Browse > Article
http://dx.doi.org/10.7842/kigas.2019.23.5.52

Deep Learning Forecast model for City-Gas Acceptance Using Extranoues variable  

Kim, Ji-Hyun (JB주식회사)
Kim, Gee-Eun (JB주식회사)
Park, Sang-Jun (JB주식회사)
Park, Woon-Hak (JB주식회사)
Publication Information
Journal of the Korean Institute of Gas / v.23, no.5, 2019 , pp. 52-58 More about this Journal
Abstract
In this study, we have developed a forecasting model for city- gas acceptance. City-gas corporations have to report about city-gas sale volume next year to KOGAS. So it is a important thing to them. Factors influenced city-gas have differences corresponding to usage classification, however, in city-gas acceptence, it is hard to classificate. So we have considered tha outside temperature as factor that influence regardless of usage classification and the model development was carried out. ARIMA, one of the traditional time series analysis, and LSTM, a deep running technique, were used to construct forecasting models, and various Ensemble techniques were used to minimize the disadvantages of these two methods.Experiments and validation were conducted using data from JB Corp. from 2008 to 2018 for 11 years.The average of the error rate of the daily forecast was 0.48% for Ensemble LSTM, the average of the error rate of the monthly forecast was 2.46% for Ensemble LSTM, And the absolute value of the error rate is 5.24% for Ensemble LSTM.
Keywords
city-gas; forecasting demand; LSTM; ARIMA; time-series; acceptance;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Park, J. S., Kim, Y. B., and Jung, C. W., "Short-Term Forecasting of City Gas Daily Demand", Journal of the Korean Institute of Industrial Engineers, 39(4), 247-252, (2013)   DOI
2 Han, J. H., and Lee, G. C., "Forcasting Hourly Demand of City Gas in Korea", Journal of the Korea Academia-Industrial, 17(2), 87-95, (2016)   DOI
3 Kweather Corp., "Analysis and Forecast Solution for City-Gas Service Providers", KMA, (2012)
4 Ratnadip Adhikari, and R. K. Agrawal, "A Novel Weighted Ensemble Technique for Time Series Forecasting", Pacific-Asia Conference on Knowledge Discovery and Data Mining, Springer, Berlin, Geidelberg, (2012)
5 S. Krstanovic, and H. Paulheim, "Ensembles of Recurrent Neural Networks for Robust Time Series Forecasting", International Conference on Innovative Techniques and Applications of Artificial Intelligence, Spinger, Cham, 34-46, (2017)
6 Park, C. W., and Park, C. H., "Estimation of the Demand Function for City Gas Based on Characteristics of Its Uses in Korea", Korean Energy Economic Review, 17(2), 1-29, (2018)