threshold status, switch announced congestion notification to the source differently. So, sources could know the congestion more quickly and fast remover from network congestion. As a experimental results, it is proved that proposed algorithm is the more efficient than ERICA. Especially, proposed switch algorithm provides congestion control mechanism to make the best use of with keeping fairness and reduce queue length.

• The KIPS Transactions:PartD
• /
• v.16D no.2
• /
• pp.153-160
• /
• 2009

Efficient buffer management is closely related to system performance. Thus, much research has been performed on various buffer management techniques. However, many of the proposed techniques utilize the temporal locality of access patterns. In spatial database environments, there exists not only the temporal locality but also spatial locality, where the objects in the recently accessed regions will be accessed again in the near future. Thus, in this paper, we present a buffer management technique, called BEAT, which utilizes both the temporal locality and spatial locality in spatial database environments. The experimental results with real-life and synthetic data demonstrate the efficiency of BEAT.

• Journal of KIISE
• /
• v.43 no.3
• /
• pp.327-335
• /
• 2016

In this paper, we propose a buffer management scheme suitable for interactive multimedia services. We consider a typical delay optimization environment so that receiver buffer lengths vary according to the round trip time estimation. In this environment, we propose an optimization technique for minimizing the loss of information that may occur when a reduced buffer length forces I/P/B frames in the buffer to drop. We modeled our problem as a Knapsack Problem for which we used dynamic programing in order to find an approximate solution. The proposed technique is compared with the existing buffer management techniques. Through simulation studies, we found that our approach could increase PSNR, which is important to video quality.

• Proceedings of the Korea Contents Association Conference
• /
• 2009.05a
• /
• pp.51-56
• /
• 2009

Flash memory has rapidly deployed as data storage. However, the flash memory has a major disadvantage that recorded data cannot be dynamically overwritten. In order to solve this "erase-before-write" problem, the log block buffer scheme used Flash memory file system. however, the current managements of the log buffer, in case random write pattern, BAST technique have problem of frequent merge operation, but FAST technique don't consider merge operation by frequently updated data. Previous methods not consider merge operation cost and frequently updated data. In this paper, we propose a new log buffer management scheme, called JBB. Our proposed method evaluates the worth of the merge of log blocks, so we conducts the merge operation between infrequently updated data and its data blocks, and postpone the merge operation between frequently updated data and its data blocks. Through the method, we prevent the unnecessary merge operations, reduce the number of the erase operation, and improve the utilization of the flash memory storage. We show the superiority of our proposed method through the performance evaluation with BAST and FAST.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.15 no.6
• /
• pp.129-134
• /
• 2015

This paper analyzes file access characteristics of smartphone apps and finds that a large portion of file writes are performed only once. Based on this observation, we present a new buffer cache management scheme that considers this characteristics. Buffer cache improves storage performance by maintaining hot file data in memory thereby servicing subsequent requests without storage accesses. However, it should flush modified data to storage in order to resist system crashes. The proposed scheme evicts cache data that has been written only once upon flushes, thus improving cache space utilization. Simulation experiments show that the proposed scheme improves cache hit ratio by 5-33% and power consumption by 27-92%.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.1
• /
• pp.157-162
• /
• 2011

In this paper, we propose enhanced methods of path finding based on an abstract graph with extension of search space to improve the quality of path. The proposed methods that are called simple buffering method, velocity constrained method and distance constrained method are to extract buffering-cells for using search space with valid-cells. The simple buffering method is to extract adjacent cells of valid-cells as buffering-cells. velocity constrained method and distance constrained method are based on simple buffering method, these eliminate buffering-cells through each of threshold. In experiment, proposed methods can improve the quality of path. The proposed methods are applicable to develop various kinds of telematics application, such as path finding and logistics.

• Proceedings of the Korea Institutes of Information Security and Cryptology Conference
• /
• 2001.11a
• /
• pp.111-114
• /
• 2001

시스템 침입을 위해서 사용할 수 있는 공격 기법은 그 종류가 매우 다양하다. 그러나 최종적인 시스템 침입의 목표는 버퍼오버플로우 공격을 통한 관리자 권한의 획득이다. 버퍼오버플로우 현상은 메모리 공간의 경계 영역에 대한 프로그래밍 언어 수준의 검사 도구를 제공하지 않는 C/C++ 의 언어적 특성으로 인해 발생한다. 본 논문에서는 리눅스 커널 수준에서 시스템 보안을 위한 참조 모니터를 제안하고 이를 이용하여 버퍼오버플로우 공격에 대응할 수 있는 보안 기법을 제시한다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.5
• /
• pp.155-160
• /
• 2018

In this paper, we found that buffer cache in general systems does not perform well in rendering software, and presented a new buffer cache management scheme that resolves this problem. To do so, we collected various file I/O traces of rending software and analyzed their characteristics. From this analysis, we observed that file I/Os in rendering consist of long loops, short loops, random accesses, and write-once accesses. Based on this observation, we presented a buffer cache management scheme that allocates cache space to each access types and manages them appropriately, thereby improving the buffer cache performances by 19% on average and up to 55%.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.10c
• /
• pp.358-360
• /
• 2004

컴퓨터와 네트워크 환경의 발달에 힘입어 고화질의 미디어 데이터를 실시간으로 전송하는 미디어 스트리밍 서비스에 대한 요구가 증가하고 있다. 스트리밍 서비스는 서버의 많은 자원을 필요로 한다. 서버의 자원 중에서 메인 메모리는 대용량의 미디어 데이터를 다루는 미디어 스트리밍 서버 성능에 중요한 역할을 한다. 그러므로 제한된 메인 메모리를 효과적으로 이용할 수 있는 방법이 필요하다. 본 논문에서는 효과적인 미디어 스트리밍 서비스를 위한 동적 버퍼 관리 기법과 버퍼 히트율을 높일 수 있는 대체 정책을 제안하고 평가한다.