• Proceedings of the KIEE Conference
• /
• 1993.07a
• /
• pp.29-32
• /
• 1993

A technique computing short-term load foadcasting is essential for monitoring and controlling power system operation. This paper shows the use of general exponential smoothing to develop an adaptive forecasting system based on observed value of hourly demand. Forecasts of hourly load with lead times of one to twenty-four hours are computed at hourly intervals throughout the week. Standard error for lead times of one to twenty-four hour range from three to four percent average load. Studies are planned to investigate the use of weather influence to increase forecast accuracy.

• Proceedings of the KIEE Conference
• /
• summer
• /
• pp.73-75
• /
• 2004

This paper presents the ability and the application of software packages for distribution planning which are DISPLAN(Distribution Planning System) and DLPLAN(Distribution Line Planning System) developed in KEPCO. After calculating size and position of maximum load by administration section for distribution, it forecasts the demand of distribution load considering growth location, increment, new load plan, etc of load by annual. Also it calculates distribution loss, voltage drop using modeled distribution line by you, and support for establishment and enlargement plan of substation and distribution line, decision of most optimal path. And it presents the abstract of used algorithm to develop this system.

• Proceedings of The Korean Society of Agricultural and Forest Meteorology Conference
• /
• 2016.09a
• /
• pp.25-28
• /
• 2016

Recently, because of the weather forecasts through the low-resolution data has been limited, the demand of the high-resolution data is sharply increasing. Therefore, in this study, we restore the ultra-high resolution synthetic precipitation and temperature data for 2000-2014 due to small-scale topographic effect using the QPM (Quantitative Precipitation Model)/QTM (Quantitative Temperature Model). First, we reproduce the detailed precipitation and temperature data with 1km resolution using the distribution of Automatic Weather System (AWS) data and Automatic Synoptic Observation System (ASOS) data, which is about 10km resolution with irregular grid over South Korea. Also, we recover the precipitation and temperature data with 1km resolution using the MERRA reanalysis data over North Korea, because there are insufficient observation data. The precipitation and temperature from restored current climate reflect more detailed topographic effect than irregular AWS/ASOS data and MERRA reanalysis data over the Korean peninsula. Based on this analysis, more detailed prospect of regional climate is investigated.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.12
• /
• pp.419-430
• /
• 2020

This paper investigated methods to improve the forecasting accuracy of the electricity consumption prediction model. Currently, the demand for electricity has continuously been rising more than ever. Since the industrial sector uses more electricity than any other sectors, the importance of a more precise forecasting model for manufacturing sites has been highlighted to lower the excess energy production. We propose a double encoder-decoder model, which uses two separate encoders and one decoder, in order to adapt both long-term and short-term data for better forecasts. We evaluated our proposed model on our electricity power consumption dataset, which was collected in a manufacturing site of Sehong from January 1st, 2019 to June 30th, 2019 with 1 minute time interval. From the experiment, the double encoder-decoder model marked about 10% reduction in mean absolute error percentage compared to a conventional encoder-decoder model. This result indicates that the proposed model forecasts electricity consumption more accurately on manufacturing sites compared to an encoder-decoder model.

• The Journal of Bigdata
• /
• v.4 no.1
• /
• pp.63-72
• /
• 2019

For power energy, optimal generation and distribution plans based on accurate demand forecasts are necessary because it is not recoverable after they have been delivered to users through power generation and transmission processes. Failure to predict power demand can cause various social and economic problems, such as a massive power outage in September 2011. In previous studies on forecasting power demand, ARIMA, neural network models, and other methods were developed. However, limitations such as the use of the national average ambient air temperature and the application of uniform criteria to distinguish seasonality are causing distortion of data or performance degradation of the predictive model. In order to improve the performance of the power demand prediction model, we divided Korea into five major regions, and the power demand prediction model of the linear regression model and the neural network model were developed, reflecting seasonal characteristics through regional characteristics and migration period learning techniques. With the proposed approach, it seems possible to forecast the future demand in short term as well as in long term. Also, it is possible to consider various events and exceptional cases during a certain period.

• Journal of Korea Water Resources Association
• /
• v.54 no.8
• /
• pp.617-628
• /
• 2021

Drought is a major natural disaster that causes serious social and economic losses. Local drought forecasts can provide important information for drought preparedness. In this study, we propose a new machine learning model that predicts drought by using historical drought indices and meteorological data from 10 sites from 1981 to 2020 in the southeastern part of the Korean Peninsula, Busan-Ulsan-Gyeongnam. Using Bayesian optimization techniques, a hyper-parameter-tuned Random Forest, XGBoost, and Light GBM model were constructed to predict the evaporative demand drought index on a 6-month time scale after 1-month. The model performance was compared by constructing a single site model and a regional model, respectively. In addition, the possibility of improving the model performance was examined by constructing a fine-tuned model using data from a individual site based on the regional model.

• Journal of Chest Surgery
• /
• v.49 no.sup1
• /
• pp.37-43
• /
• 2016

Background: While demand for cardiovascular surgery is expected to increase gradually along with the rapid increase in cardiovascular diseases with respect to the aging population, the supply of thoracic and cardiovascular surgeons has been continuously decreasing over the past 10 years. Consequently, this study aims to achieve guidance in establishing health care policy by analyzing the supply and demand for cardiovascular surgeries in the medical service area of Korea. Methods: After investigating the actual number of cardiovascular surgeries performed using the National Health Insurance claim data of the Health Insurance Review and Assessment Service, as well as drawing from national statistics concerning the elderly population aged 65 and over, this study estimated the number of future cardiovascular surgeries by using a cell-based model. To be able to analyze the supply and demand of surgeons, the recent status of new surgeons specializing in thoracic and cardiovascular surgeries and the ratio of their subspecialties in cardiovascular surgeries were investigated. Then, while taking three different scenarios into account, the number of cardiovascular surgeons expected be working in 5-year periods was projected. Results: The number of cardiovascular surgeries, which was recorded at 10,581 cases in 2014, is predicted to increase consistently to reach a demand of 15,501 cases in 2040-an increase of 46.5%. There was a total of 245 cardiovascular surgeons at work in 2014. Looking at 5 year spans in the future, the number of surgeons expected to be supplied in 2040 is 184, to retire is 249, and expected to be working is 309-an increase of -24.9%, 1.6%, and 26.1%, respectively compared to those in 2014. This forecasts a demand-supply imbalance in every scenario. Conclusion: Cardiovascular surgeons are the most central resource in the medical service of highly specialized cardiovascular surgeries, and fostering the surgeons requires much time, effort, and resources; therefore, by analyzing the various factors affecting the supply of cardiovascular surgeons, an active intervention of policies can be prescribed for the areas that have failed to meet the appropriate market distributions.

• Journal of Korea Water Resources Association
• /
• v.52 no.7
• /
• pp.505-514
• /
• 2019

Our country is making efforts to manage water resources efficiently. In the future, It is necessary to develop a plan after subdividing the basin considering regional problems and water use, topographical and climatic characteristics. This study constructed water supply and demand system based on the standard watershed unit for water shortage evaluation considering spatial resolution. In addition, water shortage were calculated and compared using the MODSIM model in the Han-river basin. As a result, the average water shortage occurring during the 49 years (1967-2015) was 129.98 million $m^3$ for the middle watershed unit and 222.24 million $m^3$ for the standard watershed unit, resulting in a difference of about 2.1 billion m3. However, the trends and distribution of water shortage occurrence were very similar. The reason for this is that, in the case of the Middle watershed unit analysis, water shortages are calculated for the demand for living, industrial, and agricultural water for the representative natural flow value, assuming that all the water can be used in basin. The standard basin unit analysis showed that the difference between the fractionated supply and demand resulted in a large water shortage due to the relatively small amount of available water, and that the main stream did not show water shortage due to the ripple effect of the return flow. If the actual water use system is considered in the model as well as the subdivision of the spatial unit, it will be possible to evaluate the water supply and demand reflecting the regional characteristics.

• Journal of Korean Society of Forest Science
• /
• v.84 no.2
• /
• pp.121-130
• /
• 1995

Forecasting accuracy is examined in the context of Michigan travel demand. Eight different annual models are used to forecast up to two years ahead, and nine different quarterly models up to four quarters. In the evaluation of annual models' performance, multiple regression performed better than the other methods in both the one year and two year forecasts. For quarterly models, Winters exponential smoothing and the Box-Jenkins method performed better than naive 1 s in the first quarter ahead, but these methods in the second, third, and fourth quarters ahead performed worse than naive 1 s. The sophisticated models did not outperform simpler models in producing quarterly forecasts. The best model, multiple regression, performed slightly better when fitted to quarterly rather than annual data: however, it is not possible to strongly recommend quarterly over annual models since the improvement in performance was slight in the case of multiple regression and inconsistent across the other models. As one would expect, accuracy declines as the forecasting time horizon is lengthened in the case of annual models, but the accuracy of quarterly models did not confirm this result.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.7
• /
• pp.1749-1758
• /
• 1997

This paper suggests the development of dynamic forecasting model for short-term power demand based on Radial Basis Function Network and Pal's GLVQ algorithm. Radial Basis Function methods are often compared with the backpropagation training, feed-forward network, which is the most widely used neural network paradigm. The Radial Basis Function Network is a single hidden layer feed-forward neural network. Each node of the hidden layer has a parameter vector called center. This center is determined by clustering algorithm. Theatments of classical approached to clustering methods include theories by Hartigan(K-means algorithm), Kohonen(Self Organized Feature Maps %3A SOFM and Learning Vector Quantization %3A LVQ model), Carpenter and Grossberg(ART-2 model). In this model, the first approach organizes the load pattern into two clusters by Pal's GLVQ clustering algorithm. The reason of using GLVQ algorithm in this model is that GLVQ algorithm can classify the patterns better than other algorithms. And the second approach forecasts hourly load patterns by radial basis function network which has been constructed two hidden nodes. These nodes are determined from the cluster centers of the GLVQ in first step. This model was applied to forecast the hourly loads on Mar. $4^{th},\;Jun.\;4^{th},\;Jul.\;4^{th},\;Sep.\;4^{th},\;Nov.\;4^{th},$ 1995, after having trained the data for the days from Mar. $1^{th}\;to\;3^{th},\;from\;Jun.\;1^{th}\;to\;3^{th},\;from\;Jul.\;1^{th}\;to\;3^{th},\;from\;Sep.\;1^{th}\;to\;3^{th},\;and\;from\;Nov.\;1^{th}\;to\;3^{th},$ 1995, respectively. In the experiments, the average absolute errors of one-hour ahead forecasts on utility actual data are shown to be 1.3795%.