• 한국산학기술학회논문지
• /
• 제16권12호
• /
• pp.8576-8584
• /
• 2015

전력수요의 예측은 안정적인 전력공급을 위한 수급계획수립을 위해서 그리고 전력계통의 최적운영계획수립을 위해서도 필요하다. 특히 안정적인 전력수급확보를 위해서는 중장기 전력수요예측이 중요하고 공급안정성 강화를 위해서는 지역별 전력수요예측이 중요하다. 지역별 전력수요예측은 지역에 소요되는 부하를 충족시킬 수 있도록 송전선로 및 변전소 등의 계통망의 최적상태 구성 및 유지를 위한 필수적인 과정으로 알려져 있다. 따라서 본 논문은 12개월(중장기)동안 대한민국 시도별 16개 지역의 전력사용량을 SARIMA 모형을 이용하여 예측하는 방법을 제안한다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2001년도 하계학술대회 논문집 A
• /
• pp.550-552
• /
• 2001

The vertically integrated power industry was divided into six generation companies and one market operator, where electricity trading was launched at power exchange. In this environment, the profits of each generation companies are guaranteed according to utilization of their own generation equipments. Especially, the electricity demand shows seasonal and weekly regular pattern, which the some capacity should be provided into ancillary service based on the past demand forecasting error and operating results of electricity market. Namely, if generation cost function is applied to SMP and BLMP as announced the previous day, the available generation capacity of the following day could be optimally distributed, and therefore contract capacity of ancillary service applied to CBP(Cost Based Pool) and TWBP(Two-Way Bidding Pool) is determined. Consequently, it is Possible to use the retained equipments optimally. This paper represents on efficient bidding strategies for generation equipments through the calculation of the contract and the application of each generator cost function based on the past demand forecasting error and market operating data.

• 농촌계획
• /
• 제14권3호
• /
• pp.1-9
• /
• 2008

In this study, by reflecting flow of age, possibility of new theme park development as private investments business based on source that is farming village that is not tried to before is verified and by analyzing potential of the site, effectiveness of new theme park development is examined. "Nonghyup Anseong Meadow Anseong-si Gyeonggi-do" is selected as researched site where accessibility is good as there is near to National Capital region and nature condition is also good. Demands are forecasted using visiting intention and realizing index through analogical method and by analyzing existing data related with increase of tourism business that people can experience English village and increasing demand of experiencing farming region tourism demands are forecasted. The results are at below. First, As average expenditure per one person is 52,209 won that is shown in result of survey, if multiplying increasing rate of price and the number of visiting people that is optimistic forecasting figure, the whole expenditure of visitors per one year is from 10.54 billions to 13.85 billions won. Second is potential power of demand aspects. Potential power of that theme park was re-examined through demands forecasting analysis through survey. Experiencing farming regions theme park business that is informed through analysis of potential power of development and demand aspects has value to invest as new business based on farming regions sources, as a result of searching through diverse aspects such as tourism, economy, public interest and cultural aspect and so on.

• 한국ITS학회 논문지
• /
• 제14권4호
• /
• pp.18-26
• /
• 2015

본 연구에서는 새마을 무궁화 열차의 주요 5개노선(경부선, 호남선, 전라선, 장항선, 중앙선)의 단기수송수요의 예측모형 선정방안을 제시하고 유용성을 확인하기 위한 검증결과를 제시하였다. 분석을 위해 계절별 특성이 반영된 SARIMA 모형을 이용하였으며, 주중/주말 통행 특성 및 대체근무제 등과 같은 공휴일 특성을 반영하고자 각 노선별 주중/주말 일평균 모형을 각각 구축하였다. 또한 모형의 신뢰도를 높이기 위해 EXPO 개최, 새로운 노선의 개통 등 노선별 개입요소를 고려하여 수송수요의 예측모형에 반영하였으며 모형 예측력의 검증을 통해 정도 높은 모형을 구축하였음을 확인하였다. 본 연구를 통해 개발된 모형은 열차 노선별 단기운행계획 수립을 위한 기초자료로 활용될 수 있을 것으로 기대된다.

• 대한공간정보학회지
• /
• 제19권3호
• /
• pp.83-90
• /
• 2011

본 논문의 목적은 공업용수 사용 추세패턴 모형을 개발하고 개발된 모형이 GIS시스템내에서 활용될 수 있는 청사진을 제시하는데 있다. 연구내용은, 사용데이터의 수집을 위해 실시간 모니터링 테크닉이 도입되었고 실시간 데이터는 5분단위로 센서 및 현장서버로부터 관리서버로 전송되었다. 취득된 데이터는 선택된 다항식에 대입되었고 결과로 요일별, 각 월의 일평균 수요모형들이 개발되었다. 도출된 모형들은 일련의 검증과정을 거쳐 최종 모형으로 압축선택되며 평균모형으로 변환되었다. 변환된 평균모형의 도식화를 통해 공업용수 수요패턴분석이 이루어졌다. 연구결과로, 수요패턴은 상당한 일관성을 보이고 있어 확률높은 요일별, 또는 계절별 수요예측이 가능하다는 결론이 도출되었다. 또한 이러한 예측모형을 활용할 정보화도구로서 GIS의 활용방안이 제시된다.

• 한국인터넷방송통신학회논문지
• /
• 제19권4호
• /
• pp.161-167
• /
• 2019

최근 안정적인 전력수급과 급증하는 전력수요를 예측하는 수요예측 기술에 대한 관심과 실시간 전력측정을 가능하게 하는 스마트 미터기의 보급의 증대로 인해 수요예측 기법에 대한 연구가 활발히 진행되고 있다. 본 연구에서는 실제 측정된 가정의 전력 사용량 데이터를 학습하여 예측결과를 출력하는 딥 러닝 예측모델 실험을 진행한다. 그리고 본 연구에서는 데이터 전처리 기법으로써 이동평균법을 도입하였다. 실제로 측정된 데이터를 학습한 모델의 예측량과 실제 전력 측정량을 비교한다. 이 예측량을 통해서 전력공급 예비율을 낮춰 사용되지 않고 낭비되는 예비전력을 줄일 수 있는 가능성을 제시한다. 또한 본 논문에서는 같은 데이터, 같은 실험 파라미터를 토대로 세 종류의 기법: 다층퍼셉트론(Multi Layer Perceptron, MLP), 순환신경망(Recurrent Neural Network, RNN), Long Short Term Memory(LSTM)에 대해 실험을 진행하여 성능을 평가한다. 성능평가는 MSE(Mean Squared Error), MAE(Mean Absolute Error)의 기준으로 성능평가를 진행했다.

• 한국환경과학회지
• /
• 제22권8호
• /
• pp.965-977
• /
• 2013

Reliable long-term streamflow forecasting is invaluable for water resource planning and management which allocates water supply according to the demand of water users. It is necessary to get probabilistic forecasts to establish risk-based reservoir operation policies. Probabilistic forecasts may be useful for the users who assess and manage risks according to decision-making responding forecasting results. Probabilistic forecasting of seasonal inflow to Andong dam is performed and assessed using selected predictors from sea surface temperature and 500 hPa geopotential height data. Categorical probability forecast by Piechota's method and logistic regression analysis, and probability forecast by conditional probability density function are used to forecast seasonal inflow. Kernel density function is used in categorical probability forecast by Piechota's method and probability forecast by conditional probability density function. The results of categorical probability forecasts are assessed by Brier skill score. The assessment reveals that the categorical probability forecasts are better than the reference forecasts. The results of forecasts using conditional probability density function are assessed by qualitative approach and transformed categorical probability forecasts. The assessment of the forecasts which are transformed to categorical probability forecasts shows that the results of the forecasts by conditional probability density function are much better than those of the forecasts by Piechota's method and logistic regression analysis except for winter season data.

• 한국환경과학회지
• /
• 제22권8호
• /
• pp.953-963
• /
• 2013

Reliable long-term streamflow forecasting is invaluable for water resource planning and management which allocates water supply according to the demand of water users. Forecasting of seasonal inflow to Andong dam is performed and assessed using statistical methods based on hydrometeorological data. Predictors which is used to forecast seasonal inflow to Andong dam are selected from southern oscillation index, sea surface temperature, and 500 hPa geopotential height data in northern hemisphere. Predictors are selected by the following procedure. Primary predictors sets are obtained, and then final predictors are determined from the sets. The primary predictor sets for each season are identified using cross correlation and mutual information. The final predictors are identified using partial cross correlation and partial mutual information. In each season, there are three selected predictors. The values are determined using bootstrapping technique considering a specific significance level for predictor selection. Seasonal inflow forecasting is performed by multiple linear regression analysis using the selected predictors for each season, and the results of forecast using cross validation are assessed. Multiple linear regression analysis is performed using SAS. The results of multiple linear regression analysis are assessed by mean squared error and mean absolute error. And contingency table is established and assessed by Heidke skill score. The assessment reveals that the forecasts by multiple linear regression analysis are better than the reference forecasts.

• 전기학회논문지P
• /
• 제63권3호
• /
• pp.189-194
• /
• 2014

Due to the increasing of power consumption, it is difficult to construct accurate prediction model for daily peak power demand. It is very important work to know power demand in next day for manager and control power system. In this research, we develop a daily peak power demand prediction method based on hybrid type composed of AR and Neuro-Fuzzy model. Using data sets between 2006 and 2010 in Korea, the proposed method has been intensively tested. As the prediction results, we confirm that the proposed method makes it possible to effective estimate daily peak power demand than conventional methods.

• 대한안전경영과학회지
• /
• 제11권1호
• /
• pp.205-211
• /
• 2009

In reality, distribution planning for a supply chain is established using a certain probabilistic distribution estimated by forecasting. However, in general, the demands used for an actual distribution planning are of deterministic value, a single value for each of periods. Because of this reason the final result of a planning has to be a single value for each period. Unfortunately, it is very difficult to estimate a single value due to the inherent uncertainty in the probabilistic distribution of customer demand. The issue addressed in this paper is the selection of single demand value among of the distributed demand estimations for a period to be used in the distribution planning. This paper proposes an efficient demand selection scheme for minimizing total inventory costs while satisfying target service level under the various experimental conditions.