DOI QR코드

DOI QR Code

선별적 샘플링을 이용한 국내 도시가스 일별 수요예측 절차 개발

Forecasting Daily Demand of Domestic City Gas with Selective Sampling

  • Lee, Geun-Cheol (College of Business Administration, Konkuk University) ;
  • Han, Jung-Hee (Department of Business Administration, Kangwon National University)
  • 투고 : 2015.07.22
  • 심사 : 2015.10.08
  • 발행 : 2015.10.31

초록

본 연구에서는 국내 도시가스 일일 수요 예측에 대한 문제를 다룬다. 정확한 일일 수요 예측은 안정적인 도시가스의 수급을 위해서 필수적인 사항으로 실제 가스 공급기관의 일상 업무에 해당한다. 본 연구에서는 수요예측 방법을 고안하기 위하여 일일 도시가스 수요 시계열에 대한 데이터 분석을 수행하였으며, 예측일 수요에 영향을 주는 주요한 요인으로 직전일 수요, 기온, 요일 등을 파악하였다. 본 연구에서는 이러한 요인들을 고려한 회귀 모형과 국내 도시가스 수요 특성에 맞는 선별적 샘플링 절차를 제안하였다. 제안 모형과 선별적 샘플링 절차로 구성된 예측 방법의 성능 검증을 위하여 실제 도시가스 수요에 대한 예측을 수행하였다. 문헌에 소개된 기존 방법과 예측 성능을 비교한 결과, 본 연구에서 제안한 방법의 평균절대백분율오차는 약 2.22%로서 개선 비율은 대략 7%에 해당한다.

In this study, we consider a problem of forecasting daily city gas demand of Korea. Forecasting daily gas demand is a daily routine for gas provider, and gas demand needs to be forecasted accurately in order to guarantee secure gas supply. In this study, we analyze the time series of city gas demand in several ways. Data analysis shows that primary factors affecting the city gas demand include the demand of previous day, temperature, day of week, and so on. Incorporating these factors, we developed a multiple linear regression model. Also, we devised a sampling procedure that selectively collects the past data considering the characteristics of the city gas demand. Test results on real data exhibit that the MAPE (Mean Absolute Percentage Error) obtained by the proposed method is about 2.22%, which amounts to 7% of the relative improvement ratio when compared with the existing method in the literature.

키워드

참고문헌

  1. Y. S. Chang, B. H. Kang, "Survey Analysis on Domestic Utilization of Natural Gas", The 2013 Spring Conference Proceedings of the Society of Air-conditioning and Refrigerating Engineers of Korea, 352-355, 2013.
  2. J.-J. Her, H.-J. Lim, "An Analysis of Growth Factors on the City-gas Industry by Input-output Structural Decomposition Analysis", Journal of Energy Engineering, 21(2), 158-167, 2012. DOI: http://dx.doi.org/10.5855/ENERGY.2012.21.2.158
  3. KEEI Quarterly Energy Outlook, Korea Energy Economics Institute, 16(3), 2014.
  4. KESIS, http://www.kesis.net/ (accessed July 2015)
  5. S.-J. Lee, S.-S. Euh, S.-H. Yoo, "Estimation of City Gas Demand Function Using Time Series Data", Journal of Energy Engineering, 22(4), 370-375, 2013. DOI: http://dx.doi.org/10.5855/ENERGY.2013.22.4.370
  6. H.-Y. Oh, "Forecasting of the Short-Term Demand for the Natural Gas Using Time Series Analysis and Artificial Neural Networks", Master Thesis, Graduate School of Management, KAIST, 1997.
  7. J.-S. Kim, C.-S. Yang, J.-G. Park, "An Empirical Study on the Consumption Function of Korean Natural Gas for City Gas", Journal of Energy Engineering, 20(4), 318-329, 2011. DOI: http://dx.doi.org/10.5855/ENERGY.2011.20.4.318
  8. B. Choi, H. Kang, K.-Y. Lee, S. T. Han, "A Development of Time-series Model for City Gas Demand Forecasting", Korean Journal of Applied Statistics, 22(5), 1019-1032, 2009. DOI: http://dx.doi.org/10.5351/KJAS.2009.22.5.1019
  9. J. S. Park, Y. B. Kim, C. W. Jung, "Short-Term Forecasting of City Gas Daily Demand", Journal of the Korean Institute of Industrial Engineers, 39(4), 247-252, 2013. DOI: http://dx.doi.org/10.7232/JKIIE.2013.39.4.247
  10. C. W. Jung, "A Study on City Gas Demand Forecasting Based on Daily Characteristics", Master Thesis, Department of Industrial Engineering, Sungkyunkwan University, 2013.
  11. B. Soldo, "Forecasting Natural Gas Consumption", Applied Energy, 92, 26-37, 2012. DOI: http://dx.doi.org/10.1016/j.apenergy.2011.11.003
  12. A. Azadeh, S.M. Asadzadeh, A. Ghanbari, "An Adaptive Network-based Fuzzy Inference System for Short-term Natural Gas Demand Estimation: Uncertain and Complex Environments", Energy Policy, 38, 1529-1536, 2010. DOI: http://dx.doi.org/10.1016/j.enpol.2009.11.036
  13. F. Taspinar, N. Celebi, N. Tutkun, "Forecasting of Daily Natural Gas Consumption on Regional Basis in Turkey Using Various Computational Methods", Energy and Building, 56, 23-31, 2013. DOI: http://dx.doi.org/10.1016/j.enbuild.2012.10.023
  14. L. Zhu, M. S. Li, Q. H. Wu, L. Jiang, "Short-term Natural Gas Demand Prediction Based on Support Vector Regression with False Neighbors Filtered", Energy, 80, 428-436, 2015. DOI: http://dx.doi.org/10.1016/j.energy.2014.11.083
  15. O.-S. Kwon, K.-B. Song, Development of Short-Term Load Forecasting Method by Analysis of Load Characteristics during Chuseok Holiday", The Transactions of The Korean Institute of Electrical Engineers, 60(12), 2215-2220, 2011. DOI: http://dx.doi.org/10.5370/KIEE.2011.60.12.2215
  16. K.-B. Song, J.-H. Lim, "Short-Term Load Forecasting for the Consecutive Holidays Considering Businesses' Operation Rates of Industries", The Transactions of The Korean Institute of Electrical Engineers, 62(12), 1657-1660, 2013. DOI: http://dx.doi.org/10.5370/KIEE.2013.62.12.1657