SCI和EI收录∣中国化工学会会刊

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

• • 上一篇    下一篇

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 Gao1,4, Zaoxiao Zhang3   

  1. 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 Gao1,4, Zaoxiao Zhang3   

  1. 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: 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