• 한국정보과학회논문지:시스템및이론
• /
• 제37권3호
• /
• pp.127-137
• /
• 2010

다양한 과학 분야에서 대규모의 계산집중적인 어플리케이션들이 많은 그리드 자원을 활용해감에 따라 그 실행 관리와 제어의 어려움도 증가하였다. 어플리케이션의 반복되는 실행으로 축적된 작업 이력을 참조하여 어플리케이션의 특성을 파악하고 그리드 자원 선택 정책을 결정하였다. 본 논문은 그리드 컴퓨팅 환경과 이를 활용한 어플리케이션의 이력을 분석하기 위해 통계적 기법인 PBDF(Plackett-Burman with Fold-Over)계획법을 적용하였다. PBDF는 그리드 환경과 어플리케이션에서 주요한 요인들을 파악하고, 그것들이 얼마만큼 영향을 미치는 가를 수치화한다. 영향력 큰 요인은 작업 이력에서 참조 프로파일을 찾고 적절한 자원을 선택하는데 사용하였다. 응용의 수행 결과를 다시 작업 이력에 포함시키고 인자의 신뢰도를 조정하였다. 본 연구는 항공우주 연구 그리드의 작업 이력을 분석하여 적응형 자원 선택 알고리즘을 제안하였다. 주요한 요인들의 영향력을 계산하고 자원 선택 정책에 반영하는 실험을 하였다. 또한, 수행이 끝난 후 인자의 신뢰도를 평가해 그리드 환경 변화에 적응하는 알고리즘의 유효성을 검증하였다. 오류가 빈번한 그리드 환경에서 자원 선택 기법을 평가하기 위해 다양한 시나리오에서 그 적응력을 실험하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권9호
• /
• pp.3126-3145
• /
• 2014

Cloud computing is a computing paradigm in which users can rent computing resources from service providers according to their requirements. A spot instance in cloud computing helps a user to obtain resources at a lower cost. However, a crucial weakness of spot instances is that the resources can be unreliable anytime due to the fluctuation of instance prices, resulting in increasing the failure time of users' job. In this paper, we propose a Genetic Algorithm (GA)-based workflow scheduling scheme that can find the optimal task size of each instance in a spot instance-based cloud computing environment without increasing users' budgets. Our scheme reduces total task execution time even if an out-of-bid situation occurs in an instance. The simulation results, based on a before-and-after GA comparison, reveal that our scheme achieves performance improvements in terms of reducing the task execution time on average by 7.06%. Additionally, the cost in our scheme is similar to that when GA is not applied. Therefore, our scheme can achieve better performance than the existing scheme, by optimizing the task size allocated to each available instance throughout the evolutionary process of GA.

• ETRI Journal
• /
• 제34권2호
• /
• pp.288-291
• /
• 2012

In this letter, a new online anomaly detection approach for software systems is proposed. The novelty of the proposed approach is to apply a new semantic kernel function for a support vector machine (SVM) classifier to detect fault-suspicious execution paths at runtime in a reasonable amount of time. The kernel uses a new sequence matching algorithm to measure similarities among program execution paths in a customized feature space whose dimensions represent the largest common subpaths among the execution paths. To increase the precision of the SVM classifier, each common subpath is given weights according to its ability to discern executions as correct or anomalous. Experiment results show that compared with the known kernels, the proposed SVM kernel will improve the time overhead of online anomaly detection by up to 170%, while improving the precision of anomaly alerts by up to 140%.

• 한국산업정보학회:학술대회논문집
• /
• 한국산업정보학회 2003년도 추계공동학술대회
• /
• pp.621-626
• /
• 2003

Mining association rules in web log files can be divided into two steps: 1) discovering frequent item sets in web data; 2) extracting association rules from the frequent item sets found in the previous step. This paper suggests an algorithm for finding frequent item sets efficiently The essence of the proposed algorithm is to transform transaction data files into matrix format. Our experimental results show that the suggested algorithm outperforms the Apriori algorithm, which is widely used to discover frequent item sets, in terms of scan frequency and execution time.

• Journal of Information Processing Systems
• /
• 제17권3호
• /
• pp.489-504
• /
• 2021

By distributing computing tasks among devices at the edge of networks, edge computing uses virtualization, distributed computing and parallel computing technologies to enable users dynamically obtain computing power, storage space and other services as needed. Applying edge computing architectures to Internet of Vehicles can effectively alleviate the contradiction among the large amount of computing, low delayed vehicle applications, and the limited and uneven resource distribution of vehicles. In this paper, a predictive offloading strategy based on the MEC load state is proposed, which not only considers reducing the delay of calculation results by the RSU multi-hop backhaul, but also reduces the queuing time of tasks at MEC servers. Firstly, the delay factor and the energy consumption factor are introduced according to the characteristics of tasks, and the cost of local execution and offloading to MEC servers for execution are defined. Then, from the perspective of vehicles, the delay preference factor and the energy consumption preference factor are introduced to define the cost of executing a computing task for another computing task. Furthermore, a mathematical optimization model for minimizing the power overhead is constructed with the constraints of time delay and power consumption. Additionally, the simulated annealing algorithm is utilized to solve the optimization model. The simulation results show that this strategy can effectively reduce the system power consumption by shortening the task execution delay. Finally, we can choose whether to offload computing tasks to MEC server for execution according to the size of two costs. This strategy not only meets the requirements of time delay and energy consumption, but also ensures the lowest cost.

• 한국정보과학회논문지:시스템및이론
• /
• 제27권7호
• /
• pp.639-649
• /
• 2000

관계형 데이타베이스 시스템에서 결합 연산자는 데이타베이스 질의를 구성하는 연산자들 중 가장 많은 처리시간을 요구한다. 따라서 이러한 결합 연산자를 효율적으로 처리하기 위해 많은 병렬 알고리즘들이 소개되었다. 그 중 다중 해쉬 결합 질의의 처리를 위해 할당 트리를 이용한 방법이 가장 우수한 것으로 알려져 왔다. 그러나 이 방법은 할당 트리의 각 노드에서 필연적인 지연이 발생되는 데 이는 튜플-시험 단계에서 외부 릴레이션을 디스크로부터 페이지 단위로 읽는 비용과 이미 읽는 페이지에 대한 해쉬 결합 비용간의 차이에 의해 발생하게 된다. 본 논문에서는 이 비용 차이로 인해 발생되는 전체 시스템의 성능 저하를 방지하기 위해 페이지 실행시간 동기화 기법을 제안하였고 이 기법을 통해 각 노드에서의 처리시간을 줄이고 나아가 전체 시스템의 성능을 향상시켰다. 또한 분석적 비용 모형을 세우고 기존 방식과의 다양한 성능 분석을 통해 비용 모형의 타당성을 입증하였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.336-338
• /
• 2006

One of the important topics concerning the safety of electrical and electronic system is the reliability of the wiring system. The Time-Frequency Domain Reflectometry(TFDR) is a state-of-the-art system for detection and estimation of the fault on a wiring/cable. The purpose of this paper is to implement a Labview based TFDR Real Time system though the instruments of PCI extensions for Instrumentation(PXI). The TFDR Real Time system consists of the five parts: Reference signal design, signal generation, signal acquisition, algorithm execution, results diplay part. In the signal generation and acquisition parts we adopt the Arbitrary Waveform Generator(AWG) and Digital Storage Oscilloscope(DSO) PXI modules which offer commonality, compatibility and easy integration at low cost. And execution of the PXI modules not only is controlled by the Labview programing but also the total system process is executed by the Labview application software.

• 전자공학회논문지CI
• /
• 제43권2호
• /
• pp.12-20
• /
• 2006

실시간 태스크들의 스케줄링에 있어서 일반적으로 주어진 태스크 집합에 대하여 최악의 실행시간을 적용하여 시스템의 요구 성능을 결정한다. 멀티미디어 시스템에서와 같이 연성 실시간 태스크들에 대해서는 이보다 낮은 성능의 저가 하드웨어로도 주어진 태스크 집합을 적절히 처리할 수 있게 된다. 태스크의 실행시간은 매 주기별로 가변적인데 실제 실행과정에서 한주기의 작업이 조기에 완료되면 남는 실행시간의 슬랙은 실행시간을 초과하는 태스크들이 공유하여 사용함으로써 전체적으로 태스크들이 마감시간을 초과하는 빈도를 줄일 수 있다. 본 논문에서는 슬랙들을 보다 적극적으로 공유하여 사용하는 알고리즘을 제시하였고 이를 통해 기존의 연구결과들에 비해서 마감시간을 초과하는 빈도를 줄이고 태스크 간의 문맥교환회수도 개선하였다.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2012년도 추계학술대회
• /
• pp.52-53
• /
• 2012

Belief propagation (BP) is a commonly used global energy minimization algorithm for solving stereo matching problem in 3D reconstruction. However, it requires large memory bandwidth and data size. In this paper, we propose a novel memory-efficient algorithm of BP in stereo matching on the Graphics Processing Units (GPU). The data size and transfer bandwidth are significantly reduced by storing only a part of the whole message. In order to maintain the accuracy of the matching result, the local messages are reconstructed using shared memory available in GPU. Experimental result shows that there is almost an order of reduction in the global memory consumption, and 21 to 46% saving in memory bandwidth when compared to the conventional algorithm. The implementation result on a recent GPU shows that we can obtain 22.8 times speedup in execution time compared to the execution on CPU.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권5호
• /
• pp.1963-1978
• /
• 2015

With the advancement of mobile web environments, identification and analysis of the user behavior play a significant role and remains a challenging task to implement with variations observed in the model. This paper presents an efficient method for mining optimized user behavior prediction model using genetic algorithm on mobile web structure. The framework of optimized user behavior prediction model integrates the temporary and permanent register information and is stored immediately in the form of integrated logs which have higher precision and minimize the time for determining user behavior. Then by applying the temporal characteristics, suitable time interval table is obtained by segmenting the logs. The suitable time interval table that split the huge data logs is obtained using genetic algorithm. Existing cluster based temporal mobile sequential arrangement provide efficiency without bringing down the accuracy but compromise precision during the prediction of user behavior. To efficiently discover the mobile users' behavior, prediction model is associated with region and requested services, a method called optimized user behavior Prediction Model using Genetic Algorithm (PM-GA) on mobile web structure is introduced. This paper also provides a technique called MAA during the increase in the number of models related to the region and requested services are observed. Based on our analysis, we content that PM-GA provides improved performance in terms of precision, number of mobile models generated, execution time and increasing the prediction accuracy. Experiments are conducted with different parameter on real dataset in mobile web environment. Analytical and empirical result offers an efficient and effective mining and prediction of user behavior prediction model on mobile web structure.