Abstract
Natural gas is an important energy source for urban development and residents’ lives. Excessive or insufficient natural gas will cause huge problems. Accurate prediction of natural gas consumption is an important way to solve this problem, which providing guidance for the rational supply and dispatch of urban energy. The existing studies working on natural gas consumption forecast usually focus on short-term forecast and medium-term forecast. However, little research has been done on long-term forecast in natural gas consumption. In this paper, we propose a hybrid time series model for long-term forecast, which predicts the gas consumption in the next three months based on a given time series of gas consumption and related weather factors in six months. This model integrates KNN, recursive feature elimination, moving average filtering, and deep neural network. KNN is used to fill missing values, recursive feature elimination is used to select features, moving average filtering is used to smooth the noise in historical data, and finally the processed data is passed to the DNN network. Experiments have validated that the proposed model performs with a 0.33 MSE and 27% MAPE on one hour resolution, a 30.74 MSE and 12.8% MAPE on one day resolution, 194.46 MSE and 5.6% MAPE on one week resolution. This outperforms CNN-based, LSTM-based, GRU-based, MVLR-based model more than two times.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Wang, J., Cao, J.X., Yuan, S., Cheng, M.: Short-term forecasting of natural gas prices by using a novel hybrid method based on a combination of the CEEMDAN-SE-and the PSO-ALS-optimized GRU network. Energy 233 (2021). https://doi.org/10.1016/j.energy.2021.121082
Qiao, W.B., Yang, Z., Kang, Z.Y., Pan, Z.: Short-term natural gas consumption prediction based on Volterra adaptive filter and improved whale optimization algorithm. Eng. Appl. Artif. Intell. 87 (2020). https://doi.org/10.1016/j.engappai.2019.103323
Andelkovic, A.S., Bajatovic, D.: Integration of weather forecast and artificial intelligence for a short-term city-scale natural gas consumption prediction. J. Clean. Prod. 266 (2020). https://doi.org/10.1016/j.jclepro.2020.122096
Li, N., Wang, J.L., Wu, L.F., Bentley, Y.: Predicting monthly natural gas production in China using a novel grey seasonal model with particle swarm optimization. Energy 215 (2021). https://doi.org/10.1016/j.energy.2020.119118
Liu, J.Y., Wang, S.X., Wei, N., Chen, X., Xie, H.Y., Wang, J.: Natural gas consumption forecasting: a discussion on forecasting history and future challenges. J. Nat. Gas Sci. Eng. 90, 20 (2021). https://doi.org/10.1016/j.jngse.2021.103930
Shu, Y.T., Yu, M.F., Yang, O., Liu, J.K., Feng, H.F.: Wireless traffic modeling and prediction using seasonal ARIMA models. IEICE Trans. Commun. E88B(10), 3992–3999 (2005). https://doi.org/10.1093/ietcom/e88-b.10.3992
Wang, Y.Y., Wang, J.Z., Zhao, G., Dong, Y.: Application of residual modification approach in seasonal ARIMA for electricity demand forecasting: a case study of China. Energy Policy 48, 284–294 (2012). https://doi.org/10.1016/j.enpol.2012.05.026
Panapakidis, I.P., Dagoumas, A.S.: Day-ahead natural gas demand forecasting based on the combination of wavelet transform and ANFIS/genetic algorithm/neural network model. Energy 118, 231–245 (2017). https://doi.org/10.1016/j.energy.2016.12.033
Fan, G.F., Wang, A., Hong, W.C.: Combining grey model and self-adapting intelligent grey model with genetic algorithm and annual share changes in natural gas demand forecasting. Energies 11(7) (2018). https://doi.org/10.3390/en11071625
Gaweł, B., Paliński, A.: Long-term natural gas consumption forecasting based on analog method and fuzzy decision tree. Energies 14(16), 4905 (2021)
Fan, D.Y., Sun, H., Yao, J., Zhang, K., Yan, X., Sun, Z.X.: Well production forecasting based on ARIMA-LSTM model considering manual operations. Energy 220, 13 (2021). https://doi.org/10.1016/j.energy.2020.119708
Bai, Y., Li, C.: Daily natural gas consumption forecasting based on a structure-calibrated support vector regression approach. Energy Build. 127, 571–579 (2016). https://doi.org/10.1016/j.enbuild.2016.06.020
Lu, H.F., Azimi, M., Iseley, T.: Short-term load forecasting of urban gas using a hybrid model based on improved fruit fly optimization algorithm and support vector machine. Energy Rep. 5, 666–677 (2019). https://doi.org/10.1016/j.egyr.2019.06.003
Wei, N., Li, C.J., Peng, X.L., Li, Y., Zeng, F.H.: Daily natural gas consumption forecasting via the application of a novel hybrid model. Appl. Energy 250, 358–368 (2019). https://doi.org/10.1016/j.apenergy.2019.05.023
Zhang, T.: Short-term gas load forecasting method based on WT-LMD and GRU. Shanghai Normal University (2019)
Wei, N., Li, C.J., Duan, J.H., Liu, J.Y., Zeng, F.H.: Daily natural gas load forecasting based on a hybrid deep learning model. Energies 12(2) (2019). https://doi.org/10.3390/en12020218
Hai, W., Wang, Y., Song, Y., Wang, H.: Gas load prediction based on ARIMA combined with ConvLSTM. Microelectron. Comput. 39, 62–70 (2022)
Yang, L.B., Nguyen, H., Bui, X.N., Nguyen-Thoi, T., Zhou, J., Huang, J.N.: Prediction of gas yield generated by energy recovery from municipal solid waste using deep neural network and moth-flame optimization algorithm. J. Clean. Prod. 311 (2021). https://doi.org/10.1016/j.jclepro.2021.127672
Leng, J., Xu, X.: Short-term gas load forecasting based on EEMD-MIPCA-LSTM. Comput. Syst. Appl. 29(12), 163–169 (2020)
Xu, J.: Daily gas load forecasting based on SARIMAX+EMD+GRU. Harbin Institute of Technology (2020)
Misra, P., Yadav, A.S.: Improving the classification accuracy using recursive feature elimination with cross-validation. Int. J. Emerg. Technol 11(3), 659–665 (2020)
Fang, G., Xu, P., Liu, W.: Automated Ischemic stroke subtyping based on machine learning approach. IEEE Access 8, 118426–118432 (2020)
de Keijzer, B., de Visser, P., Romillo, V.G., et al.: Forecasting residential gas consumption with machine learning algorithms on weather data. In: E3S Web of Conferences, vol. 111, p. 05019. EDP Sciences (2019)
Acknowledgments
The authors would like to respect and thank all reviewers for their constructive and helpful review. This research was funded by National Natural Science Foundation of China (62106136, 61902231), Natural Science Foundation of Guangdong Province (2019A1515010943), The Basic and Applied Basic Research of Colleges and Universities in Guangdong Province (Special Projects in Artificial Intelligence) (2019KZDZX1030), 2020 Li Ka Shing Foundation Cross-Disciplinary Research Grant (2020LKSFG04D), The college students' science and technology innovation project (Shantou University).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Li, J. et al. (2022). Natural Gas Consumption Forecasting Based on KNN-REFCV-MA-DNN Model. In: Li, K., Liu, Y., Wang, W. (eds) Exploration of Novel Intelligent Optimization Algorithms. ISICA 2021. Communications in Computer and Information Science, vol 1590. Springer, Singapore. https://doi.org/10.1007/978-981-19-4109-2_22
Download citation
DOI: https://doi.org/10.1007/978-981-19-4109-2_22
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-4108-5
Online ISBN: 978-981-19-4109-2
eBook Packages: Computer ScienceComputer Science (R0)