• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.13 no.1
• /
• pp.39-49
• /
• 2013

This paper presents a method of improving the performance of a day-ahead 24-h load curve and peak load forecasting. The next-day load curve is forecasted using radial basis function (RBF) neural network models built using the best design parameters. To improve the forecasting accuracy, the load curve forecasted using the RBF network models is corrected by the weighted sum of both the error of the current prediction and the change in the errors between the current and the previous prediction. The optimal weights (called "gains" in the error correction) are identified by differential evolution. The peak load forecasted by the RBF network models is also corrected by combining the load curve outputs of the RBF models by linear addition with 24 coefficients. The optimal coefficients for reducing both the forecasting mean absolute percent error (MAPE) and the sum of errors are also identified using differential evolution. The proposed models are trained and tested using four years of hourly load data obtained from the Korea Power Exchange. Simulation results reveal satisfactory forecasts: 1.230% MAPE for daily peak load and 1.128% MAPE for daily load curve.

• Proceedings of the KIEE Conference
• /
• 2000.07a
• /
• pp.295-297
• /
• 2000

In case of power demand forecasting the most important problem is to deal with the load of special-days, Accordingly, this paper presents a method that forecasting special-days load with regression models and neural networks. Special-days load in summer season was forecasted by the multiple regression models using weekday change ratio Neural networks models uses pattern conversion ratio, and orthogonal polynomial models was directly forecasted using past special-days load data. forecasting result obtains % forecast error of about $1{\sim}2[%]$. Therefore, it is possible to forecast long and short special-days load.

• Journal of Electrical Engineering and Technology
• /
• v.10 no.3
• /
• pp.832-837
• /
• 2015

The group method of data handling (GMDH) algorithm has proven to be a powerful and effective way to extract rules or polynomials from an electric load pattern. However, because it is nonstationary, the load pattern needs to be decomposed using a discrete wavelet transform. In addition, if a load pattern has a complicated curve pattern, GMDH should use a higher polynomial, which requires complex computing and consumes a lot of time. This paper suggests a method for short-term electric load forecasting that uses a wavelet transform and a GMDH algorithm. Case studies with the proposed algorithm were carried out for one-day-ahead forecasting of hourly electric loads using data during the years 2008-2011. To prove the effectiveness of our proposed approach, the results were evaluated and compared with those obtained by Holt-Winters method and artificial neural network. Our suggested method resulted in better performance than either comparison group.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.7
• /
• pp.1088-1095
• /
• 2015

In most cases, the use of electric power is associated with the economic scale of a nation closely. Thus, the electric power load forecasting plays an important role for the national economic plan. This paper deals with the design method for the electric power load forecasting system. In this paper, RCR-MA data processing, which can make the complex properties of the original data form simple, is proposed. Next, IT2TSK FLS, which can reflect the uncertainty of data more than T1TSK FLS, is applied. Consequently, the structural advantage of the proposed system can improve the forecasting accuracy, and is verified by using two types of electric power data.

• Journal of Electrical Engineering and Technology
• /
• v.5 no.3
• /
• pp.363-370
• /
• 2010

Load forecasting has always been essential to the operation and planning of power systems in deregulated electricity markets. Various methods have been proposed for load forecasting, and the neural network is one of the most widely accepted and used techniques. However, to obtain more accurate results, more information is needed as input variables, resulting in huge computational costs in the learning process. In this paper, to reduce training time in multi-layer perceptron-based short-term load forecasting, a graphics processing unit (GPU)-based computing method is introduced. The proposed approach is tested using the Korea electricity market historical demand data set. Results show that GPU-based computing greatly reduces computational costs.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.7
• /
• pp.1115-1120
• /
• 2016

This paper presents the daily load forecasting for special days considering the rate of operation of industrial consumers. The authors analyzed the power consumption pattern for both the special and ordinary days according to the contract power classification of industrial consumers, and selected 400~600 specific consumers for which the rates of operation during special days are needed. Load forecasting for 2014 special days considering the rate of operation of industrial consumers showed a noticeable improvement on forecasting error of daily peak demand, which proved the effectiveness of the survey for the rates of operation during special days of industrial consumers.

• 전기의세계
• /
• v.22 no.2
• /
• pp.28-32
• /
• 1973

System modeling is applied in developing a probabilistic linear estimator for the load of an electric power system for the purpose of short term load forecasting. The model assumer that the load in given by the suns of a periodic discrete time serier with a period of 24 hour and a residual term such that the output of a discrete time dynamical linear system driven by a white random process and a deterministic input. And also we have established the main forecasting algorithms, which are essemtally the Kalman filter-predictor equations.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.32 no.5
• /
• pp.183-188
• /
• 1983

This paper deals with short-term load forecasting. The load model is represented by the state variable form to exploit the Kalman filter technique. The load model is derived from Taylor series expansion and remainder term is considered as noise term. In order to solve recursive filter form, among various algorithm of solving Kalman filter, this paper uses exponential data weighting technique. This paper also deals with the asymptotic stability of filter. Case studies are carried out for the hourly power demand forecasting of the Korea electrical system.

• Proceedings of the KIEE Conference
• /
• 2003.07a
• /
• pp.584-586
• /
• 2003

Load Forecasting is essential in the electricity market to the participants to manage the market efficiently and stably. Therefore, we review the past researches of load forecasting and investigate various characteristics of load variation. Finally, future studies are discussed.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.52 no.8
• /
• pp.450-456
• /
• 2003

This paper proposes a multiple time-series model with dummy variables for one-hour ahead load forecasting. We used 11 dummy variables that were classified by day characteristics such as day of the week, holiday, and special holiday. Also, model specification and selection of input variables including dummy variables were made by test statistics such as AIC(Akaike Information Criterion) and t-test statistics of each coefficient. OLS (Ordinary Least Squares) method was used for estimation and forecasting. We found out that model specifications for each hour are not identical usually at 30％ of optimal significance level, and dummy variables reduce the forecasting error if they are classified properly. The proposed model has much more accurate estimates in forecasting with less MAPE (Mean Absolute Percentage Error).