• 한국정보처리학회논문지
• /
• 제4권6호
• /
• pp.1550-1556
• /
• 1997

본 논문에서는 진화 알고리즘에 기반하여 조합 최적화 문제를 해결하고자 한다. 진화 알고리즘은 대규모 문제 공간에서 최적화 문제를 해결하는데 적합한 알고리즘이다. 본 논문의 조합 최적화의 예는 경수로 원자로로부터 나온 폐연료를 중수로에서 재사용하는데 필요한 폐연료의 조합 문제이다. 이와 같은 조합 최적화 문제는 0/1 knapsack 문제와 같이 NP-Comprete 문제에 해당한다. 이러한 문제를 해결하기 위해서는 고전적인 진화 알고리즘의 전략에 기반하여 랜덤 연산자를 이용하여 평가 함수 값이 좋은 방향으로만 탐색을 수행하는 방법, 그리고 벡터 연산자를 이용하여 최적의 해를 보다 빨리 얻을 수 있는 휴리스틱을 사용하는 방법이 있다. 본 논문에서는 중수로 연료 조합 문제 영역의 모든 지식을 벡터화하여 벡터의 연산만으로 가능성 검사, 해를 평가하는 방법을 소개한다. 또한 벡터 휴리스틱이 고전적인 진화 알고리즘에 비해 어느 정도의 성능을 보이는지 비교한다.

• 대한조선학회논문집
• /
• 제44권2호
• /
• pp.139-147
• /
• 2007

The ultimate goal of structural design is to find the optimal design results which satisfies both safety and economy at the same time. Optimum design has been studied for the last several decades and is being studied. in this study, an optimum algorithm which is based on the genetic algorithm has been applied to the multi-object problem to obtain the optimum solutions which minimizes structural weight and construction cost of panel blocks in ship structures at the same time. Mathematical problems are dealt at first to justify the reliability of the present optimum algorithm. And then the present method has been applied to the panel block model which can be found in ship structures. From the present findings it has been seen that the present optimum algorithm can reasonably give the optimum design results.

• 한국정보시스템학회지:정보시스템연구
• /
• 제25권1호
• /
• pp.159-182
• /
• 2016

Purpose This paper aims to develop a novel tabu search algorithm for solving the sequencing problems with precedence constraints. Due to constraints, the traditional meta heuristic methods can generate infeasible solutions during search procedure, which must be carefully dealt with. On the contrary, the candidate order based tabu search (COTS) is based on a novel neighborhood structure that guarantees the feasibility of solutions, and can dealt with a wide range of sequencing problems in flexible manner. Design/methodology/approach Candidate order scheme is a strategy for constructing a feasible sequence by iteratively appending an item at a time, and it has been successfully applied to genetic algorithm. The primary benefit of the candidate order scheme is that it can effectively deal with the additional constraints of sequencing problems and always generates the feasible solutions. In this paper, the candidate order scheme is used to design the neighborhood structure, tabu list and diversification operation of tabu search. Findings The COTS has been applied to the single machine job sequencing problems, and we can see that COTS can find the good solutions whether additional constraints exist or not. Especially, the experiment results reveal that the COTS is a promising approach for solving the sequencing problems with precedence constraints. In addition, the operations of COTS are intuitive and easy to understand, and it is expected that this paper will provide useful insights into the sequencing problems to the practitioners.

• 한국시뮬레이션학회:학술대회논문집
• /
• 한국시뮬레이션학회 1994년도 추계학술발표회 및 정기총회
• /
• pp.1-2
• /
• 1994

With the prevalence of computers in modern organizations, simulation is receiving more atention as an effectvie decision -making tool. Simualtion is a computer-based numerical technique which uses mathmatical and logical models to approximate the behaviror of a real-world system. However, iptimization of synamic stochastic systems often defy analytical and algorithmic soluions. Although a simulation approach is often free fo the liminting assumption s of mathematical modeling, cost and time consiceration s make simulation the henayst's last resort. Therefore, whenever possible, analytical and algorithmica solutions are favored over simulation. This paper discussed the issues and procedrues for using simulation as a tool for optimization of stochastic complex systems that are dmodeled by computer simulation . Its emphasis is mostly on issues that are speicific to simulation optimization instead of consentrating on the general optimizationand mathematical programming techniques . A simulation optimization problem is an optimization problem where the objective function. constraints, or both are response that can only be evauated by computer simulation. As such, these functions are only implicit functions of decision parameters of the system, and often stochastic in nature as well. Most of optimization techniqes can be classified as single or multiple-resoneses techniques . The optimization of single response functins has been researched extensively and consists of many techniques. In the single response category, these strategies are gradient based search techniques, stochastic approximate techniques, response surface techniques, and heuristic search techniques. In the multiple response categroy, there are basically five distinct strategies for treating the responses and finding the optimum solution. These strategies are graphica techniqes, direct search techniques, constrained optimization techniques, unconstrained optimization techniques, and goal programming techniques. The choice of theprocedreu to employ in simulation optimization depends on the analyst and the problem to be solved. For many practival and industrial optimization problems where some or all of the system components are stochastic, the objective functions cannot be represented analytically. Therefore, modeling by computersimulation is one of the most effective means of studying such complex systems. In this paper, after discussion of simulation optmization techniques, the applications of above techniques will be presented in the modeling process of many flexible manufacturing systems.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2000년도 춘계학술대회 논문집
• /
• pp.330-335
• /
• 2000

Faults detection and containment requirements are typically allocated from a top-level specification as a percentage of total faults detection and containment, weighted by failure rate. This faults detection and containments are called as a fault coverage. The fault coverage requirements are typically allocated identically to all units in the system, without regard to complexity, cost of implementation or failure rate for each units. In this paper a simple methodology and mathematical model to support the allocation of system fault coverage rates to lower-level units by considering the inherent differences in reliability is presented. The models are formed as a form of constrained optimization. The objectives and constraints are modeled as a linear form and this problems are solved by linear programming. It is identified by simulation that the proposed solving methods for these problems are effective to such requirement allocating.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권10호
• /
• pp.4865-4886
• /
• 2017

The user experience of practical indoor power line communication (PLC) applications is greatly affected by the system quality-of-service (QoS) criteria. With a general broadcast-and-multi-access (BMA) relay scheme, in this work we investigate the joint source and relay power optimization of the amplify-and-forward (AF) relay systems used under indoor broad-band PLC environments. To achieve both time diversity and spatial diversity from the relay-involved PLC channel, which is time-varying in nature, the source node has been configured to transmit an identical message twice in the first and second signalling phase, respectively. The QoS constrained power allocation problem is not convex, which makes the global optimal solution is computationally intractable. To solve this problem, an alternating optimization (AO) method has been adopted and decomposes this problem into three convex/quasi-convex sub-problems. Simulation results show the fast convergence and short delay of the proposed algorithm under realistic relay-involved PLC channels. Compared with the two-hop and broadcast-and-forward (BF) relay systems, the proposed general relay system meets the same QoS requirement with less network power assumption.

• 대한기계학회논문집A
• /
• 제31권3호
• /
• pp.355-364
• /
• 2007

Multidisciplinary design optimization based on independent subspaces (MDOIS) is a simple and practical method that can be applied to the practical engineering MDO problems. However, the current version of MDOIS does not handle the common design variables. A new version of MDOIS is proposed and named as MDOIS/2006. It is a two-level MDO method while the original MDOIS is a single-level method. At first, system analysis is performed to solve the coupling in the analysis. If the termination criteria are not satisfied, each discipline solves its own design problem. Each discipline in the lower level solves the problem with common design variables while they are constrained by equality constraints. In the upper level, the common design variables of related disciplines are determined by using the optimum sensitivity of the objective function. To validate MDOIS/2006, mathematical problem and NASA test bed problem are solved. The results are compared with those from other MDO methods. Finally, MDOIS/2006 is applied to flow patterner design and shows that it can be successfully applied to the practical engineering MDO problem.

• 한국전산구조공학회논문집
• /
• 제20권5호
• /
• pp.671-680
• /
• 2007

본 연구의 최종 목적은 유체가 빠른 속도로 가해지는 물체의 경계면에서 흡입(suction) 혹은 방출(injection)을 통해 유체를 제어함으로 드래그(drag)를 감소하고자 하는 것이다. 그러나 유체는 대용량, 비선형성을 가지고 있어서 직접적인 해석은 물론, 최적화를 적용한다는 것은 매우 어려운 일이다. 이를 위해 우리는 새로운 알고리즘과 기법들을 개발하였다. 본 연구에서는 이 기법들에 대한 검증을 하고, 나아가 최적화 기법을 사용하여 드래그를 감소하기 위해 흡입량과 방출량을 구하였다. 그리고 이 흡입과 방출을 가할 수 있는 구멍의 수와 위치에 따른 변화를 알아보았다. 본 연구에서 개발된 알고리즘과 기법들을 사용하였을 경우, 기존에는 해결 할 수도 없었던 문제를 가능하게 만들었으며, 기존에 저자가 1차로 개발한 바 있는 방법에 비해서도 더욱 효과적이라는 것을 입증하였다. 그리고 드래그 감소라는 차원에서 본다면 흡입과 방출을 가할 수 있는 구멍의 숫자가 많을수록 효과가 높으나 그다지 많은 수를 필요로 하지 않는다는 것을 알게 되었으며, 구멍의 위치는 유체의 경계층이 분리되는 약간 아래가 가장 최적의 위치라는 것을 알게 되었다.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 2003년도 추계학술대회 및 정기총회
• /
• pp.81-84
• /
• 2003

The ability to determine the optimal frequencies and offsets for independent and unrestricted ordering cycles for multiple items can be very valuable for managing storage capacity constrained facilities in a supply chain. The complexity of this problem has resulted in researchers focusing on more tractable surrogate problems that are special cases of the base problem. Murthy et al. (European Journal of Operation Research 2003) developed insights leading to solution of the original problem and present a heuristic for offsetting independent and unrestricted ordering cycles for items to minimize their joint storage requirements. However, their study cannot find optimal solution due to the Greedy Heuristic solution procedure. In this paper, we present a complete procedure to find the optimal solution for the model with a integer programming optimization approach and genetic algorithm. Numerical examples are included to compare each model with that of Murthy et at. Research of this type may prove useful in solving the more general problem of selecting order policies to minimize combined holding, ordering, and storage costs.

• 품질경영학회지
• /
• 제5권1호
• /
• pp.23-29
• /
• 1977

Geometric programming is very useful for the solution of certain nonlinear programming problems in which the objective function and the constraints are posynomial expressions. By solving the dual program, it can be obtained that the solution of the primal program of Geometric programming. And, more efficient solution is to form an Augmented program possessing degree of difficult zero. A regional water-quality management problem may involve a multistage constrained optimization with many decision variables. In this problem, especially, appling that solution to it is also useful. This paper is described that : 1) the efficient solution of a water-quality management model formed by Geometric programming and 2) the algorithm developed to apply easily a real system by modifing and simplifing the solution.