A hybrid hourly natural gas demand forecasting method based on the integration of wavelet transform and enhanced Deep-RNN model

Abstract The rapid development of big data and smart technology in the natural gas industry requires timely and accurate forecasting of natural gas consumption on different time horizons. In this work, we propose a robust hybrid hours-ahead gas consumption method by integrating Wavelet Transform, RNN-structured deep learning and Genetic Algorithm. The Wavelet Transform is used to reduce the complexity of the forecasting tasks by decomposing the original series of gas loads into several sub-components. The RNN-structured deep learning method is built up via combining a multi-layer Bi-LSTM model and a LSTM model. The multi-layer Bi-LSTM model can comprehensively capture the features in the sub-components and the LSTM model is used to forecast the future gas consumption based on these abstracted features. To enhance the performance of the RNN-structured deep learning model, Genetic Algorithm is employed to optimize the structure of each layer in the model. Besides, the dropout technology is applied in this work to overcome the potential problem of overfitting. In this case study, the effectiveness of the developed method is verified from multiple perspective, including graphical examination, mathematical errors analysis and model comparison, on different data sets.

[1]  Sílvio Mariano,et al.  A bat optimized neural network and wavelet transform approach for short-term price forecasting , 2018 .

[2]  John Psarras,et al.  How does a natural gas supply interruption affect the EU gas security? A Monte Carlo simulation , 2015 .

[3]  V. Ismet Ugursal,et al.  Comparison of neural network, conditional demand analysis, and engineering approaches for modeling end-use energy consumption in the residential sector , 2008 .

[4]  Vivek Srikumar,et al.  Predicting electricity consumption for commercial and residential buildings using deep recurrent neural networks , 2018 .

[5]  Fausto Pedro García Márquez,et al.  A survey of artificial neural network in wind energy systems , 2018, Applied Energy.

[6]  Attila Matyas Nagy,et al.  Survey on traffic prediction in smart cities , 2018, Pervasive Mob. Comput..

[7]  Thomas Fischer,et al.  Deep learning with long short-term memory networks for financial market predictions , 2017, Eur. J. Oper. Res..

[8]  Lin Jiang,et al.  Short-term natural gas demand prediction based on support vector regression with false neighbours filtered , 2015 .

[9]  Michele Marchesi,et al.  Fast wavelet transform assisted predictors of streaming time series , 2017, Digit. Signal Process..

[10]  Soteris A. Kalogirou,et al.  Artificial intelligence techniques for sizing photovoltaic systems: A review , 2009 .

[11]  Thorsten Koch,et al.  Forecasting day-ahead high-resolution natural-gas demand and supply in Germany , 2018, Applied Energy.

[12]  Qiang Wang,et al.  Forecasting energy demand in China and India: Using single-linear, hybrid-linear, and non-linear time series forecast techniques , 2018, Energy.

[13]  Jun Ma,et al.  A structure optimization framework for feed-forward neural networks using sparse representation , 2016, Knowl. Based Syst..

[14]  Xiaohua Li,et al.  Electric load forecasting in smart grids using Long-Short-Term-Memory based Recurrent Neural Network , 2017, 2017 51st Annual Conference on Information Sciences and Systems (CISS).

[15]  William E. Roper,et al.  Energy demand estimation of South Korea using artificial neural network , 2009 .

[16]  Primoz Potocnik,et al.  Forecasting risks of natural gas consumption in Slovenia , 2007 .

[17]  Jolanta Szoplik,et al.  Forecasting of natural gas consumption with artificial neural networks , 2015 .

[18]  Numan Çelebi,et al.  Forecasting of daily natural gas consumption on regional basis in Turkey using various computational methods , 2013 .

[19]  Thomas Reindl,et al.  Short term solar irradiance forecasting using a mixed wavelet neural network , 2016 .

[20]  Muhammad Arshad Khan.  Modelling and forecasting the demand for natural gas in Pakistan , 2015 .

[21]  Long Chen,et al.  Short-Term Load Forecasting Using EMD-LSTM Neural Networks with a Xgboost Algorithm for Feature Importance Evaluation , 2017 .

[22]  M. H. Fazel Zarandi,et al.  Forecasting semi-dynamic response of natural gas networks to nodal gas consumptions using genetic fuzzy systems , 2015 .

[23]  Erkan Erdogdu,et al.  Natural gas demand in Turkey , 2009 .

[24]  John H. Herbert,et al.  A statistical evaluation of aggregate monthly industrial demand for natural gas in the U.S.A. , 1987 .

[25]  Enrico Zio,et al.  Ensemble of optimized echo state networks for remaining useful life prediction , 2017, Neurocomputing.

[26]  Andreas Kamilaris,et al.  Deep learning in agriculture: A survey , 2018, Comput. Electron. Agric..

[27]  Zhiyong Cui,et al.  Deep Bidirectional and Unidirectional LSTM Recurrent Neural Network for Network-wide Traffic Speed Prediction , 2018, ArXiv.

[28]  Vladimir Ceperic,et al.  Short-term forecasting of natural gas prices using machine learning and feature selection algorithms , 2017 .

[29]  Feng Yu,et al.  A short-term load forecasting model of natural gas based on optimized genetic algorithm and improved BP neural network , 2014 .

[30]  Donatien Njomo,et al.  Forecasting Natural Gas: A Literature Survey , 2018 .

[31]  Jose A. Romagnoli,et al.  A machine learning approach to optimize shale gas supply chain networks , 2017 .

[32]  Yugang Niu,et al.  Hourly day-ahead solar irradiance prediction using weather forecasts by LSTM , 2018 .

[33]  Ioannis P. Panapakidis,et al.  Day-ahead natural gas demand forecasting based on the combination of wavelet transform and ANFIS/genetic algorithm/neural network model , 2017 .

[34]  Božidar Soldo,et al.  Forecasting natural gas consumption , 2012 .

[35]  Cleber Zanchettin,et al.  Gesture recognition: A review focusing on sign language in a mobile context , 2018, Expert Syst. Appl..

[36]  Zhe Yang,et al.  A systematic hybrid method for real-time prediction of system conditions in natural gas pipeline networks , 2018, Journal of Natural Gas Science and Engineering.

[37]  Kameshwar Poolla,et al.  Exploiting sparsity of interconnections in spatio-temporal wind speed forecasting using Wavelet Transform , 2016 .

[38]  Bartlomiej Placzek,et al.  Period-aware local modelling and data selection for time series prediction , 2016, Expert Syst. Appl..

[39]  Zoubin Ghahramani,et al.  A Theoretically Grounded Application of Dropout in Recurrent Neural Networks , 2015, NIPS.

[40]  Nursel Öztürk,et al.  A genetic algorithm for minimizing energy consumption in warehouses , 2016 .