A new method to forecast multi-time scale load of natural gas based on augmentation data-machine learning model

doi:10.1016/j.cjche.2021.11.023

中国化学工程学报 ›› 2022, Vol. 48 ›› Issue (8): 166-175.DOI: 10.1016/j.cjche.2021.11.023

A new method to forecast multi-time scale load of natural gas based on augmentation data-machine learning model

Denglong Ma¹, Ruitao Wu¹, Zekang Li¹, Kang Cen², Jianmin Gao^1,4, Zaoxiao Zhang³

1. School of Mechanical Engineering, Xi’an Jiaotong University, Xi’an 710049, China;
2. School of Civil Engineering and Architecture, Southwest Petroleum University, Chengdu 610500, China;
3. School of Chemical Engineering and Technology, Xi’an Jiaotong University, Xi’an 710049, China;
4. State Key Laboratory for Manufacturing System Engineering, Xi’an Jiaotong University, Xi’an 710049, China

收稿日期:2021-07-27 修回日期:2021-11-11 出版日期:2022-08-28 发布日期:2022-09-30
通讯作者: Denglong Ma,E-mail:denglong.ma@xjtu.edu.cn
基金资助:
Financial support was provided by the National Natural Science Foundation of China (21808181), China Postdoctoral Science Foundation (2019M653651, 2021T140544), Basic research project of natural science in Shaanxi province (2020JM-021).

A new method to forecast multi-time scale load of natural gas based on augmentation data-machine learning model

Denglong Ma¹, Ruitao Wu¹, Zekang Li¹, Kang Cen², Jianmin Gao^1,4, Zaoxiao Zhang³

1. School of Mechanical Engineering, Xi’an Jiaotong University, Xi’an 710049, China;
2. School of Civil Engineering and Architecture, Southwest Petroleum University, Chengdu 610500, China;
3. School of Chemical Engineering and Technology, Xi’an Jiaotong University, Xi’an 710049, China;
4. State Key Laboratory for Manufacturing System Engineering, Xi’an Jiaotong University, Xi’an 710049, China

Received:2021-07-27 Revised:2021-11-11 Online:2022-08-28 Published:2022-09-30
Contact: Denglong Ma,E-mail:denglong.ma@xjtu.edu.cn
Supported by:
Financial support was provided by the National Natural Science Foundation of China (21808181), China Postdoctoral Science Foundation (2019M653651, 2021T140544), Basic research project of natural science in Shaanxi province (2020JM-021).

摘要/Abstract

摘要： Gas load forecasting is important for the economic and reliable operation of the city gas transmission and distribution system. In this paper, a nonlinear autoregressive model (NARX) with exogenous inputs, support vector machine (SVM), Gaussian process regression (GPR) and ensemble tree model (ETREE) were used to predict and compare the gas load based on the gas load data in a certain region for past 3?years. The results showed that the prediction errors for most of days were higher than 10%. Further, simulation data were generated by considering the gas load variation trend, which was then combined with historical data to form the augmentation data set to train the model. The test results indicated that the prediction error of daily gas load in one year reduced to below 7% with a machine learning prediction method based on augmentation data. In addition, the model based on augmentation data set still performed better than original data in predicting the monthly gas load in last year as well as daily gas load in last month and week. Therefore, the method based on augmentation data proposed in this paper is a potentially good tool to forecast natural gas load.

关键词: Natural gas, Machine learning, Prediction, Neural network, Augmentation data

Abstract: Gas load forecasting is important for the economic and reliable operation of the city gas transmission and distribution system. In this paper, a nonlinear autoregressive model (NARX) with exogenous inputs, support vector machine (SVM), Gaussian process regression (GPR) and ensemble tree model (ETREE) were used to predict and compare the gas load based on the gas load data in a certain region for past 3?years. The results showed that the prediction errors for most of days were higher than 10%. Further, simulation data were generated by considering the gas load variation trend, which was then combined with historical data to form the augmentation data set to train the model. The test results indicated that the prediction error of daily gas load in one year reduced to below 7% with a machine learning prediction method based on augmentation data. In addition, the model based on augmentation data set still performed better than original data in predicting the monthly gas load in last year as well as daily gas load in last month and week. Therefore, the method based on augmentation data proposed in this paper is a potentially good tool to forecast natural gas load.

Key words: Natural gas, Machine learning, Prediction, Neural network, Augmentation data

Denglong Ma, Ruitao Wu, Zekang Li, Kang Cen, Jianmin Gao, Zaoxiao Zhang. A new method to forecast multi-time scale load of natural gas based on augmentation data-machine learning model[J]. 中国化学工程学报, 2022, 48(8): 166-175.

参考文献

[1] M. Doroodi, A. Mokhtar, Comparison of time series approaches for prediction of energy consumption focusing on greenhouse gases emission in Iran, Int. J. Energy Sect. Manag. 13 (3) (2019) 486–499
[2] M. Akpinar, N. Yumusak, Year ahead demand forecast of City natural gas using seasonal time series methods, Energies 9 (9) (2016) 727
[3] S. Ding, A novel self-adapting intelligent grey model for forecasting China's natural-gas demand, Energy 162 (2018) 393–407
[4] 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
[5] V. Bianco, F. Scarpa, L.A. Tagliafico, Scenario analysis of nonresidential natural gas consumption in Italy, Appl. Energy 113 (2014) 392–403
[6] J. Szoplik, Forecasting of natural gas consumption with artificial neural networks, Energy 85 (2015) 208–220
[7] Z. Xiao, S.J. Ye, B. Zhong, C.X. Sun, BP neural network with rough set for short term load forecasting, Expert. Syst. Appl. 36 (1) (2009) 273–279
[8] A. Paul, S. Bhowmik, R. Panua, D. Debroy, Artificial neural network-based prediction of performances-exhaust emissions of diesohol piloted dual fuel diesel engine under varying compressed natural gas flowrates, J. Energy Resour. Technol. 140 (11) (2018) 112201
[9] A. Azari, M. Shariaty-Niassar, M. Alborzi, Short-term and mediumterm gas demand load forecasting by neural networks, Iran J. Chem. Chem. Eng.-Int. Engl. Ed. 31(4)(2012) 77–84
[10] D. Cinar, G. Kayakutlu, T. Daim, Development of future energy scenarios with intelligent algorithms: Case of hydro in Turkey, Energy 35 (4) (2010) 1724–1729
[11] Z.R. Jiao, P.F. Hu, H.F. Xu, Q.S. Wang, Machine learning and deep learning in chemical health and safety: A systematic review of techniques and applications, ACS Chem. Heal. Saf. 27 (6) (2020) 316–334
[12] H. Aras, N. Aras, Forecasting residential natural gas demand, Energy Sources 26 (5) (2004) 463–472
[13] L. Ferbar Tratar, E. Strm?nik, The comparison of Holt-Winters method and Multiple regression method: A case study, Energy 109 (2016) 266–276
[14] P. Poto?nik, E. Govekar, Applied short-term forecasting for the Slovenian natural gas market, 2016 13th International Conference on the European Energy Market (EEM). Porto, Portugal. IEEE, (2016) 1–5
[15] V.?. Ediger, S. Akar, ARIMA forecasting of primary energy demand by fuel in Turkey, Energy Policy 35 (3) (2007) 1701–1708
[16] W.L. Jiao, Y.L. Qin, L.B. Zhao, Research on urban gas load forecasting system, Natural Gas Industry, 25(1)(2005) 155-157
[17] A. Khotanzad, H. Elragal, T.L. Lu, Combination of artificial neural-network forecasters for prediction of natural gas consumption, IEEE Trans. Neural Networks 11 (2) (2000) 464–473
[18] R. Kizilaslan, B. Karlik, Comparison neural networks models for short term forecasting of natural gas consumption in Istanbul, 2008 First International Conference on the Applications of Digital Information and Web Technologies (ICADIWT). August 4-6, 2008, Ostrava, Czech Republic. IEEE (2008) 448–453
[19] K. Kato, M. Sakawa, K. Ishimaru, S. Ushiro, T. Shibano, Heat load prediction through recurrent neural network in district heating and cooling systems, in: 2008 IEEE International Conference on Systems, Man and Cybernetics (SMC), Singapore, Singapore, 2008, pp. 1401–1406.
[20] Y. Xie, M. Li, Research on prediction model of natural gas consumption based on Grey modeling optimized by genetic algorithm, in: 2009 IITA International Conference on Control, Automation and Systems Engineering (CASE), Zhangjiajie, China, 2009, pp. 335–337
[21] H.W. Ma, Y.H. Wu, Grey predictive on natural gas consumption and production in China, 2009 Second Pacific-Asia Conference on Web Mining and Web-based Application. June 6-7, 2009, Wuhan, China. IEEE, (2009) 91–94
[22] S. Barak, S.S. Sadegh, Forecasting energy consumption using ensemble ARIMA-ANFIS hybrid algorithm, Int. J. Electr. Power Energy Syst. 82 (2016) 92–104
[23] A. Krizhevsky, I. Sutskever, G.E. Hinton, ImageNet classification with deep convolutional neural networks, Commun. ACM 60 (6) (2017) 84–90
[24] J. Lemley, S. Bazrafkan, P. Corcoran, Smart augmentation learning an optimal data augmentation strategy, IEEE Access 5 (2017) 5858–5869
[25] S. Liang, M. Liu, Z.Y. Wang, T.X. Zhang, Infrared spectrum image inversion method for augmenting data sets, Proc SPIE 11428, MIPPR 2019: Multispectral Image Acquisition, Processing, and Analysis 1142 (2020) 162–168
[26] D.L. Ma, J.M. Gao, Z.Y. Gao, H.Q. Jiang, Z.X. Zhang, J.T. Xie, Gas leakage recognition for CO2 geological sequestration based on the time series neural network, Chin. J. Chem. Eng. 28 (9) (2020) 2343–2357
[27] R. Panja, N.R. Pal, MS-SVM: Minimally spanned support vector machine, Appl. Soft Comput. 64 (2018) 356–365
[28] P.F. Pai, W.C. Hong, Support vector machines with simulated annealing algorithms in electricity load forecasting, Energy Convers. Manag. 46 (17) (2005) 2669–2688
[29] K.X. Bi, T. Qiu, An intelligent SVM modeling process for crude oil properties prediction based on a hybrid GA-PSO method, Chin. J. Chem. Eng. 27 (8) (2019) 1888–1894
[30] 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
[31] C.L. Mei, Y. Su, G.H. Liu, Y.H. Ding, Z.L. Liao, Dynamic soft sensor development based on Gaussian mixture regression for fermentation processes, Chin. J. Chem. Eng. 25 (1) (2017) 116–122
[32] C. Zhang, H.K. Wei, X. Zhao, T.H. Liu, K.J. Zhang, A Gaussian process regression based hybrid approach for short-term wind speed prediction, Energy Convers. Manag. 126 (2016) 1084–1092
[33] J.L. Liu, C. Ulishney, C.E. Dumitrescu, Random forest machine learning model for predicting combustion feedback information of a natural gas spark ignition engine, J. Energy Resour. Technol. 143 (1) (2021) 012301

A new method to forecast multi-time scale load of natural gas based on augmentation data-machine learning model

A new method to forecast multi-time scale load of natural gas based on augmentation data-machine learning model

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]	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.
[2]	Li Xia, Yule Pan, Tingting Zhao, Xiaoyan Sun, Shaohui Tao, Yushi Chen, Shuguang Xiang. Estimating heat capacities of liquid organic compounds based on elements and chemical bonds contribution[J]. 中国化学工程学报, 2023, 57(5): 30-38.
[3]	Shanwei Xiong, Li Zhou, Yiyang Dai, Xu Ji. Attention-based long short-term memory fully convolutional network for chemical process fault diagnosis[J]. 中国化学工程学报, 2023, 56(4): 1-14.
[4]	Haoshan Duan, Xi Meng, Jian Tang, Junfei Qiao. Prediction of NO_x concentration using modular long short-term memory neural network for municipal solid waste incineration[J]. 中国化学工程学报, 2023, 56(4): 46-57.
[5]	Yiming Bai, Shuaiyu Xiang, Feifan Cheng, Jinsong Zhao. A dynamic-inner LSTM prediction method for key alarm variables forecasting in chemical process[J]. 中国化学工程学报, 2023, 55(3): 266-276.
[6]	Kun Ren, Zheng Jiao, Xiaolong Wu, Honggui Han. Multivariable identification of membrane fouling based on compacted cascade neural network[J]. 中国化学工程学报, 2023, 53(1): 37-45.
[7]	Ping Zhang, Chao Gong, Tao Zhou, Peng Du, Jieyu Song, Mengyang Shi, Xuerui Wang, Xuehong Gu. Helium extraction from natural gas using DD3R zeolite membranes[J]. 中国化学工程学报, 2022, 49(9): 122-129.
[8]	Jia Ren, Zengqiang Chen, Mingwei Sun, Qinglin Sun, Zenghui Wang. Proportion integral-type active disturbance rejection generalized predictive control for distillation process based on grey wolf optimization parameter tuning[J]. 中国化学工程学报, 2022, 49(9): 234-244.
[9]	Zhouxin Chang, Feng Yu, Zhisong Liu, Zijun Wang, Jiangbing Li, Bin Dai, Jinli Zhang. Ni-Al mixed metal oxide with rich oxygen vacancies: CO methanation performance and density functional theory study[J]. 中国化学工程学报, 2022, 46(6): 73-83.
[10]	Tong Qin, Zhenhao Xi, Ling Zhao, Weikang Yuan. Monte Carlo simulation of sequential structure control of AN-MA-IA aqueous copolymerization by different operation modes[J]. 中国化学工程学报, 2022, 46(6): 231-242.
[11]	Pengtao Guo, Miao Chang, Tongan Yan, Yuxiao Li, Dahuan Liu. A pillared-layer metal-organic framework for efficient separation of C₃H₈/C₂H₆/CH₄ in natural gas[J]. 中国化学工程学报, 2022, 42(2): 10-16.
[12]	Xionghui Liu, Jianfeng Du, Yu Ye, Yuchuan Liu, Shun Wang, Xianyu Meng, Xiaowei Song, Zhiqiang Liang, Wenfu Yan. Boosting selective C₂H₂/CH₄, C₂H₄/CH₄ and CO₂/CH₄ adsorption performance via 1,2,3-triazole functionalized triazine-based porous organic polymers[J]. 中国化学工程学报, 2022, 42(2): 64-72.
[13]	Xinran Zhang, Hua Shang, Jiangfeng Yang, Libo Li, Jinping Li. Nitrogen rejection from low quality natural gas by pressure swing adsorption experiments and simulation using dynamic adsorption isotherms[J]. 中国化学工程学报, 2022, 42(2): 120-129.
[14]	Jun Zhang, Qin Wang, Weifeng Shen. Hyper-parameter optimization of multiple machine learning algorithms for molecular property prediction using hyperopt library[J]. 中国化学工程学报, 2022, 52(12): 115-125.
[15]	Ruoshi Qin, Jinsong Zhao. Adaptive multiscale convolutional neural network model for chemical process fault diagnosis[J]. 中国化学工程学报, 2022, 50(10): 398-411.