• The KIPS Transactions:PartD
• /
• v.17D no.6
• /
• pp.395-404
• /
• 2010

Solid-State Disks (SSDs) have been currently considered as a promising candidate to replace hard disks, due to their significantly short access time, low power consumption, and shock resistance. SSDs, however, have drawbacks such that their write throughput and life span are decreased by random-writes, nearly regardless of SSDs controller designs. Previous studies have mostly focused on better designs of SSDs controller and reducing the number of write operations to SSDs. We suggest another method that reallocates data pages that tend to be simultaneously written to contiguous blocks. Our method gathers write operations during a period of time and generates write traces. After transforming each trace to a set of transactions, our method mines frequent itemsets from the transactions and reallocates the pages of the frequent itemsets. In addition, we introduce an algorithm that reallocates the pages of the frequent itemsets with moderate time complexity. Experiments using TPC-C workload demonstrated that our method successfully reduce 6% of total logical block access.

• Journal of KIISE:Computer Systems and Theory
• /
• v.28 no.5
• /
• pp.228-235
• /
• 2001

본 논문에서는 분산메모리를 가진 병렬 컴퓨터에서 밀집 행렬 연산을 위한 PoLAPACK 패키지를 소개한다. PoLAPACK은 새로운 연산 기법을 적용한 LU, QR, Cholesky 인수분해 알고리즘들을 포함하고 있다. 블록순환분산법으로 분산되어 있는 행렬에 알고리즘적인 블록 기법(algorithimic blocking)을 적용하여, 실제 행렬의 분산에 사용된 블록의 크기와 다른, 최대의 성능을 보일 수 있는 최적의 블록 크기로 연산을 수행할 수 있다. 이러한 연산 방식은 분산되어 있는 원래의 행렬 A의 순서를 따르지 않으며, 따라서 최적의 블록 크기로 연산을 수행한 후에 얻어진 해 x를 원래 행렬 분산법을 따라서 재배치하여야 한다. 본 연구는 Cray T3E 컴퓨터에서 구현하였으며 ScaLAPACK의 인수분해 루틴들과 그 성능을 비교.분석하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10a
• /
• pp.557-559
• /
• 2000

본 논문에서는 기존의 정렬 알고리즘의 성능을 향상시키기 위하여 정보블록 전처리알고리즘(IBPA)이라는 전처리 알고리즘을 제안한다. IBPA는 정렬된 리스트(list)에 있는 데이터에 관한 정보를 생성하고, 생성된 정보를 이용하여 각 데이터를 재배치하며, 실제적인 정렬은 기존의 정렬 알고리즘을 그대로 이용하여 이루어진다. IBPA의 성능을 측정해본 결과, 2백만개의 랜덤데이터를 정렬한 경우, O(N2)의 평균시간복잡도를 갖는 정렬알고리즘의 0.003%, O(NlogN)의 평균시간복잡도를 갖는 정렬알고리즘의 52%, 그리고 O(N)의 평균시간복잡도를 갖는 정렬알고리즘의 89%정도의 비교회수만으로도 정렬할 수 있음을 보여주었다.

• Journal of Digital Contents Society
• /
• v.9 no.4
• /
• pp.543-550
• /
• 2008

There exist many QoS problems such as delay and jitter for mobile streaming due to limited bandwidth. This paper proposed a transaction update method based on Fuzzy chunk to solve the problems. The proposed method updated a transaction, which is classified as a read or an update, using Fuzzy filtering. A chunk block is rearranged according to the fuzziness which is classified as better relevance for fuzziness greater than 0.8, relevance for fuzziness between 0.5 and 0.7, and less irrelevance for fuzziness less than 0.5. According to the simulation result for the rearranged chunk block, the proposed method has better performance than those of RBM(Randon Based method), DBM(Distance Based Method), and FBM(Frequency Based Method).

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.42 no.4
• /
• pp.291-297
• /
• 2014

A Design of Experiments(DOE) approach to an experimental study of fuselage drag and stability characteristics of a helicopter configuration was applied to achieve an accuracy improvement in the wind tunnel testing. The impact of blocking the test was assessed by comparing the ANOVA table for the blocked and unblocked cases. For a second-order response model, the role of blocking resulted in a substantial increase in the accuracy of test results. These accuracy improvement could be achieved through randomization, blocking, and replication of the data points i.e. a re-ordering of the test sequence where the data were acquired.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2006.05a
• /
• pp.1186-1193
• /
• 2006

이적작업은 하역작업 시간을 단축하고 장치장의 효율을 높이기 위해 최근 중요하게 다루어지는 운영 전략들 중의 하나이다. 자동화 컨테이너 터미널에서 수출 컨테이너 이적작업은 작업영역에 제약을 가진 하역장비를 이용하여 장치장 블록에 산재되어 있는 수출 컨테이너들을 적하작업이 용이한 형태로 재배치하는 것이다. 이 연구는 이적 및 적하작업과 연관된 총비용을 최소화하기 위해 어느 베이의 어떤 컨테이너를 어느 베이로 재배치할 지를 결정하기 위한 이적계획을 정의하고 이를 혼합정수계획법으로 모형화하였다. 또한, 실제 현장에서 사용이 가능한 휴리스틱 알고리즘을 제안하였으며 다양한 시나리오를 구성하여 배치형태 및 비용 가중치 등에 대한 민감도를 분석하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 1998.10c
• /
• pp.571-573
• /
• 1998

정보전달에 있어서 멀티미디어 정보가 차지하는 비중이 점점 증대됨에 따라 멀티미디어 데이터 암호화의 필요성이 부각되고 있는 실정이다. 그러나 기존의 암호화에 일반적으로 적용되어온 DES(Data Encription Standard)와 같은 전통적인 암호화 알고리즘은 멀티미디어 데이터를 암호화하여 실시간으로 처리하기에는 충분히 신속하지 못한 단점이 있다. 그래서 본 논문에서는 디지털 이미지 프로세싱 기법중 압축기법과암호화 기법을 일련의 과정으로 통합하여 멀티미디어 정보의 중요부분을 차지하는 디지털 이미지의 실시간 암호화 처리기법을 연구하였다. 디지털 이미지의 저주파수 성분과 고주파수 성분을 다단계의 레벨로 분리하여 각 대역별로 성분을 집중시킨 후 임의의 배치 순서로 재배치하는 방법을 통해 DCT(Discrete Cosine Transform)과정 및 양자화과정을 거친 공간주파수 성분을 Zig-Zag순서가 아닌 임의의 배치 순서로 재배열할 때 발생되는 이미지의 크기가 상대적으로 커지는 점과 저주파수 성분이 주요 성분으로 구성된 이미지의 경우 해독이 비교적 용이하다는 점, 또한 약간의 응용으로 각 블록의 DC값만을 추출하여 이미지의 주요 내용을 파악할 수 있는 문제점을 해결하였다.

• The Journal of the Korea Contents Association
• /
• v.13 no.9
• /
• pp.20-27
• /
• 2013

In recently years, with the growth of social media and the development of mobile devices, the data have been significantly increased. MapReduce is an emerging programming model that processes large amount of data. However, since MapReduce evenly places the data in the dedicated distributed computing environment, it is not suitable to the non-dedicated distributed computing environment. The data replacement algorithms were proposed for performance optimization of MapReduce in the non-dedicated distributed computing environments. However, they spend much time for date replacement and cause the network load for unnecessary data transmission. In this paper, we propose an efficient data replacement algorithm for the performance optimization of MapReduce in the non-dedicated distributed computing environments. The proposed scheme computes the ratio of data blocks in the nodes based on the node availability model and reduces the network load by transmitting the data blocks considering the data placement. Our experimental results show that the proposed scheme outperforms the existing scheme.

• The Journal of the Acoustical Society of Korea
• /
• v.38 no.2
• /
• pp.207-213
• /
• 2019

In this paper, we evaluate the communication performance of convolutional code with block interleaving in a frequency-selective channel. Block interleaving is a technique for spreading and rearranging digital data streams. A block interleaving technique is applied to improve the performance by dispersing the concentration of burst errors in a frequency-selective channel. As a result of evaluating the performance of the convolutional code with block interleaving in the water tank experiment, There was no difference in the performance of convolutional codes using block interleaving in a frequency-selective channel. However, in the frequency-selective channel, the convolutional code with block interleaving has a gain of 2dB, and it is confirmed that the underwater acoustic communication performance is improved.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.6
• /
• pp.21-30
• /
• 2011

In the global IT market, a lot of issues for responding to various environmental regulations emerged. In case of the data centers, it is consuming huge amounts of energy to maintain. So there have been various technical attempts as Consolidation, Virtualization, Optimization to efficiently manage energy and data storage to fix the problems. In this paper, we propose a new RAID(Redundant Array of Independent Disks) mechanism which is differing the intensity of power consumption and works to provide data protection and disaster recovery(backup, mirroring etc.) to stratify multiple volumes. G-RAID minimize the power consumption and the lower of I/O performance by selecting the volume depending on the frequency of data access while classifying the power consumption between volumes in storage system. Also, it is possible that a filesystem and block map information of G-RAID is processed by basic unit which is group located in a row for the blocks to work efficiently and can minimize the performance degradation of block mapping load by the access frequency in each groups. As a result, we obtained to elevate a little bit of response time caused by block relocation work, but showed the decrease of power consumption by 38%.