Development a Hybrid Computational Model Based on Artificial Neural Network to Predict Natural Gas Global Demand

Authors

Abstract

Recently natural gas global market has attracted much attention since natural gas is much cleaner than oil and is also cheaper than renewable energy sources. However, price fluctuations, environmental concerns, technological developments, unconventional resources, energy security challenges, and shipment are some of the factors which have made energy market more dynamic and complex in the last decade. Studying the demand side behavior of natural gas market has been targeted by this research to focus on the plausible trends of global natural gas demands. This paper proposes a hybrid time series model which starts with data mining oriented techniques to detect input features and pre-processing data; then a neural network based prediction model is used to uncover global natural gas trends. Thirteen different features were studied, Yet six features were finally selected as the most relevant features: Alternative and Nuclear Energy, CO2 Emissions, GDP per Capita, Urban Population, Natural Gas Production, Oil Consumption. In the end, the proposed prediction model overcame other competitive models in regard to five different error-based evaluation statistics.

Keywords


[1] Hafezi, Reza, et al. "A Layered Uncertainties Scenario Synthesizing (LUSS) Model Applied to Evaluate Multiple Potential Long-Run Outcomes for Iran’s Natural Gas Exports." Energy , 169: pp. 646-659, 2018. [2] Erdogdu, E., "Natural Gas Demand in Turkey". Applied Energy, 87(1): pp. 211-219, 2010. [3] Shaffer, B., "Natural Gas Supply Stability and Foreign Policy". Energy policy, 56: pp. 114-125, 2013. [4] Smith, W.J., "Projecting EU Demand for Natural Gas to 2030: A Meta-Analysis". Energy policy, 58: pp. 163-176, 2013. [5] Heidari, H., S.T. Katircioglu, and L. Saeidpour, "Natural Gas Consumption and Economic Growth: Are We Ready to Natural Gas Price Liberalization in Iran?" Energy Policy, 63: pp. 638-645, 2013. [6] Esen, V. and B. Oral, "Natural Gas Reserve/Production Ratio in Russia, Iran, Qatar and Turkmenistan: A Political and Economic Perspective". Energy Policy, 93: pp. 101-109, 2016. [7] Matsumoto, K.i. and V. Voudouris", Potential Impact of Unconventional Oil Resources on Major Oil-Producing Countries: Scenario Analysis with the ACEGES Model". Natural Resources Research, 24(1): pp. 107-119, 2015. [8] Alipour, Mohammad, et al. "Long-Term Policy Evaluation: Application of a New Robust Decision Framework for Iran’s Energy Exports Security." Energy , 157: pp. 914-931, 2018. [9] Alipour, M., et al. "A New Hybrid Decision Framework for Prioritizing Funding Allocation to Iran's Energy Sector." Energy 121: 388-402, 2017. [10] Alipour, M., et al., "A New Hybrid Fuzzy Cognitive Map-Based Scenario Planning Approach for Iran's Oil Production Pathways in the Post–Sanction Period". Energy,135, pp. 851-864, 2017. [11] Hafezi, R., A. Akhavan, and S. Pakseresht, "Projecting Plausible Futures for Iranian Oil and Gas Industries: Analyzing of Historical Strategies". Journal of Natural Gas Science and Engineering, 39: pp. 15-27, 2017. [12] Panapakidis, I.P. and A.S. Dagoumas, "Day-Ahead Natural Gas Demand Forecasting Based on the Combination of Wavelet Transform and ANFIS/Genetic Algorithm/Neural Network Model". Energy, 118: pp. 231-245, 2017. [13] Wadud, Z., et al., "Modeling and Forecasting Natural Gas Demand in Bangladesh". Energy Policy, 39(11): pp. 7372-7380, 2011. [14] Izadyar, N., et al., "Intelligent Forecasting of Residential Heating Demand for the District Heating System based on the Monthly Overall Natural Gas Consumption". Energy and Buildings, 104: pp. 208-214, 2015. [15] Hafezi, R, et al., "A Bat-Neural Network Multi-Agent System (BNNMAS) for Stock Price Prediction: Case Study of DAX Stock Price." Applied Soft Computing 29: pp. 196-210, 2015. [16] Soldo, B., et al., "Improving the Residential Natural Gas Consumption Forecasting Models by Using Solar Radiation". Energy and buildings, 69: pp. 498-506, 2014. [17] Szoplik, J., "Forecasting of Natural Gas Consumption With Artificial Neural Networks". Energy, 85: p. 208-220, 2015. [18] Askari, S., N. Montazerin, and M.F. Zarandi, "Forecasting Semi-Dynamic Response of Natural Gas Networks to Nodal Gas Consumptions Using Genetic Fuzzy Systems". Energy, 83: pp. 252-266, 2015. [19] Ervural, B.C., O.F. Beyca, and S. Zaim, "Model Estimation of ARMA Using Genetic Algorithms: A Case Study of Forecasting Natural Gas Consumption". Procedia-Social and Behavioral Sciences, 235: pp. 537-545, 2016. [20] Fagiani, M., et al., "A Review of Datasets and Load Forecasting Techniques for Smart Natural Gas and Water Grids: Analysis and Experiments". Neurocomputing, 170: pp. 448-465, 2015. [21] Amasyali, K. and N. El-Gohary, "Building Lighting Energy Consumption Prediction for Supporting Energy Data Analytics". Procedia Engineering, 145: pp. 511-517, 2016. [22] Paudel, S., et al., "A Relevant Data Selection Method for Energy Consumption Prediction of Low Energy Building Based on Support Vector Machine". Energy and Buildings, 138: pp. 240-256, 2017. [23] Zhu, L., et al., "Short-Term Natural Gas Demand Prediction Based on Support Vector Regression With False Neighbours Filtered". Energy, 80: pp. 428-436, 2015. [24] Ramanathan, R., "A Multi-Factor Efficiency Perspective to the Relationships Among World GDP, Energy Consumption and Carbon Dioxide Emissions". Technological Forecasting and Social Change, 73(5): pp. 483-494, 2006. [25] Arsenault, E., et al., "A Total Energy Demand Model of Québec: Forecasting Properties". Energy Economics, 17(2): pp. 163-171, 1995. [26] Tolmasquim, M.T., C. Cohen, and A.S. Szklo, "CO2 Emissions in the Brazilian Industrial Sector According to the Integrated Energy Planning Model (IEPM)". Energy Policy, 29(8): pp. 641-651, 2001. [27] Intarapravich, D., et al., 3. "Asia-Pacific Energy Supply and Demand to 2010". Energy, 21(11): pp. 1017-1039, 1996. [28] Raghuvanshi, S.P., A. Chandra, and A.K. Raghav, "Carbon Dioxide Emissions from Coal Based Power Generation in India". Energy Conversion and Management', 47(4): pp. 427-441, 2006. [29] Mackay, R. and S. Probert, "Crude Oil and Natural Gas Supplies and Demands up to the Year AD 2010 for France". Applied energy, 50(3): pp. 185-208, 1995. [30] Parikh, J., P. Purohit, and P. Maitra, "Demand Projections of Petroleum Products and Natural Gas in India". Energy, 32(10): pp. 1825-1837, 2007. [31] Nel, W.P. and C.J. Cooper, "A Critical Review of IEA's Oil Demand Forecast For China". Energy Policy, 36(3): pp. 1096-1106, 2008. [32] Zhang, M., et al., "Forecasting the Transport Energy Demand Based on PLSR Method in China". Energy, 2009. 34(9): pp. 1396-1400. [33] Dincer, I. and S. Dost, "Energy and GDP". International Journal of Energy Research, 21(2): pp. 153-167, 1997. [34] Sözen, A. and E. Arcaklioglu, "Prediction of Net Energy Consumption Based on Economic Indicators (GNP and GDP) in Turkey". Energy policy, 35(10): pp. 4981-4992, 2007. [35] Ekonomou, L., "Greek Long-Term Energy Consumption Prediction Using Artificial Neural Networks". Energy, 35(2): pp. 512-517, 2010. [36] Toksarı, M.D., "Ant Colony Optimization Approach to Estimate Energy Demand of Turkey". Energy Policy, 35(8): pp. 3984-3990, 2007. [37] Ünler, A., "Improvement of Energy Demand Forecasts Using Swarm Intelligence: The case of Turkey With Projections to 2025". Energy Policy, 36(6): pp. 1937-1944, 2008. [38] Kankal, M., et al., "Modeling and Forecasting of Turkey’s Energy Consumption Using Socio-Economic and Demographic Variables". Applied Energy, 88(5): pp. 1927-1939, 2011. [39] Iniyan, S., L. Suganthi, and A.A. Samuel, "Energy Models for Commercial Energy Prediction and Substitution of Renewable Energy Sources". Energy Policy, 34(17): pp. 2640-2653, 2006. [40] Suganthi, L. and T. Jagadeesan, "A Modified Model for Prediction of India's Future Energy Requirement". Energy & Environment, 3(4): pp. 371-386, 1992. [41] Suganthi, L. and A. Williams, "Renewable Energy in India—A Modelling Study for 2020–2021". Energy policy, 28(15): pp. 1095-1109, 2000. [42] Sözen, A., E. Arcaklioğlu, and M. Özkaymak, "Turkey’s Net Energy Consumption". Applied Energy, 81(2): pp. 209-221, 2005. [43] Gorucu, F., "Evaluation and Forecasting of Gas Consumption by Statistical Analysis". Energy Sources, 26(3): pp. 267-276, 2004. [44] Ceylan, H. and H.K. Ozturk, "Estimating Energy Demand of Turkey Based on Economic Indicators Using Genetic Algorithm Approach". Energy Conversion and Management, 45(15): pp. 2525-2537, 2004. [45] Canyurt, O.E. and H.K. Ozturk, "Application of Genetic Algorithm (GA) Technique on Demand Estimation of Fossil Fuels in Turkey". Energy Policy, 36(7): pp. 2562-2569, 2008. [46] Persaud, A.J. and U. Kumar, "An Eclectic Approach in Energy Forecasting: A Case of Natural Resources Canada's (NRCan's) Oil and Gas Outlook". Energy policy, 29(4): pp. 303-313, 2001. [47] Hall, M.A., "Correlation-Based Feature Selection for Machine Learning". 1999. [48] Rich, E. and K. Knight, "Artificial Intelligence". McGraw-Hill, 1991. [49] Freitag, D. "Greedy Attribute Selection". in Machine Learning Proceedings. pp. 28-36, 1994. [50] Holland, J.H., "Adaptation in Natural and Artificial Systems", University of Michigan Press, Ann Arbor, 1975. [51] Zhang, J., et al., "Prediction of LBB Leakage for Various Conditions by Genetic Neural Network and Genetic Algorithms". Nuclear Engineering and Design, 325: pp. 33-43, 2017. [52] Anemangely, M., A. Ramezanzadeh, and B. Tokhmechi, "Shear Wave Travel Time Estimation from Petrophysical Logs Using ANFIS-PSO Algorithm: A Case Study From Ab-Teymour Oilfield". Journal of Natural Gas Science and Engineering, 38: pp. 373-387, 2017. [53] Zendehboudi, A., X. Li, and B. Wang, "Utilization of ANN and ANFIS Models to Predict Variable Speed Scroll Compressor With Vapor Injection". International Journal of Refrigeration, 74: pp. 473-485, 2017. [54] Abdi, J., et al., "Forecasting of Short-Term Traffic-Flow Based on Improved Neurofuzzy Models Via Emotional Temporal Difference Learning Algorithm". Engineering Applications of Artificial Intelligence, 25(5): pp. 1022-1042, 2012. [55] Fath, A.H., "Application of Radial Basis Function Neural Networks in Bubble Point Oil Formation Volume Factor Prediction for Petroleum Systems". Fluid Phase Equilibria, 437: pp.14-22, 2017. [56] Mohammadi, R., S.F. Ghomi, and F. Zeinali, "A New Hybrid Evolutionary Based RBF Networks Method for Forecasting Time Series: A Case Study of Forecasting Emergency Supply Demand Time Series". Engineering Applications of Artificial Intelligence, 36: pp. 204-214, 2014. [57] Park, J. and K.-Y. Kim, "Meta-Modeling Using Generalized Regression Neural Network and Particle Swarm Optimization". Applied Soft Computing, 51: pp. 354-369, 2017. [58] Hu, R., et al., "A Short-Term Power Load Forecasting Model Based on the Generalized Regression Neural Network With Decreasing Step Fruit Fly Optimization Algorithm". Neurocomputing, 221: pp. 24-31, 2017. [59] Heidari, E., M.A. Sobati, and S. Movahedirad, "Accurate Prediction of Nanofluid Viscosity Using a Multilayer Perceptron Artificial Neural Network (MLP-ANN)". Chemometrics and Intelligent Laboratory Systems, 155: pp. 73-85, 2016. [60] Kasabov, N.K., "Foundations of Neural Networks, Fuzzy Systems, and Knowledge Engineering", Marcel Alencar, 1996. [61] Hagan, M.T., H.B. Demuth, and M. Beale, "Neural Network Design". PWS Publishing Company, USA, Boston, 1996. [62] Jang, J.-S.R. "Fuzzy Modeling Using Generalized Neural Networks and Kalman Filter Algorithm". in AAAI. 91: pp. 762-767, 1991. [63] Jang, J.-S., "ANFIS: Adaptive-Network-Based Fuzzy Inference System". IEEE transactions on systems, man, and cybernetics, 23(3): pp. 665-685, 1993. [64] Lotfinejad, Mohammad Mehdi, et al. "A Comparative Assessment of Predicting Daily Solar Radiation Using Bat Neural Network (BNN), Generalized Regression Neural Network (GRNN), and Neuro-Fuzzy (NF) System: A Case Study." Energies 11(5): pp. 1188-1203, 2018. [65] Abraham, A., "Adaptation of Fuzzy Inference System Using Neural Learning". Fuzzy systems engineering, pp. 914-914, 2005. [66] Kamari, A., et al., "Decline Curve Based Models for Predicting Natural Gas Well Performance". Petroleum, 3(2): pp. 242-248, 2017. [67] Jang, J.-S.R., C.-T. Sun, and E. Mizutani, "Neuro-fuzzy and Soft Computing: S Computational Approach to Learning and Machine Intelligence", 1997. [68] Schalkoff, R.J., "Artificial Neural Networks", McGraw-Hill Higher Education, 1997. [69] Dua, D., K. Li, and MinruiFei, "A Fastmulti-Output RBF Neural Network Construction Method". Neurocomputing, 73: pp. 2196–2202, 2010. [70] Park, J. and I.W. Sandberg, Universal "Approximation Using Radial-Basis-Function Networks". Neural Computation, 3: pp. 246-257, 1991. [71] Specht, D.F., "A General Regression Neural Network". IEEE transactions on neural networks, 2(6): pp. 568-576, 1991. [72] Hafezi, Reza, and Amir Akhavan. "Forecasting Gold Price Changes: Application of an Equipped Artificial Neural Network." AUT Journal of Modeling and Simulation, 50)1): pp. 71-82, 2018.