• Journal of Wind Energy
• /
• v.15 no.3
• /
• pp.21-29
• /
• 2024

Wind power is highly variable due to the intermittent nature of wind. This can lead to power grid instability and decreased efficiency. Therefore, it is necessary to improve wind power prediction performance to minimize the negative impact on the power system. Recently, wind power prediction using machine learning has gained popularity, and ensemble models in machine learning have shown high prediction accuracy. RF, GB, XGB and LGBM are decision tree-based ensemble models and have high predictive performance in wind power, but these models have problems from over-fitting and strong dependence on certain variables. However, the stacking model can improve prediction performance by combining individual models and compensate for the shortcomings of each model. In this study, The MAE of RF, XGB and LGBM is 310.42 kWh, 217.07 kWh and 265.20 kWh, respectively, while the stacking model based on RF, XGB and LGBM is 202.33 kWh. Stacking models can improve prediction performance. Finally, it is expected to contribute to electricity supply and demand planning.

• The Korean Journal of Applied Statistics
• /
• v.29 no.7
• /
• pp.1373-1383
• /
• 2016

The wind energy industry and wind power generation have increased; consequently, the stable supply of the wind power has become an important issue. It is important to accurately predict the wind power with short-term basis in order to make a reliable planning for the power supply and demand of wind power. In this paper, we first analyzed the speed, power and the directions of the wind. The neural network and the time series models (ARMA, ARMAX, ARMA-GARCH, Holt Winters) for wind power generation forecasting were compared based on mean absolute error (MAE). For one to three hour-ahead forecast, ARMA-GARCH model was outperformed, and the neural network method showed a better performance in the six hour-ahead forecast.

• International Area Studies Review
• /
• v.16 no.3
• /
• pp.53-73
• /
• 2012

In this study we investigate the ability of the yield spread to predict economic recessions in two Asian economies. For our purpose we use the data from two emerging economies (South Korea and Thailand) that are also known for their openness in terms of exports and imports. We employ both two-regime Markov-Switching model (MS) and three-regime MS model to estimate the probability of recessions during Asian crisis. We found that the yield spread is confirmed to be a reliable recession predictor for Thailand but not for South Korea. The three-regime MS model is better for capturing the Asian financial crisis than two-regime MS model. We also tried to find the duration of economic expansions and recessions. We tested the hypothesis of asymmetric movements of business cycles. The MS results are also compared with that of the standard probit model for comparison. The MS model does not significantly improve the forecasting ability of the yield spread in forecasting business cycles.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.7
• /
• pp.187-194
• /
• 2022

LNG is known as the transitional energy source for the future eco-friendly, attracting enormous market attention due to global eco-friendly regulations, Covid-19 Pandemic, Russia-Ukraine War. In addition, since new LNG suppliers such as the U.S. and Australia are also diversifying, the LNG spot market is expected to grow. On the other hand, research on the LNG transportation market has been marginalized. Therefore, this study attempted to predict short-term LNG 160K spot rates and compared the prediction performance between artificial neural networks and the ARIMA model. As a result of this paper, while it was difficult to determine the superiority and superiority of ARIMA and artificial neural networks, considering the relative free of ANN's contraints, we confirmed the feasibility of ANN in LNG 160K spot rate prediction. This study has academic significance as the first attempt to apply an artificial neural network to forecasting LNG 160K spot rates and are expected to contribute significantly in practice in that they can improve the quality of short-term investment decisions by market participants by increasing the accuracy of short-term prediction.

• Journal of the Korean Society of Systems Engineering
• /
• v.18 no.2
• /
• pp.94-107
• /
• 2022

Accidents prevention and mitigation is the highest priority of nuclear power plant (NPP) operation, particularly in the aftermath of the Fukushima Daiichi accident, which has reignited public anxieties and skepticism regarding nuclear energy usage. To deal with accident scenarios more effectively, operators must have ample and precise information about key safety parameters as well as their future trajectories. This work investigates the potential of machine learning in forecasting NPP response in real-time to provide an additional validation method and help reduce human error, especially in accident situations where operators are under a lot of stress. First, a base-case SGTR simulation is carried out by the best-estimate code RELAP5/MOD3.4 to confirm the validity of the model against results reported in the APR1400 Design Control Document (DCD). Then, uncertainty quantification is performed by coupling RELAP5/MOD3.4 and the statistical tool DAKOTA to generate a large enough dataset for the construction and training of neural-based machine learning (ML) models, namely LSTM, GRU, and hybrid CNN-LSTM. Finally, the accuracy and reliability of these models in forecasting system response are tested by their performance on fresh data. To facilitate and oversee the process of developing the ML models, a Systems Engineering (SE) methodology is used to ensure that the work is consistently in line with the originating mission statement and that the findings obtained at each subsequent phase are valid.

• The Bulletin of The Korean Astronomical Society
• /
• v.46 no.1
• /
• pp.42.1-42.1
• /
• 2021

In this study, we present a visual explanation of a deep learning solar flare forecast model and its relationship to physical parameters of solar active regions (ARs). For this, we use full-disk magnetograms at 00:00 UT from the Solar and Heliospheric Observatory/Michelson Doppler Imager and the Solar Dynamics Observatory/Helioseismic and Magnetic Imager, physical parameters from the Space-weather HMI Active Region Patch (SHARP), and Geostationary Operational Environmental Satellite X-ray flare data. Our deep learning flare forecast model based on the Convolutional Neural Network (CNN) predicts "Yes" or "No" for the daily occurrence of C-, M-, and X-class flares. We interpret the model using two CNN attribution methods (guided backpropagation and Gradient-weighted Class Activation Mapping [Grad-CAM]) that provide quantitative information on explaining the model. We find that our deep learning flare forecasting model is intimately related to AR physical properties that have also been distinguished in previous studies as holding significant predictive ability. Major results of this study are as follows. First, we successfully apply our deep learning models to the forecast of daily solar flare occurrence with TSS = 0.65, without any preprocessing to extract features from data. Second, using the attribution methods, we find that the polarity inversion line is an important feature for the deep learning flare forecasting model. Third, the ARs with high Grad-CAM values produce more flares than those with low Grad-CAM values. Fourth, nine SHARP parameters such as total unsigned vertical current, total unsigned current helicity, total unsigned flux, and total photospheric magnetic free energy density are well correlated with Grad-CAM values.

• Atmosphere
• /
• v.34 no.2
• /
• pp.177-185
• /
• 2024

As increasing global interest in renewable energy due to the ongoing climate crisis, there is a growing need for efficient technologies to manage such resources. This study focuses on the predictive skill of daily solar power generation using weather observation and forecast data. Meteorological data from the Korea Meteorological Administration and solar power generation data from the Korea Power Exchange were utilized for the period from January 2017 to May 2023, considering both inland (Daejeon) and coastal (Busan) regions. Temperature, wind speed, relative humidity, and precipitation were selected as relevant meteorological variables for solar power prediction. All data was preprocessed by removing their systematic components to use only their residuals and the residual of solar data were further processed with weighted adjustments for homoscedasticity. Four models, MLR (Multiple Linear Regression), RF (Random Forest), DNN (Deep Neural Network), and RNN (Recurrent Neural Network), were employed for solar power prediction and their performances were evaluated based on predicted values utilizing observed meteorological data (used as a reference), 1-day-ahead forecast data (referred to as fore1), and 2-day-ahead forecast data (fore2). DNN-based prediction model exhibits superior performance in both regions, with RNN performing the least effectively. However, MLR and RF demonstrate competitive performance comparable to DNN. The disparities in the performance of the four different models are less pronounced than anticipated, underscoring the pivotal role of fitting models using residuals. This emphasizes that the utilized preprocessing approach, specifically leveraging residuals, is poised to play a crucial role in the future of solar power generation forecasting.

• Journal of Ocean Engineering and Technology
• /
• v.31 no.6
• /
• pp.405-412
• /
• 2017

Because of the rapid development of computer technology in recent years, wave models can utilize parallel calculations for the high-resolution prediction of open sea and coastal areas with high accuracy. Parallel calculations also allow national agencies in the relevant sectors to produce marine forecasting data through massive parallel calculations. Meanwhile, the eastern coast of the Korean Peninsula has been increasingly damaged by swell-like high waves, and many researchers and scientists are continuing their efforts to anticipate and reduce the damage. In general, the short-term transformation of swell-like high waves can be reproduced relatively well in the third generation wave models, but the transformation of relatively long period waves needs to be simulated with higher accuracy in terms of the nonlinear wave interactions to gain a better understanding of the low-frequency wave generation and development mechanisms. In this study, we developed a calculation module to improve the calculation of the nonlinear energy transfer in the 3rd generation wave model and integrated it into the wave model to effectively consider the nonlinear wave interaction. First, the nonlinear energy transfer calculation module and third generation model were combined. Then, the combined model was used to reproduce the wave transformation due to the nonlinear interaction, and the performance of the developed operation module was verified.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.05a
• /
• pp.629-631
• /
• 2015

Recently, the actual demand for electricity usage to out of demand forecasting demand appears to be based on the power of Government to address the insecurity is there are a lot of efforts on a more efficient energy management. In 2011, the first major outage, blackout since the current rate of no more than 10% of our power plants, such as power supply and demand crisis is being repeated. In addition, energy management systems, the demand for care and social areas are being expanded. In this paper, Building power supply and wired/wireless router and to optimize the DDNS (Dynamic Domain Name Service) for remote control and monitoring device for electric consumption Presonal Energy Management System offers a way to implement it. In the future, remote control and access the user's can minimize the settings for additional research is needed.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.41 no.1
• /
• pp.84-93
• /
• 2018

In this paper, we propose an Elman recurrent neural network to predict and analyze a time series of power energy consumption. To this end, we consider the volatility of the time series and apply the sample variance and the detrended fluctuation analyses to the volatilities. We demonstrate that there exists a correlation in the time series of the volatilities, which suggests that the power consumption time series contain a non-negligible amount of the non-linear correlation. Based on this finding, we adopt the Elman recurrent neural network as the model for the prediction of the power consumption. As the simplest form of the recurrent network, the Elman network is designed to learn sequential or time-varying pattern and could predict learned series of values. The Elman network has a layer of "context units" in addition to a standard feedforward network. By adjusting two parameters in the model and performing the cross validation, we demonstrated that the proposed model predicts the power consumption with the relative errors and the average errors in the range of 2%~5% and 3kWh~8kWh, respectively. To further confirm the experimental results, we performed two types of the cross validations designed for the time series data. We also support the validity of the model by analyzing the multi-step forecasting. We found that the prediction errors tend to be saturated although they increase as the prediction time step increases. The results of this study can be used to the energy management system in terms of the effective control of the cross usage of the electric and the gas energies.