Town gas daily load forecasting based on machine learning combinatorial algorithms: A case study in North China

doi:10.1016/j.cjche.2024.07.011

中国化学工程学报 ›› 2024, Vol. 75 ›› Issue (11): 239-252.DOI: 10.1016/j.cjche.2024.07.011

Town gas daily load forecasting based on machine learning combinatorial algorithms: A case study in North China

Peng Xu^1,2, Yuwei Song^1,2, Jingbo Du³, Feilong Zhang⁴

1. Beijing Key Lab of Heating, Gas Supply, Ventilating and Air Conditioning Engineering, Beijing University of Civil Engineering and Architecture, Beijing 100044, China;
2. Research Centre for Gas Engineering, Beijing University of Civil Engineering and Architecture, Beijing 100044, China;
3. Beijing Gas Group Co. LTD, Beijing 100035, China;
4. China Construction Eighth Engineering Division Co. Ltd., Zhengzhou 450000, China

收稿日期:2024-02-26 修回日期:2024-06-12 接受日期:2024-07-09 出版日期:2024-11-28 发布日期:2024-08-21
通讯作者: Peng Xu,E-mail:xupeng@bucea.edu.cn
基金资助:
The authors acknowledge the financial support from Science and Technology Major Project of Inner Mongolia Autonomous Region of China (2021ZD0038).

Town gas daily load forecasting based on machine learning combinatorial algorithms: A case study in North China

Peng Xu^1,2, Yuwei Song^1,2, Jingbo Du³, Feilong Zhang⁴

1. Beijing Key Lab of Heating, Gas Supply, Ventilating and Air Conditioning Engineering, Beijing University of Civil Engineering and Architecture, Beijing 100044, China;
2. Research Centre for Gas Engineering, Beijing University of Civil Engineering and Architecture, Beijing 100044, China;
3. Beijing Gas Group Co. LTD, Beijing 100035, China;
4. China Construction Eighth Engineering Division Co. Ltd., Zhengzhou 450000, China

Received:2024-02-26 Revised:2024-06-12 Accepted:2024-07-09 Online:2024-11-28 Published:2024-08-21
Contact: Peng Xu,E-mail:xupeng@bucea.edu.cn
Supported by:
The authors acknowledge the financial support from Science and Technology Major Project of Inner Mongolia Autonomous Region of China (2021ZD0038).

摘要/Abstract

摘要： Timely and accurate gas load forecasting is critical for optimal scheduling under tight winter gas supply conditions. Under the background of the implementation of “coal-to-gas” for winter heating in rural areas of North China and the sufficient field research, this paper proposes a correction algorithm for daily average temperature based on the cumulative effect of temperature and a set of combined forecasting models for gas load forecasting based on machine learning and introduces its application through a detailed case study. In order to solve the problems of forecasting performance degradation and complexity increase caused by too many influencing factors, a combined forecasting model back-propagation-improved complete ensemble empirical mode decomposition with adaptive-noise-gated recurrent unit based on residual sequence analysis is proposed. Back propagation (BP) neural network is used to analyze the main influencing factors, so that the secondary influencing factors are reflected in the residual sequence generated by the forecasting. After decomposition, reconstruction, and re-forecast, the mean absolute percentage error (MAPE) of the combined models for the daily gas load in the case study has been controlled under 1.9%, which is significantly improved compared with each single algorithm. The forecasting error before and after the temperature correction are also compared. It is found that the MAPE with the temperature correction is reduced by 1.7%, which reflects the effectiveness of the temperature correction to eliminate the impact of temperature cumulative effect and its contribution to the improvement of the forecasting accuracy for the combined forecasting models.

关键词: Natural gas, Prediction, Neural networks, Cumulative effect of temperature, Residual series analysis, ICEEMDAN algorithm

Abstract: Timely and accurate gas load forecasting is critical for optimal scheduling under tight winter gas supply conditions. Under the background of the implementation of “coal-to-gas” for winter heating in rural areas of North China and the sufficient field research, this paper proposes a correction algorithm for daily average temperature based on the cumulative effect of temperature and a set of combined forecasting models for gas load forecasting based on machine learning and introduces its application through a detailed case study. In order to solve the problems of forecasting performance degradation and complexity increase caused by too many influencing factors, a combined forecasting model back-propagation-improved complete ensemble empirical mode decomposition with adaptive-noise-gated recurrent unit based on residual sequence analysis is proposed. Back propagation (BP) neural network is used to analyze the main influencing factors, so that the secondary influencing factors are reflected in the residual sequence generated by the forecasting. After decomposition, reconstruction, and re-forecast, the mean absolute percentage error (MAPE) of the combined models for the daily gas load in the case study has been controlled under 1.9%, which is significantly improved compared with each single algorithm. The forecasting error before and after the temperature correction are also compared. It is found that the MAPE with the temperature correction is reduced by 1.7%, which reflects the effectiveness of the temperature correction to eliminate the impact of temperature cumulative effect and its contribution to the improvement of the forecasting accuracy for the combined forecasting models.

Key words: Natural gas, Prediction, Neural networks, Cumulative effect of temperature, Residual series analysis, ICEEMDAN algorithm

Peng Xu, Yuwei Song, Jingbo Du, Feilong Zhang. Town gas daily load forecasting based on machine learning combinatorial algorithms: A case study in North China[J]. 中国化学工程学报, 2024, 75(11): 239-252.

Peng Xu, Yuwei Song, Jingbo Du, Feilong Zhang. Town gas daily load forecasting based on machine learning combinatorial algorithms: A case study in North China[J]. Chinese Journal of Chemical Engineering, 2024, 75(11): 239-252.

参考文献

[1] A.L. Jia, G. Cheng, W.Y. Chen, Y.L. Li, Forecast of natural gas supply and demand in China under the background of “Dual Carbon Targets”, Petrol. Explor. Dev. 50 (2) (2023) 492-504.
[2] G.L. Luo, S.S. Liu, X.H. Yan, Y.W. Guo, Institutional constraints to China’s low carbon transition: A case study of China’s coal-to-gas program, Struct. Change Econ. Dyn. 57 (2021) 121-135.
[3] Z.Zhou, Research on daily gas load combination forecast model of towns, Master Thesis, Harbin Institute of Technology, China, 2019. (in Chinese).
[4] Y.S. Miao, Research on the city gas load forecasting, PhD Thesis, Harbin Institute of Technology, China, 2006. (in Chinese).
[5] T. Catalina, V. Iordache, B. Caracaleanu, Multiple regression model for fast prediction of the heating energy demand, Energy Build. 57 (2013) 302-312.
[6] M.K. Hubbert, Energy from fossil fuels, Science 109 (2823) (1949) 103-109.
[7] M.K. Hubbert, Nuclear energy and the fossil fuels, Shell Development Company, Exploration and Production Research Division, Houston, 1956.
[8] S.M. Tinic, B.M. Harnden, C.T.L. Janssen, Estimation of rural demand for natural gas, Manag. Sci. 20 (4-part-ii) (1973) 604-616.
[9] P.J. Werbos, Generalization of backpropagation with application to a recurrent gas market model, Neural Netw. 1 (4) (1988) 339-356.
[10] F.B. Gorucu, Artificial neural network modeling for forecasting gas consumption, Energy Sources 26 (3) (2004) 299-307.
[11] G.D. Merkel, R.J. Povinelli, R.H. Brown, Short-term load forecasting of natural gas with deep neural network regression, Energies 11 (8) (2018) 2008.
[12] A. Anagnostis, E. Papageorgiou, D. Bochtis, Application of artificial neural networks for natural gas consumption forecasting, Sustainability 12 (16) (2020) 6409.
[13] Y.Q. Deng, X. Ma, P. Zhang, Y.B. Cai, Multi-step ahead forecasting of daily urban gas load in Chengdu using a Tanimoto kernel-based NAR model and Whale optimization, Energy 260 (2022) 124993.
[14] N. Wei, C.J. Li, C. Li, H.Y. Xie, Z.W. Du, Q.S. Zhang, F.H. Zeng, Short-term forecasting of natural gas consumption using factor selection algorithm and optimized support vector regression, J. Energy Resour. Technol. 141 (3) (2019) 032701.
[15] S.B. Peng, R.L. Chen, B. Yu, M. Xiang, X.G. Lin, E.B. Liu, Daily natural gas load forecasting based on the combination of long short term memory, local mean decomposition, and wavelet threshold denoising algorithm, J. Nat. Gas Sci. Eng. 95 (2021) 104175.
[16] H.F. Lu, M. Azimi, T. Iseley, 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 (2019) 666-677.
[17] Y. Chen, X.Q. Xu, T. Koch, Day-ahead high-resolution forecasting of natural gas demand and supply in Germany with a hybrid model, Appl. Energy 262 (2020) 114486.
[18] I.E. Livieris, E. Pintelas, N. Kiriakidou, S. Stavroyiannis, An advanced deep learning model for short-term forecasting US natural gas price and movement, In: IFIP International Conference on Articial Intelligence Applications and Innovations, Springer, 2020.
[19] Z.X. Wang, L.Y. He, Y.F. Zhao, Forecasting the seasonal natural gas consumption in the US using a gray model with dummy variables, Appl. Soft Comput. 113 (2021) 108002.
[20] N. Li, J.L. Wang, L.F. Wu, Y. Bentley, Predicting monthly natural gas production in China using a novel grey seasonal model with particle swarm optimization, Energy 215 (2021) 119118.
[21] G.F. Fan, A. Wang, W.C. Hong, 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) 1625.
[22] N. Wei, L.H. Yin, C. Li, C.J. Li, C. Chan, F.H. Zeng, Forecasting the daily natural gas consumption with an accurate white-box model, Energy 232 (2021) 121036.
[23] Y.H. Tang, Natural gas load forecasting based on improved genetic algorithm and BP neural network, 2022 IEEE 5th International Conference on Knowledge Innovation and Invention (ICKII). July 22-24, 2022, Hualien, Taiwan, China. IEEE, (2022) 164-168.
[24] I.P. Panapakidis, A.S. Dagoumas, Day-ahead natural gas demand forecasting based on the combination of wavelet transform and ANFIS/genetic algorithm/neural network model, Energy 118 (2017) 231-245.
[25] H. Su, E. Zio, J.J. Zhang, M.J. Xu, X.Y. Li, Z.J. Zhang, A hybrid hourly natural gas demand forecasting method based on the integration of wavelet transform and enhanced Deep-RNN model, Energy 178 (2019) 585-597.
[26] T. Sujjaviriyasup, A new class of MODWT-SVM-DE hybrid model emphasizing on simplification structure in data pre-processing: A case study of annual electricity consumptions, Appl. Soft Comput. 54 (2017) 150-163.
[27] S. Jiang, X.T. Zhao, N. Li, Predicting the monthly consumption and production of natural gas in the USA by using a new hybrid forecasting model based on two-layer decomposition, Environ. Sci. Pollut. Res. Int. 30 (14) (2023) 40799-40824.
[28] H.T. Li, F. Jin, S.L. Sun, Y.W. Li, A new secondary decomposition ensemble learning approach for carbon price forecasting, Knowl. Based Syst. 214 (2021) 106686.
[29] T.Y. Li, Z.J. Qian, W. Deng, D.Z. Zhang, H.H. Lu, S.H. Wang, Forecasting crude oil prices based on variational mode decomposition and random sparse Bayesian learning, Appl. Soft Comput. 113 (2021) 108032.
[30] W.B. Qiao, K. Huang, M. Azimi, S. Han, A novel hybrid prediction model for hourly gas consumption in supply side based on improved whale optimization algorithm and relevance vector machine, IEEE Access 7 (2019) 88218-88230.
[31] F.Y. Li, H.F. Zheng, X.M. Li, F. Yang, Day-ahead city natural gas load forecasting based on decomposition-fusion technique and diversified ensemble learning model, Appl. Energy 303 (2021) 117623.
[32] L. Chen, W. Wang, Y. Yang, CELOF: Effective and fast memory efficient local outlier detection in high-dimensional data streams, Appl. Soft Comput. 102 (2021) 107079.
[33] O. Alghushairy, R. Alsini, T. Soule, X.G. Ma, A review of local outlier factor algorithms for outlier detection in big data streams, Big Data Cogn. Comput. 5 (1) (2020) 1.
[34] H.S. Hippert, C.E. Pedreira, Estimating temperature profiles for short-term load forecasting: Neural networks compared to linear models, IEE Proc., Gener. Transm. Distrib. 151 (4) (2004) 543.
[35] X. Duan, Z.Q. Wang, J. Ma, L. Han, X.L. Zhao, J. Gong, Analysis of relationship between natural gas load and air temperature in heating season in Hebei Province, Chemical Engineering of Oil & Gas 48 (5) (2019) 42-48. (in Chinese).
[36] M. Wang, Z.X. Yu, Y. Chen, X.G. Yang, J. Zhou, Short-term load forecasting considering improved cumulative effect of hourly temperature, Electr. Power Syst. Res. 205 (2022) 107746.
[37] D.E. Rumelhart, J.L. McClelland, Parallel distributed processing, MIT press, 1986.
[38] J. Li, J.H. Cheng, J.Y. Shi, F. Huang, Brief introduction of back propagation (BP) neural network algorithm and its improvement. Advances in Intelligent and Soft Computing. Springer Berlin Heidelberg, (2012), pp 53-558.
[39] N.E. Huang, Z. Shen, S.R. Long, M.C. Wu, H.H. Shih, Q.A. Zheng, N.C. Yen, C.C. Tung, H.H. Liu, The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis, Proc. R. Soc. Lond. A 454 (1971) (1998) 903-995.
[40] C.X. Ma, X.T. Huang, K. Wang, Y.P. Zhao, Prediction of remaining parking spaces based on EMD-LSTM-BiLSTM neural network, traffic transport, http://kns.cnki.net/kcms/detail/61.1494.U.20230330.1412.002.html. (in Chinese)
[41] P. Lv, Y.T. Shu, J. Xu, Q.J. Wu, Modal decomposition-based hybrid model for stock index prediction, Expert Syst. Appl. 202 (2022) 117252.
[42] M.E. Torres, M.A. Colominas, G. Schlotthauer, P. Flandrin, A complete ensemble empirical mode decomposition with adaptive noise, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). May 22-27, 2011, Prague, Czech Republic. IEEE, (2011) 4144-4147.
[43] M.A. Colominas, G. Schlotthauer, M.E. Torres, Improved complete ensemble EMD: A suitable tool for biomedical signal processing, Biomed. Signal Process. Contr. 14 (2014) 19-29.

Town gas daily load forecasting based on machine learning combinatorial algorithms: A case study in North China

Town gas daily load forecasting based on machine learning combinatorial algorithms: A case study in North China

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	Can Ding, Minglei Yang, Yunmeng Zhao, Wenli Du. Graph convolutional network for axial concentration profiles prediction in simulated moving bed[J]. 中国化学工程学报, 2024, 73(9): 270-280.
[2]	Zongyu Yao, Qingchao Jiang, Xingsheng Gu. Distributed process monitoring based on Kantorovich distance-multiblock variational autoencoder and Bayesian inference[J]. 中国化学工程学报, 2024, 73(9): 311-323.
[3]	Baowei Niu, Yanjie Yi, Yuwen Wei, Fuzhen Zhang, Lili Wang, Li Xia, Xiaoyan Sun, Shuguang Xiang. Phase equilibrium data prediction and process optimizationin butadiene extraction process[J]. 中国化学工程学报, 2024, 71(7): 1-12.
[4]	Zhiwei Zhu, Minglei Yang, Wangli He, Renchu He, Yunmeng Zhao, Feng Qian. A deep reinforcement learning approach to gasoline blending real-time optimization under uncertainty[J]. 中国化学工程学报, 2024, 71(7): 183-192.
[5]	Cheng Yang, Chao Jiang, Guo Yu, Jun Li, Cuimei Bo. Transferable adversarial slow feature extraction network for few-shot quality prediction in coal-to-ethylene glycol process[J]. 中国化学工程学报, 2024, 71(7): 258-271.
[6]	Bohui Shi, Shangfei Song, Yuchuan Chen, Shunkang Fu, Lihao Liu, Xinyao Yang, Haihao Wu, Guangjin Chen, Jing Gong. Rheological study of methane gas hydrates in the presence of micron-sized sand particles[J]. 中国化学工程学报, 2024, 70(6): 149-161.
[7]	Feng Wang, Haoran Li, Zhenghui Zhang, Yan Bai, Hong Yin, Jing Bian. A method for establishing a bearing residual life prediction model for process enhancement equipment based on rotor imbalance response analysis[J]. 中国化学工程学报, 2024, 66(2): 203-215.
[8]	Qianlin Wang, Jiaqi Han, Feng Chen, Xin Zhang, Cheng Yun, Zhan Dou, Tingjun Yan, Guoan Yang. Real-time risk prediction of chemical processes based on attention-based Bi-LSTM[J]. 中国化学工程学报, 2024, 75(11): 131-141.
[9]	Jianan Fan, Xianggang Zhang, Xia Jiang, Zhenghao Yang, Lingling Xie, Liwang Wang, Liang Ma, Hualin Wang, Yulong Chang. Cyclone-coalescence separation technology for enhanced droplet removal in natural gas purification process[J]. 中国化学工程学报, 2024, 75(11): 191-203.
[10]	Jiawei Wu, Zhihong Chen, Zhongwen Si, Xiaoling Lou, Junxian Yun. Radial basis function neural network and overlay sampling uniform design toward polylactic acid molecular weight prediction[J]. 中国化学工程学报, 2024, 75(11): 214-221.
[11]	Chenyang Xu, Lijuan Guo, Kang Zhou, Hai Yu, Chaoliang Wei, Fengqi Fan, Lei Zhang. RSscore: Reaction superiority learned from reaction mapping hypergraph[J]. 中国化学工程学报, 2024, 74(10): 203-215.
[12]	Zeeshan Ikram Butt, Iftikhar Ahmad, Muhammad Shoaib, Syed Ibrar Hussain, Hira Ilyas, Muhammad Asif Zahoor Raja. Stochastic neuro-swarming intelligence paradigm for the analysis of magneto-hydrodynamic Prandtl-Eyring fluid flow with diffusive magnetic layers effect over an elongated surface[J]. 中国化学工程学报, 2024, 74(10): 295-311.
[13]	Jian Long, Kai Deng, Renchu He. Closed-loop scheduling optimization strategy based on particle swarm optimization with niche technology and soft sensor method of attributes-applied to gasoline blending process[J]. 中国化学工程学报, 2023, 61(9): 43-57.
[14]	Xi Luo, Xiayuan Feng, Xu Ji, Yagu Dang, Li Zhou, Kexin Bi, Yiyang Dai. Extraction and analysis of risk factors from Chinese chemical accident reports[J]. 中国化学工程学报, 2023, 61(9): 68-81.
[15]	Yaran Bu, Changchun Wu, Lili Zuo, Qian Chen. The calculation and optimal allocation of transmission capacity in natural gas networks with MINLP models[J]. 中国化学工程学报, 2023, 59(7): 251-261.