• 한국항공운항학회지
• /
• 제27권3호
• /
• pp.98-105
• /
• 2019

In the past 30 years, our aviation demand has been growing continuously. As such, the importance of the demand forecasting field is increasing. In this study, the factors influencing Korea's international air demand were selected, and the international air demand was analyzed, forecasted and reviewed through OLS multiple regression analysis. As a result, passenger demand was affected by GDP per capita, oil price and exchange rate, while cargo demand was affected by GDP per capita and private consumption growth rate. In particular, passenger demand was analyzed to be sensitive to temporary external shocks, and cargo demand was more affected by economic variables than temporary external shocks. Demand forecasting, OLS multiple regression analysis, passenger demand, cargo demand, transient external shocks, economic variables.

• 한국항공운항학회지
• /
• 제27권1호
• /
• pp.43-50
• /
• 2019

The aviation demand forecast field has been actively studied along with the recent growth of the aviation market. In this study, the demand for domestic passenger demand and freight demand was estimated through cross-validation method. As a result, passenger demand is influenced by private consumption growth rate, oil price, and exchange rate. Freight demand is affected by GDP per capita, private consumption growth rate, and oil price. In particular, passenger demand is characterized by temporary external shocks, and freight demand is more affected by economic variables than temporary shocks.

• 설비공학논문집
• /
• 제29권3호
• /
• pp.97-104
• /
• 2017

Reinforcement of insulation in apartment buildings reduces the heating and cooling energy consumption by lowering the heat transfer in the building envelope. There are differences between internal and external insulation methods in heat transmission properties. However, some building load calculation programs cannot analysis the differences between the two. This is because these programs do no account for the timelag or thermal storage effect of the wall according to the location of insulation. In this study, the heat transmission characteristics of internal and external insulation were analyzed by EnergyPlus, and heating and cooling energy demand was compared. The results showed that external insulation system had lower heating and cooling loads than internal insulation system. Also the heat transfer rate of external insulation is steadier than internal insulation. About 13.6% of heating and cooling energy demand decreased when the outdoor wall was finished with external insulation compared to the demand with internal insulation.

• 대한토목학회논문집
• /
• 제35권4호
• /
• pp.907-920
• /
• 2015

자동차 보유의 증가로 수도권 지역에서 인구가 출 퇴근하는 행태가 자동차이용형으로 급변하는 현실에서 자동차를 받아들일 수 있는 인프라가 대단히 열악하다. 교통수요관리 정책이 시행됨에도 불구하고 여전히 많은 통행이 나타나고 있으며, 이에 상응하는 국내 외 연구는 미미한 실정이다. 이에 본 연구에서는 현재 국내 외에서 시행되고 있는 교통수요관리 정책을 선정하여 설문조사를 실시하였다. 이 설문조사를 바탕으로 AHP(Analytic Hierarchy Process)분석을 수행하여 국내 외에서 시행되고 있는 교통수요관리 정책을 비교하여 우위를 정하고 이용자들이 느끼는 각 항목별 중요도와 만족도를 파악하였다. 또한 AHP분석 기법을 통하여 얻어낸 항목별 중요도와 만족도를 바탕으로 각 교통수요관리 정책 특성을 비교하였다. 마지막으로 본 연구를 통해 파악된 요인들로 현재의 현황을 분석하고 앞으로의 교통수요 정책 방향을 정립하여 향후 교통여건개선에 활용하고자 한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권3호
• /
• pp.528-550
• /
• 2024

Warehousing demand prediction is an essential part of the supply chain, providing a fundamental basis for product manufacturing, replenishment, warehouse planning, etc. Existing forecasting methods cannot produce accurate forecasts since warehouse demand is affected by external factors such as holidays and seasons. Some aspects, such as consumer psychology and producer reputation, are challenging to quantify. The data can fluctuate widely or do not show obvious trend cycles. We introduce a new model for warehouse demand prediction called MAGRU, which stands for Multi-layer Attention with GRU. In the model, firstly, we perform the embedding operation on the input sequence to quantify the external influences; after that, we implement an encoder using GRU and the attention mechanism. The hidden state of GRU captures essential time series. In the decoder, we use attention again to select the key hidden states among all-time slices as the data to be fed into the GRU network. Experimental results show that this model has higher accuracy than RNN, LSTM, GRU, Prophet, XGboost, and DARNN. Using mean absolute error (MAE) and symmetric mean absolute percentage error(SMAPE) to evaluate the experimental results, MAGRU's MAE, RMSE, and SMAPE decreased by 7.65%, 10.03%, and 8.87% over GRU-LSTM, the current best model for solving this type of problem.

• KIEAE Journal
• /
• 제15권4호
• /
• pp.77-84
• /
• 2015

Purpose: In 2008, As the green growth policy was presented, Green Building is made any effort to propagation. In this paper, the respective technologies that are able to considerably reduce the energy demands for heating, cooling, hot-water, lighting and ventilation among the variety of technologies were selected. Method: Design factors such as (1) External insulation, (2) Triple glazing window, (3) LED lighting, (4) External venetian blind, (5) Geothermal and (6) Heat recovery ventilator were derived. In addition, energy saving effects in terms of energy demand, energy consumption and energy cost were investigated using EnergyPlus, building energy analysis tool. Result : The results were as follows. (1) It can be seen that high insulated triple glazing window, heat recovery ventilator and external insulation technology is excellent for energy demand. (2) Unlike energy demand, saving effect of energy consumption and energy cost was shown in order of Geothermal > Triple Window > Heat recovery Ventilation> Insulation> LED Lighting > EVB Blind.

• Journal of the Korean Data and Information Science Society
• /
• 제28권2호
• /
• pp.395-406
• /
• 2017

전력 공급 시스템의 효율적인 운영을 위해 전력수요예측은 필수적이다. 본 연구에서는 군집분석과 분류분석을 이용하여 일 단위 시간별 전력수요량 시계열 패턴의 유형을 살펴보고자 한다. 전력거래소에서 수집된 2008년 1월 1일부터 2012년 12월 31일까지의 일 단위 시간별 전력수요량 데이터를 추세성분, 계절성분, 오차 성분으로 구성된 시계열 자료로 변환하여 사용하였다. 추세성분을 제거한 시계열 자료의 패턴을 구분하기 위한 군집 분석방법은 k-평균 군집분석 (k-means), 가우시안혼합모델 혼합 모델 군집분석 (Gaussian mixture model), 함수적 군집분석 (functional clustering)을 고려하였다. 주성분분석을 통해 24시간 자료를 2개의 요인로 축소한 후 k-평균 군집분석과 가우시안 혼합 모델, 함수적 군집분석을 수행하였다. 군집분석 결과를 토대로 2008년부터 2011년까지 총 4년간 데이터를 4가지 분류분석방법인 의사결정나무, RF (random forest), Naive bayes, SVM (support vector machine)을 통해 훈련시켜 2012년 군집을 예측하였다. 분석 결과 가우시안 혼합 분포기반 군집분석과 RF를 이용한 군집예측 결과의 성능이 가장 우수하였다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 춘계학술대회
• /
• pp.35-37
• /
• 2021

외래 관광객 수요를 분석하고 예측하는 것은 관광 정책을 수립하고 기획하는데 지대한 영향을 미치기 때문에 관광 산업 분야에서 매우 중요하다. 외래 관광객 데이터는 여러 외적 요인들에 의해 영향을 받기 때문에, 시간에 따른 미세한 변화가 많다는 특징을 갖는다. 따라서, 최근에는 관광객 입국자 수요를 예측하기 위해 경제 변수 등 여러 외적 요인들도 함께 반영하여 예측 모델을 설계하는 연구를 진행하고 있다. 그러나 기존의 시계열 예측에 주로 사용되는 회귀분석 모델과 순환신경망 모델은 여러 변수들을 반영하는 시계열 예측에 있어 좋은 성능을 보이지 못했다. 따라서 우리는 합성곱 신경망을 활용하여 이러한 한계점들을 보완한 외래 관광객 수요 예측 모델을 소개한다. 본 논문에서는 한국관광공사에서 제공한 과거 10개년 외래 관광객 데이터와 추가적으로 수집한 여러 외적 요인들을 입력 변수로 반영하는 1차원 합성곱 신경망을 설계하여 외래 관광객 수요를 예측하는 모델을 제시한다.

• 전기학회논문지
• /
• 제57권8호
• /
• pp.1342-1348
• /
• 2008

One important objective of the electricity market is to decrease the price by ensuring stability in the market operation. Interconnected to this is another objective; namely, to realize sustainable consumption of electricity by equitably distributing the effects and benefits of participating in the market among all participants of the industry. One method that can help achieve these objectives is the ^{(R)}$demand-response program, - which allows for active adjustment of the loadage from the demand side in response to the price. The demand-response program requires a customer baseline load (CBL), a criterion of calculating the success of decreases in demand. This study was conducted in order to calculate undistorted CBL by analyzing the correlations between such external or seasonal factors as temperature, humidity, and discomfort indices and the amounts of electricity consumed. The method and findings of this study are accordingly explicated.

• The Journal of Asian Finance, Economics and Business
• /
• 제7권11호
• /
• pp.575-583
• /
• 2020

Vietnam is the country with the largest animal feed production in Southeast Asia. Domestic animal feed manufacturing enterprises play an important role in animal husbandry in particular and in agriculture in general. However, domestic animal feed enterprises in Vietnam are encountering shortcomings. This paper is conducted to investigate the impact levels of external determinants on business performance of domestic animal feed manufacturing enterprises, including: (i) policy and economic mechanism, (ii) supply-demand of animal feed products, and (iii) nature and level of market competition. We presented a research method, explaining the dependent variable 'business performance' and the independent variables. Data were collected from 120 questionnaires from domestic animal feed manufacturing enterprises. Based on these data, we use Cronbach's Alpha, EFA and run regression model for assessing the impact levels of each independent variable on the dependent variable of business performance of domestic animal feed manufacturing enterprises. The results show that three external determinants including (i) policy and economic mechanism, (ii) supply-demand of animal feed products, and (iii) nature and level of market competition, have positive relationships with business performance. Based on the findings, some recommendations are given for improving business performance of domestic animal feed manufacturing enterprises to ensure sustainability.