• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.31-34
• /
• 2024

태양광 에너지는 탄소 중립 이행을 위한 주요 방안으로 많은 주목을 받고 있다. 태양광 발전량은 여러 환경적 요인에 따라 크게 달라질 수 있으므로, 정확한 발전량 예측은 전력 네트워크의 안정성과 효율적인 에너지 관리에 근본적으로 중요하다. 대표적인 인공지능 기술인 신경망(Neural Network)은 불안정한 환경 변수와 복잡한 상호작용을 효과적으로 학습할 수 있어 태양광 발전량 예측에서 우수한 성능을 도출하였다. 하지만, 신경망은 모델의 구조나 초매개변수(Hyperparameter)를 최적화하는 것은 복잡하고 시간이 많이 드는 작업이므로, 에너지 분야에서 실제 산업 적용에 한계가 존재한다. 본 논문은 2단계 신경망 최적화를 통한 태양광 발전량 예측 기법을 제안한다. 먼저, 태양광 발전량 데이터 셋을 훈련 집합과 평가 집합으로 분할한다. 훈련 집합에서, 각기 다른 은닉층의 개수로 구성된 여러 신경망 모델을 구성하고, 모델별로 Optuna를 적용하여 최적의 초매개변숫값을 선정한다. 다음으로, 은닉층별 최적화된 신경망 모델을 이용해 훈련과 평가 집합에서는 각각 5겹 교차검증을 적용한 발전량 추정값과 예측값을 출력한다. 마지막으로, 스태킹 앙상블 방식을 채택해 기본 초매개변숫값으로 설정해도 우수한 성능을 도출하는 랜덤 포레스트를 이용하여 추정값을 학습하고, 평가 집합의 예측값을 입력으로 받아 최종 태양광 발전량을 예측한다. 인천 지역으로 실험한 결과, 제안한 방식은 모델링이 간편할 뿐만 아니라 여러 신경망 모델보다 우수한 예측 성능을 도출하였으며, 이를 바탕으로 국내 에너지 산업에 이바지할 수 있을 것으로 기대한다.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.43 no.10 s.352
• /
• pp.80-89
• /
• 2006

The rapid development of process technology and the introduction of new materials not only make it difficult for process control but also as a result increase process variations. These process variations are barriers to successful implementation of design circuits because there are disparities between data on layout and that on wafer. This paper proposes a new design environment to determine the interconnect worstcase with accuracy and speed so that the interconnect effects due to process-induced variations can be applied to designs of $0.13{\mu}m$ and below. Common Geometry and Maximum Probability methods have been developed and integrated into the new worstcase optimization algorithm. The delay time of the 31-stage Ring Oscillator, manufactured in UMC $0.13{\mu}m$ Logic, was measured, and the results proved the accuracy of the algorithm. When the algorithm was used to optimize worstcase determination, the relative error was less than 1.00%, two times more accurate than the conventional methods. Furthermore, the new worstcase design environment improved optimization speed by 32.01% compared to that of conventional worstcase optimizers. Moreover, the new worstcitse design environment accurately predicted the worstcase of non-normal distribution which conventional methods cannot do well.

• Journal of Korean Society of Transportation
• /
• v.26 no.3
• /
• pp.145-153
• /
• 2008

This study proposes a facility location model in consideration of spatial coverage and travel cost as an effort to make objective and effective decisions of natural gas filling stations. The proposed model is developed for fixed stations and consists of two stages. The first stage employs a heuristic algorithm to find a set of locations which satisfy the spatial coverage constraints determined by the maximum travel distance between the filling stations and bus depots. In the second stage, the optimal location of filling stations is determined based on the minimum travel cost estimated by using a modified transportation problem as well as the construction and maintenance costs of the filling stations. The applicability of the model is analyzed through finding the optimal location of filling stations for the city of Anyang, a typical medium-sized city in metropolitan Seoul, based on the demand of natural gas buses. This study is expected to help promote the spread of natural gas buses by providing a starting point of a objective and reasonable methodological perspective to address the filling station location problem.

• Journal of KIISE:Computer Systems and Theory
• /
• v.30 no.3_4
• /
• pp.168-185
• /
• 2003

This paper presents a progressive algorithm that not only can narrow down the search domain in the course of face identification but also can fast reconstruct various 3D objects from a sketch drawing. The sketch drawing, edge-vertex graph without hidden line removal, which serves as input for reconstruction process, is obtained from an inaccurate freehand sketch of a 3D wireframe object. The algorithm is executed in two stages. In the face identification stage, we generate and classify potential faces into implausible, basis, and minimal faces by using geometrical and topological constraints to reduce search space. The proposed algorithm searches the space of minimal faces only to identify actual faces of an object fast. In the object reconstruction stage, we progressively calculate a 3D structure by optimizing the coordinates of vertices of an object according to the sketch order of faces. The progressive method reconstructs the most plausible 3D object quickly by applying 3D constraints that are derived from the relationship between the object and the sketch drawing in the optimization process. Furthermore, it allows the designer to change viewpoint during sketching. The progressive reconstruction algorithm is discussed, and examples from a working implementation are given.

• Journal of the Korean Society of Hazard Mitigation
• /
• v.10 no.6
• /
• pp.81-87
• /
• 2010

In order to calculate the accurate runoff from a basin, nonlinearity in the relationship between rainfall and runoff has to be considered. Many runoff calculation models assume the linearity in the relationship or are too complicated to be analyzed. Therefore, the storage function method has been used in the prediction of flood because of the simplicity of the model. The storage function method has five parameters with related to the basin and rainfall characteristics which can be estimated by the empirical trial and error method. To optimize these parameters, regression method or optimization techniques such as genetic algorithm have been used, however, it is not easy to optimize them because of the complexity of the method. In this study, the metamodel is proposed to estimate those model parameters. The metamodel is the combination of artificial neural network and genetic algorithm. The model is consisted of two stages. In the first stage, an artificial neural network is constructed using the given rainfall-runoff relationship. In the second stage, the parameters of the storage function method are estimated using genetic algorithm and the trained artificial neural network. The proposed metamodel is applied in the Peong Chang River basin and the results are presented.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.32 no.4
• /
• pp.53-60
• /
• 2004

Optimal design of the hybrid motor has been performed for the first stage of nanosat air launch vehicle using F-4E Phantom as mother plane. Selected design variables are number of ports, the initial oxidizer flux, the combustion chamber pressure, and the nozzle expansion ratio. GBM(Gradient Based Method) and GA(Genetic Algorithm) are simultaneously used to compare the versatility of each algorithm for optimal design in this problem. Also, two objective functions of motor weight, and length are treated separatedly in the optimization to study how the objective function can affect the optimal design. The design results show that the optimal design can be successfully achieved either using GBM or GA regardless of the choice of the objective function; motor weight or length. And nanosat air launch vehicle which has total mass of 704.74kg, and length of first stage 3.74m is designed.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.5 no.2
• /
• pp.89-101
• /
• 2005

Research on highly abstracted system modeling and simulation has received a great deal of attention as of the concept of platform based design is becoming ubiquitous. From a practical design point of view, such modeling and simulation must consider the following: (i) fast simulation speed and cycle accuracy, (ii) early availability for early stage software development, (iii) inter-operability with external tools for software development, and (iv) reusability of the models. Unfortunately, however, all of the previous works only partially addresses the requirements, due to the inherent conflicts among the requirements. The objective of this study is to develop a new system design methodology to effectively address the requirements mentioned above. We propose a new transaction-level system modeling methodology, called ViP (Virtual Platform). We propose a two-step approach in the ViP method. In phase 1, we create a ViP for early stage software development (before RTL freeze). The ViP created in this step provides high speed simulation, lower cycle accuracy with only minor modeling effort.(satisfying (ii)). In phase 2, we refine the ViP to increase the cycle accuracy for system performance analysis and software optimization (satisfying (i)). We also propose a systematic ViP modeling flow and unified interface scheme based on utilities developed for maximizing reusability and productivity (satisfying (ii) and (iv)) and finally, we demonstrate VChannel, a generic scheme to provide a connection between the ViP and the host-resident application software (satisfying (iii)). ViP had been applied to several System-on-a-chip (SoC) designs including mobile applications, enabling engineers to improve performance while reducing the software development time by 30% compared to traditional methods.

• Nuclear Engineering and Technology
• /
• v.54 no.9
• /
• pp.3516-3525
• /
• 2022

The high capture cross-section (𝜎_c) of Gadolinium (Gd-155 and Gd-157) causes reactivity penalty and swing at the initial stage of fuel burnup in Pressurized Water Reactor (PWR). The present study is concerned with the feasibility of the combination of mixed burnable poison with both low and high 𝜎_c as an approach to minimize these effects. Two considered reference designs are fuel assemblies with 24 IBA rods of Gd₂O₃ and Er₂O₃ respectively. Models comprise nuclear fuel with a homogeneous mixture of Er₂O₃, AmO₂, SmO₂, and HfO₂ with Gd₂O₃ as well as the coating of PaO₂ and ZrB₂ on the Gd₂O₃ pellet's outer surface. The infinite multiplication factor was determined and reactivity was calculated considering 3% neutron leakage rate. All models except Er₂O₃ and SmO₂ showed expected results namely higher values of these parameters than the reference design of Gd₂O₃ at the early burnup period. The highest value was found for the model of PaO₂ and Gd₂O₃ followed by ZrB₂ and HfO₂. The cycle burnup, discharge burnup, and cycle length for three batch refueling were calculated using Linear Reactivity Model (LRM). The pin power distribution, energy-dependent neutron flux and Fuel Temperature Coefficient (FTC) were also studied. An optimization of model 1 was carried out to investigate effects of different isotopic compositions of Gd₂O₃ and absorber coating thickness.

• Journal of Microbiology and Biotechnology
• /
• v.33 no.2
• /
• pp.260-267
• /
• 2023

In this study, we sought to improve lutein and zeaxanthin production in Mychonastes sp. 247 and investigated the effect of environmental factors on lutein and zeaxanthin productivity in Mychonastes sp. The basic medium selection and N:P ratio were adjusted to maximize cell growth in one-stage culture, and lutein and zeaxanthin production conditions were optimized using a central composite design for two-stage culture. The maximum lutein production was observed at a light intensity of 60 μE/m²/s and salinity of 0.49%, and the maximum zeaxanthin production was observed at a light intensity of 532 μE/m²/s and salinity of 0.78%. Lutein and zeaxanthin production in the optimized medium increased by up to 2 and 2.6 folds, respectively, compared to that in the basic medium. Based on these results, we concluded that the optimal conditions for lutein and zeaxanthin production are different and that optimization of light intensity and culture salinity conditions may help increase carotenoid production. This study presents a useful and potential strategy for optimizing microalgal culture conditions to improve the productivity of lutein and zeaxanthin, which has applications in the functional food field.

• Journal of Korean Society of Water and Wastewater
• /
• v.23 no.6
• /
• pp.799-810
• /
• 2009

With time, the stable management of turbidity is becoming more important in the water treatment process. So optimization of coagulation is important for the improvement of the sedimentation efficiency. we evaluated the mixing and hydrodynamic behavior in the coagulation basin using Computational Fluid Dynamics (CFD). The items for evaluation are a location and the speed of agitator and angle of an injection pipe. The results of the CFD simulation, the efficacy of mixing in the coagulation basin was not affected according to one or two injection pipe and angle of an injection pipe. If there is a agitator near outlet of coagulation basin, the efficacy of mixing don't improve even though the speed of agitator increase. So location of agitator is perfect when it locate center at the inlet stream. The coagulation basin at this study, the proper speed of agitator is form 20rpm to 30rpm.