An Enhancement Method Based on Long Short-Term Memory Neural Network for Short-Term Natural Gas Consumption Forecasting

Artificial intelligence models have been widely applied for natural gas consumption forecasting over the past decades, especially for short-term consumption forecasting. This paper proposes a three-layer neural network forecasting model that can extract key information from input factors and improve the weight optimization mechanism of long short-term memory (LSTM) neural network to effectively forecast short-term consumption. In the proposed model, a convolutional neural network (CNN) layer is adopted to extract the features among various factors affecting natural gas consumption and improve computing efficiency. The LSTM layer is able to learn and save the long-distance state through the gating mechanism and overcomes the defects of gradient disappearance and explosion in the recurrent neural network. To solve the problem of encoding input sequences as fixed-length vectors, the layer of attention (ATT) is used to optimize the assignment of weights and highlight the key sequences. Apart from the comparisons with other popular forecasting models, the performance and robustness of the proposed model are validated on datasets with different fluctuations and complexities. Compared with traditional two-layer models (CNN-LSTM and LSTM-ATT), the mean absolute range normalized errors (MARNE) of the proposed model in Athens and Spata are improved by more than 16% and 11%, respectively. In comparison with single LSTM, back propagation neural network, support vector regression, and multiple linear regression methods, the improvement in MARNE exceeds 42% in Athens. The coefficient of determination is improved by more than 25%, even in the high-complexity dataset, Spata.

[1]  Wei Wang,et al.  Short-term load forecasting using detrend singular spectrum fluctuation analysis , 2022, Energy.

[2]  Marko G. Ignjatović,et al.  Explainable heat demand forecasting for the novel control strategies of district heating systems , 2022, Annu. Rev. Control..

[3]  C. Bergmeir,et al.  Forecast evaluation for data scientists: common pitfalls and best practices , 2022, Data Mining and Knowledge Discovery.

[4]  Changjun Li,et al.  Data complexity of daily natural gas consumption: Measurement and impact on forecasting performance , 2022, Energy.

[5]  Enbin Liu,et al.  Daily natural gas load forecasting based on the combination of long short term memory, local mean decomposition, and wavelet threshold denoising algorithm , 2021 .

[6]  M. V. Sebt,et al.  Predicting the number of customer transactions using stacked LSTM recurrent neural networks , 2021, Soc. Netw. Anal. Min..

[7]  Hongbo Duan,et al.  Analysis and forecasting of crude oil price based on the variable selection-LSTM integrated model , 2021, Energy Inform..

[8]  Xiaoyuan Zhang,et al.  Equipping Seasonal Exponential Smoothing Models with Particle Swarm Optimization Algorithm for Electricity Consumption Forecasting , 2021, Energies.

[9]  Changjun Li,et al.  Forecasting the daily natural gas consumption with an accurate white-box model , 2021 .

[10]  Jinyuan Liu,et al.  Natural gas consumption forecasting: A discussion on forecasting history and future challenges , 2021 .

[11]  Eenjun Hwang,et al.  An Attention-Based Multilayer GRU Model for Multistep-Ahead Short-Term Load Forecasting † , 2021, Sensors.

[12]  F. Petropoulos,et al.  Fast and Frugal Time Series Forecasting , 2021, SSRN Electronic Journal.

[13]  Sung-Bae Cho,et al.  Time Series Forecasting with Multi-Headed Attention-Based Deep Learning for Residential Energy Consumption , 2020, Energies.

[14]  Aneela Zameer,et al.  Predictions for COVID-19 with deep learning models of LSTM, GRU and Bi-LSTM , 2020, Chaos, Solitons & Fractals.

[15]  Zhen Pan,et al.  Short-term natural gas consumption prediction based on Volterra adaptive filter and improved whale optimization algorithm , 2020, Eng. Appl. Artif. Intell..

[16]  Tom Iseley,et al.  Short-term load forecasting of urban gas using a hybrid model based on improved fruit fly optimization algorithm and support vector machine , 2019, Energy Reports.

[17]  Sung Wook Baik,et al.  Improving Electric Energy Consumption Prediction Using CNN and Bi-LSTM , 2019, Applied Sciences.

[18]  Sung-Bae Cho,et al.  Predicting residential energy consumption using CNN-LSTM neural networks , 2019, Energy.

[19]  Jia-Qi Zhu,et al.  Data‐driven wind speed forecasting using deep feature extraction and LSTM , 2019, IET Renewable Power Generation.

[20]  Jianyu Long,et al.  A comparison of dimension reduction techniques for support vector machine modeling of multi-parameter manufacturing quality prediction , 2019, J. Intell. Manuf..

[21]  Beyzanur Cayir Ervural,et al.  Using machine learning tools for forecasting natural gas consumption in the province of Istanbul , 2019, Energy Economics.

[22]  Shahzad Muzaffar,et al.  Short-Term Load Forecasts Using LSTM Networks , 2019, Energy Procedia.

[23]  Changjun Li,et al.  Daily Natural Gas Load Forecasting Based on a Hybrid Deep Learning Model , 2019, Energies.

[24]  Gregor Papa,et al.  A comparison of models for forecasting the residential natural gas demand of an urban area , 2019, Energy.

[25]  Yuan Zhang,et al.  Short-Term Residential Load Forecasting Based on LSTM Recurrent Neural Network , 2019, IEEE Transactions on Smart Grid.

[26]  Rossana Castaldo,et al.  On the use of approximate entropy and sample entropy with centre of pressure time-series , 2018, Journal of NeuroEngineering and Rehabilitation.

[27]  Changjun Li,et al.  Short-Term Forecasting of Natural Gas Consumption Using Factor Selection Algorithm and Optimized Support Vector Regression , 2018, Journal of Energy Resources Technology.

[28]  Wei-Chiang Hong,et al.  Combining Grey Model and Self-Adapting Intelligent Grey Model with Genetic Algorithm and Annual Share Changes in Natural Gas Demand Forecasting , 2018, Energies.

[29]  Duncan Fyfe Gillies,et al.  A Review of Feature Selection and Feature Extraction Methods Applied on Microarray Data , 2015, Adv. Bioinformatics.

[30]  Nejat Yumusak,et al.  Forecasting household natural gas consumption with ARIMA model: A case study of removing cycle , 2013, 2013 7th International Conference on Application of Information and Communication Technologies.

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

[32]  Kristian Sabo,et al.  Mathematical models of natural gas consumption , 2011 .

[33]  S. Hochreiter,et al.  Long Short-Term Memory , 1997, Neural Computation.

[34]  S. M. Sarathy,et al.  A comprehensive neural network model for predicting flash point of oxygenated fuels using a functional group approach , 2022, Fuel.

[35]  Wanli Xie,et al.  Forecasting natural gas consumption of China by using a novel fractional grey model with time power term , 2021 .

[36]  Bin Li,et al.  LSTM-Attention-Embedding Model-Based Day-Ahead Prediction of Photovoltaic Power Output Using Bayesian Optimization , 2019, IEEE Access.

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

[38]  S. Gil,et al.  Generalized model of prediction of natural gas consumption , 2003 .

[39]  Michael J. Verhulst,et al.  The Theory of Demand Applied to the French Gas Industry , 1950 .