• Journal of Electrical Engineering and Technology
• /
• v.13 no.3
• /
• pp.1089-1098
• /
• 2018

This study aims at developing and applying a hybrid model to the wind power prediction (WPP). The hybrid model for a very-short-term WPP (VSTWPP) is achieved through analytical data, multiple linear regressions and least square methods (MLR&LS). The data used in our hybrid model are based on the historical records of wind power from an offshore region. In this model, the WPP is achieved in four steps: 1) transforming historical data into ratios; 2) predicting the wind power using the ratios; 3) predicting rectification ratios by the total wind power; 4) predicting the wind power using the proposed rectification method. The proposed method includes one-step and multi-step predictions. The WPP is tested by applying different models, such as the autoregressive moving average (ARMA), support vector machine (SVM), and artificial neural network (ANN). The results of all these models confirmed the validity of the proposed hybrid model in terms of error as well as its effectiveness. Furthermore, forecasting errors are compared to depict a highly variable WPP, and the correlations between the actual and predicted wind powers are shown. Simulations are carried out to definitely prove the feasibility and excellent performance of the proposed method for the VSTWPP versus that of the SVM, ANN and ARMA models.

• Nuclear Engineering and Technology
• /
• v.53 no.8
• /
• pp.2610-2615
• /
• 2021

The prediction of irradiation-induced transition temperature shift for RPV steels is an important method for long term operation of nuclear power plant. Based on the irradiation embrittlement data, an irradiation-induced transition temperature shift prediction model is developed with machine learning method XGBoost. Then the residual, standard deviation and predicted value vs. measured value analysis are conducted to analyze the accuracy of this model. At last, Cu content threshold and saturation values analysis, temperature dependence, Ni/Cu dependence and flux effect are given to verify the reliability. Those results show that the prediction model developed with XGBoost has high accuracy for predicting the irradiation embrittlement trend of RPV steel. The prediction results are consistent with the current understanding of RPV embrittlement mechanism.

• Journal of Korean Institute of Industrial Engineers
• /
• v.33 no.4
• /
• pp.402-409
• /
• 2007

Markov Chains has proven to be effective in predicting human behaviors in the areas of web site assess, multimedia educational system, and driving environment. In order to extend an application area of predicting human behaviors using Markov Chains, this study was conducted to investigate whether Markov Chains could be used to predict human behavior in selecting mobile phone menu item. Compared to the aforementioned application areas, this study has different aspects in using Markov Chains : m-order 1-step Markov Model and the concept of Power Law of Learning. The results showed that human behaviors in predicting mobile phone menu selection were well fitted into with m-order 1-step Markov Model and Power Law of Learning in allocating history path vector weights. In other words, prediction of mobile phone menu selection with Markov Chains was capable of user's actual menu selection.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.27 no.5
• /
• pp.61-66
• /
• 2013

In this paper, a control scheme with the capability of high efficiency, which is realized by predicting the conditions of a load power and an input power, is proposed for the uninterruptible power supply (UPS). Generally, on-line UPS system supplies a constant voltage and a constant frequency (CVCF). However, the efficiency of the On-line UPS system can be reduced due to the switching losses of semiconductor devices during the power conversion. The these losses are improved by the proposed smart UPS with the high efficiency drive system, which is realized by analysing and predicting the conditions of a load power and an input power.

• Journal of the Korean Home Economics Association
• /
• v.48 no.3
• /
• pp.15-30
• /
• 2010

The objective of this study is to identify the relationship quality and relationship benefit, which has greater explanatory power in predicting fashion consumers' future loyalty. This study is particularly interested in the different explanatory power of each relationship quality with various relationship partners of fashion consumers. The participants were 507 female consumers over 20 years old and they responed questionnaire. The result showed that relationship quality types and relationship benefits having greater explanatory power in predicting consumers' loyal relationship intention varied with multi-loyal relations. Consumers' intention to be loyal to an apparel brand and apparel company was more explained by self attachment than by any other relationship quality types, whereas the intention to be loyal to specific department store was predicted by low involved relationship quality types such as habitual alternative and compensational bind. Trusted intimacy was the only relationship quality type that was significant in predicting consumers' intention to be loyal to salesperson in the future. Among relationship benefits, the influence of convenience benefit was significant in predicting consumers' future loyalty in most relations.

• Journal of Biosystems Engineering
• /
• v.27 no.1
• /
• pp.19-24
• /
• 2002

According to the field test, the transient power transmission efficiency of a tractor driveline fluctuated in a range of 56 to 86% and the mean value was about 72.5%. Therefore, the constant efficiency model commonly used for a simulation of power performance was not proper far predicting such a variable of efficiency. In order to predict power efficiency more accurately, new concepts of the maximum efficiency and drag torque were introduced and a new model based on the these concepts was proposed. The difference between measured and model-predicted efficiencies was about 1.5% in average with a standard deviation of 1.1%. The new power efficiency model was expected to enhance the accuracy of predicting power transmission efficiencies of tractor drivelines.

• Proceedings of the Korean Radioactive Waste Society Conference
• /
• 2018.11a
• /
• pp.129-130
• /
• 2018

• The Journal of Bigdata
• /
• v.5 no.1
• /
• pp.227-239
• /
• 2020

This paper introduces a method for predicting the maximum power demand despite communication errors in industrial sites. Due to the recent policy of de-nuclearization in Korea, the price of electricity is inevitable, and the amount of electricity used and maximum load management for the management of power demand are becoming important issues. Accordingly, it is important to predict and manage peak power. However, problems such as loss and modulation of measured power data occur at industrial sites due to noise generated by various facilities and sensors. It is difficult to predict the exact value when measured effective power data are lost. The study presents a model for predicting and correcting anomalies and missing values when measured effective power data are lost. The models used in this study are expected to be useful in predicting peak power demand in the event of communication errors at industrial sites.

• Journal of Integrative Natural Science
• /
• v.12 no.1
• /
• pp.20-23
• /
• 2019

Demand response is usually operated through using the power rates and incentives. Demand management based on power charges is the most rational and efficient demand management method, and such methods include rolling base charges with peak time, sliding scaling charges depending on time, sliding scaling charges depending on seasons, and nighttime power charges. Search for other methods to stimulate resources on demand by actively deriving the demand reaction of loads to increase the energy efficiency of loads. In this paper, ESS algorithm for saving energy based on predicting the amount of solar power generation that can be used for buildings with small loads not under electrical grid.

• Proceedings of the Korean Society of Near Infrared Spectroscopy Conference
• /
• 2001.06a
• /
• pp.1618-1618
• /
• 2001

Predicting quality traits using near infrared (NIR) spectroscopy on whole grain samples has gained wide acceptance as a non-destructive, rapid and cost effective technique. Barley breeding programs throughout southern Australia currently use this technology as a tool for selecting malting quality lines. For the past 3 years whole grain barley calibrations have been developed at VIDA to predict malting quality traits in the early generation selections of the breeding program. More recently calibrations for whole grain malt have been developed and introduced to aid in selecting malted samples at the mid-generation stage for more complex malting quality traits. Using the same population set, barley and malt calibrations were developed to predict hot water extracts (EBC and IoB), diastatic power, free $\alpha$-amino nitrogen, soluble protein, wort $\beta$-glucan and $\beta$-glucanase. The correlation coefficients between NIR predicted values and laboratory methods for malt were all highly significant ($R^2$ > 0.84), whereas the correlation coefficients for the barley calibrations were lower ($R^2$ > 0.57) but still significant. The magnitude of the error in predicting hot water extract, diastatic power and wort $\beta$-glucan using whole grain malt was reduced by 50% when compared with predicting the same trait using whole grain barley. This can be explained by the complex nature of attempting to develop calibrations on whole grain barley utilizing malt data. During malting, the composition of barley is modified by the action of enzymes throughout the steeping and germination stages and by heating during the kilning stage. Predicting malting quality on whole grain malt is a more reliable alternative to predicting whole grain barley, although there is the added expense of micro-malting the samples. The ability to apply barley and malt calibrations to different generations is an advantage to a barley breeding program that requires thousands of samples to be assessed each year.