• Journal of Electrical Engineering and Technology
• /
• v.13 no.1
• /
• pp.38-50
• /
• 2018

Spatio-temporal load forecasting (STLF) is a foundation for building the prediction-based power map, which could be a useful tool for the visualization and tendency assessment of urban energy application. Constructing one point-forecasting model for each electricity cell in the geographic space is possible; however, it is unadvisable and insufficient, considering the aggregation features of electricity cells and uncertainties in input variables. This paper presents a new STLF method, with a data-driven framework consisting of 3 subroutines: multi-level clustering of cells considering their aggregation features, load regression for each category of cells based on SLS-SVRNs (sparse least squares support vector regression networks), and interval forecasting of spatio-temporal load with sampled blind number. Take some area in Pudong, Shanghai as the region of study. Results of multi-level clustering show that electricity cells in the same category are clustered in geographic space to some extent, which reveals the spatial aggregation feature of cells. For cellular load regression, a comparison has been made with 3 other forecasting methods, indicating the higher accuracy of the proposed method in point-forecasting of spatio-temporal load. Furthermore, results of interval load forecasting demonstrate that the proposed prediction-interval construction method can effectively convey the uncertainties in input variables.

• Journal of the Institute of Convergence Signal Processing
• /
• v.5 no.1
• /
• pp.53-59
• /
• 2004

In case of load forcasting the most important problem is to deal with the load of special days. According this paper presents forecasting method for speaial days peak load by neural networks model. by means of neural networks mothod using the historical past special- days load data, special-days load was directly forecasted, and forecasting % error showed good result as 1∼2% except vacation season in summer Consequently, it is capable of directly special days load, With the models, precision of forecasting was brought satisfactory result. When neural networks was compared with the orthogonal polynomials models at a view of the results of special-days load forecasting, neural networks model which used pattern conversion ratio was more effective on forecasting for special-days load. On the other hand, in case of short special-days load forecasting, both were valid.

• Journal of Industrial Technology
• /
• v.18
• /
• pp.379-384
• /
• 1998

Conventional short-term load forecasting techniques have limitation in their use on holidays due to dissimilar load behaviors of holidays and insufficiency of pattern data. Thus, a new short-term load forecasting method for special days in anomalous load conditions is proposed in this paper. The proposed method uses two Artificial Neural Networks(ANN); one is for the estimation of load curve, and the other is for the estimation of minimum and maximum value of load. The forecasting procedure is as follows. First, the normalized load curve is estimated by ANN. At next step, minimum and maximum values of load in a special day are estimated by another ANN. Finally, the estimate of load in a whole special day is obtained by combining these two outputs of ANNs. The proposed method shows a good performance, and it may be effectively applied to the practical situations.

• Proceedings of the KIEE Conference
• /
• 1999.07c
• /
• pp.1522-1522
• /
• 1999

This paper proposes the methods of short-term load forecasting using Kohonen neural networks and back-propagation neural networks. Historical load data is divided into 5 patterns for the each seasonal data using Kohonen neural networks and using these results, load forecasting neural network is used for next day hourly load forecasting. Normal days and holidays are forecasted. For load forecasting in summer, max-, and min-temperature data are included in neural networks for a better forecasting accuracy. To show the possibility of the proposed method, it was tested with hourly load data of Korea Electric Power Corporation. (1993-1997)

• Journal of Electrical Engineering and Technology
• /
• v.7 no.6
• /
• pp.807-813
• /
• 2012

In this paper, we introduce data mining techniques for short-term load forecasting (STLF). First, we use the K-mean algorithm to classify historical load data by season into four patterns. Second, we use the k-NN algorithm to divide the classified data into four patterns for Mondays, other weekdays, Saturdays, and Sundays. The classified data are used to develop a time series forecasting model. We then forecast the hourly load on weekdays and weekends, excluding special holidays. The historical load data are used as inputs for load forecasting. We compare our results with the KEPCO hourly record for 2008 and conclude that our approach is effective.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.1
• /
• pp.18-22
• /
• 2009

Short-term load forecasting (STLF) is an important task in power system planning and operation. Its accuracy affects the reliability and economic operation of power systems. STLF is to be classified into load forecasting for weekdays, weekends, and holidays. Due to the limited historical data available, it is more difficult to accurately forecast load for holidays than to forecast load for weekdays and weekends. It has been recognized that the forecasting errors for holidays are large compared with those for weekdays in Korea. This paper presents a polynomial regression with data mining technique to forecast load for holidays. In statistics, a polynomial is widely used in situations where the response is curvilinear, because even complex nonlinear relationships can be adequately modeled by polynomials over a reasonably small range of the dependent variables. In the paper, the coefficient of determination is proposed as a selection criterion for screening weekday data used in holiday load forecasting. A numerical example is presented to validate the effectiveness of the proposed holiday load forecasting method.

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.590-591
• /
• 2011

This paper proposes a short-term load forecasting by using a temperature and load pattern. The forecasting model that represents the relations between load and temperature which get a numeral expected temperature based on the past temperature was constructed. Case studies were applied to load forecasting for 2009 data, and the results show its appropriate accuracy.

• Proceedings of the Korean Institute of IIIuminating and Electrical Installation Engineers Conference
• /
• 2007.05a
• /
• pp.397-399
• /
• 2007

This paper presents multiple regression analysis and data update to improve present spatial electric load forecasting algorithm of the DISPLAN. Spatial electric load forecasting considers a local economy, the number of local population and load characteristics. A Case study is performed for Jeon-Ju and analyzes a trend of the spatial load for the future 20 years. The forecasted information can contribute to an asset management of distribution systems.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.15 no.6
• /
• pp.35-42
• /
• 2001

Since daily peak load forecasted data are essential to economic operation and power monitor, the technique of accurate forecasting is needled. The chief advantage of forecasting technique using neural network and fuzzy theory is high accuracy and operative implicity but the loaming time is long, and it makes large forecasting error when the load changes rapidly. This paper has resented a new forecasting technique to improve those faults and the forecasting technique prove to be valid by forcasted results.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.62 no.2
• /
• pp.149-154
• /
• 2013

Short term load forecasting for electric power demand is essential for stable power system operation and efficient power market operation. High accuracy of the short term load forecasting can keep the power system more stable and save the power market operation cost. We propose an optimal coefficient selection method for exponential smoothing model in short term load forecasting on weekdays. In order to find the optimal coefficient of exponential smoothing model, load forecasting errors are minimized for actual electric load demand data of last three years. The proposed method are verified by case studies for last three years from 2009 to 2011. The results of case studies show that the average percentage errors of the proposed load forecasting method are improved comparing with errors of the previous methods.