• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.67 no.4
• /
• pp.183-190
• /
• 2018

Predicting accurate electricity prices is an important task in the electricity trading market. To address the electricity price forecasting problem, various approaches have been proposed so far and it is known that linear regression-based approaches are the best. However, the use of such linear regression-based methods is limited due to low accuracy and performance. In traditional linear regression methods, it is not practical to find a nonlinear regression model that explains the training data well. If the training data is complex (i.e., small-sized individual data and large-sized features), it is difficult to find the polynomial function with n terms as the model that fits to the training data. On the other hand, as a linear regression model approximating a nonlinear regression model is used, the accuracy of the model drops considerably because it does not accurately reflect the characteristics of the training data. To cope with this problem, we propose a new electricity price forecasting method that divides the entire dataset to multiple split datasets and find the best linear regression models, each of which is the optimal model in each dataset. Meanwhile, to improve the performance of the proposed method, we modify the proposed localized linear regression method in the map and reduce way that is a framework for parallel processing data stored in a Hadoop distributed file system. Our experimental results show that the proposed model outperforms the existing linear regression model. Specifically, the accuracy of the proposed method is improved by 45% and the performance is faster 5 times than the existing linear regression-based model.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.52 no.4
• /
• pp.233-237
• /
• 2003

An accurate load forecasting is essential for economics and stability power system operation. Due to high relationship between the electric power load and the electric power price, the participants of the competitive power market are very interested in load forecasting. The percentage errors of load forecasting for holidays is relatively large. In order to improve the accuarcy of load forecasting for holidays, this paper proposed load forecasting method for holidays using a fuzzy least squares linear regression algorithm. The proposed algorithm is tested for load forecasting for holidays in 1996, 1997, and 2000. The test results show that the proposed algorithm is better than the algorithm using fuzzy linear regression.

• Journal of Digital Convergence
• /
• v.11 no.2
• /
• pp.175-182
• /
• 2013

In this paper, the simulation model of house price is presented on the basis of pricing mechanism between the demand and the supply of apartments in seoul. The algorithm of house price simulation model for calculating the rate of price over time includes feedback control theory. The feedback control theory consists of stock variable, flow variable, auxiliary variable and constant variable. We suggest that the future price of apartment is simulated using mutual interaction variables which are demand, supply, price and parameters among them. In this paper we considers three items which include the behavior of apartment price index, the size of demand and supply, and the forecasting of the apartment price in the future economic scenarios. The proposed price simulation model could be used in public needs for developing a house price regulation policy using financial and non-financial aids. And the quantitative simulation model is to be applied in practice with more specific real data and Powersim Software modeling tool.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.6
• /
• pp.1573-1583
• /
• 2016

It is necessary to check mutual correlations between related variables because housing prices are influenced by a lot of variables of the economy both internally and externally. In this paper, employing the Granger causality test, we have validated interrelated relationship between the variables. In addition, there is cointegration associations in the results of the cointegration test between the variables. Therefore, an analysis using a vector error correction model including an error correction term has been attempted. As a result of the empirical comparative analysis of the forecasting performance with ARIMA and VAR models, it is confirmed that the forecasting performance by vector error correction model is superior to those of the former two models.

• Journal of Korea Port Economic Association
• /
• v.33 no.1
• /
• pp.75-87
• /
• 2017

The purpose of this study is to utilize the system dynamics to carry out a medium and long-term forecasting analysis of the bunker price. In order to secure accurate bunker price forecast, a quantitative analysis was established based on the casual loop diagram between various variables that affects bunker price. Based on various configuration variables such as crude oil price which affects crude oil consumption & production, GDP and exchange rate which influences economic changes and freight rate which is decided by supply and demand in shipping and logistic market were used in accordance with System Dynamics to forecast bunker price and then objectivity was verified through MAPEs. Based on the result of this study, bunker price is expected to rise until 2029 compared to 2016 but it will not be near the surge sighted in 2012. This study holds value in two ways. First, it supports shipping companies to efficiently manage its fleet, offering comprehensive bunker price risk management by presenting structural relationship between various variables affecting bunker price. Second, rational result derived from bunker price forecast by utilizing dynamic casual loop between various variables.

• Proceedings of the KIEE Conference
• /
• 2015.07a
• /
• pp.300-301
• /
• 2015

Accurate and robust load forecasting model plays very important role in power system operation. In case of short-term electric load forecasting, its results offer standard to decide a price of electricity and also can be used shaving peak. For this reason, various models have been developed to improve accuracy of load forecasting. This paper proposes a newly forecasting model for weather sensitive season including temperature and Cooling Degree Hour(C.D.H) data as an input. This Forecasting model consists of previous electric load and preprocessed temperature, constant, parameter. It optimizes load forecasting model to fit actual load by PSO and results are compared to Holt-Winters and Artificial Neural Network. Proposing method shows better performance than comparison groups.

• Journal of Agricultural Extension & Community Development
• /
• v.22 no.4
• /
• pp.423-434
• /
• 2015

This paper predicts the onion's cultivation areas, yields per unit area, and wholesale prices during ship dates by using wholesale price data from the Korea Agro-Fisheries & Food Trade Corporation, the production data from the Statistics Korea, and the weather data from the Korea Meteorological Administration with an ARDL model. By analyzing the data of wholesale price, rural household income and rural total earnings, onion cultivation areas in 2015 are estimated to be 21,035, 17,774 and 20,557(ha). In addition, onion yields per unit area of South Jeolla Province, North Gyeongsang Province, South Gyeongsang Province, Jeju Island, and the whole country in 2015 are estimated to be 5,980, 6,493, 6,543, 6,614, 6,139 (kg/10a) respectively. By using onion production's predictive value found from onion's cultivation areas and yields per unit area in 2015, the onion's wholesale prices in June are estimated to be 780 won, 1,100 won, and 820 won for each model. Predicted monthly price after the onion's ship dates is analyzed to exceed 1,000 won after August.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.10
• /
• pp.179-184
• /
• 2021

In this paper, we propose the deep learning-based neural network model to predict bunker price. In the shipping industry, since fuel oil accounts for the largest portion of ship operation costs and its price is highly volatile, so companies can secure market competitiveness by making fuel oil purchasing decisions based on rational and scientific method. In this paper, short-term predictive analysis of HSFO 380CST in Singapore is conducted by using three recurrent neural network models like RNN, LSTM, and GRU. As a result, first, the forecasting performance of RNN models is better than LSTM and GRUs using long-term memory, and thus the predictive contribution of long-term information is low. Second, since the predictive performance of recurrent neural network models is superior to the previous studies using econometric models, it is confirmed that the recurrent neural network models should consider nonlinear properties of bunker price. The result of this paper will be helpful to improve the decision quality of bunker purchasing.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2005.05a
• /
• pp.798-805
• /
• 2005

Estimating the effects of price increase on a company's sales is important task faced by managers. If consumer has prior information on price increase or expect it, there would be stockpiling and subsequent drops in sales. In addition, consumer can suppress demand in the short run. Above factors make the sales dynamic and unstable. We develop a time series model to evaluate the sales patterns with stockpiling and short term suppression of demand and also propose a forecasting procedure. For estimation, we use panel data and extend the model to Bayesian hierarchical structure. By borrowing strength across cross-sectional units, this estimation scheme gives more robust and reasonable result than one from the individual estimation. Furthermore, the proposed scheme yields improved predictive power in the forecasting of hold-out sample periods.

• Proceedings of the KIEE Conference
• /
• summer
• /
• pp.698-700
• /
• 2004

Electric power restructuring offers a major change to the vertically integrated utility monopoly. Deregulation has had a great impact on the electric power industry in various countries. Bidding competition is one of the main transaction approaches after deregulation. The energy trading levels between market participants is largely dependent on the short-term price forecasts. This paper presents the short-term System Marginal Price (SMP) forecasting implementation using backpropagation Neural Network in competitive electricity market. Demand and SMP that supplied from Korea Power Exchange (KPX) are used by a input data and then predict SMP. It needs to analysis the input data for accurate prediction.