• Journal of Electrical Engineering and Technology
• /
• 제10권3호
• /
• pp.1342-1348
• /
• 2015

The objective of this study is to propose a method to calculate prediction intervals for one-day-ahead hourly forecasts of photovoltaic power generation and to evaluate its performance. One year of data of two systems, representing contrasting examples of forecast’ accuracy, were used. The method is based on the maximum likelihood estimation, the similarity between the input data of future and past forecasts of photovoltaic power, and on an assumption about the distribution of the error of the forecasts. Two assumptions for the forecast error distribution were evaluated, a Laplacian and a Gaussian distribution assumption. The results show that the proposed method models well the photovoltaic power forecast error when the Laplacian distribution is used. For both systems and intervals calculated with 4 confidence levels, the intervals contained the true photovoltaic power generation in the amount near to the expected one.

• 전기학회논문지
• /
• 제64권3호
• /
• pp.393-398
• /
• 2015

City or Community-scale Energy Management System(CEMS) is used to reduce the total energy consumed in the city by arranging the energy resources efficiently at the planning stage and controlling them economically at the operating stage. Of the operational functions of the CEMS, generation forecasting of renewable energy resources is an essential feature for the effective supply scheduling. This is because it can develop daily operating schedules of controllable generators in the city (e.g. diesel turbine, micro-gas turbine, ESS, CHP and so on) in order to minimize the inflow of the external power supply system, considering the amount of power generated by the uncontrollable renewable energy resources. This paper is written to introduce numerical models for photo-voltaic power generation prediction based on the weather forecasting information. Unlike the conventional methods using the average radiation or average utilization rate, the proposed models are developed for CEMS applications using the realtime weather forecast information provided by the National Weather Service.

• 한국수소및신에너지학회논문집
• /
• 제31권5호
• /
• pp.436-443
• /
• 2020

The performance prediction model of a solid oxide fuel cell stack has been developed using deep neural network technique, one of the machine learning methods. The machine learning has been received much interest in various fields, including energy system mo- deling. Using machine learning technique can save time and cost requried in developing an energy system model being compared to the conventional method, that is a combination of a mathematical modeling and an experimental validation. Results reveal that the mean average percent error, root mean square error, and coefficient of determination (R2) range 1.7515, 0.1342, 0.8597, repectively, in maximum. To improve the predictability of the model, the pre-processing is effective and interpolative machine learning and application is more accurate than the extrapolative cases.

• KEPCO Journal on Electric Power and Energy
• /
• 제1권1호
• /
• pp.163-168
• /
• 2015

In order to integrate high wind generation resources into power grid, it is an essential to predict power outputs of wind generating resources. As wind farm outputs depend on natural wind resources that vary over space and time, spatial modeling based on geographic information such as latitude and longitude is needed to estimate power outputs of wind generation resources. In this paper, we introduce the basic concept of spatial modeling and present the spatial prediction model based on Kriging techniques. The empirical data, wind farm power output in Texas, is considered to verify the proposed prediction model.

• 한국CDE학회논문집
• /
• 제21권2호
• /
• pp.143-150
• /
• 2016

In shipbuilding, hull assemblies are manufactured by welding. The thermal deformation caused by the welding produces shape deformation. Counter-deformed design methods have been used in shipyards to cope with the weld-induced deformation of ship assembles. Finite element methods (FEMs) are frequently used to estimate welding distortion in the counter-deformed design. For the estimation of welding distortion, producing uniform rectangular elements is required to enter thermal loads on the welding line and obtain accurate analysis results. In this paper, a new automatic mesh generation method is proposed for prediction of welding deformation in FEM. Meshes are constructed for test cases to demonstrate the feasibility of the proposed mesh generation method.

• 한국정밀공학회지
• /
• 제16권4호통권97호
• /
• pp.229-236
• /
• 1999

The surface, generated by end milling operation, is deteriorated by tool runout, vibration, tool wear and tool deflection, etc. Among them, the effect of tool deflection on surface accuracy is analyzed. Surface generation model for the prediction of the topography of machined srufaces has been developed based on cutting mechanism and cutting tool geometry. This model accounts for not only the ideal geometrical surface, but also the deflection of tool due to cutting force. For the more accurate prediction of cutting force, flexible end mill model is used to simulate cutting process. Computer simulation has shown the feasibility of the surface generation system. Using developed simulation system, the relations between the shape of end mill and cutting conditions are analyzed.

• 전기전자학회논문지
• /
• 제26권3호
• /
• pp.355-363
• /
• 2022

우리나라는 2050년 탄소중립을 목표로 신재생에너지 중심으로 에너지 공급원을 전환하고 확대하는 계획을 추진 중이다. 신재생에너지의 간헐적 특성으로 에너지 공급이 불안정성이 커짐에 따라 정확한 신재생에너지 발전량 예측의 중요성이 함께 커지고 있다. 이에 따라 정부는 신재생에너지를 집합화하여 관리하기 위한 소규모 전력중개시장을 개설하였고, 재생에너지 발전량 예측제도를 도입하여 예측정확도에 따라 정산금을 지급하는 제도를 시행 중이다. 본 논문에서는 우리나라 신재생에너지 전원의 대부분을 차지하는 태양광 발전에 대하여 통계적 및 인공지능 모형을 이용하여 예측모델을 구현하였으며, 각 모형의 예측정확도 결과를 비교 분석하였다. 비교 모델 중에서 CNN-LSTM(Convolutional Long Short-Term Memory Neural Networks) 모형이 가장 높은 성능을 가짐을 확인하였다. 예측정확도에 따른 예측제도 정산금 수익을 추정해보았고, 예측보유 기술 수준에 따라 수익 편차가 24% 정도 커질 수 있음을 확인하였다.

• 한국시뮬레이션학회논문지
• /
• 제17권3호
• /
• pp.19-26
• /
• 2008

본 논문에서는 중기 국채(Treasure Note; T-Note)의 실제 자료를 이용하여 채권 가격에 대한 이자율을 예측하는 동적인 예측 알고리즘을 제안하고 있다. 제안한 알고리즘은 이자율 기간 구조를 근본으로 하고 있으며 표준 위너 과정(standard Wiener process)과 같은 다양한 금융 모형의 대안으로 활용 가능하다. 본 논문에서는 실제 자료의 누적 분포 함수(Cumulative Distribution Function; CDF)를 이용하여 이자율을 측정하였으며 CDF는 수치적 방법인 보간법 중에 자주 활용되는 내츄럴 큐빅 스플라인(natural cubic spline; NCS)방법을 통하여 얻었다. 위에서 얻은 CDF를 통하여 난수 생성기법(random number generation scheme; RNGS)을 이용하여 채권의 가격를 계산하였다. 컴퓨터 시뮬레이션을 통해 얻은 실험결과로부터 제안된 예측 알고리즘에서 엄밀도(precision)의 낮은 값을 얻음으로써 채권의 가치가 더욱 예리하고 정확하게 평가되었음을 확인할 수 있었으며, 이는 매우 근거 있는 예측이라 할 수 있다.

• 전기전자학회논문지
• /
• 제25권4호
• /
• pp.766-769
• /
• 2021

딥러닝을 포함한 머신러닝 기법을 기반으로 비행체의 궤적 설계, 제어, 최적화, 예측 등의 작업을 수행하기 위해서는 일정한 양 이상의 비행체 궤적 데이터를 필요로 한다. 그러나 다양한 이유(예를 들어 비행체 궤적 데이터셋 구축에 필요한 비용, 시간, 인력 등)로 일정한 양 이상의 비행체 궤적 데이터를 확보하기 어려운 경우가 존재한다. 이러한 경우 합성 데이터 생성이 머신러닝을 가능하게 하는 방법 중 하나가 될 수 있다. 본 논문에서는 이와 같은 가능성을 탐구하기 위하여 시계열 생성적 적대 신경망을 이용하여 비행체 궤적 합성 데이터를 생성하고 평가하였다. 또한 비행체의 상태를 인식하기 위한 비행체 궤적 예측 작업에서 합성 데이터의 활용 가능성을 탐구하기 위하여 다양한 ablation study(비교 실험)를 수행하였다. 본 논문에서 제시된 생성 평가 및 비교 실험 결과는 비행체 궤적 합성 데이터 생성 및 비행체 궤적 관련 작업에서 합성 데이터의 활용 가능성에 대한 연구를 수행하고자 하는 연구자들에게 실질적인 도움이 될 것으로 예상한다.

• Asia pacific journal of information systems
• /
• 제30권1호
• /
• pp.31-52
• /
• 2020

Stock markets are popular investment avenues to people who plan to receive premium returns compared to other financial instruments, but they are highly volatile and risky due to the complex financial dynamics and poor understanding of the market forces involved in the price determination. A system that can forecast, predict the stock prices and automatically create a portfolio of top performing stocks is of great value to individual investors who do not have sufficient knowledge to understand the complex dynamics involved in evaluating and predicting stock prices. In this paper the authors propose a Stock prediction, Portfolio Generation and Selection model based on Machine learning algorithms, Artificial neural networks (ANNs) are used for stock price prediction, Mathematical and Statistical techniques are used for Portfolio generation and Un-Supervised Machine learning based on K-Means Clustering algorithms are used for Portfolio Evaluation and Selection which take in to account the Portfolio Return and Risk in to consideration. The model presented here is limited to predicting stock prices on a long term basis as the inputs to the model are based on fundamental attributes and intrinsic value of the stock. The results of this study are quite encouraging as the stock prediction models are able predict stock prices at least a financial quarter in advance with an accuracy of around 90 percent and the portfolio selection classifiers are giving returns in excess of average market returns.