EMLP: short-term gas load forecasting based on ensemble multilayer perceptron with adaptive weight correction

Fengyong Li; Meng Sun; Fengyong Li; Meng Sun

doi:10.3934/mbe.2021082

Mathematical Biosciences and Engineering

2021, Volume 18, Issue 2: 1590-1608. doi: 10.3934/mbe.2021082

Previous Article Next Article

Research article Special Issues

EMLP: short-term gas load forecasting based on ensemble multilayer perceptron with adaptive weight correction

Fengyong Li ^,,
Meng Sun

College of Computer Science and Technology, Shanghai University of Electric Power, Shanghai 201306, China

Received: 20 October 2020 Accepted: 20 January 2021 Published: 01 February 2021

This paper tackles a recent challenge in smart city that how to improve the accuracy of short-term natural gas load forecasting. Existing works on natural gas forecasting mostly reply on a combined forecasting model by simply integrating several single-forecasting models. However, due to the existence of redundant single-forecasting models, these works may not attain a higher prediction accuracy. To address the problem, we design a new natural gas load forecasting scheme based on ensemble multilayer perceptron (EMLP) with adaptive weight correction. Our method firstly normalizes multi-source data as original data set, which is further segmented by a window model. Then, the abnormal data is removed and subsequently interpolated to form a complete normalized data set. Furthermore, we integrate a series of multilayer perceptron (MLP) network to construct an ensemble forecasting model. An adaptive weight correction function is introduced to dynamically modify the weight of the previous predicted result. Since the correction function can match well the volatility characteristics of load data, the prediction accuracy is significantly improved. Extensive experiments demonstrate that our method outperforms existing state-of-the-art load forecasting schemes in terms of the prediction accuracy and stability.
- load forecasting,
- ensemble learning,
- multilayer perceptron,
- smart city
Citation: Fengyong Li, Meng Sun. EMLP: short-term gas load forecasting based on ensemble multilayer perceptron with adaptive weight correction[J]. Mathematical Biosciences and Engineering, 2021, 18(2): 1590-1608. doi: 10.3934/mbe.2021082

Related Papers:

Abstract

This paper tackles a recent challenge in smart city that how to improve the accuracy of short-term natural gas load forecasting. Existing works on natural gas forecasting mostly reply on a combined forecasting model by simply integrating several single-forecasting models. However, due to the existence of redundant single-forecasting models, these works may not attain a higher prediction accuracy. To address the problem, we design a new natural gas load forecasting scheme based on ensemble multilayer perceptron (EMLP) with adaptive weight correction. Our method firstly normalizes multi-source data as original data set, which is further segmented by a window model. Then, the abnormal data is removed and subsequently interpolated to form a complete normalized data set. Furthermore, we integrate a series of multilayer perceptron (MLP) network to construct an ensemble forecasting model. An adaptive weight correction function is introduced to dynamically modify the weight of the previous predicted result. Since the correction function can match well the volatility characteristics of load data, the prediction accuracy is significantly improved. Extensive experiments demonstrate that our method outperforms existing state-of-the-art load forecasting schemes in terms of the prediction accuracy and stability.

References

[1]	H. Jiang, K. Wang, Y. Wang, M. Gao, Y. Zhang, Energy big data: A survey, IEEE Access, 4 (2016), 3844–3861.
[2]	Z. Ma, J. Xie, H. Li, Q. Sun, Z. Si, J. Zhang, et al., The role of data analysis in the development of intelligent energy networks, IEEE Network, 31 (2017), 88–95.
[3]	M. Fagiani, S. Squartini, L. Gabrielli, S.Spinsante, F.Piazza, A review of datasets and load forecasting techniques for smart natural gas and water grids: Analysis and experiments, Neurocomputing, 170 (2015), 448–465. doi: 10.1016/j.neucom.2015.04.098
[4]	O. Laib, M. T. Khadir, L. Mihaylova, A Gaussian process regression for natural gas consumption prediction based on time series data, 2018 21st International Conference on Information Fusion (FUSION), IEEE, 2018.
[5]	J. Ravnik, M. Hribersek, A method for natural gas forecasting and preliminary allocation based on unique standard natural gas consumption profiles, Energy, 180 (2019), 149–162. doi: 10.1016/j.energy.2019.05.084
[6]	W. Qiao, Z. Yang, Z. Kang, Z. Pan, Short-term natural gas consumption prediction based on volterra adaptive filter and improved whale optimization algorithm, Eng. Appl. Artif. Intell., 87 (2020), 103323. doi: 10.1016/j.engappai.2019.103323
[7]	N. Wei, C. Li, X. Peng, Y. Li, F. Zeng, Daily natural gas consumption forecasting via the application of a novel hybrid model, Appl. Energy, 250 (2019), 358–368. doi: 10.1016/j.apenergy.2019.05.023
[8]	G. D. Merkel, R. J. Povinelli, R. H. Brown, Short-term load forecasting of natural gas with deep neural network regression, Energies, 11 (2018), 2008. doi: 10.3390/en11082008
[9]	B. Ervural, O. Beyca, S. Zaim, Model estimation of ARMA using genetic algorithms: A case study of forecasting natural gas consumption, Procedia Soc. Behav. Sci., 235 (2016), 537–545. doi: 10.1016/j.sbspro.2016.11.066
[10]	I. Panapakidis, A. 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. doi: 10.1016/j.energy.2016.12.033
[11]	W. 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. doi: 10.1109/ACCESS.2019.2918156
[12]	J. Lei, T. Jin, J. Hao, F. Li, Short-term load forecasting with clustering-regression model in distributed cluster, Cluster Comput., 22 (2019), 10163–10173. doi: 10.1007/s10586-017-1198-4
[13]	L. Wang, S. Mao, B. M. Wilamowski, R. M. Nelms, Ensemble learning for load forecasting, IEEE Trans. Green Commun. Networking, 4 (2020), 616–628. doi: 10.1109/TGCN.2020.2987304
[14]	T. Li, Y. Wang, N. Zhang, Combining probability density forecasts for power electrical loads, IEEE Trans. Smart Grid, 11 (2020), 1679–1690. doi: 10.1109/TSG.2019.2942024
[15]	C. Feng, M. Sun, J. Zhang, Reinforced deterministic and probabilistic load forecasting via $Q$-learning dynamic model selection, IEEE Trans. Smart Grid, 11 (2020), 1377–1386. doi: 10.1109/TSG.2019.2937338
[16]	W. Zheng, Z. Li, X. Liang, J. Zheng, Q. H. Wu, F. Hu, Decentralized state estimation of combined heat and power system considering communication packet loss, J. Mod. Power Syst. Clean Energy, 8 (2020), 646–656. doi: 10.35833/MPCE.2020.000120
[17]	B. Zhang, C. Dou, D. Yue, Z. Zhang, T. Zhang, A packet loss-dependent event-triggered cyber-physical cooperative control strategy for islanded microgrid, IEEE Trans. Cybern., 51 (2021), 267–282. doi: 10.1109/TCYB.2019.2954181
[18]	F. Yu, X. Xu, A short-term load forecasting model of natural gas based on optimized genetic algorithm and improved BP neural network, Appl. Energy, 134 (2014), 102–113. doi: 10.1016/j.apenergy.2014.07.104
[19]	Y. Karadede, G. Ozdemir, E. Aydemir. Breeder hybrid algorithm approach for natural gas demand forecasting model, Energy, 141 (2017), 1269–1284. doi: 10.1016/j.energy.2017.09.130
[20]	F. Taspinar, N. Celebi, N. Tutkun, Forecasting of daily natural gas consumption on regional basis in Turkey using various computational methods, Energy Build., 56 (2013), 23–31. doi: 10.1016/j.enbuild.2012.10.023
[21]	G. Zu, L. Lu, X. Xu, Study of information entropy combination model for short-term gas load prediction, Comput. Appl. Software, 30 (2013), 129–131.
[22]	J. Tang, C. Deng, G. B. Huang, Extreme learning machine for multilayer perceptron, IEEE Trans. Neural Networks Learn, Syst., 27 (2016), 809–821. doi: 10.1109/TNNLS.2015.2424995
[23]	M. Walker, Y. Dovoedo, S. Chakraborti, C. W. Hilton, An improved boxplot for univariate data, Am. Stat., 72 (2018), 348–353. doi: 10.1080/00031305.2018.1448891
[24]	F. Li, K. Wu, J. Lei, M. Wen, Z. Bi, C. Gu, Steganalysis over large-scale social networks with high-order joint features and clustering ensembles, IEEE Trans. Inf. Forensics Secur., 11 (2016), 344–357. doi: 10.1109/TIFS.2015.2496910
[25]	C. Li, Y. Tao, W. Ao, S. Yang, Y. Bai, Improving forecasting accuracy of daily enterprise electricity consumption using a random forest based on ensemble empirical mode decomposition, Energy, 165 (2018), 1220–1227. doi: 10.1016/j.energy.2018.10.113
[26]	T. Chen, C. Guestrin, Xgboost: A scalable tree boosting system, Proceedings of the 22nd ACM Sigkdd International Conference on Knowledge Discovery and Data Mining, 2016.
[27]	A. Sagheer, M. Kotb, Time series forecasting of petroleum production using deep LSTM recurrent networks, Neurocomputing, 323 (2019), 203–213. doi: 10.1016/j.neucom.2018.09.082
[28]	S. Chen, Y. Wu, B. Luk, Combined genetic algorithm optimization and regularized orthogonal least squares learning for radial basis function networks, IEEE Trans. Neural Networks, 10 (1999), 1239–1243. doi: 10.1109/72.788663
[29]	X. Liu, X. Zhu, M. Li, L. Wang, E. Zhu, T. Liu, et al., Multiple kernel $k$-means with incomplete kernels, IEEE Trans. Pattern Anal. Mach. Intell., 42 (2020), 1191–1204.
[30]	F. Li, G. Zhou, J. Lei, Reliable data transmission in wireless sensor networks with data decomposition and ensemble recovery, Math. Biosci. Eng., 16 (2019), 4526–4545. doi: 10.3934/mbe.2019226

Reader Comments

Your name:*

Email:*
© 2021 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)