• 대한수학회논문집
• /
• 제28권2호
• /
• pp.383-396
• /
• 2013

We consider an M/PH/1 queue with deterministic impatience time. An exact analytical expression for the stationary distribution of the workload is derived. By modifying the workload process and using Markovian structure of the phase-type distribution for service times, we are able to construct a new Markov process. The stationary distribution of the new Markov process allows us to find the stationary distribution of the workload. By using the stationary distribution of the workload, we obtain performance measures such as the loss probability, the waiting time distribution and the queue size distribution.

• 전기학회논문지P
• /
• 제67권4호
• /
• pp.200-207
• /
• 2018

In recent, KEPCO (Korea Electric Power Corporation) faced difficulties of the DCC (distribution control center) due to the increase of field equipment and operational cost, and aging of operating staffs. In response to these changes in the DCC, KEPCO is trying to change the organization and system of the DCC. In this paper, we present a new attempt to change organization and structure of distribution control center, which was implemented by KEPCO recently. This paper is divided into three major parts. First, to examine the adequacy of the divided basis of current DCCs based on the quantity of installed electrical equipment, we analyzed the correlation between the operational history of the DCCs and the number of equipment. Through the analysis, we confirmed that there is little relationship between the number of equipment and actual workload. Second, we conducted visits and questionnaire surveys of all the DCCs to identify factors affecting the actual workload of distribution operators and then summarized the results. Third, based on this survey, a general formula for analyzing the workload of a DCC was derived, and each DCC's average annual total workload, day/night workload, and required number of personnel were calculated. Through this study, we proposed a more realistic management method of DCCs that can overcome the division criteria based on equipment quantity.

• 정보처리학회논문지:컴퓨터 및 통신 시스템
• /
• 제8권10호
• /
• pp.245-250
• /
• 2019

모바일 분야의 발전으로 인해 낸드 플래시 메모리의 사용이 급증하였다. 그러나 낸드 플래시 메모리는 수명에 제한이 있어서 수명을 예측하기 위한 연구가 진행되고 있다. 낸드 플래시 메모리의 수명에 큰 영향을 주는 요소 중 하나가 워크로드인데, 모바일 환경에서의 워크로드 분석 연구는 미비하다. 이에 본 논문에서는 안드로이드 기반의 스마트폰을 사용하면서 발생하는 트레이스를 수집하고, 모바일 환경에서의 워크로드 분포를 분석하였다. 수집한 트레이스는 hotness 그룹을 3개로 분류할 수 있다. 또한 트레이스의 분포는 무거운 꼬리를 가지는 형태이다. 본 논문은 이를 Pareto, Lognormal, Weibull 분포에 피팅하였고, 그 결과 Pareto 분포에 가장 가까운 것을 확인하였다.

• Journal of the Korean Statistical Society
• /
• 제36권2호
• /
• pp.285-297
• /
• 2007

We consider the $P_{\lambda}^M-service$ policy for an M/G/1 queueing system in which the workload is monitored randomly at discrete points in time. If the level of the workload exceeds a threshold ${\lambda}$ when it is monitored, then the service rate is increased from 1 to M instantaneously and is kept as M until the workload reaches zero. By using level-crossing arguments, we obtain explicit expressions for the stationary distribution of the workload in the system.

• 간호행정학회지
• /
• 제14권4호
• /
• pp.432-439
• /
• 2008

Purpose: The purpose of this study was to examine nursing workload associated with patient and anesthetic factors in the post-anesthesia care unit(PACU). Method: The data used in this study were collected from February 26th, 2008 to May 16th, 2008. The subjects were 828patients and collected data were analyzed by using SPSS program. Results: It was found that there were statistical differences in gender, age, past history, type of anesthesia, duration of anesthesia, type of surgery. The mean PRN for nursing workload was 25 for below 17 years, and 27.5 for above 61 years. The mean PRN for nursing workload was 27 for general anesthesia, and 16 for regional anesthesia. The mean PRN for nursing workload was 29 for orthopedic surgery and neurosurgery, and 23 for ophthalmology. The mean PRN for nursing workload was 24.6 for below 1hour in duration of anesthesia, and 27.5 for above 2hours in duration of anesthesia. Conclusion: This study was carried out to examine nursing workload in the PACU. The results from this study will be help to improve nursing in PACU through efficient distribution of nursing workload in PACU.

• 한국통계학회:학술대회논문집
• /
• 한국통계학회 2004년도 학술발표논문집
• /
• pp.301-306
• /
• 2004

We consider the $P_\lambda\;^M$ service policy for an M/G/1 queue in which the service rate is increased from 1 to M at the exponential setup time after the level of workload exceeds $\lambda$. The stationary distribution of the workload is explicitly obtained through the level crossing argument.

• 정보처리학회논문지:컴퓨터 및 통신 시스템
• /
• 제4권8호
• /
• pp.245-252
• /
• 2015

최근 고성능 컴퓨팅과 모바일 컴퓨팅에서 성능가속기를 사용하는 병렬처리 방법들이 소개되어왔다. 포토모자이크 응용은 내재된 데이터 병렬성을 활용하고 성능가속기를 사용하여 병렬처리가 가능하다. 본 논문에서는 CPU와 GPU로 구성된 이기종 컴퓨팅 환경에서 포토모자이크 수행 시 작업부하 분배 방법을 제안한다. 즉, 포토모자이크 응용을 비동기 방식으로 병렬화하여 CPU와 GPU 자원을 동시에 활용하고, 각 처리기에 할당할 최적의 작업부하량을 예측하기 위해 CPU-only와 GPU-only 작업 분배 환경에서 수행시간을 측정한다. 제안 방법은 간단하지만 매우 효과적이고, CPU와 GPU로 구성된 이기종 컴퓨팅 환경에서 다른 응용을 병렬화하 데에도 적용될 수 있다. 실험 결과, 이기종 컴퓨팅 환경에서 최적의 작업 분배량으로 수행한 경우, GPU-only의 방법과 비교하여 141%의 성능이 개선되었음을 확인한다.

• 한국산학기술학회논문지
• /
• 제8권1호
• /
• pp.65-72
• /
• 2007

본 논문은 단국대학교의 e-learning 서버의 부하 분석을 통해 교육용 서버의 통계적 부하 모델 작성을 위한 기초 자료 제공을 목적으로 한다. 분석 결과로 파일의 크기 분포, 파일 유형별 접속 빈도와 전송량, 접근 간격, 선호도 변화, 네트워크별 접근 비율 등을 제시하였다. 특히, 동영상 파일의 크기 분포와 접근 빈도별 파일 분포는 이전의 연구들과는 다른 결과가 나타났다. 이것은 동영상 강의를 제작하기 위해 저작 도구를 사용하고 수강생 수의 제약이 없는 온라인 교육의 특성이 반영되었기 때문이다. 본 논문에서 제시된 분석 결과는 e-learning 시스템 구조와 서버 성능 향상을 위한 연구에 기초 자료로 이용될 수 있다.

• 한국시뮬레이션학회논문지
• /
• 제12권4호
• /
• pp.103-111
• /
• 2003

A distributed sewer cluster system is a cost-effective system to provide a service application for clients with reliable, scalable, available, and fault-tolerant features. In order to provide high quality services, it is necessary to evaluate service performances, tune the server system, and analyze performances. In this paper, we propose a simulator to generate workloads based on statistic configuration according to estimated application traffics, apply workload scheduling algorithms, and evaluate the simulation results. We introduce the simulator design modelling and architecture. By using flexible parameters, the simulator is able to generate various patterns of workloads with different statistics, and configure system environments such as the number of server nodes, system resources considered, and their capacities. With this simulator, we introduce two scenarios: one is to find appropriate thresholds for the best performance of cluster system, and the other is to find the suitable scheduling algorithm for workload characteristics of service applications.

• 한국시뮬레이션학회:학술대회논문집
• /
• 한국시뮬레이션학회 2003년도 추계학술대회 및 정기총회
• /
• pp.27-34
• /
• 2003

A distributed server cluster system is a cost-effective system to provide a service application for clients with reliable, scalable, available, and fault-tolerant features. In order to provide high quality services, it is necessary to evaluate service performances, tune the server system, and analyze performances. In this paper, we propose a simulator to generate workloads based on statistic configuration according to estimated application traffics, apply workload scheduling algorithms, and evaluate the simulation results. We introduce the simulator design modelling and architecture. By using flexible parameters, the simulator is able to generate various patterns of workloads with different statistics, and configure system environments such as the number of server nodes, system resources considered, and their capacities. With this simulator, we introduce two scenarios: one is to find appropriate thresholds for the best performance of cluster system, and the other is to find the suitable scheduling algorithm for workload characteristics of service applications.