• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.6
• /
• pp.9-20
• /
• 2018

When a large-scale photovoltaic (PV) system is introduced into a distribution system, the customer's voltage may exceed the allowable limit ($220V{\pm}6%$) due to voltage variations and reverse power flow in the PV system. In order to solve this problem, we propose a method for adjusting the customer voltage using the existing step voltage regulator (SVR) installed in the primary feeder. However, due to the characteristics of a mechanically operating SVR, the customer voltage during the tap changing time of the SVR is likely to deviate from the allowable limit. In this paper, an energy storage system (ESS) with optimal operation strategies, and an appropriate capacity calculation algorithm are proposed, and the parallel driving scheme between the SVR and the ESS is also proposed to solve the customer voltage problem that may occur during the tap changing time of the SVR. The simulation results show that the allowable limit of the customer voltage is verified by the proposed methods during the tap changing time of the SVR when the large-scale PV system is connected to the distribution system.

• Journal of KIISE:Software and Applications
• /
• v.30 no.7_8
• /
• pp.672-680
• /
• 2003

A shopbot is a software agent whose goal is to maximize buyer´s satisfaction through automatically gathering the price and quality information of goods as well as the services from on-line sellers. In the response to shopbots´ activities, sellers on the Internet need the agents called pricebots that can help them maximize their own profits. In this paper we adopts Q-learning, one of the model-free reinforcement learning methods as a price-setting algorithm of pricebots. A Q-learned agent increases profitability and eliminates the cyclic price wars when compared with the agents using the myoptimal (myopically optimal) pricing strategy Q-teaming needs to select a sequence of state-action fairs for the convergence of Q-teaming. When the uniform random method in selecting state-action pairs is used, the number of accesses to the Q-tables to obtain the optimal Q-values is quite large. Therefore, it is not appropriate for universal on-line learning in a real world environment. This phenomenon occurs because the uniform random selection reflects the uncertainty of exploitation for the optimal policy. In this paper, we propose a Mixed Nonstationary Policy (MNP), which consists of both the auxiliary Markov process and the original Markov process. MNP tries to keep balance of exploration and exploitation in reinforcement learning. Our experiment results show that the Q-learning agent using MNP converges to the optimal Q-values about 2.6 time faster than the uniform random selection on the average.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.3D
• /
• pp.409-416
• /
• 2006

Real-time traveler information disseminated through Variable Message Signs (VMS) is known to have effects on driver route choice decisions. In the past, many studies have attempted to optimize the system performance using VMS message content as the primary control variable of driver route choice. This research proposes a VMS information provision optimization model which searches the best combination of VMS message contents and display sequence to minimize the total travel time on a highway network considered. The driver route choice models under VMS information provision are developed using a stated preference (SP) survey data in order to realistically capture driver response behavior. The genetic algorithm (GA) is used to find the optimal VMS information provision strategies which consists of the VMS message contents and the sequence of message display. In the process of the GA module, the system performance is measured using micro traffic simulation. The experiment results highlight the capability of the proposed model to search the optimal solution in an efficient way. The results show that the traveler information conveyed via VMS can reduce the total travel time on a highway network. They also suggest that as the frequency of VMS message update gets shorter, a smaller number of VMS message contents performs better to reduce the total travel time, all other things being equal.

• The Journal of Information Systems
• /
• v.25 no.4
• /
• pp.105-119
• /
• 2016

Purpose The conventional solution methods for production scheduling problems typically focus on the active schedules, which result in short makespans. However, the active schedules are more difficult to generate than the semi active schedules. In other words, semi active schedule based search strategy may help to reduce the computational costs associated with production scheduling. In this context, this paper aims to compare the performances of active schedule based and semi active schedule based search methods for production scheduling problems. Design/methodology/approach Two decoding approaches, active schedule decoding and semi active schedule decoding, are introduced in this paper, and they are used to implement genetic algorithms for classical job shop scheduling problem. The permutation representation is adopted by the genetic algorithms, and the decoding approaches are used to obtain a feasible schedule from a sequence of given operations. Findings The semi active schedule based genetic algorithm requires slightly more iterations in order to find the optimal schedule, while its execution time is quite shorter than active schedule based genetic algorithm. Moreover, the operations of semi active schedule decoding is easy to understand and implement. Consequently, this paper concludes that semi active schedule based search methods also can be useful if effective search strategies are given.

• Journal of the Korea Society for Simulation
• /
• v.22 no.4
• /
• pp.139-147
• /
• 2013

This paper proposes a novel method for feature selection for mass spectrometric proteomic data based on Random Forest. The method includes an effective preprocessing step to filter a large amount of redundant features with high correlation and applies a tournament strategy to get an optimal feature subset. Experiments on three public datasets, Ovarian 4-3-02, Ovarian 7-8-02 and Prostate shows that the new method achieves high performance comparing with widely used methods and balanced rate of specificity and sensitivity.

• Transactions of The Korea Fluid Power Systems Society
• /
• v.2 no.3
• /
• pp.1-5
• /
• 2005

There are two types of solenoid actuator for force and position control of the fluid power system. One is an on-off solenoid actuator and the other is an electro-magnetic proportional actuator. They have some different characteristics for attraction force according to solenoid shape. Attraction force of the on-off solenoid actuator only depends on flux density. And the stroke-force characteristics of the proportional solenoid actuator are determined by the shape of the control cone. In this paper, steady state characteristics of the solenoid actuator for electro-hydraulic proportional valve determined by the shape of control cone are analyzed using finite element method and it is confirmed that the proportional solenoid actuator has a constant attractive force in the control region independently on the stroke position. And the shape of control cone is optimized using 1+1 evolution strategy to get a constant force. In the optimization algorithm, control cone length, thickness and taper length are used as a design parameter.

• Journal of the Society of Naval Architects of Korea
• /
• v.48 no.2
• /
• pp.178-182
• /
• 2011

Generally in order to reduce the steel weight of stiffened plate, stiffener spaces tend to be narrow and the plate gets thin. However, it will involve more fabrication cost because it can lead to the increase of welding length and the number of structural members. In the yard, the design which is able to reduce the total fabrication cost is needed, although it requires more steel weight. The purpose of this study is to find optimum stiffener spaces to minimize the fabrication cost for the cargo tank of LPG Carriers. Global optimization methods such as ES(Evolution Strategy) and GA(Genetic Algorithm) are introduced to find a global optimum solution and the sum of steel material cost and labor cost is selected as main objective function. Convergence degree of both methods in according to the size of searching population is examined and an efficient size is investigated. In order to verify the necessity of the optimum design based on the cost, minimum weight design and minimum cost design are carried out.

• Journal of The Korean Association of Information Education
• /
• v.8 no.3
• /
• pp.307-317
• /
• 2004

In web-based education environment, it is necessary to provide individually adjusting feedback according to learner's characteristic. Despite this necessity, it is a current state that there are difficulties in deriving the variables of learners' characteristics and lack in developing the systematic strategies and practical tools for providing individually adjusting feedback. This study analyzed the learners' learning patterns, one of learner's characteristic variables regarded as important in web-based teaching and learning environment by employing Apriori algorithm, and also grouped the learners by learning pattern. Under this framework, the e-SRM feedback system was designed and developed to provide learning content, learning channel, and learning situation, etc. for individual learners. The proposed system in this study is expected to provide an optimal learning environment complying with learner's characteristic.

• The Journal of Information Technology
• /
• v.3 no.2
• /
• pp.73-85
• /
• 2000

The efficient algorithms are suggested in this study for solving the multicommodity network flow problems applied to Communications Systems. These problems are typical NP-complete optimization problems that require integer solution and in which the computational complexity increases numerically in appropriate with the problem size. Although the suggested algorithms are not absolutely optimal, they are developed for computationally efficient and produce near-optimal and primal integral solutions. We supplement the traditional Lagrangian method with a price-directive decomposition. It proceeded as follows. First, A primal heuristic from which good initial feasible solutions can be obtained is developed. Second, the dual is initialized using marginal values from the primal heuristic. Generally, the Lagrangian optimization is conducted from a naive dual solution which is set as ${\lambda}=0$. The dual optimization converged very slowly because these values have sort of gaps from the optimum. Better dual solutions improve the primal solution, and better primal bounds improve the step size used by the dual optimization. Third, a limitation that the Lagrangian decomposition approach has Is dealt with. Because this method is dual based, the solution need not converge to the optimal solution in the multicommodity network problem. So as to adjust relaxed solution to a feasible one, we made efficient re-allocation heuristic. In addition, the computational performances of various versions of the developed algorithms are compared and evaluated. First, commercial LP software, LINGO 4.0 extended version for LINDO system is utilized for the purpose of implementation that is robust and efficient. Tested problem sets are generated randomly Numerical results on randomly generated examples demonstrate that our algorithm is near-optimal (< 2% from the optimum) and has a quite computational efficiency.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.11a
• /
• pp.478-481
• /
• 2010

본 논문에서는 경제학, 사회학, 수학 분야에서 수십년 전부터 연구해오던 죄수의 딜레마 게임의 협동진화에 대해 고찰해보고자 한다. 반복적 죄수의 딜레마 게임은 게임이론의 가장 기본적인 이론으로써, 사회적 상호작용, 경제활동, 국제관계 등 다양한 현상들을 모델링 하기 위한 하나의 방법이다. 그 중에 N명이 참가하는 반복적 죄수 딜레마 게임의 전략은 유전 알고리즘(Genetic Algorithms, GAs)을 통해 진화적으로 만들어 낼 수 있으며, 이 경우에 그 결과를 일반적인 내쉬 균형 이 아닌, 모든 개체들이 유전알고리즘을 통해 협동으로 수렴하도록 유도할 수 있다는 사실은 상당히 시사하는 바가 크다. 기존에 주로 연구되어오던 죄수의 딜레마 게임은 협동으로의 수렴과정에서 일반적으로 순위기반선택(Rank-based selection)과 1점 교배기법(1point crossover)을 사용한다. 그러나 순위기반선택은 모든 개체에 순위을 매겨야 하기 때문에, 개체수가 커질수록 성능이 저하되며, 1점 교배기법은 개체 값이 분산되어있을 경우, 최적해(Optimal solution)을 찾기 힘들다는 단점이 있어, 개체수가 많은 경우에 적용하기에는 비효율적이다. 본 논문에서는 토너먼트 선택기법(Tournament selection)과 자기 적응형 교배기법(Self-adaptive crossover)을 적용한 새로운 기법을 제안한다. 또한 기존 기법과 비교 실험을 통해 제안기법이 기존기법에 비해 평균 수렴시간과 수렴 횟수에서 뛰어난 성능을 보이고 있음을 확인하였다.