An Application of Grey Neural Network for Forecasting Short-term Natural Gas
Consumption of Korea

doi:10.12972/ksmer.2016.53.1.078

All Issue

2016 Vol.53, Issue 1 Preview Page

Research Paper

An Application of Grey Neural Network for Forecasting Short-term Natural Gas Consumption of Korea 우리나라 단기 가스 소비량 예측에 있어서 Grey Neural Network활용 가능성 분석: 박성준·김진수
Sungjun Park and Jinsoo Kim

28 February 2016. pp. 78-87

PDF

Abstract

Due to recent shale gas boom and recession, natural gas prices are placed at low level. It is thusnecessary to establishing new strategy for stable natural gas demand and supply considering changes in energymarkets, geopolitical situation, and actions for a climate change. In the light of this, a more accurate forecastingof natural gas consumption is important. Therefore, we setup a Grey Neural Network (GNN) model to forecastKorean natural gas consumption. For empirical analysis, gas consumption data from January 1997 to June 2014was gathered and a root mean squared error of artificial neural network (ANN), Grey model (GM), hybridGM-ANN, and GNN models were compared. As a result, the GNN model showed the best forecasting power.

Keywords

Forecasting

Gas consumption

Grey neural network

Korea

최근 셰일가스 개발로 인하여 천연가스 공급이 증가한 반면 수요는 침체되어 가격이 많이 하락한상황이다. 따라서 에너지 시장 변화와 지정학적 영향, 기후변화 대비 전략을 고려하여 보다 안정적으로 가스수급 전략을 재편할 필요가 있으며, 이를 위하여 보다 정확한 가스 소비량 예측이 중요하다. 이에 본 연구에서는한국의 단기 가스 소비량 예측을 위하여 Grey 신경망(GNN)을 구성하였다. 1997년 1월～2014년 6월의 월별가스 소비량 자료로 실증 분석을 수행하였으며, 인공신경망, Grey 모형, GNN, hybrid GM-ANN의 평균제곱근오차를 비교하였다. 분석 결과 가스 소비량 예측 시 GNN의 설명력이 가장 높은 것으로 나타났다.

키워드

예측

가스 소비

Grey 신경망

한국

References

BP, 2015, Bp energy outlook 2035, BP p.l.c. 2015, London, United Kingdom.
Brown, R.H. and Matin, I., 1995, “Development of artificial neural network models to predict daily gas consumption,” Industrial Electronics, Control, and Instrumentation, 1995., Proceedings of the 1995 IEEE IECON 21st International Conference on, 6-10 Nov 1995, pp. 1389-1394.
Brown, R.H., Kharouf, P., Xin, F., Piessens, L.P. and Nestor, D., 1994, “Development of feed-forward network models to predict gas consumption,” Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on, 27 Jun-2 Jul 1994, pp. 802-805.
Cooper, J.C.B., 1999, “Artificial neural networks versus multivariate statistics: An application from economics,” Journal of Applied Statistics, Vol. 26, No. 8, pp. 909-921.
Dahai, Z., Zhiwu, R., Yanbing, B., Dazhou, Z. and Yanqiu, B., 2008, “Power load forecasting based on grey neural network,” Industrial Electronics, 2008. ISIE 2008. IEEE International Symposium on, June 30 2008-July 2 2008, pp. 1885-1889.
Deng, J.L., 1989, “Introduction to grey system theory,” J. Grey Syst., Vol. 1, No. 1, pp. 1-24.
Dombaycı, Ö.A., 2010, “The prediction of heating energy consumption in a model house by using artificial neural networks in denizli–turkey,” Advances in Engineering Software, Vol. 41, No. 2, pp. 141-147.
Dutta, S. and Shashi, S., 1988, “Bond rating: A nonconservative application of neural networks,” Neural Networks, 1988., IEEE International Conference on, 24-27 July 1988, pp. 443-450.
EIA, 2014, Korea, south, international energy data and analysis, The U.S. Energy Information Administration, Washington, DC.
Gorucu, F.B., 2004, “Artificial neural network modeling for forecasting gas consumption,” Energy Sources, Vol. 26, No. 3, pp. 299-307.
Hongwei, M. and Yonghe, W., 2009, “Grey predictive on natural gas consumption and production in china,” Web Mining and Web-based Application, 2009. WMWA '09. Second Pacific-Asia Conference on, 6-7 June 2009, pp. 91-94.
Hsu, C.-C. and Chen, C.-Y., 2003, “Applications of improved grey prediction model for power demand forecasting,” Energy Conversion and Management, Vol. 44, No. 14, pp. 2241-2249.
IEA, 2013, Natural gas information 2013, International Energy Agency, Paris, France.
Jin, J. and Kim, J., 2015, “Forecasting and event matching of natural gas price using wavelet decomposition,” 38th IAEE International Conference, Antalya, Turkey, 25-27 May 2015, p. 1.
Karimi, H. and Dastranj, J., 2014, “Artificial neural network- based genetic algorithm to predict natural gas consumption,” Energy Systems, Vol. 5, No. 3, pp. 571-581. (English)
Khotanzad, A. and Elragal, H., 1999, “Natural gas load forecasting with combination of adaptive neural networks,” Neural Networks, 1999. IJCNN '99. International Joint Conference on, Jul 1999, pp. 4069-4072.
Khotanzad, A., Elragal, H. and Lu, T.L., 2000, “Combination of artificial neural-network forecasters for prediction of natural gas consumption,” Neural Networks, IEEE Transactions on, Vol. 11, No. 2, pp. 464-473.
Kim, D.S., 2005, Neural networks theory and applications, Jinhan M＆B, Seoul, Korea.
Kim, T., Hong, J. and Kang, P., 2015, “Box office forecasting using machine learning algorithms based on sns data,” International Journal of Forecasting, Vol. 31, No. 2, pp. 364-390.
Lee, K.H., Jeh, S.H. and Kang, B., 2013. The rise of shale gas and russia's countermeasures. KIEP,
Park, S. and Kim, J., 2014, “An application of artificial neural network in short-run natural gas price forecasting,” Journal of the Korean Society for Geosystem Engineering, Vol. 51, No. 6, pp. 761-770. (Korean)
Park, S. and Kim, J., 2015, “Forecasting of natural gas consumption using hybrid grey-ann method,” 38th IAEE International Conference, Antalya, Turkey, 25-27 May 2015, p. 1.
Salchenberger, L.M., Cinar, E.M. and Lash, N.A., 1992, “Neural networks: A new tool for predicting thrift failures*,” Decision Sciences, Vol. 23, No. 4, pp. 899-916.
Shin, Y., 2013, “The impacts of shale gas on energy market and industry,” KIET Industrial Economic Review 2013, pp. 58-66.
Shin, Y., Park, K., Kwak, D., Jung, Y., Youn, J. and Lee, J., 2013. The impacts of shale gas revolution on korea industries and implications. KIET Research Report 2013, Sejong, Korea.
Suykens, J., Lemmerling, P., Favoreel, W., de Moor, B., Crepel, M. and Briol, P., 1996, “Modelling the belgian gas consumption using neural networks,” Neural Processing Letters, Vol. 4, No. 3, pp. 157-166. (English)
Tonković, Z., Zekić-Sušac, M. and Somolanji, M., 2009, “Predicting natural gas consumption by neural networks,” Tehnički vjesnik, Vol. 16, No. 3, pp. 51-61.
Viet, N.H. and Mandziuk, J., 2005, “Neural and fuzzy neural networks in prediction of natural gas consumption,” Neural, Parallel & Scientific Computations, Vol. 13, No. 3, pp. 265-286.
Yidan, H.Y.B., 1992, “Grey-markov forecasting model and its application,” Systems Engineering-theory & Practice, Vol. 4, p. 12.
Yoon, J., 2013. South korea's 11th long-term natural gas supply/demand plan. Ministry of trade, industry & energy, Sejong, Korea.
Yu, F. and Xu, X., 2014, “A short-term load forecasting model of natural gas based on optimized genetic algorithm and improved bp neural network,” Applied Energy, Vol. 134, pp. 102-113.
Zhang, G., Eddy Patuwo, B. and Y. Hu, M., 1998, “Forecasting with artificial neural networks:: The state of the art,” International Journal of Forecasting, Vol. 14, No. 1, pp. 35-62.

Information

Publisher :The Korean Society of Mineral and Energy Resources Engineers
Publisher(Ko) :한국자원공학회
Journal Title :Journal of the Korean Society of Mineral and Energy Resources Engineers
Journal Title(Ko) :한국자원공학회지
Volume : 53
No :1
Pages :78-87
DOI :https://doi.org/10.12972/ksmer.2016.53.1.078

[1] BP, 2015, Bp energy outlook 2035, BP p.l.c. 2015, London, United Kingdom.

[2] Brown, R.H. and Matin, I., 1995, “Development of artificial neural network models to predict daily gas consumption,” Industrial Electronics, Control, and Instrumentation, 1995., Proceedings of the 1995 IEEE IECON 21st International Conference on, 6-10 Nov 1995, pp. 1389-1394.

[3] Brown, R.H., Kharouf, P., Xin, F., Piessens, L.P. and Nestor, D., 1994, “Development of feed-forward network models to predict gas consumption,” Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on, 27 Jun-2 Jul 1994, pp. 802-805.

[4] Cooper, J.C.B., 1999, “Artificial neural networks versus multivariate statistics: An application from economics,” Journal of Applied Statistics, Vol. 26, No. 8, pp. 909-921.

[5] Dahai, Z., Zhiwu, R., Yanbing, B., Dazhou, Z. and Yanqiu, B., 2008, “Power load forecasting based on grey neural network,” Industrial Electronics, 2008. ISIE 2008. IEEE International Symposium on, June 30 2008-July 2 2008, pp. 1885-1889.

[6] Deng, J.L., 1989, “Introduction to grey system theory,” J. Grey Syst., Vol. 1, No. 1, pp. 1-24.

[7] Dombaycı, Ö.A., 2010, “The prediction of heating energy consumption in a model house by using artificial neural networks in denizli–turkey,” Advances in Engineering Software, Vol. 41, No. 2, pp. 141-147.

[8] Dutta, S. and Shashi, S., 1988, “Bond rating: A nonconservative application of neural networks,” Neural Networks, 1988., IEEE International Conference on, 24-27 July 1988, pp. 443-450.

[9] EIA, 2014, Korea, south, international energy data and analysis, The U.S. Energy Information Administration, Washington, DC.

[10] Gorucu, F.B., 2004, “Artificial neural network modeling for forecasting gas consumption,” Energy Sources, Vol. 26, No. 3, pp. 299-307.

[11] Hongwei, M. and Yonghe, W., 2009, “Grey predictive on natural gas consumption and production in china,” Web Mining and Web-based Application, 2009. WMWA '09. Second Pacific-Asia Conference on, 6-7 June 2009, pp. 91-94.

[12] Hsu, C.-C. and Chen, C.-Y., 2003, “Applications of improved grey prediction model for power demand forecasting,” Energy Conversion and Management, Vol. 44, No. 14, pp. 2241-2249.

[13] IEA, 2013, Natural gas information 2013, International Energy Agency, Paris, France.

[14] Jin, J. and Kim, J., 2015, “Forecasting and event matching of natural gas price using wavelet decomposition,” 38th IAEE International Conference, Antalya, Turkey, 25-27 May 2015, p. 1.

[15] Karimi, H. and Dastranj, J., 2014, “Artificial neural network- based genetic algorithm to predict natural gas consumption,” Energy Systems, Vol. 5, No. 3, pp. 571-581. (English)

[16] Khotanzad, A. and Elragal, H., 1999, “Natural gas load forecasting with combination of adaptive neural networks,” Neural Networks, 1999. IJCNN '99. International Joint Conference on, Jul 1999, pp. 4069-4072.

[17] Khotanzad, A., Elragal, H. and Lu, T.L., 2000, “Combination of artificial neural-network forecasters for prediction of natural gas consumption,” Neural Networks, IEEE Transactions on, Vol. 11, No. 2, pp. 464-473.

[18] Kim, D.S., 2005, Neural networks theory and applications, Jinhan M＆B, Seoul, Korea.

[19] Kim, T., Hong, J. and Kang, P., 2015, “Box office forecasting using machine learning algorithms based on sns data,” International Journal of Forecasting, Vol. 31, No. 2, pp. 364-390.

[20] Lee, K.H., Jeh, S.H. and Kang, B., 2013. The rise of shale gas and russia's countermeasures. KIEP,

[21] Park, S. and Kim, J., 2014, “An application of artificial neural network in short-run natural gas price forecasting,” Journal of the Korean Society for Geosystem Engineering, Vol. 51, No. 6, pp. 761-770. (Korean)

[22] Park, S. and Kim, J., 2015, “Forecasting of natural gas consumption using hybrid grey-ann method,” 38th IAEE International Conference, Antalya, Turkey, 25-27 May 2015, p. 1.

[23] Salchenberger, L.M., Cinar, E.M. and Lash, N.A., 1992, “Neural networks: A new tool for predicting thrift failures*,” Decision Sciences, Vol. 23, No. 4, pp. 899-916.

[24] Shin, Y., 2013, “The impacts of shale gas on energy market and industry,” KIET Industrial Economic Review 2013, pp. 58-66.

[25] Shin, Y., Park, K., Kwak, D., Jung, Y., Youn, J. and Lee, J., 2013. The impacts of shale gas revolution on korea industries and implications. KIET Research Report 2013, Sejong, Korea.

[26] Suykens, J., Lemmerling, P., Favoreel, W., de Moor, B., Crepel, M. and Briol, P., 1996, “Modelling the belgian gas consumption using neural networks,” Neural Processing Letters, Vol. 4, No. 3, pp. 157-166. (English)

[27] Tonković, Z., Zekić-Sušac, M. and Somolanji, M., 2009, “Predicting natural gas consumption by neural networks,” Tehnički vjesnik, Vol. 16, No. 3, pp. 51-61.

[28] Viet, N.H. and Mandziuk, J., 2005, “Neural and fuzzy neural networks in prediction of natural gas consumption,” Neural, Parallel & Scientific Computations, Vol. 13, No. 3, pp. 265-286.

[29] Yidan, H.Y.B., 1992, “Grey-markov forecasting model and its application,” Systems Engineering-theory & Practice, Vol. 4, p. 12.

[30] Yoon, J., 2013. South korea's 11th long-term natural gas supply/demand plan. Ministry of trade, industry & energy, Sejong, Korea.

[31] Yu, F. and Xu, X., 2014, “A short-term load forecasting model of natural gas based on optimized genetic algorithm and improved bp neural network,” Applied Energy, Vol. 134, pp. 102-113.

[32] Zhang, G., Eddy Patuwo, B. and Y. Hu, M., 1998, “Forecasting with artificial neural networks:: The state of the art,” International Journal of Forecasting, Vol. 14, No. 1, pp. 35-62.

Journal of the Korean Society of Mineral and Energy Resources Engineers ISSN:2288-0291(Print) 2288-2790(Online) 한국자원공학회지

All Issue