• 물과 미래
• /
• 제28권3호
• /
• pp.123-132
• /
• 1995

본 연구는 대유역의 유량예측을 위한 수공학적 모형 시스템을 개발하는데 있다. 이 시스템은 각각의 부분유역에서의 기상학적, 수문학적 입력자료를 바탕으로 하천유량을 예측하는 개념적인 수문학적 강우유출모형과 각부분유역의 예측유량을 입력치로 하여 하도홍수추적을 하는 수리학적 모형으로 구성되어 있다. 실시간 해석시 새로운 관측자료로부터 모형의 상태변량을 최적화 할 수 있는 효율적인 상태변량 추정자가 사용되었다. 실시간 유량예측을 위해서 본 연구에서 개발된 모형을 적용하여 본 결과, 예측가능시간이 짧은 경우 대유역의 실시간 유량예측모형으로서 타당한 것으로 판단된다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1993년도 정기총회 및 추계학술대회 논문집 학회본부
• /
• pp.29-31
• /
• 1993

This paper presents Neural Network(NN) approach to short-term load forecasting. Input to the NN are past loads and the output is the predicted load for a given day. The NN is used to learn the relationship among past, current and future temperature and loads. Three different cases are presented. Case 1 divides into weekday and weekendday load pattern. Case 2 forcasts 24-hour ahead load. Case 3 searchs for the same load pattern as present load pattern in past load pattern. From result of forecasting, an average absolute percentage errors of case 1 shows 2.0%. That of case 2 shows 2.2, and That of case 3 shows 1.6%.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1992년도 하계학술대회 논문집 A
• /
• pp.495-497
• /
• 1992

Hourly load forecasting has become indispensable for practical simulation of electric power system as the system become larger and more complicated. To forecast the future hourly load the cyclic behavior of electric load which follows seasonal weather, day or week and office hours is to be analyzed so that the trend of the recent behavioral change can be extrapolated for the short term. For the long term, on the other hand, the changes in the infra-structure of each electricity consumer groups should be assessed. In this paper the concept and process of hourly load forecasting for hourly load is introduced.

• 한국축산시설환경학회지
• /
• 제4권2호
• /
• pp.113-126
• /
• 1998

This study was conducted to develop pig-housings based on the forecasting models of swine production, the weather conditions, and so on in Korea. The Korean pig-housings were developed according to the following basis : 1. They should be suitable to domestic weather conditions. 2. They should be designed based on the forecasting models of swine production of farrow to finish operation among the forecasting models of swine production in Korea. 3. Proper environments should be offered to pigs according to the growth. 4. The environmental control, the treatment of swine wastewater, and so on should be interrelated. 5. Manual energy should be saved by effective arrangements of pig-housings. In the future, performance test of the Korean pig-housings and development of facility automation systems which are suitable to these should be accomplished.

• Communications for Statistical Applications and Methods
• /
• 제24권1호
• /
• pp.67-80
• /
• 2017

Over the last few decades, ensemble forecasts based on global climate models have become an important part of climate forecast due to the ability to reduce uncertainty in prediction. Moreover in ensemble forecast, assessing the prediction uncertainty is as important as estimating the optimal weights, and this is achieved through a probabilistic forecast which is based on the predictive distribution of future climate. The Bayesian model averaging has received much attention as a tool of probabilistic forecasting due to its simplicity and superior prediction. In this paper, we propose a new Bayesian model averaging method for probabilistic ensemble forecasting. The proposed method combines a deterministic ensemble forecast based on a multivariate regression approach with Bayesian model averaging. We demonstrate that the proposed method is better in prediction than the standard Bayesian model averaging approach by analyzing monthly average precipitations and temperatures for ten cities in Korea.

• 정보통신설비학회논문지
• /
• 제9권3호
• /
• pp.107-111
• /
• 2010

This paper is concerned with data center remote management service for demanding forecasting and reduction of energy usage. More particularly, intelligent server rack, mounted on inside of the data center, collects information about energy usage and temperature per server. Using this information, management platform forecasts energy demand in the future and automatically makes report according green environment raw. By providing the remote management service through remote terminals, users are not tied to a time and place to control device inside the data center. In this way, the data center remote management service enhances operability of the facility.

• 한국멀티미디어학회논문지
• /
• 제18권7호
• /
• pp.864-872
• /
• 2015

The purpose of this study is to design the algorithm, Predictive Service Component - PSC, for forecasting and judging obsolescence of solar system that is implemented based on the micro-inverter. PSC proposed in this study is suitable for monitoring of distributed power generation systems. It provides a diagnosis functionality to detect failures and anomaly events. It also can determine the aging of PV systems. The conclusion of this study shows the research and development of this kind of integrated system using PSC will be needed more and varied in the near future.

• 한국조사연구학회지:조사연구
• /
• 제1권2호
• /
• pp.15-34
• /
• 2000

지난 4월 13일에 실시된 16대 총선에서 방송사와 조사기관들이 공동으로 조사하여 발표한 선거예측조사에서 많은 오류가 발생하여 선거예측조사에 대한 신뢰성에 큰 타격을 받았다. 이에 향후 선거예측조사의 신뢰성을 회복하고 보다 정확한 예측을 위해 기 발표된 예측조사내용을 다각도로 심층분석하여 조사의 오류가 발생한 원인을 살펴보고 이들 오류를 줄이는 방안들을 제시하였다. 아울러 이번에 처음으로 실시된 출구조사에 대한 문제점과 개선안도 함께 살펴보았다.

• 한국지능시스템학회논문지
• /
• 제21권1호
• /
• pp.100-105
• /
• 2011

학습과 추론을 이용하여 주어진 환경에서 최적의 문제해결을 수행하는 지능형시스템에 대한 사용은 날로 증가하고 있다. 다양한 분야에서 지능형시스템은 과거와 현재 뿐만 아니라 미래에도 인간의 삶의 질을 향상시키는 중요한 역할을 수행하기 때문에 이에 대한 기술적 동향파악과 기술예측은 중요하게 다루어져야 할 것이다. 본 논문에서는 지금까지 개발된 기술에 대한 객관적이고 광범위한 정보를 포함하고 있는 특허데이터를 정량적으로 분석하여 지능형시스템에 대한 기술적 예측에 필요한 특허분석 방법을 제안한다. 지금까지 출원, 등록된 특허데이터를 이용하여 제안방법에 대한 성능평가를 수행한다.

• 한국조명전기설비학회지:조명전기설비
• /
• 제6권1호
• /
• pp.29-39
• /
• 1992

In this paper, the basic idea of optimum electric system design by means of the forecasting of maximum demand is presented, and the load characteristics and practical operating conditions are based on the technical data. After reconstruction of th model plant by use of above method, power supply reliability, future extention, initial cost, and running cost saving effects are analyzed. As a result, it is verified that the systems wherein the power is supply to each load frm main transformer whose capacity is calculated by forecasting are economic rather than the systems wherein the power is supply to each electric feeders from each corresponding transformer.