# Application of Artificial Neural Networks for Natural Gas Consumption Forecasting

^{1}

^{2}

^{3}

^{*}

## Abstract

**:**

## 1. Introduction

## 2. Materials and Methods

#### 2.1. Dataset

#### 2.2. Feature Engineering

## 3. Methodology

#### 3.1. Artificial Neural Networks (ANN)

#### 3.2. Long Short-Term Memory Networks (LSTM)

#### 3.3. Deep Neural Networks (DNN)

#### 3.4. Process Flow

#### 3.4.1. Preprocessing

#### 3.4.2. Data Split

#### 3.4.3. Standardization

#### 3.4.4. Processing

## 4. Evaluation metrics

^{2}) are all being used in order to determine the best performing model [5,7,43].

^{2}value close to 1 is preferred, signifying better performance for the model and that the regression curve is well fit on the data. A coefficient of determination value of 1 would signify that the regression line fits the data perfectly; however, this could also denote overfitting on the data.

## 5. Results

^{2}were used.

#### 5.1. Results from ANN

#### 5.2. Results from LSTM

^{2}values. LSTMs can offer excellent accuracy for single-variable time series; however, it is evident that they are highly susceptible to the depth of the forecasting period, as well as to the data that are required for proper training.

#### 5.3. Results from DNN

#### 5.4. Comparison (Cities)

^{2}. Seven out of fourteen cities achieved an accuracy of >90%, however, for the other seven cities, the performance of the model is disappointing.

^{2}as the primary metric. Here, six cities achieved an accuracy of >94%, with the rest achieving higher accuracy when compared to the ANN.

^{2}. For seven out of fourteen cities, the proposed methodology achieved an accuracy of >94%, which is considered very satisfactory for prediction, considering that the MSE of these models is also very low.

#### 5.5. Sensitivity Analysis

## 6. Discussion

^{2}for the city of Larissa (0.9846) while the LSTM implementation for the city of Athens (0.9644) and the ANN for the city of Trikala (0.699). For the worst-case scenario, the city of Agioi Theodoroi, has consistently obtained the worst accuracies, with the DNN (0.5748) achieving significant higher accuracy, even though still not so good, compared to the LSTM (0.3848) and ANN (0.1440) implementation. The dataset of Agioi Theodoroi is the smallest compared to the rest, being one reason for achieving these low accuracies. It ca be argued that the size of the city (<5000 habitants) is another important reason, since the consumption trends are sparser due its low population.

^{2}values. This can be derived from several facts. The more important is that since the dataset is finite, the further ahead in time the prediction is, the less training data the model is left with to “learn” from. Machine learning models are highly dependent on data, and their performance is highly correlated to the data quality and quantity. Particularly for the ANN approach, it’s simplistic implementation cannot capture the complexity that is required for the long-term forecasting, even if in general ANNs are powerful. Another reason is that the scale of the energy prediction units is large (in absolute numbers), thus the worse the prediction is, the larger is the penalty for it. Additionally, since the forecasting timescale increases for additionally 1, 2, and 3 years, the ill-fitted models produce large errors in predictions which are accumulated, because the forecasting time is 1, 2, and 3 times larger, respectively. The R

^{2}metric is based on the MSE, and is scale-dependent, while MAPE is not, therefore it is useful for understanding the performance of the models. It is considered that R

^{2}is still probably the best metric for forecasts [62], however, MAPE can still be used because the percentage of error makes sense and there are no zero values in our dataset.

## 7. Conclusions

## Author Contributions

## Funding

## Conflicts of Interest

## Appendix

**Figure A1.**Correlation of the energy demand and the mean temperature for the training set and the test set for all the examined cities.

## References

- Tamba, J.G.; Essiane, S.N.; Sapnken, E.F.; Koffi, F.D.; Nsouandélé, J.L.; Soldo, B.; Njomo, D. Forecasting natural gas: A literature survey. Int. J. Energy Econ. Policy
**2018**, 8, 216–249. [Google Scholar] - Ivezić, D. Short-Term Natural Gas Consumption Forecast. FME Trans.
**2006**, 34, 165–169. [Google Scholar] - Ghalehkhondabi, I.; Ardjmand, E.; Weckman, G.R.; Young, W.A. An overview of energy demand forecasting methods published in 2005–2015. Energy Syst.
**2017**, 8, 411–447. [Google Scholar] [CrossRef] - Motlagh, O.; Grozev, G.; Papageorgiou, E.I. A Neural Approach to Electricity Demand Forecasting. In Artificial Neural Network Modelling; Shanmuganathan, S., Samarasinghe, S., Eds.; Springer International Publishing: Cham, Switzerland, 2016; pp. 281–306. [Google Scholar]
- Raza, M.Q.; Khosravi, A. A review on artificial intelligence based load demand forecasting techniques for smart grid and buildings. Renew. Sustain. Energy Rev.
**2015**, 50, 1352–1372. [Google Scholar] [CrossRef] - Gorucu, F.B.; Geriş, P.U.; Gumrah, F. Artificial Neural Network Modeling for Forecasting Gas Consumption. Energy Sources
**2004**, 26, 299–307. [Google Scholar] [CrossRef] - Papageorgiou, E.I.; Poczęta, K. A two-stage model for time series prediction based on fuzzy cognitive maps and neural networks. Neurocomputing
**2017**, 232, 113–121. [Google Scholar] [CrossRef] - Karimi, H.; Dastranj, J. Artificial neural network-based genetic algorithm to predict natural gas consumption. Energy Syst.
**2014**, 5, 571–581. [Google Scholar] [CrossRef] - Khotanzad, A.; Elragal, H. Natural gas load forecasting with combination of adaptive neural networks. In Proceedings of the International Joint Conference on Neural Networks, Washington, DC, USA, 10–16 July 1999; IEEE: Piscataway Township, NJ, USA, 2002. [Google Scholar]
- Khotanzad, A.; Elragal, H.; Lu, T.L. Combination of artificial neural-network forecasters for prediction of natural gas consumption. IEEE Trans. Neural Netw.
**2000**, 11, 464–473. [Google Scholar] [CrossRef] - Kizilaslan, R.; Karlik, B. Comparison neural networks models for short term forecasting of natural gas consumption in Istanbul. In Proceedings of the 1st International Conference on the Applications of Digital Information and Web Technologies, ICADIWT 2008, Ostrava, Czech Republic, 4–6 August 2008. [Google Scholar]
- Kizilaslan, R.; Karlik, B. Combination of neural networks forecasters for monthly natural gas consumption prediction. Neural Netw. World
**2009**, 19, 191–199. [Google Scholar] - Musilek, P.; Pelikan, E.; Brabec, T.; Simunek, M. Recurrent Neural Network Based Gating for Natural Gas Load Prediction System. In Proceedings of the 2006 IEEE International Joint Conference on Neural Network Proceedings, Vancouver, BC, Canada, 16–21 July 2006. [Google Scholar]
- Soldo, B. Forecasting natural gas consumption. Appl. Energy
**2012**, 92, 26–37. [Google Scholar] [CrossRef] - Szoplik, J. Forecasting of natural gas consumption with artificial neural networks. Energy
**2015**, 85, 208–220. [Google Scholar] [CrossRef] - Merkel, G.D.; Povinelli, R.J.; Brown, R.H. Deep neural network regression as a component of a forecast ensemble. In Proceedings of the International Symposium on Forecasting, Cairns, Australia, 25–28 June 2017. [Google Scholar]
- Merkel, G.D. Deep Neural Networks as Time Series Forecasters of Energy Demand. Master’s Thesis, Marquette University, Milwaukee, WI, US, 2017. Available online: https://epublications.marquette.edu/theses_open/434/ (accessed on 5 May 2020).
- Merkel, G.D.; Povinelli, R.J.; Brown, R.H. Short-term load forecasting of natural gas with deep neural network regression. Energies
**2018**, 11, 2008. [Google Scholar] [CrossRef][Green Version] - Azadeh, A.; Asadzadeh, S.M.; Ghanbari, A. An adaptive network-based fuzzy inference system for short-term natural gas demand estimation: Uncertain and complex environments. Energy Policy
**2010**, 38, 1529–1536. [Google Scholar] [CrossRef] - Behrouznia, A.; Saberi, M.; Azadeh, A.; Asadzadeh, S.M.; Pazhoheshfar, P. An adaptive network based fuzzy inference system-fuzzy data envelopment analysis for gas consumption forecasting and analysis: The case of South America. In Proceedings of the 2010 International Conference on Intelligent and Advanced Systems, ICIAS 2010, Kuala Lumpur, Malaysia, 15–17 June 2010. [Google Scholar]
- Yu, F.; Xu, X. A short-term load forecasting model of natural gas based on optimized genetic algorithm and improved BP neural network. Appl. Energy
**2014**, 134, 102–113. [Google Scholar] [CrossRef] - Panapakidis, I.P.; Dagoumas, A.S. Day-ahead natural gas demand forecasting based on the combination of wavelet transform and ANFIS/genetic algorithm/neural network model. Energy
**2017**, 118, 231–245. [Google Scholar] [CrossRef] - Homenda, W.; Jastrzebska, A.; Pedrycz, W. Modeling time series with fuzzy cognitive maps. In Proceedings of the IEEE International Conference on Fuzzy Systems, Beijing, China, 6–11 July 2014. [Google Scholar]
- Homenda, W.; Jastrzębska, A.; Pedrycz, W.; Pedrycz, W. Nodes selection criteria for fuzzy cognitive maps designed to model time series. Adv. Intell. Syst. Comput.
**2015**, 323, 859–870. [Google Scholar] - Salmeron, J.L.; Froelich, W. Dynamic optimization of fuzzy cognitive maps for time series forecasting. Knowl. Based Syst.
**2016**, 105, 29–37. [Google Scholar] [CrossRef] - Froelich, W.; Salmeron, J.L. Evolutionary learning of fuzzy grey cognitive maps for the forecasting of multivariate, interval-valued time series. Int. J. Approx. Reason.
**2014**, 55, 1319–1335. [Google Scholar] [CrossRef] - Papageorgiou, E.I.; Poczeta, K.; Laspidou, C. Application of Fuzzy Cognitive Maps to water demand prediction. In Proceedings of the IEEE International Conference on Fuzzy Systems, Istanbul, Turkey, 2–5 August 2015. [Google Scholar]
- Poczęta, K.; Yastrebov, A.; Papageorgiou, E.I. Learning fuzzy cognitive maps using structure optimization genetic algorithm. In Proceedings of the 2015 Federated Conference on Computer Science and Information Systems, FedCSIS 2015, Lodz, Poland, 13–16 September 2015. [Google Scholar]
- Poczeta, K.; Papageorgiou, E.I. Implementing fuzzy cognitive maps with neural networks for natural gas prediction. In Proceedings of the Proceedings—International Conference on Tools with Artificial Intelligence, ICTAI, Volos, Greece, 5–7 November 2018. [Google Scholar]
- Papageorgiou, K.I.; Poczeta, K.; Papageorgiou, E.; Gerogiannis, V.C.; Stamoulis, G. Exploring an ensemble of methods that combines fuzzy cognitive maps and neural networks in solving the time series prediction problem of gas consumption in Greece. Algorithms
**2019**, 12, 235. [Google Scholar] [CrossRef][Green Version] - Bhattacharyya, S.C.; Timilsina, G.R. Energy Demand Models for Policy Formulation: A Comparative Study of Energy Demand Models. 2009. Available online: https://core.ac.uk/reader/6521667 (accessed on 24 November 2019).
- Han, Y.; Sha, X.; Grover-Silva, E.; Michiardi, P. On the impact of socio-economic factors on power load forecasting. In Proceedings of the 2014 IEEE International Conference on Big Data, IEEE Big Data 2014, Washington, DC, USA, 27–30 October 2014; IEEE: Piscataway Township, NJ, USA, 2015. [Google Scholar]
- McLoughlin, F.; Duffy, A.; Conlon, M. Characterising domestic electricity consumption patterns by dwelling and occupant socio-economic variables: An Irish case study. Energy Build.
**2012**, 48, 240–248. [Google Scholar] [CrossRef][Green Version] - Beckel, C.; Sadamori, L.; Santini, S. Automatic socio-economic classification of households using electricity consumption data. In Proceedings of the e-Energy 2013—Proceedings of the 4th ACM International Conference on Future Energy Systems, Berkeley, CA, USA, 22–24 May 2013. [Google Scholar]
- Sánchez-Oro, J.; Duarte, A.; Salcedo-Sanz, S. Robust total energy demand estimation with a hybrid Variable Neighborhood Search—Extreme Learning Machine algorithm. Energy Convers. Manag.
**2016**, 123, 445–452. [Google Scholar] [CrossRef] - Liu, B.; Fu, C.; Bielefield, A.; Liu, Y.Q. Forecasting of Chinese Primary Energy Consumption in 2021 with GRU artificial neural network. Energies
**2017**, 10, 1453. [Google Scholar] [CrossRef] - Oğcu, G.; Demirel, O.F.; Zaim, S. Forecasting Electricity Consumption with Neural Networks and Support Vector Regression. Procedia Soc. Behav. Sci.
**2012**, 58, 1576–1585. [Google Scholar] [CrossRef][Green Version] - Günay, M.E. Forecasting annual gross electricity demand by artificial neural networks using predicted values of socio-economic indicators and climatic conditions: Case of Turkey. Energy Policy
**2016**, 90, 92–101. [Google Scholar] [CrossRef] - Parfenenko, Y.; Shendryk, V.; Vashchenko, S.; Fedotova, N. The forecasting of the daily heat demand of the public sector buildings with district heating. In Information and Software Technologies; Springer: Cham, Switzerland, 2015. [Google Scholar]
- Benalcazar, P.; Kamiński, J. Short-term heat load forecasting in district heating systems using artificial neural networks. In Proceedings of the IOP Conference Series: Earth and Environmental Science, Krakow, Poland, 14–17 November 2017; IOP: London, UK, 2019. [Google Scholar]
- Dolinay, V.; Vasek, L.; Novak, J.; Chalupa, P.; Kral, E. Heat demand model for district heating simulation. In Proceedings of the MATEC Web of Conferences, Majorca, Spain, 14–17 July 2018. [Google Scholar]
- Powell, K.M.; Sriprasad, A.; Cole, W.J.; Edgar, T.F. Heating, cooling, and electrical load forecasting for a large-scale district energy system. Energy
**2014**, 74, 877–885. [Google Scholar] [CrossRef] - Anagnostis, A.; Papageorgiou, E.; Dafopoulos, V.; Bochtis, D. Applying Long Short-Term Memory Networks for natural gas demand prediction. In Proceedings of the 2019 10th International Conference on Information, Intelligence, Systems and Applications, Patras, Greece, 15–17 July 2019; pp. 1–7. [Google Scholar]
- McCulloch, W.S.; Pitts, W. A logical calculus of the ideas immanent in nervous activity. Bull. Math. Biophys.
**1943**, 5, 115–133. [Google Scholar] [CrossRef] - Rosenblatt, F. The perceptron: A probabilistic model for information storage and organization in the brain. Psychol. Rev.
**1958**, 65, 386–408. [Google Scholar] [CrossRef][Green Version] - Pal, S.K.; Mitra, S. Multilayer Perceptron, Fuzzy Sets, and Classification. IEEE Trans. Neural Netw.
**1992**, 3, 683–697. [Google Scholar] [CrossRef] - Linnainmaa, S. Taylor expansion of the accumulated rounding error. BIT
**1976**, 16, 146–160. [Google Scholar] [CrossRef] - Hochreiter, S.; Schmidhuber, J. Long Short-Term Memory. Neural Comput.
**1997**, 9, 1735–1780. [Google Scholar] [CrossRef] - Lecun, Y.; Bengio, Y.; Hinton, G. Deep learning. Nature
**2015**, 521, 436–444. [Google Scholar] [CrossRef] [PubMed] - He, K.; Zhang, X.; Ren, S.; Sun, J. Deep residual learning for image recognition. In Proceedings of the Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June 2016. [Google Scholar]
- Huang, G.; Liu, Z.; Van Der Maaten, L.; Weinberger, K.Q. Densely connected convolutional networks. In Proceedings of the 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, 21–26 July 2017. [Google Scholar]
- Szegedy, C.; Liu, W.; Jia, Y.; Sermanet, P.; Reed, S.; Anguelov, D.; Erhan, D.; Vanhoucke, V.; Rabinovich, A. Going deeper with convolutions. In Proceedings of the Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Boston, MA, USA, 7–12 June 2015. [Google Scholar]
- Kenton, L.; Kristina, T.; Devlin, J.; Chang, M.-W. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv
**2017**, arXiv:1810.04805. [Google Scholar] - Chung, J.; Gulcehre, C.; Cho, K.; Bengio, Y. Gated feedback recurrent neural networks. In Proceedings of the 32nd International Conference on Machine Learning, ICML 2015, Lille, France, 6–11 July 2015. [Google Scholar]
- Anagnostis, A.; Asiminari, G.; Papageorgiou, E.; Bochtis, D. A Convolutional Neural Networks Based Method for Anthracnose Infected Walnut Tree Leaves Identification. Appl. Sci.
**2020**, 10, 469. [Google Scholar] [CrossRef][Green Version] - Chollet, F.; Allaire, J.J. Keras 2015. Available online: https://keras.io/getting_started/faq/#how-should-i-cite-keras (accessed on 27 March 2015).
- Srivastava, N.; Hinton, G.; Krizhevsky, A.; Sutskever, I.; Salakhutdinov, R. Dropout: A simple way to prevent neural networks from overfitting. J. Mach. Learn. Res.
**2014**, 15, 1929–1958. [Google Scholar] - Hazra, A. Using the confidence interval confidently. J. Thorac. Dis.
**2017**, 9, 4125–4130. [Google Scholar] [CrossRef][Green Version] - Ruppert, D. The Elements of Statistical Learning: Data Mining, Inference, and Prediction. J. Am. Stat. Assoc.
**2004**, 99, 567. [Google Scholar] [CrossRef] - Molnar, C. Interpretable Machine Learning: A Guide for Making Black Box Models Explainable; Lulu: Morrisville, NC, USA, 2019. [Google Scholar]
- Graham, B.; Reizenstein, J.; Robinson, L. Efficient batchwise dropout training using submatrices. arXiv
**2015**, arXiv:1502.02478. [Google Scholar] - Cameron, A.C.; Windmeijer, F.A.G. An R-squared measure of goodness of fit for some common nonlinear regression models. J. Econom.
**1997**, 77, 329–342. [Google Scholar] [CrossRef]

**Figure 1.**Natural gas energy consumption [MWh] for Athens, Thessaloniki, and Larissa over the years.

**Figure 2.**Natural gas energy consumption [MWh] for Alexandroupoli, Drama, Karditsa, and Trikala over the years.

**Figure 3.**Correlation of the energy demand and the mean temperature for the training set (

**a**) and the test set (

**b**) for the city of Athens.

**Figure 6.**Forecasts of (

**a**) one-, (

**b**) two-, (

**c**) three-, and (

**d**) four-year ahead of natural gas demand with the use of ANN.

**Figure 10.**Forecasts of (

**a**) one-, (

**b**) two-, (

**c**) three-, and (

**d**) four-year ahead of natural gas demand with the use of DNN.

**Figure 11.**Partial Dependence Plots for the dataset of Athens on the mean daily temperature for the ANN (

**a**) and the DNN (

**b**) models, and the energy consumption values of 1-day (

**c**) and 2-days (

**d**) prior.

**Table 1.**Variables that are used as output and input for each implementation of the neural network variants. ANN: Artificial neural network; LSTM: Long Short-Term Memory; DNN: Deep neural network.

Output | Inputs | ||||||
---|---|---|---|---|---|---|---|

Energy Current Day (MJ) | Daily Mean Temperature (°C) | Energy 1 Previous Day (MJ) | Energy 2 Previous Days (MJ) | Month (Jan, Feb, Mar, Apr, May, Jun, Jul, Aug, Sep, Oct, Nov, Dec) | Day of the Week (Mon, Tue, Wen, Thu, Fri, Sat, Sun) | Bank Holiday (Yes, No) | |

ANN | × | × | |||||

LSTM | × | ||||||

DNN | × | × | × | × | × | × | × |

City | Start Date | Ratio of Training/Testing |
---|---|---|

Agioi Theodoroi | 07/06/2014 | 3.41 |

Alexandroupoli | 02/02/2013 | 4.78 |

Athens | 01/03/2010 | 7.68 |

Drama | 07/09/2011 | 6.15 |

Karditsa | 01/05/2014 | 3.51 |

Kilkis | 01/03/2010 | 7.68 |

Lamia | 01/02/2013 | 4.75 |

Larissa | 01/03/2010 | 7.68 |

Laurio | 01/03/2010 | 7.68 |

Markopoulo | 01/03/2010 | 7.68 |

Serres | 01/06/2013 | 4.42 |

Thessaloniki | 01/03/2012 | 5.67 |

Trikala | 12/09/2012 | 5.14 |

Volos | 01/03/2010 | 7.68 |

Xanthi | 01/03/2010 | 7.68 |

**Table 3.**Performance metrics of the selected ANN architecture. MSE: Mean square error; MAE: Mean absolute error; MAPE: Mean absolute percentage error; R

^{2}: Coefficient of determination.

ANN | Architecture Selection | ||||
---|---|---|---|---|---|

Layers | Nodes | MSE (MJ^{2}) | MAE (MJ^{2}) | MAPE (%) | R^{2} |

1 | 8 | 7.70 × 10^{–3} | 7.01 × 10^{–2} | 16.41 | 0.87 |

1 Layer/ 8 Nodes | Dropout Comparison | |||
---|---|---|---|---|

Dropout | MSE (MJ^{2}) | MAE (MJ^{2}) | MAPE (%) | R^{2} |

0 | 7.70 × 10^{−3} | 7.01 × 10^{−2} | 16.41 | 0.87 |

0.25 | 8.20 × 10^{−3} | 6.94 × 10^{−2} | 30.30 | 0.86 |

0.50 | 9.00 × 10^{−3} | 7.41 × 10^{−2} | 52.74 | 0.84 |

0.75 | 1.25 × 10^{−2} | 8.66 × 10^{−2} | 73.02 | 0.78 |

1 Layer/ 8 Nodes | Forecasting Comparison | |||
---|---|---|---|---|

Years ahead | MSE (MJ^{2}) | MAE (MJ^{2}) | MAPE (%) | R^{2} |

1 | 7.70 × 10^{−3} | 7.01 × 10^{−2} | 16.41 | 0.87 |

2 | 1.08 × 10^{−1} | 3.07 × 10^{−1} | 48.61 | −1.39 |

3 | 9.28 × 10^{−2} | 2.83 × 10^{−1} | 52.46 | −1.31 |

4 | 1.42 × 10^{−1} | 3.53 × 10^{−1} | 49.73 | −2.57 |

LSTM | Architecture Selection | ||||
---|---|---|---|---|---|

Layers | Units | MSE (MJ^{2}) | MAE (MJ^{2}) | MAPE (%) | R^{2} |

1 | 200 | 2.20 × 10^{−3} | 2.95 × 10^{−2} | 11.07 | 0.96 |

1 Layer/ 200 Units | Dropout Comparison | |||
---|---|---|---|---|

Dropout | MSE (MJ^{2}) | MAE (MJ^{2}) | MAPE (%) | R^{2} |

0 | 2.20 × 10^{−3} | 2.95 × 10^{−2} | 11.07 | 0.96 |

0.25 | 2.40 × 10^{−3} | 3.31 × 10^{−2} | 20.94 | 0.96 |

0.50 | 2.20 × 10^{−3} | 3.10 × 10^{−2} | 18.50 | 0.96 |

0.75 | 2.10 × 10^{−3} | 2.92 × 10^{−2} | 9.77 | 0.96 |

1 Layer/ 8 Nodes | Forecasting Comparison | |||
---|---|---|---|---|

Years ahead | MSE (MJ^{2}) | MAE (MJ^{2}) | MAPE (%) | R^{2} |

1 | 2.10 × 10^{−3} | 2.92 × 10^{−2} | 9.77 | 0.96 |

2 | 6.30 × 10^{−3} | 5.90 × 10^{−2} | 15.00 | 0.86 |

3 | 5.26 × 10^{−2} | 2.06 × 10^{−1} | 59.06 | −0.31 |

4 | 8.73 × 10^{−2} | 2.44 × 10^{−1} | 80.87 | −1.20 |

DNN | Architecture Selection | ||||
---|---|---|---|---|---|

Layers | Nodes | MSE (MJ^{2}) | MAE (MJ^{2}) | MAPE (%) | R^{2} |

4 | 32 | 1.70 × 10^{−3} | 2.75 × 10^{−2} | 7.53 | 0.97 |

4 Layer/ 32 Nodes | Dropout Comparison | |||
---|---|---|---|---|

Dropout | MSE (MJ^{2}) | MAE (MJ^{2}) | MAPE (%) | R^{2} |

0 | 1.70 × 10^{−3} | 2.75 × 10^{−2} | 7.53 | 0.97 |

0.25 | 2.20 × 10^{−3} | 3.11 × 10^{−2} | 10.98 | 0.96 |

0.50 | 2.90 × 10^{−3} | 4.32 × 10^{−2} | 26.45 | 0.95 |

0.75 | 3.00 × 10^{−3} | 3.82 × 10^{−2} | 48.61 | 0.95 |

4 Layer/ 32 Nodes | Forecasting Comparison | |||
---|---|---|---|---|

Years ahead | MSE (MJ^{2}) | MAE (MJ^{2}) | MAPE (%) | R^{2} |

1 | 1.70 × 10^{−3} | 2.75 × 10^{−2} | 7.53 | 0.97 |

2 | 1.50 × 10^{−3} | 2.76 × 10^{−2} | 8.98 | 0.97 |

3 | 1.30 × 10^{−3} | 2.06 × 10^{−2} | 8.68 | 0.97 |

4 | 1.70 × 10^{−3} | 3.22 × 10^{−2} | 9.40 | 0.96 |

ANN | Cities Comparison | ||||
---|---|---|---|---|---|

Cities | MSE (MJ^{2}) | MAE (MJ^{2}) | MAPE (%) | R^{2} | CI |

Agioi Theodoroi | 4.96 × 10^{−2} | 1.70 × 10^{−1} | 58.29 | 0.14 | [92,246–101,257] |

Alexandroupoli | 8.30 × 10^{−3} | 6.72 × 10^{−2} | 13.43 | 0.89 | [80,527–88,566] |

Athens | 2.40 × 10^{−3} | 3.53 × 10^{−2} | 10.94 | 0.96 | [7,710,057–9,006,556] |

Drama | 8.50 × 10^{−3} | 6.77 × 10^{−2} | 6.42 | 0.78 | [736,302–764,636] |

Karditsa | 2.60 × 10^{−3} | 3.54 × 10^{−2} | 28.66 | 0.97 | [234,893–293,622] |

Kilkis | 2.87 × 10^{−2} | 1.23 × 10^{−1} | 20.16 | 0.43 | [1,023,806–1,088,807] |

Lamia | 3.96 × 10^{−2} | 1.62 × 10^{−1} | 33.76 | 0.20 | [125,129–135,568] |

Larissa | 2.60 × 10^{−3} | 3.43 × 10^{−2} | 14.18 | 0.96 | [1,329,088–1,609,373] |

Laurio | 1.32 × 10^{−2} | 7.59 × 10^{−2} | 86,605.00 | 0.74 | [6,004,693–7,432,331] |

Markopoulo | 3.06 × 10^{−2} | 1.38 × 10^{−1} | 19.38 | 0.27 | [250,400–264,171] |

Serres | 3.60 × 10^{−3} | 4.52 × 10^{−2} | 11.69 | 0.96 | [400,111–467,284] |

Thessaloniki | 3.40 × 10^{−3} | 4.52 × 10^{−2} | 16.80 | 0.95 | [6,283,167–7,449,531] |

Trikala | 2.40 × 10^{−3} | 2.76 × 10^{−2} | 25.62 | 0.97 | [213,058–266,020] |

Volos | 3.90 × 10^{−3} | 4.92 × 10^{−2} | 11.41 | 0.91 | [1,662,841–1,845,579] |

Xanthi | 2.94 × 10^{−2} | 1.33 × 10^{−1} | 36.12 | 0.17 | [153,935–168,218] |

LSTM | Cities Comparison | ||||
---|---|---|---|---|---|

Cities | MSE (MJ^{2}) | MAE (MJ^{2}) | MAPE (%) | R^{2} | CI |

Agioi Theodoroi | 3.56 × 10^{−2} | 1.50 × 10^{−1} | 59.68 | 0.38 | [86,688–94,424] |

Alexandroupoli | 4.20 × 10^{−3} | 4.60 × 10^{−2} | 8.29 | 0.94 | [86,103–95,178] |

Athens | 2.10 × 10^{−3} | 2.92 × 10^{−2} | 9.77 | 0.96 | [7,634,555–8,986,641] |

Drama | 1.06 × 10^{−2} | 7.82 × 10^{−2} | 9.86 | 0.72 | [765,187–790,777] |

Karditsa | 8.40 × 10^{−3} | 7.61 × 10^{−2} | 72.99 | 0.89 | [290,871–357,268] |

Kilkis | 1.15 × 10^{−2} | 8.17 × 10^{−2} | 10.97 | 0.77 | [1,008,757–1,071,517] |

Lamia | 1.86 × 10^{−2} | 1.11 × 10^{−1} | 32.19 | 0.62 | [157,729–167,902] |

Larissa | 3.30 × 10^{−3} | 4.43 × 10^{−2} | 17.39 | 0.95 | [1,377,457–1,661,699] |

Laurio | 2.45 × 10^{−2} | 1.30 × 10^{−1} | 78,544.00 | 0.53 | [8,712,884–10,054,310] |

Markopoulo | 8.00 × 10^{−3} | 6.79 × 10^{−2} | 9.70 | 0.81 | [258,990–272,945] |

Serres | 4.00 × 10^{−3} | 4.85 × 10^{−2} | 15.78 | 0.96 | [375,137–443,421] |

Thessaloniki | 3.90 × 10^{−3} | 4.79 × 10^{−2} | 19.54 | 0.94 | [6,268,458–7,571,520] |

Trikala | 4.60 × 10^{−3} | 5.41 × 10^{−2} | 32.77 | 0.94 | [256,379–318,363] |

Volos | 4.80 × 10^{−3} | 5.21 × 10^{−2} | 13.18 | 0.89 | [1,480,596–1,649,836] |

Xanthi | 9.80 × 10^{−3} | 7.60 × 10^{−2} | 24.43 | 0.72 | [169,605–180,582] |

DNN | Cities Comparison | ||||
---|---|---|---|---|---|

Cities | MSE (MJ^{2}) | MAE (MJ^{2}) | MAPE (%) | R^{2} | CI |

Agioi Theodoroi | 2.46 × 10^{−2} | 1.19 × 10^{−1} | 38.70 | 0.57 | [89,946–98,778] |

Alexandroupoli | 3.00 × 10^{−3} | 4.01 × 10^{−2} | 7.57 | 0.96 | [80,268–88,430] |

Athens | 1.70 × 10^{−3} | 2.75 × 10^{−2} | 7.53 | 0.97 | [7,571,538–8,863,422] |

Drama | 1.03 × 10^{−2} | 7.69 × 10^{−2} | 7.32 | 0.73 | [729,057–757,898] |

Karditsa | 3.50 × 10^{−3} | 4.84 × 10^{−2} | 25.10 | 0.95 | [230,724–290,272] |

Kilkis | 8.20 × 10^{−3} | 6.73 × 10^{−2} | 10.36 | 0.84 | [984,497–1,049,268] |

Lamia | 1.41 × 10^{−2} | 9.71 × 10^{−2} | 21.23 | 0.71 | [126,988–137,111] |

Larissa | 1.10 × 10^{−3} | 2.40 × 10^{−2} | 9.95 | 0.98 | [1,413,437–1,698,290] |

Laurio | 2.03 × 10^{−2} | 1.17 × 10^{−1} | 78,518.00 | 0.61 | [6,822,570–8,233,887] |

Markopoulo | 6.80 × 10^{−3} | 6.29 × 10^{−2} | 10.10 | 0.84 | [245,857–259,800] |

Serres | 4.50 × 10^{−3} | 5.21 × 10^{−2} | 17.46 | 0.95 | [396,910–466,370] |

Thessaloniki | 1.60 × 10^{−3} | 2.72 × 10^{−2} | 10.25 | 0.98 | [6,289,857–7,456,553] |

Trikala | 4.40 × 10^{−3} | 5.04 × 10^{−2} | 22.98 | 0.95 | [222,492–276,310] |

Volos | 5.10 × 10^{−3} | 5.70 × 10^{−2} | 11.73 | 0.89 | [1,644,087–1,825,076] |

Xanthi | 1.02 × 10^{−2} | 7.44 × 10^{−2} | 26.04 | 0.71 | [165,997–179,896] |

**Table 15.**Comparison of results between machine learning and soft computing methods for three benchmark cities.

Cities | ||||||
---|---|---|---|---|---|---|

Athens | Thessaloniki | Larissa | ||||

Methods | MSE (MJ^{2}) | MAE (MJ^{2}) | MSE (MJ^{2}) | MAE (MJ^{2}) | MSE (MJ^{2}) | MAE (MJ^{2}) |

ANN | 7.70 × 10^{−3} | 7.01 × 10^{−2} | 3.40 × 10^{−3} | 4.52 × 10^{−2} | 2.60 × 10^{−3} | 3.43 × 10^{−2} |

LSTM | 2.10 × 10^{−3} | 2.92 × 10^{−2} | 3.90 × 10^{−3} | 4.79 × 10^{−2} | 3.30 × 10^{−3} | 4.43 × 10^{−2} |

Hybrid FCM | 3.20 × 10^{−3} | 3.28 × 10^{−2} | 3.30 × 10^{−3} | 3.81 × 10^{−2} | 4.10 × 10^{−3} | 4.17 × 10^{−2} |

Ensemble (EB) | 3.10 × 10^{−3} | 3.28 × 10^{−2} | 3.10 × 10^{−3} | 3.69 × 10^{−2} | 4.00 × 10^{−3} | 4.17 × 10^{−2} |

Proposed DNN | 1.70× 10^{−3} | 2.75× 10^{−2} | 1.60× 10^{−3} | 2.72× 10^{−2} | 1.10× 10^{−3} | 2.40× 10^{−2} |

© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Anagnostis, A.; Papageorgiou, E.; Bochtis, D.
Application of Artificial Neural Networks for Natural Gas Consumption Forecasting. *Sustainability* **2020**, *12*, 6409.
https://doi.org/10.3390/su12166409

**AMA Style**

Anagnostis A, Papageorgiou E, Bochtis D.
Application of Artificial Neural Networks for Natural Gas Consumption Forecasting. *Sustainability*. 2020; 12(16):6409.
https://doi.org/10.3390/su12166409

**Chicago/Turabian Style**

Anagnostis, Athanasios, Elpiniki Papageorgiou, and Dionysis Bochtis.
2020. "Application of Artificial Neural Networks for Natural Gas Consumption Forecasting" *Sustainability* 12, no. 16: 6409.
https://doi.org/10.3390/su12166409