• 한국컴퓨터정보학회논문지
• /
• 제27권5호
• /
• pp.11-19
• /
• 2022

본 논문에서는 전가상화 방식의 가상 머신 모니터를 기반으로 메모리 중복을 통한 고장 감내 기능을 적용한 임베디드 시스템을 제안한다. 제안된 가상 머신 모니터는 우선 효율적인 섀도우 페이지 테이블 기법을 사용하여 메모리를 가상화한다. 이를 기반으로 대상 임베디드 시스템을 하나의 가상 머신으로 동작하게 하는 한편, 동일한 시스템을 별도의 가상 머신에서 동작하도록 백업 시스템을 구축함으로써 대상 임베디드 시스템의 메모리 영역이 미리 정해진 시점과 대상에 따라 백업 시스템의 메모리 공간으로 복사되도록 하였다. 이렇게 중복이 이루어진 임베디드 시스템은 고장이 발생하면 백업 시스템으로 전환하여 정상적인 동작을 이어나가게 된다. 성능 평가를 통해 제안된 기법이 임베디드 시스템의 성능을 크게 저하시키지 않으면서도 시스템의 가용성을 크게 향상시킬 수 있음을 확인하였다.

• 산업경영시스템학회지
• /
• 제21권48호
• /
• pp.113-122
• /
• 1998

In this paper we consider the CSP requirements determination problem of new equipment(machine) system. For the newly procured equipment systems, mathematical analyses are made for the system which is constructed with the consumable parts to derive the associated CSP requirement determination model in mathematical expression. Based on these analyses, a mathematical model is derived for making an optimal CSP requirement determination subject to tile constraint of satisfying any given operational availability limitation. We assume that the failure of a part follows a Poisson process. Firstly, the operational availability concept in CSP is defined and the relation between the general system availability and the operational availability is established. Secondly, the problem is formulated as the cost minimization problem that should satisfy the operational availability limitation, and then, using the generalized Lagrange multipliers method, the optimal solution procedure is derived.

• 산업경영시스템학회지
• /
• 제23권59호
• /
• pp.53-67
• /
• 2000

In this paper we consider the CSP requirements determination problem of new equipment(machine) system. For the newly procured equipment systems, mathematical analyses are made for the system which is constructed with the consumable parts and the repairable parts to derive the associated CSP requirement determination model in mathematical expression. Based on these analyses, a mathematical model Is derived for making an optimal CSP requirement determination subject to the constraint of satisfying any given operational availability limitation. We assume that the failure of a part follows a Poisson process and the repair time has an exponential distribution. Firstly, the operational availability concept in CSP is defined and the relation between the general system availability and the operational availability is established. Secondly, the problem is formulated as the cost minimization problem that should satisfy the operational availability limitation, and then, using the generalized Lagrange multipliers method, the optimal solution procedure Is derived.

• 대한산업공학회지
• /
• 제34권3호
• /
• pp.318-327
• /
• 2008

This paper considers a single-machine scheduling problem with availability constraints. In many realistic situations, machines may not be always available due to various reasons such as maintenance, breakdown and repair. However, most literature on scheduling assume that the machines are available at all times. This paper deals with a single-machine scheduling problem with periodic maintenance. If the maintenance decision is made jointly with the job scheduling, the system will be more effective. The objective is to minimize the total completion time of jobs. This problem is proved to be NP-hard in the strong sense. The proposed breaking heuristic(BH) algorithm rule is established by some theorems and conditions. Our computational results show that the BH algorithm is much more efficient than existing heuristic.

• 산업경영시스템학회지
• /
• 제9권13호
• /
• pp.17-22
• /
• 1986

Man-machine system is an integrated total system which is linked by functions of man and machine, and the value of the system is determined by its compatability. And it is able to evaluate the system value on the aspects of utility, availability, and cost benefit. The authors previously represented the methodology of system utility using transfer functions, and this paper successively discusses the reliability of man-machine system. The reliability estimation and evaluation methodologies are briefly mentioned, and some examples are shown in this paper.

• 한국시뮬레이션학회논문지
• /
• 제22권1호
• /
• pp.77-86
• /
• 2013

클라우드 환경은 여러 개의 컴퓨팅 자원들을 이용하는 분산 컴퓨팅 환경의 일종으로 가상머신을 이용 하여 작업을 처리한다. 클라우드 환경은 작업 요청에 따르는 부하분산과 빠른 작업 처리를 위한 프로비저닝 기술을 이용하여 가상머신의 상태에 따라 작업을 할당 한다. 하지만, 클라우드 환경의 작업 스케줄링을 위해서는 가상머신의 성능에 따르는 애매모호한 상태에 대한 가용성의 정의가 필요하다. 본 논문에서는 클라우드 환경의 프로비저닝 스케줄링을 위해 퍼지 로직 기반의 자원평가를 이용한 가상머신 프로비저닝 스케줄링(FVPRE: Fuzzy logic driven Virtual machine Provisioning scheduling using Resource Evaluation)을 제안한다. FVPRE는 각 가상머신의 정의하기 어려운 성능의 상태를 분석하여 자원 가용성에 대한 값을 구체화하여 정확한 자원의 가용성 평가를 통해 효율적인 프로비저닝 스케줄링이 가능하다. FVPRE는 클라우드 환경의 작업 처리에 대해 높은 처리율과 활용율을 보인다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1997년도 추계학술대회 논문집
• /
• pp.109-114
• /
• 1997

As CNC machine tool is one of core elements of manufacturing system, it is much important that it remains without troubleshoots. As a virtual machine is a recent alternative using IT for optimal utilization of CNC machine tool, it is a computer model that represents a CNC machine tool. But a virtual machine is still conceptual. So, in this paper, it is proposed that a virtual machine be a realistic model in the fault diagnosis module. For this purpose, the fault diagnosis system of machine tool using CORBA and fault diagnosis expert system has been implemented. Using this system, we have expections to diagnose exactly and prompty without the restriction of time or location, to reduce MTTR(Mean Time To Repair) and finally to increase the availability of manufacturing system.

• Soft Computing and Machine Intelligence
• /
• 제1권1호
• /
• pp.24-30
• /
• 2021

The accelerated growth of the internet and the enormous amount of data availability has become the primary reason for machine learning applications for data analysis and, more specifically, pattern recognition and decision making. In this paper, we focused on the crowdfunding site Kickstarter and collected the comments in order to apply neural networks to classify the projects based on the sentiments of backers. The power of customer reviews and sentiment analysis has motivated us to apply this technique in crowdfunding to find timely indications and identify suspicious activities and mitigate the risk of money loss.

• 한국신뢰성학회지:신뢰성응용연구
• /
• 제4권2호
• /
• pp.91-104
• /
• 2004

In this paper we consider the concurrent spare part(CSP) requirements problem of new equipment system. When a part fails, the part is replaced and the repair of failed part is impossible and cannibalization is allowed. We assume that the failure of a part knows a Poisson process. The operational availability concept in CSP is defined, and derive a formula to calculate the operational availability using expected machine operating time during CSP period. A mathematical model is derived for making an CSP requirement determination subject to the constraint of satisfying any given operational availability limitation and an heuristic solution search procedure is derived. An illustrative example is shown to explain the solution procedure.

• Journal of Electrical Engineering and information Science
• /
• 제3권1호
• /
• pp.1-7
• /
• 1998

High-Level synthesis of digital circuits calls for automatic translation of a behavioral description to a structural design entity represented in terms of components and connection. One of the critical steps in high-level synthesis is to determine a particular scheduling algorithm that will assign behavioral operations to control states. A new scheduling algorithm called Data Availability Scheduling (DAS) for high-level synthesis is presented. It can determine an appropriate scheduling algorithm and minimize the number of states required using data availability and dependency conditions extracted from the behavioral code, taking into account of states required using data availability and dependency conditions extracted from the behavioral code, taking into account resource constraint in each control state. The DAS algorithm is efficient because data availability conditions, and conditional and wait statements break the behavioral code into manageable pieces which are analyzed independently. The output is the number of states in a finite state machine and shows better results than those of previous algorithms.