• Journal of the Korea Society of Computer and Information
• /
• v.29 no.11
• /
• pp.31-40
• /
• 2024

In the summer, when the cooling load rises due to high temperatures, the hourly demand increases during the day and is relatively less at night compared to the day. These characteristics are considered important information in predicting summer electricity demand. However, if time information is simply expressed as a dummy variable, the model simply recognizes differences between time zones rather than learning changes in time. In this study, we would like to approach this problem by using a time variable using the Fourier transform. Time variables using the Fourier transform will be able to effectively learn differences between times. As a result of evaluating the type of time variable in the summer electricity demand forecast for 2022 and 2023 using the BiGRU model, the model using the time variable using Fourier transform showed the best performance with MAPE of 2.01% and 2.04% confirmed. The results of this study are expected to improve prediction accuracy in the summer when power usage increases and prevent problems such as large-scale power outages.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.10a
• /
• pp.427-432
• /
• 1998

최근 산업발전에 따라 야기되는 문제점 중 전력수요의 증가에 의한 피해가 증대되고 있다. 여름철 하계부하등에 의한 과부하는 가정이나 대형건물의 정전을 발생시키거나 공장의 기계를 파손시키기도 하기 때문에 이를 미연에 방지할 수 있는 부하예측기법이 점차로 강조되고 있는 현실이다. 이에 본 논문에서는 초(sec)단위의 순시부하예측/제어를 위한 새로운 방법과 퍼지제어기를 제안한다. 제안한 순시부하예측/제어는 크게 과거의 데이터를 가지고 일정시간 후의 값을 예측하는 예측부와 이 결과의 신뢰도를 높여주기 위한 퍼지제어기로나눌 수 있다. 예측부는 SOFM (Self-Organizing Feature Map) 신경망을 이용하며, 예측된 출력값을 퍼지제어기의 입력으로 사용한다.

• Journal of the Institute of Convergence Signal Processing
• /
• v.2 no.3
• /
• pp.73-78
• /
• 2001

BP neural network model and multiple-regression model were composed for forecasting the special-days load. Special-days load was forecasted using that neural network model made use of pattern conversion ratio and multiple-regression made use of weekday-change ratio. This methods identified the suitable as that special-days load of short and long term was forecasted with the weekly average percentage error of 1∼2[%] in the weekly peak load forecasting model using pattern conversion ratio. But this methods were hard with special-days load forecasting of summertime. therefore it was forecasted with the multiple-regression models. This models were used to the weekday-change ratio, and the temperature-humidity and discomfort-index as explanatory variable. This methods identified the suitable as that compared forecasting result of weekday load with forecasting result of special-days load because months average percentage error was alike. And, the fit of the presented forecast models using statistical tests had been proved. Big difficult problem of peak load forecasting had been solved that because identified the fit of the methods of special-days load forecasting in the paper presented.

• Proceedings of the KIEE Conference
• /
• 2008.11a
• /
• pp.447-449
• /
• 2008

미래에 예측되는 수요를 보다 바람직한 방향으로 개선하고자 시행하는 제반활동을 의미하는 전력수요관리는 고유가와 온실가스 문제가 큰 현안이 된 지금의 상황에 비추어 볼 때 그 중요성이 날로 커지고 있다고 할 수 있다. 그러나 현재의 수요관리 시스템은 하계의 수급문제 해결에 그 초점이 맞춰져 있으며, 현재 문제가 되고 있는 동계 전력수급문제에 대해서는 특별한 관리 대책이 없는 상황이다 따라서 동계 수요관리를 위한 수요관리자원 발굴 작업이 시급하며, 그 대책중의 하나로 PV(Photovoltaics) DSM(Demand Side Management)를 제안하고, 실제 건물에 적용 시 그 효과에 대하여 알아보았다.

• Proceedings of the KIEE Conference
• /
• 2008.11a
• /
• pp.435-438
• /
• 2008

우리나라 최대전력은 70년대 연도별로 36만 kW, 약 15%씩 증가하였으나, 최근 2000년대에는 연도별로 300만kW 이상, 약 6%대의 증가를 보이고 있다. 발생시간도 70년대에는 저녁시간대에 주로 발생했으나 80년대부터 최근까지는 15시에 하계 최대전력이 발생하고 있다 아울러 최근에는 기상의 변동폭 증가로 여름과 겨울의 계절성이 증폭되는 추세에 있고 이러한 최대전력 발생의 이면에는 시간별 부하패턴이 다양하게 나타나고 있다. 과거 70-80년대에는 연간이나 월간 부하패턴 모두 평균전력대비 변동폭이 크게 나타났으나 최근에는 변동폭이 상당히 작아지고 있다. 이는 최대전력에 못지않게 전력소비량이 지속적으로 증가하여 부하수준이 평준화되고, 부하율이 높아지고 있다는 것을 나타내며 연중 및 일간 피크 발생시점도 다변화되는 특징을 보이고 있다. 따라서 이러한 부하패턴 변화에 합리적으로 대응하기 위해서는 짧은 기간의 부하관리보다는 상시 수요관리인 효율향상 위주의 프로그램이 필요하고, 저렴한 전기 요금의 정상화를 통한 전력소비 감축을 통한 대응이 중요하다. 외국의 사례를 보면 우리나라 냉방 및 난방전력은 현재보다 10%p-20%p 정도 점유비가 추가적으로 상승할 개연성이 높으므로 다양한 시나리오 예측을 통한 철저한 위험관리 체계 확립이 요구된다.

• 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.

• 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.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.62 no.4
• /
• pp.482-488
• /
• 2013

Load forecasting is essential to the economical and the stable power system operations. In general, the forecasting days can be classified into weekdays, weekends, special days and special light-load periods in short-term load forecast. Special light-load periods are the consecutive holidays such as Lunar New Years holidays, Korean Thanksgiving holidays and summer special light-load period. For the weekdays and the weekends forecast, the conventional methods based on the statistics are mainly used and show excellent results for the most part. The forecast algorithms for special days yield good results also but its forecast error is relatively high than the results of the weekdays and the weekends forecast methods. For summer special light-load period, none of the previous studies have been performed ever before so if the conventional methods are applied to this period, forecasting errors of the conventional methods are considerably high. Therefore, short-term load forecast for summer special light-load period have mainly relied on the experience of power system operation experts. In this study, the trends of load profiles during summer special light-load period are classified into three patterns and new forecast algorithms for each pattern are suggested. The proposed method was tested with the last ten years' summer special light-load periods. The simulation results show the excellent average forecast error near 2%.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.8
• /
• pp.1137-1144
• /
• 2015

Accurate and robust load forecasting model is very important in power system operation. In case of short-term electric load forecasting, its result is offered as an standard to decide a price of electricity and also can be used shaving peak. For this reason, various models have been developed to improve forecasting accuracy. In order to achieve accurate forecasting result for summer season, this paper proposes a forecasting model using corrected effective temperature based on Heat Index and CDH data as inputs. To do so, we establish polynomial that expressing relationship among CDH, load, temperature. After that, we estimate parameters that is multiplied to each of the terms using PSO algorithm. The forecasting results are compared to Holt-Winters and Artificial Neural Network. Proposing method shows more accurate by 1.018%, 0.269%, 0.132% than comparison groups, respectively.