• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2004년도 학술발표회
• /
• pp.709-712
• /
• 2004

The development of a basin-wide runoff analysis model is to analysis monthly and daily hydrologic runoff components including surface runoff, subsurface runoff, return flow, etc. at key operation station in the targeted basin. h short-term water demand forecasting technology will be developed fatting into account the patterns of municipal, industrial and agricultural water uses. For the development and utilization of runoff analysis model, relevant basin information including historical precipitation and river water stage data, geophysical basin characteristics, and water intake and consumptions needs to be collected and stored into the hydrologic database of Integrated Real-time Water Information System. The well-known SSARR model was selected for the basis of continuous daily runoff model for forecasting short and long-term natural flows.

• 대한전기학회논문지
• /
• 제32권5호
• /
• 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.

• 한국ITS학회 논문지
• /
• 제16권2호
• /
• pp.13-22
• /
• 2017

본 연구는 국도변에 설치되는 화물차휴게소의 이용수요를 예측하는 방법론을 제시하였다. 연구의 진행은 기존의 수요예측 방법론을 검토하여 이를 보완할 사항들을 제시하였다. 연구결과, 수요예측 과정에서 우선 할 사항은 휴게소를 이용할 화물차를 단기주차차량과 장기주차차량으로 구분하는 것이었다. 또한 단기와 장기 등 주차시간에 따라 소요주차면수 산정에 적용되는 이용률과 혼잡률 및 회전율에 차이가 발생하므로 이들 영향요소를 달리 적용할 것이 요구되었다. 그리고 화물차휴게소에 입주하는 업체와 편의시설의 활성화에 따라 서도 이용수요에 영향을 미치므로 이의 반영 필요성도 나타났다. 이로부터 국도변에 설치되는 거점형 화물차휴게소는 고속도로변에 설치되는 화물차전용 휴게소보다 수요예측 과정에 주의를 기울여야 되며, 또한 다양한 영향요소들을 감안할 필요성이 제기되었다.

• 상하수도학회지
• /
• 제28권4호
• /
• pp.377-389
• /
• 2014

In recent years, Smart Water Grid (SWG) concept has globally emerged over the last decade and also gained significant recognition in South Korea. Especially, there has been growing interest in water demand forecast and this has led to various studies regarding energy saving and improvement of water supply reliability. In this regard, this study aims to develop a nonlinear ensemble model for hourly water demand forecasting which allow us to estimate uncertainties across different model classes. The concepts was demonstrated through application to observed from water plant (A) in the South Korea. Various statistics (e.g. the efficiency coefficient, the correlation coefficient, the root mean square error, and a maximum error rate) were evaluated to investigate model efficiency. The ensemble based model with an cross-validate prediction procedure showed better predictability for water demand forecasting at different temporal resolutions. In particular, the performance of the ensemble model on hourly water demand data showed promising results against other individual prediction schemes.

• 한국콘크리트학회:학술대회논문집
• /
• 한국콘크리트학회 1991년도 가을 학술발표회 논문집
• /
• pp.146-151
• /
• 1991

In recent years a reasonable supply and demand plan of construction materials which is based upon an accurate forecast has been greatly required to prevent construction works from delaying and slapdash. To meet an above requirement, a short-term forecasting system of construction materials, in this paper, is established, which is approached in engineering aspect and emerged from conventional forecasting systems. The major considerations in setting up this system are the distributed lag of consrection business indicators and seasonal variations in consumption of constuction materials.

• 제어로봇시스템학회논문지
• /
• 제15권10호
• /
• pp.1056-1061
• /
• 2009

This paper proposes a short-term water demand forecasting algorithm based on kalman filtering with data mining for sustainable water supply and effective energy saving. The proposed algorithm utilizes a mining method of water supply data and a decision tree method with special days like Chuseok. And the parameters of MLAR (Multi Linear Auto Regression) model are estimated by Kalman filtering algorithm. Thus, we can achieve the practicality of the proposed forecasting algorithm through the good results applied to actual operation data.

• Journal of Electrical Engineering and Technology
• /
• 제5권3호
• /
• 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.

• 한국조명전기설비학회:학술대회논문집
• /
• 한국조명전기설비학회 2008년도 추계학술대회 논문집
• /
• pp.225-228
• /
• 2008

The electricity supply and demand to be stable to a system link increase of the variance power supply and operation are requested in jeju Island electricity system. A short-term Load forecasting which uses the characteristic of the Load is essential consequently. We use the interrelationship of the electricity Load and change of a summertime temperature and data refining in the paper. We presented a short-term Load forecasting algorithm of jeju Island and used the correlation coefficient to the criteria of the refining. We used each temperature area data to be refined and forecasted a short-term Load to an exponential smoothing method.

• Communications for Statistical Applications and Methods
• /
• 제22권6호
• /
• pp.675-683
• /
• 2015

In the 21st century, we now face the serious problems of the enormous consumption of the energy resources. Depending on the power consumption increases, both China and South Korea face a reduction in available resources. This paper considers the regression models and time-series models to compare the performance of the forecasting accuracy based on Mean Absolute Percentage Error (MAPE) in order to forecast the electricity demand accurately on the short-term period (68 months) data in Northeast China and find the relationship with Korea. Among the models the support vector regression (SVR) model shows superior performance than time-series models for the short-term period data and the time-series models show similar results with the SVR model when we use long-term period data.

• 조명전기설비학회논문지
• /
• 제21권10호
• /
• pp.126-133
• /
• 2007

본 연구에서는 데이터 마이닝 기법을 이용하여 전력계통의 단기 부하 예측을 하는 방안을 제시한다. 기존의 단기 부하 예측은 시계열 분석 방법이 주를 이루었으며, 이러한 방법은 방대한 양의 자료를 기반으로 데이터베이스를 만들고 이를 이용하여 여러 가지 계수를 이용하여 수요를 예측함으로써 많은 시간과 노력이 소요되고 있다. 따라서 본 연구에서는 좀 더 적은 시간과 노력으로 부하예측이 가능하도록 데이터마이닝 기법을 이용하여 요일별 그리고 특수 일의 패턴을 분석하고 의사결정트리를 이용한 예측방법을 제시하고자 한다. 그리고 현재 전력거래소를 통해 거래되고 있는 계통한계가격과의 관계를 분석하여 예측 계수에 계통한계가격을 추가하여 예측방법을 제시하고자 한다.