A Hybrid Model Based on Grey Wolf Optimizer and Lagrangian Support Vector Regression for European Natural Gas Consumption Forecasting

Kai Tang *

School of Science, Southwest University of Science and Technology, Mianyang 621010, China.

Jiahui Li

School of Science, Southwest University of Science and Technology, Mianyang 621010, China.

MengTing Yang

School of Science, Southwest University of Science and Technology, Mianyang 621010, China.

Xinyi Yang

School of Science, Southwest University of Science and Technology, Mianyang 621010, China.

Junxiong Feng

School of Science, Southwest University of Science and Technology, Mianyang 621010, China.

Suhang Liu

School of Science, Southwest University of Science and Technology, Mianyang 621010, China.

*Author to whom correspondence should be addressed.


Abstract

Natural gas plays an important role in industry as a clean energy, with the intensification of the Russia-Ukraine war, there is a large-scale energy shortage in Europe, and the natural gas supply in Europe has a natural gas crisis due to the cut-off of the Nord Stream No.1 pipeline. Therefore, it is necessary to accurately predict the consumption of natural gas. In order to fulfill this requirement, this paper uses the Lagrangian Support Vector Regression model with Sorensen kernel based on the Nonlinear Auto-Regressive model and Grey Wolf Optimizer for 5-step forecasting of monthly natural gas consumption in all European countries. Under three time lags, comparing the 5-step predict results of GWO-LSVR with SVR, RF, LightGBM, XGBoost, and MLP, those five models’ hyperparameters also optimized by GWO, it found that GWO-LSVR has smallest MAPE in almost all cases, and the numerical results of MAPE generated by GWO-LSVR is from 5.844% to 11.622%, the smaller the forecasting step size, the better the effect. Moreover, compares the difference of GWO and WOA, it is found that GWO can obtained better model hyperparameters and smaller MAPE results. To sum up, the proposed GWO-LSVR model has strong generalization performance and robustness, and is a reliable natural gas consumption prediction model.

Keywords: Lagrangian support vector regression, grey wolf optimizer, nonlinear auto-regressive, kernel learning, natural gas consumption in Europe


How to Cite

Tang , K., Li , J., Yang , M., Yang , X., Feng , J., & Liu , S. (2023). A Hybrid Model Based on Grey Wolf Optimizer and Lagrangian Support Vector Regression for European Natural Gas Consumption Forecasting. Journal of Energy Research and Reviews, 13(2), 11–19. https://doi.org/10.9734/jenrr/2023/v13i2258

Downloads

Download data is not yet available.

References

Tang K, Li H, Qian Z. Forecasting study of natural gas consumption by combined models based on LASSO and WOA. ARJOM. 2023 Jan;19(1):23-31.

Yucesan M, Pekel E, Celik E, et al. Forecasting daily natural gas consumption with regression, time series and machine learning based methods[J]. Energy Sources, Part A: Recovery, Utilization, and Environmental Effects. 2021;1-16.

Cihan P. Impact of the COVID-19 lockdowns on electricity and natural gas consumption in the different industrial zones and forecasting consumption amounts: Turkey case study [J]. International Journal of Electrical Power & Energy Systems. 2022;134:107369.

Ma X, Liu Z. Application of a novel time-delayed polynomial grey model to predict the natural gas consumption in China[J]. Journal of Computational and Applied Mathematics. 2017;324:17-24.

Liu C, Wu W Z, Xie W, et al. Forecasting natural gas consumption of China by using a novel fractional grey model with time power term[J]. Energy Reports. 2021;7: 788-797.

Xiong P, Li K, Shu H, et al. Forecast of natural gas consumption in the Asia-Pacific region using a fractional-order incomplete gamma grey model [J]. Energy. 2021;237:121533.

Panek W, Włodek T. Natural Gas Consumption Forecasting Based on the Variability of External Meteorological Factors Using Machine Learning Algorithms [J]. Energies. 2022;15(1): 348.

Singh S, Bansal P, Hosen M, et al. Forecasting annual natural gas consumption in USA: Application of machine learning techniques-ANN and SVM[J]. Resources Policy. 2023;80: 103159.

Yucesan M, Pekel E, Celik E, et al. Forecasting daily natural gas consumption with regression, time series and machine learning based methods[J]. Energy Sources, Part A: Recovery, Utilization, and Environmental Effects. 2021;1-16.

Laib O, Khadir M T, Mihaylova L. Toward efficient energy systems based on natural gas consumption prediction with LSTM Recurrent Neural Networks[J]. Energy, 2019;177:530-542.

Mangasarian O L, Musicant D R. Lagrangian support vector machines[J]. Journal of Machine Learning Research, 2001;1(Mar):161-177.

Balasundaram S. On Lagrangian support vector regression[J]. Expert Systems with Applications. 2010;37(12):8784-8792.

Hripcsak G, Rothschild AS. Agreement, the f-measure, and reliability in information retrieval[J]. Journal of the American Medical Informatics Association. 2005; 12(3):296-298.

Bhattacharya R, Lee C. On geometric ergodicity of nonlinear autoregressive models[J]. Stats & Probability Letters, 1995;22(4):311-315.

Deng Y, Ma X, Zhang P, et al. Multi-step ahead forecasting of daily urban gas load in Chengdu using a Tanimoto kernel-based NAR model and Whale optimization[J]. Energy. 2022;260:124993.

Zhang L, Ma X, Zhang H, et al. Multi-Step ahead natural gas consumption forecasting based on a hybrid model: case studies in The Netherlands and the United Kingdom [J]. Energies. 2022;15(19): 7437.