• 전기학회논문지
• /
• 제61권12호
• /
• pp.1765-1773
• /
• 2012

The accuracy of load forecast is very important from the viewpoint of economical power system operation. In general, the weekdays' load demand pattern has the continuous time series characteristics. Therefore, the conventional methods expose stable performance for weekdays. In case of special days or weekends, the load demand pattern has the discontinuous time series characteristics, so forecasting error is relatively high. Especially, weekdays near the thanksgiving day and lunar new year's day have the mixed load profile characteristics of both weekdays and weekends. Therefore, it is difficult to forecast these days by using the existing algorithms. In this study, a new load forecasting method is proposed in order to enhance the accuracy of the forecast result considering the characteristics of weekdays and weekends. The proposed method was tested with these days during last decades, which shows that the suggested method considerably improves the accuracy of the load forecast results.

• 인터넷정보학회논문지
• /
• 제18권1호
• /
• pp.121-129
• /
• 2017

수리부속 수요예측은 장비가동률 향상과 국방 운영 예산 효율화 제고를 위한 국방 군수 분야의 핵심 과제 중 하나이다. 현재 우리군은 수리부속 소요 데이터를 활용한 시계열 기법으로 과거 데이터 분석을 통해 수리부속 수요예측에 활용하고 있으나 정확도 제고에 지속적인 노력이 요구되고 있는 실정이다. 이에 본 연구에서는 지난 5개년의 수리부속 18,476개 품목의 수요데이터를 수집하고 데이터마이닝 기법을 활용한 수리부속 수요예측 모델을 제안하였다. 제안한 모델에 따른 실험 결과는 기존 시계열 기법에 비해 개선된 수요예측 정확도를 보였다.

• 대한전기학회논문지:전력기술부문A
• /
• 제49권3호
• /
• pp.107-117
• /
• 2000

This paper proposes a systematic method to develop short-term electrical load forecasting systems using neuro-fuzzy models. The primary goal of the proposed method is to improve the performance of the prediction model in terms of accuracy and reliability. For this, the proposed method explores the advantages of the structure learning of the neuro-fuzzy model. The proposed load forecasting system first builds an initial structure off-line for each hour of four day types and then stores the resultant initial structures in the initial structure bank. Whenever a prediction needs to be made, the proposed system initializes the neuro-fuzzy model with the appropriate initial structure stored and trains the initialized model. In order to demonstrate the viability of the proposed method, we develop an one hour ahead load forecasting system by using the real load data collected during 1993 and 1994 at KEPCO. Simulation results reveal that the prediction system developed in this paper can achieve a remarkable improvement on both accuracy and reliability compared with the prediction systems based on multilayer perceptrons, radial basis function networks, and neuro-fuzzy models without the structure learning.

• 재무관리연구
• /
• 제20권1호
• /
• pp.93-124
• /
• 2003

본 연구에서는 2000년부터 2002년까지의 기간에서 국내 외의 재무분석가들이 1999년$\sim$2003년까지의 각 연도별 연간 매출액, 영업이익과 순이익에 대하여 발표한 예측치를 대상으로 하여 재무분석가들이 기업실적을 얼마나 정확하게 예측하며, 예측치를 수정할 때 어떤 체계적인 경향을 보이며, 기업실적을 예측할 때 전년도의 실적변화에 대해 어떤 반응을 보이는지를 분석하는데 목적을 두었다. 이러한 분석목적을 달성하기 위하여 재무분석가별, 예측년도별, 전년도의 기업실적 변화별로 표본을 각각 분류하여 재무분석가별 예측의 정확성, 합의예측치의 상대적 정확성, 예측치의 수정패턴 및 예상 밖의 전년도 실적변화에 대한 반응을 분석하였다. 본 연구에서 발견된 분석결과를 요약하면 다음과 같다. 첫째, 매출액, 영업이익과 순이익의 표준예측오차가 모두 통계적으로 유의적인 음(-)의 값을 보임으로써 재무분석가들이 기업실적을 상향 편의적으로 예측하는 경향이 있음을 발견하였다. 둘째, 국내. 외 재무분석가의 예측정확성을 비교한 분석에서 국내 재무분석가들이 국외 재무분석가들에 비해 상대적으로 정확한 예측을 하고 있음을 발견하였다. 셋째, 예측시점별로 측정한 평균표준예측오차에 대한 분석에서는 예측시점이 기업실적의 발표시점에 가까워질수록 예측의 정확성이 높아짐을 발견하였다. 넷째, 개별재무분석가와 비교할 때, 합의예측치의 정확성이 상대적으로 떨어지는 것으로 나타났으며, 합의 예측치를 추정할 때 평균보다 중위값을 이용하여 추정한 경우 예측오차를 줄일 수 있는 것으로 나타났다. 다섯째, 재무분석가들이 기업실적을 과대 예측한 다음 예측치를 하향 수정하는 것으로 나타났으나 체계적이지 않음을 발견할 수 있었다. 즉 재무분석가들은 전년도의 기업실적에 따라 예측치를 상향 또는 하향 수정하는 것으로 나타났다. 여섯째, 재무분석가들은 예측활동을 수행하는 과정에서 전년도의 매출액 변화에 대하여 과대 반응하는 한편 전년도의 영업이익과 순이익 변화에 대하여 과소 반응함을 발견할 수 있었다. 일곱째, 재무분석가들의 예측편의를 보다 정확하게 분석하기 위하여 정보변수인 전년기업실적 변수를 예상된 실적변화와 예상치 못한 실적변화로 분류하여 Easterwood-Nutt(1999)모형을 이용해 분석한 결과 세 개의 기업실적변수(매출액, 영업이익과 순이익)모두의 예상치 못한 전년실적변화에 대해 재무분석가들이 과대 예측하는 것이 아니라 낙관적 예측을 수행하는 경향이 있음을 발견할 수 있었다.

• 한국건설관리학회논문집
• /
• 제4권4호
• /
• pp.114-122
• /
• 2003

Dynamic and fragmented characteristics are two of the most significant factors that distinguish the construction industry from other industries. Previous forecasting techniques have failed to solve the problems derived from the above characteristics, and do not provide considerable support This paper deals with providing a more precise forecasting by applying Case-based Reasoning (CBR). The newly developed model in this study enables project managers to forecast monthly expenditures with less time and effort by retrieving and referring only projects of a similar nature, while filtering out irrelevant cases included in database. For the purpose of accurate forecasting, the choice of the numbers of referring projects was investigated. It is concluded that selecting similar projects at $5{\~}6{\%}$ out of the whole database will produce a more precise forecasting. The new forecasting model, which suggests the predicted values based on previous projects, is more than just a forecasting methodology; it provides a bridge that enables current data collection techniques to be used within the context of the accumulated information. This will eventually help all the participants in the construction industry to build up the knowledge derived from invaluable experience.

• 전기학회논문지
• /
• 제65권9호
• /
• pp.1486-1492
• /
• 2016

This study presents the electrical load forecasting and error correction method using a real building load pattern, and the way to manage the energy storage system with forecasting results for economical load operation. To make a unique pattern of target load, we performed the Hierarchical clustering that is one of the data mining techniques, defined load pattern(group) and forecasted the demand load according to the clustering result of electrical load through the previous study. In this paper, we propose the new reference demand for improving a predictive accuracy of load demand forecasting. In addition we study an error correction method for response of load events in demand load forecasting, and verify the effects of proposed correction method through EMS scheduling simulation with load forecasting correction.

• 전기학회논문지
• /
• 제64권8호
• /
• 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.

• Journal of Electrical Engineering and Technology
• /
• 제13권1호
• /
• pp.38-50
• /
• 2018

Spatio-temporal load forecasting (STLF) is a foundation for building the prediction-based power map, which could be a useful tool for the visualization and tendency assessment of urban energy application. Constructing one point-forecasting model for each electricity cell in the geographic space is possible; however, it is unadvisable and insufficient, considering the aggregation features of electricity cells and uncertainties in input variables. This paper presents a new STLF method, with a data-driven framework consisting of 3 subroutines: multi-level clustering of cells considering their aggregation features, load regression for each category of cells based on SLS-SVRNs (sparse least squares support vector regression networks), and interval forecasting of spatio-temporal load with sampled blind number. Take some area in Pudong, Shanghai as the region of study. Results of multi-level clustering show that electricity cells in the same category are clustered in geographic space to some extent, which reveals the spatial aggregation feature of cells. For cellular load regression, a comparison has been made with 3 other forecasting methods, indicating the higher accuracy of the proposed method in point-forecasting of spatio-temporal load. Furthermore, results of interval load forecasting demonstrate that the proposed prediction-interval construction method can effectively convey the uncertainties in input variables.

• 대한전기학회논문지:전력기술부문A
• /
• 제48권1호
• /
• pp.8-14
• /
• 1999

This paper presents the methods of short-term load forecasting Kohonen neural networks and back-propagation neural networks. First, historical load data is divided into 5 patterns for the each seasonal data using Kohonen neural networks and using these results, load forecasting neural network is used for next day hourly load forecasting. Next day hourly load of weekdays and weekend except holidays are forecasted. For load forecasting in summer, max-temperature and min-temperature data as well as historical hourly load date are used as inputs of load forecasting neural networks for a better forecasting accuracy. To show the possibility of the proposed method, it was tested with hourly load data of Korea Electric Power Corporation(1994-95).

• 전기학회논문지
• /
• 제65권7호
• /
• pp.1144-1150
• /
• 2016

Short-term load forecasting is essential to the electricity pricing and stable power system operations. The conventional weekday 24-hour load forecasting algorithms consider the temperature model to forecast maximum load and minimum load. But 24-hour load pattern forecasting models do not consider temperature effects, because hourly temperature forecasts were not present until the latest date. Recently, 3 hour temperature forecast is announced, therefore hourly temperature forecasts can be produced by mathematical techniques such as various interpolation methods. In this paper, a new 24-hour load pattern forecasting method is proposed by using similar day search considering the hourly temperature. The proposed method searches similar day input data based on the anomalous weather features such as continuous temperature drop or rise, which can enhance 24-hour load pattern forecasting performance, because it uses the past days having similar hourly temperature features as input data. In order to verify the effectiveness of the proposed method, it was applied to the case study. The case study results show high accuracy of 24-hour load pattern forecasting.