• Proceedings of the KIEE Conference
• /
• 2003.11a
• /
• pp.491-493
• /
• 2003

Load foretasting model used generally such as times series and econometric regression model often doesn't reflect the load characteristics of small remote islands. Therefore, in this paper load demand forecast is peformed using EGARCH-M non-linear forecasting model.

• Journal of the Korea Convergence Society
• /
• v.9 no.5
• /
• pp.1-6
• /
• 2018

In smart grid an accurate load forecasting is crucial in planning resources, which aids in improving its operation efficiency and reducing the dynamic uncertainties of energy systems. Research in this area has included the use of shallow neural networks and other machine learning techniques to solve this problem. Recent researches in the field of computer vision and speech recognition, have shown great promise for Deep Neural Networks (DNN). To improve the performance of daily electric peak load forecasting the paper presents a new deep neural network model which has the architecture of two multi-layer neural networks being serially connected. The proposed network model is progressively pre-learned layer by layer ahead of learning the whole network. For both one day and two day ahead peak load forecasting the proposed models are trained and tested using four years of hourly load data obtained from the Korea Power Exchange (KPX).

• Journal of IKEEE
• /
• v.22 no.3
• /
• pp.672-679
• /
• 2018

Recently, microgrid (MG) has been proposed as one of the most critical solutions for various energy problems. For the optimal and economic operation of MGs, it is very important to forecast the load profile. However, it is not easy to predict the load accurately since the load in a MG is small and highly variable. In this paper, we propose an artificial neural network (ANN) based method to predict the energy use in campus buildings in short-term time series from one hour up to one week. The proposed method analyzes and extracts the features from the historical data of load and temperature to generate the prediction of future energy consumption in the building based on sparsified K-means. To evaluate the performance of the proposed approach, historical load data in hourly resolution collected from the campus buildings were used. The experimental results show that the proposed approach outperforms the conventional forecasting methods.

• Proceedings of the KIEE Conference
• /
• 1999.11b
• /
• pp.242-244
• /
• 1999

This paper proposes a novel wavelet transform based algorithm for the seasonal load forecasting. In this paper, Daubechies DB2, DB4 and DB10 wavelet transforms are adopted to predict the seasonal loads and the numerical results reveal that certain wavelet components can effectively be used to identify the load characteristics in electric power systems. The wavelet coefficients associated with certain frequency and time localization are adjusted using the conventional multiple regression method and then reconstructed. In order to forecast the final loads through a four-scale synthesis technique. The outcome of the study clearly indicates that the wavelet transform approach can be used as an attractive and effective means of the seasonal load forecasting.

• Proceedings of the KIEE Conference
• /
• 2001.11b
• /
• pp.432-434
• /
• 2001

This paper proposes a special-day load forecasting method with the characteristics of temperature based on fuzzy linear regression. We can obtain a linear regression model from the relation between daily peak load and daily maximum or minimum temperature. Simulation results show that the proposed method can improve an accuracy of a special-day load forecasting.

• Journal of Electrical Engineering and Technology
• /
• v.13 no.2
• /
• pp.559-567
• /
• 2018

In this paper, we propose a new load forecasting method for smart air conditioning (A/C) based on the modified thermodynamics of indoor temperature and the unbiased finite memory estimator (UFME). Based on modified first-order thermodynamics, the dynamic behavior of indoor temperature can be described by the time-domain state-space model, and an accurate estimate of indoor temperature can be achieved by the proposed UFME. In addition, a reliable A/C load forecast can be obtained using the proposed method. Our study involves the experimental validation of the proposed A/C load forecasting method and communication construction between DR server and HEMS in a test bed. Through experimental data sets, the effectiveness of the proposed estimation method is validated.

• Proceedings of the KIEE Conference
• /
• 1996.11a
• /
• pp.447-449
• /
• 1996

This paper describes an algorithm for short term load forecasting using the Kohonen neural network. Single layer Kohonen neural network presents a lot of advantageous features for practical application. It takes less training time compared to other networks such as BP network, and moreover, its self organized feature can amend the distorted data. The originality of proposed approach is to use a Kohonen map toclassify data representing load patterns and to use directly the information stored in the weight vectors of the Kohonen map to pridict the load. Proposed method was tested with KEPCO hourly record(1993-1995) show better forecasting results compared with conventional exponential smoothing method.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.05a
• /
• pp.833-836
• /
• 2012

Demand Controller is a load control device that monitor the current power consumption and calculate the forecast power to not exceed the power set by consumer. Accurate demand forecasting is important because of controlling the load use the way that sound a warning and then blocking the load when if forecasted demand exceed the power set by consumer. When if consumer with fluctuating power consumption use the existing forecasting method, management of demand control has the disadvantage of not stable. In this paper, examine the existing forecasting method and the exponential smoothing method, and then propose the forecasting method using Kalman Filter algorithm.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.10
• /
• pp.1257-1264
• /
• 2018

This paper proposes Autoregressive Integrated Moving Average (ARIMA)-based forecasting algorithms using meteorological indices to predict seasonal peak load. First of all, this paper observes a seasonal pattern of the peak load that appears intensively in winter and summer, and generates ARIMA models to predict the peak load of summer and winter. In addition, this paper also proposes hybrid ARIMA-based models (ARIMA-Hybrid) using a discomfort index and a sensible temperature to enhance the conventional ARIMA model. To verify the proposed algorithm, both ARIMA and ARIMA-Hybrid models are developed based on peak load data obtained from 2006 to 2015 and their forecasting results are compared by using the peak load in 2016. The simulation result indicates that the proposed ARIMA-Hybrid models shows the relatively improved performance than the conventional ARIMA model.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.19 no.7
• /
• pp.20-25
• /
• 2005

In this paper, the short-term load forecasting of transformers is performed by artificial neural networks. Input parameters of the proposed algorithm are peak loads of pole-transformer of previous days and their maximum and minimum temperatures. The proposed algorithm is tested for one of transformers in Seoul, Korea. Test results show that the proposed algorithm improves the accuracy of the load forecasting of transformer compared with the conventional algorithm. The reposed algorithm can help to prevent some damages by over-loads of transformers.