• Communications for Statistical Applications and Methods
• /
• 제17권3호
• /
• pp.473-481
• /
• 2010

본 연구는 최근에 활발히 연구가 진행 중인 항공수요 예측을 위하여 계절형 다변량 시계열 모형을 기반으로 하고 다른 모형과의 비교를 RMSE(Root Mean Square Error)를 기준으로 비교한 것이다. 여기서 싱가폴 국제항공유가, 수출액을 추가하여 예측성능을 좋게 하고자 한다.

• 한국인공지능학회지
• /
• 제12권1호
• /
• pp.17-24
• /
• 2024

This paper introduces a novel approach to time-series estimation for energy load forecasting within Virtual Power Plant (VPP) systems, leveraging advanced artificial intelligence (AI) algorithms, namely Long Short-Term Memory (LSTM) and Seasonal Autoregressive Integrated Moving Average (SARIMA). Virtual power plants, which integrate diverse microgrids managed by Energy Management Systems (EMS), require precise forecasting techniques to balance energy supply and demand efficiently. The paper introduces a hybrid-method forecasting model combining a parametric-based statistical technique and an AI algorithm. The LSTM algorithm is particularly employed to discern pattern correlations over fixed intervals, crucial for predicting accurate future energy loads. SARIMA is applied to generate time-series forecasts, accounting for non-stationary and seasonal variations. The forecasting model incorporates a broad spectrum of distributed energy resources, including renewable energy sources and conventional power plants. Data spanning a decade, sourced from the Korea Power Exchange (KPX) Electrical Power Statistical Information System (EPSIS), were utilized to validate the model. The proposed hybrid LSTM-SARIMA model with parameter sets (1, 1, 1, 12) and (2, 1, 1, 12) demonstrated a high fidelity to the actual observed data. Thus, it is concluded that the optimized system notably surpasses traditional forecasting methods, indicating that this model offers a viable solution for EMS to enhance short-term load forecasting.

• 품질경영학회지
• /
• 제50권3호
• /
• pp.349-371
• /
• 2022

Purpose: Compared to the rapid growth rate of the domestic automotive LED industry so far, the predictive analysis method for demand forecasting or market outlook was insufficient. Accordingly, product characteristics are analyzed through the life trend of LEDs for automotive exterior lamps and the relative strengths of p and q using the Bass model. Also, future demands are predicted. Methods: We used sales data of a leading company in domestic market of automotive LEDs. Considering the autocorrelation error term of this data, parameters m, p, and q were estimated through the modified estimation method of OLS and the NLS(Nonlinear Least Squares) method, and the optimal method was selected by comparing prediction error performance such as RMSE. Future annual demands and cumulative demands were predicted through the growth curve obtained from Bass-NLS model. In addition, various nonlinear growth curve models were applied to the data to compare the Bass-NLS model with potential market demand, and an optimal model was derived. Results: From the analysis, the parameter estimation results by Bass-NLS obtained m=1338.13, p=0.0026, q=0.3003. If the current trend continues, domestic automotive LED market is predicted to reach its maximum peak in 2021 and the maximum demand is $102.23M. Potential market demand was $1338.13M. In the nonlinear growth curve model analysis, the Gompertz model was selected as the optimal model, and the potential market size was $2864.018M. Conclusion: It is expected that the Bass-NLS method will be applied to LED sales data for automotive to find out the characteristics of the relative strength of q/p of products and to be used to predict current demand and future cumulative demand.

• 인터넷정보학회논문지
• /
• 제24권2호
• /
• pp.47-56
• /
• 2023

수소 에너지는 높은 에너지 효율로 열과 전기를 생산하면서도 온실가스와 미세먼지 등 유해물질 배출이 없는 친환경 에너지로서, 전 세계적으로 탄소중립으로의 전환을 위한 핵심으로 주목받고 있다. 특히 스마트 수소에너지는 경제적이고 지속 가능하며, 안전한 미래 스마트 수소에너지 서비스로써 수소 에너지의 기반 시설이 디지털로 통합되어 '데이터' 기반으로 안정적으로 운영되는 서비스를 의미한다. 본 논문에서는 데이터 기반 수소 충전소 수요예측 모델 구현을 위해 강원도 내 설치되어 있는 수소 충전소 3곳(춘천, 속초, 평창)을 선정, 수소 충전소의 수요공급 데이터를 확보하였고, 머신러닝 및 딥러닝 알고리즘 7개를 선정하여 총 27종 입력 데이터(기상데이터+수소 충전소 수요량)로 모델을 학습하였고, 평균 제곱근 오차(RMSE)로 모델을 평가하였다. 이를 통해 본 논문에서는 최적의 수소 에너지 수요공급을 위한 머신러닝 기반 수소 충전소 에너지 수요 예측 모델을 제안한다.

• 한국보육지원학회지
• /
• 제12권6호
• /
• pp.123-137
• /
• 2016

The purpose of this study was to forecast demand of childcare teachers based ion four different scenarios. In order to, the demand for childcare teachers from 2015 to 2024 were forecasted using time series techniques with data on the number of childcare teachers from 2003 to 2014. Results were as followings. Firstly, the demand for childcare teachers was expected to increase until 2019, but after 2020 steadily decreased in terms of scenario 1(child teacher ratio regulation). According to scenario 2(child teacher ratio based on 17 cities and provinces), the demand for childcare teachers was expected to need 440 teachers more until 2016. Then, according to scenario 3(two teachers each class), Scenario 4-1(one teacher and one staff each 2 toddler class and 3 older class) and scenario 4-2(one teacher and one staff each class), the demand of childcare teachers and staffs were estimated. These results implicated that childcare teachers and staffs supply policy would be established according to forecast demand.

• 한국산학기술학회논문지
• /
• 제17권2호
• /
• pp.87-95
• /
• 2016

본 연구에서는 국내 도시가스 수요 데이터를 분석하여 시간대별 도시가스 수요의 특성을 파악하고 정확한 시간대별 도시가스 수요 예측을 위해 다중회귀모형(multiple regression model)을 개발하였다. 시간대별 도시가스 수요를 정확하게 예측하는 것은 공급자의 비용 절감뿐만 아니라 안정적인 배관망 관리 측면에서도 매우 중요하다. 수요 예측 오류로 인해 가스 공급이 부족한 상황이 발생하면 부족한 공급량을 빠른 시간내에 보충하기 위해 가스 배관망의 압력을 급격히 증가시켜야 하는 응급 상황이 전개될 수 있다. 반면, 시간대별 가스 생산량이 실제 수요보다 많은 경우에는 과다한 저장 시설 운용 및 불필요한 생산 비용이 발생하는 문제가 있다. 과거 시간대별 도시가스 수요 데이터를 분석한 결과 시간대별 도시 가스 수요는 직전 시간대(즉, 24시간 전) 수요와 매우 높은 상관관계를 보이며 24시간 수요 패턴은 1주일전 동일 요일(즉, 168시간전)의 24시간 수요 패턴과 매우 높은 상관관계가 있음을 확인하였다. 또한, 외기 온도가 도시가스 수요에 영향을 주는 특수한 조건을 파악하였다. 즉, 시간대별 도시가스 수요와 시간대별 외기 온도는 평균적으로 0.853의 높은 상관계수 절대값을 보여주며, 상관관계 분석시 같은 요일에 속한 데이터만 분석하면 상관계수의 절대값은 최저 0.861 및 최고 0.965까지 증가한다. 이상의 분석 결과를 바탕으로 본 연구에서는 24시간 전 수요와 168시간 전 수요를 독립변수로 고려한 다중회귀모형 및 외기 온도를 추가한 두 번째 다중회귀모형을 제안하며, 제안한 예측모형의 성능을 확인하기 위해 2009년부터 2013년까지 5년간의 시간대별 수요 예측 결과를 평가하였다. 본 연구에서 제안한 24시간 전 수요와 168시간 전 수요를 독립변수로 고려한 다중회귀모형의 경우 과거 5년간의 수요 예측 오차율의 절대값 평균(mean absolute percentage error)은 4.5% 수준이며, 외기 온도를 추가한 모형의 경우 오차율의 절대값 평균은 5.13%임을 확인하였다.

• International Journal of Advanced Culture Technology
• /
• 제2권2호
• /
• pp.11-14
• /
• 2014

In the smart grid, it will be possible to communicate with the consumers for the purposes of monitoring and controlling their power consumption without disturbing their business or comfort. This will bring easier administration capabilities for the utilities. On the other hand, consumers will require more advanced home automation tools which can be implemented by using advanced sensor technologies. For instance, consumers may need to adapt their consumption according to the dynamically varying electricity prices which necessitates home automation tools. This paper tries to combine neural network and nonlinear autoregressive with exogenous variable (NARX) class for next week electric load forecasting. The suitability of the proposed approach is illustrated through an application to electric load consumption data. The suggested system provides a useful and suitable tool especially for the load forecasting.

• 한국항공운항학회지
• /
• 제9권2호
• /
• pp.101-111
• /
• 2001

Heuksando is an island which belongs to Shinangun, Jeonllanamdo and is located on the southwest sea of the Korean peninsula. Around this island, there are many beautiful islands which embroider the archipelago such as Hongdo, Soheuksando, Haeuido, Gageodo. However in the transportation mode we could not offer convenience to all the visitors coming to this area because access to this place can be made only by ship from Mokpo harbor. So new airport is desirable to solve this problem in this area. Therefore, this study is forecasting air transportation demand between Heuksando and several domestic places in order to give the fundamental materials not only to address the appropriateness to construct a new airport but also to determine it's size and necessary facilities.

• 한국건설관리학회:학술대회논문집
• /
• 한국건설관리학회 2003년도 학술대회지
• /
• pp.67-72
• /
• 2003

Infrastructure asset management is a methodology for programming infrastructure capital investments and adjusting infrastructure service provision to fulfil established performance, considering the life-cycle perspective of infrastructure. In this study, the methodologies for infrastructure asset management system implemented in sewer management system, bridge management system, pavement and highway management system, and embankment dam management system are described with focus on the system in U.S. As the major methodology to support the decision-making for asset mangers to better allocate the limited funds to the area needing it the most. various demand forecasting methodologies used in wastewater, water, transportation, electricity, and construction are also introduced for their applicability towards infrastructure asset management.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회/대한산업공학회 2005년도 춘계공동학술대회 발표논문
• /
• pp.798-805
• /
• 2005

Estimating the effects of price increase on a company's sales is important task faced by managers. If consumer has prior information on price increase or expect it, there would be stockpiling and subsequent drops in sales. In addition, consumer can suppress demand in the short run. Above factors make the sales dynamic and unstable. We develop a time series model to evaluate the sales patterns with stockpiling and short term suppression of demand and also propose a forecasting procedure. For estimation, we use panel data and extend the model to Bayesian hierarchical structure. By borrowing strength across cross-sectional units, this estimation scheme gives more robust and reasonable result than one from the individual estimation. Furthermore, the proposed scheme yields improved predictive power in the forecasting of hold-out sample periods.