• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2004.04a
• /
• pp.523-527
• /
• 2004

This paper presents a new design methods of the short-term load forecasting system (STLFS) using the data mining. The proposed predictor takes form of the convex combination of the linear time series predictors for each inputs. The problem of estimating the consequent parameters is formulated by the convex optimization problem, which is to minimize the norm distance between the real load and the output of the linear time series estimator, The problem of estimating the premise parameters is to find the parameter value minimizing the error between the real load and the overall output. Finally, to show the feasibility of the proposed method, this paper provides the short-term load forecasting example.

• Journal of Korean Society on Water Environment
• /
• v.27 no.4
• /
• pp.533-541
• /
• 2011

Algal blooms have caused problems for drinking water as well as eutrophication. However it is difficult to control algal blooms by current warning manual in rainy season because the algal blooms happen in a few days. The water quality data, which have high correlations with Chlorophyll-a on Daecheongho station, were analyzed and chosen as input data of Artificial Neural Networks (ANN) for training pattern changes. ANN was applied to early forecasting of algal blooms, and ANN was assessed by forecasting errors. Water temperature, pH and Dissolved oxygen were important factors in the cross correlation analysis. Some water quality items like Total phosphorus and Total nitrogen showed similar pattern to the Chlorophyll-a changes with time lag. ANN model (No. 3), which was calibrated by water temperature, pH and DO data, showed lowest error. The combination of 1 day, 3 days, 7 days forecasting makes outputs more stable. When automatic monitoring data were used for algal bloom forecasting in Daecheong reservoir, ANN model must be trained by just input data which have high correlation with Chlorophyll-a concentration. Modular type model, which is combined with the output of each model, can be effectively used for stable forecasting.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.16 no.3
• /
• pp.163-172
• /
• 2016

Electric load forecasting is essential for effective power system planning and operation. Complex and nonlinear relationships exist between the electric loads and their exogenous factors. In addition, time-series load data has non-stationary characteristics, such as trend, seasonality and anomalous day effects, making it difficult to predict the future loads. This paper proposes a locally-weighted polynomial neural network (LWPNN), which is a combination of a polynomial neural network (PNN) and locally-weighted regression (LWR) for daily shortterm peak load forecasting. Model over-fitting problems can be prevented effectively because PNN has an automatic structure identification mechanism for nonlinear system modeling. LWR applied to optimize the regression coefficients of LWPNN only uses the locally-weighted learning data points located in the neighborhood of the current query point instead of using all data points. LWPNN is very effective and suitable for predicting an electric load series with nonlinear and non-stationary characteristics. To confirm the effectiveness, the proposed LWPNN, standard PNN, support vector regression and artificial neural network are applied to a real world daily peak load dataset in Korea. The proposed LWPNN shows significantly good prediction accuracy compared to the other methods.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.134-134
• /
• 2022

Streamflow forecasting plays a crucial role in water resource control, especially in highly urbanized areas that are very vulnerable to flooding during heavy rainfall event. In addition to providing the accurate prediction, the evaluation of effects and importance of the input predictors can contribute to water manager. Recently, machine learning techniques have applied their advantages for modeling complex and nonlinear hydrological processes. However, the techniques have not considered properly the importance and uncertainty of the predictor variables. To address these concerns, we applied the GA-BART, that integrates a genetic algorithm (GA) with the Bayesian additive regression tree (BART) model for hourly streamflow forecasting and analyzing input predictors. The Jungrang urban basin was selected as a case study and a database was established based on 39 heavy rainfall events during 2003 and 2020 from the rain gauges and monitoring stations. For the goal of this study, we used a combination of inputs that included the areal rainfall of the subbasins at current time step and previous time steps and water level and streamflow of the stations at time step for multistep-ahead streamflow predictions. An analysis of multiple datasets including different input predictors was performed to define the optimal set for streamflow forecasting. In addition, the GA-BART model could reasonably determine the relative importance of the input variables. The assessment might help water resource managers improve the accuracy of forecasts and early flood warnings in the basin.

• Journal of Korea Water Resources Association
• /
• v.44 no.7
• /
• pp.537-551
• /
• 2011

Based on optimal input data combination selected in the earlier study, Neuro-Fuzzy flood forecasting model linked Takagi-Sugeno fuzzy inference theory with neural network in Wangsukcheon and Gabcheon is established. The established model was applied to Wangsukcheon and Gabcheon and water levels for lead time of 0.5 hr, 1 hr, 1.5 hr, 2.0 hr, 2.5 hr, 3.0 hr are forecasted. For the verification of the model, the comparisons between forecasting floods and observation data are presented. The forecasted results have shown good agreements with observed data. Additionally to evaluate quantitatively for applicability of the model, various statistical errors such as Root Mean Square Error are calculated. As a result of the flood forecasting can be simulated successfully without large errors in all statistical error. This study can greatly contribute to the construction of a high accuracy flood information system that secure lead time in medium and small streams.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.59 no.12
• /
• pp.2202-2211
• /
• 2010

The wind power prediction system is composed of a meteorological forecasting module, calculation module of wind power output and HMI(Human Machine Interface) visualization system. The final information from this system is a short-term (6hr ahead) and mid-term (48hr ahead) wind power prediction value. The meteorological forecasting module for wind speed and direction forecasting is a combination of physical and statistical model. In this system, the WRF(Weather Research and Forecasting) model, which is a three-dimensional numerical weather model, is used as the physical model and the GFS(Global Forecasting System) models is used for initial condition forecasting. The 100m resolution terrain data is used to improve the accuracy of this system. In addition, optimization of the physical model carried out using historic weather data in Jeju. The mid-term prediction value from the physical model is used in the statistical method for a short-term prediction. The final power prediction is calculated using an optimal adjustment between the currently observed data and data predicted from the power curve model. The final wind power prediction value is provided to customs using a HMI visualization system. The aim of this study is to further improve the accuracy of this prediction system and develop a practical system for power system operation and the energy market in the Smart-Grid.

• Industrial Engineering and Management Systems
• /
• v.12 no.3
• /
• pp.244-253
• /
• 2013

In industries, shipping is an important issue in improving the forecasting accuracy of sales. This paper introduces a hybrid method and plural methods are compared. Focusing the equation of exponential smoothing method (ESM) that is equivalent to (1, 1) order autoregressive-moving-average (ARMA) model equation, a new method of estimating the smoothing constant in ESM had been proposed previously by us which satisfies minimum variance of forecasting error. Generally, the smoothing constant is selected arbitrarily. However, this paper utilizes the above stated theoretical solution. Firstly, we make estimation of ARMA model parameter and then estimate the smoothing constant. Thus, theoretical solution is derived in a simple way and it may be utilized in various fields. Furthermore, combining the trend removing method with this method, we aim to improve forecasting accuracy. This method is executed in the following method. Trend removing by the combination of linear and 2nd order nonlinear function and 3rd order nonlinear function is executed to the original production data of two kinds of bread. Genetic algorithm is utilized to search the optimal weight for the weighting parameters of linear and nonlinear function. For comparison, the monthly trend is removed after that. Theoretical solution of smoothing constant of ESM is calculated for both of the monthly trend removing data and the non-monthly trend removing data. Then forecasting is executed on these data. The new method shows that it is useful for the time series that has various trend characteristics and has rather strong seasonal trend. The effectiveness of this method should be examined in various cases.

• The Korean Journal of Applied Statistics
• /
• v.24 no.3
• /
• pp.465-475
• /
• 2011

In this paper, we have considered the problems of the estimation of the gross areas of a factory site relating to the areas of industrial complex lands based on a statistical forecasting model and the results of a sampling survey. In respect to the data of a gross areas of a factory site, we have only the sizes from 1981-2003. In 2009, the Korea Industrial Complex Corp. conducted a sampling survey to estimate its bulk size, and investigate the demands of its sizes for the next five years. In this study, we have adopted the sampling survey results, and have created a statistical growth model for the gross areas of a factory site to improve the prediction for the areas of a factory site. The three-different parts of data: the results of areas of a factory site by Korea National Statistical Office, imputation results by the statistical forecasting model, and sampling survey results have used as the basis for analysis. The combination of the three-different parts of data has created a new forecasting value of the areas of a factory site through the spline smoothing method.

• The Journal of the Korea Contents Association
• /
• v.20 no.12
• /
• pp.49-57
• /
• 2020

This study predicts the ratio of added value, which represents the competitiveness of export industries in South Korea, using various machine learning techniques. To enhance the accuracy and stability of prediction, forecast combination technique was applied to predicted values of machine learning techniques. In particular, this study improved the efficiency of the prediction process by selecting key variables out of many variables using recursive feature elimination method and applying them to machine learning techniques. As a result, it was found that the predicted value by the forecast combination method was closer to the actual value than the predicted values of the machine learning techniques. In addition, the forecast combination method showed stable prediction results unlike volatile predicted values by machine learning techniques.

• Communications for Statistical Applications and Methods
• /
• v.21 no.6
• /
• pp.471-486
• /
• 2014

This study introduces a new type of symbolic data, a candle chart-valued time series. We aggregate four stock indices (i.e., open, close, highest and lowest) as a one data point to summarize a huge amount of data. In other words, we consider a candle chart, which is constructed by open, close, highest and lowest stock indices, as a type of symbolic data for a long period. The proposed candle chart-valued time series effectively summarize and visualize a huge data set of stock indices to easily understand a change in stock indices. We also propose novel approaches for the candle chart-valued time series modeling based on a combination of two midpoints and two half ranges between the highest and the lowest indices, and between the open and the close indices. Furthermore, we propose three types of sum of square for estimation of the candle chart valued-time series model. The proposed methods take into account of information from not only ordinary data, but also from interval of object, and thus can effectively perform for time series modeling (e.g., forecasting future stock index). To evaluate the proposed methods, we describe real data analysis consisting of the stock market indices of five major Asian countries'. We can see thorough the results that the proposed approaches outperform for forecasting future stock indices compared with classical data analysis.