Research Papers: Energy Systems Analysis

Predictive Modeling Techniques to Forecast Energy Demand in the United States: A Focus on Economic and Demographic Factors

[+] Author and Article Information
Angshuman Deka

Department of Mechanical
and Aerospace Engineering,
University at Buffalo-SUNY,
Buffalo, NY 14260
e-mail: angshuma@buffalo.edu

Nima Hamta

Department of Industrial
and Systems Engineering,
University at Buffalo-SUNY,
Buffalo, NY 14260
e-mail: nimahamt@buffalo.edu

Behzad Esmaeilian

Department of Industrial
and Systems Engineering,
Northern Illinois University,
DeKalb, IL 60115
e-mail: besmaeilian@niu.edu

Sara Behdad

Department of Mechanical
and Aerospace Engineering,
University at Buffalo-SUNY,
Buffalo, NY 14260;
Department of Industrial
and Systems Engineering,
University at Buffalo-SUNY,
Buffalo, NY 14260
e-mail: sarabehd@buffalo.edu

1Corresponding author.

Contributed by the Advanced Energy Systems Division of ASME for publication in the JOURNAL OF ENERGY RESOURCES TECHNOLOGY. Manuscript received May 24, 2015; final manuscript received September 13, 2015; published online October 15, 2015. Editor: Hameed Metghalchi.

J. Energy Resour. Technol 138(2), 022001 (Oct 15, 2015) (9 pages) Paper No: JERT-15-1194; doi: 10.1115/1.4031632 History: Received May 24, 2015; Revised September 13, 2015

Effective energy planning and governmental decision-making policies heavily rely on accurate forecast of energy demand. This paper discusses and compares five different forecasting techniques to model energy demand in the United States using economic and demographic factors. Two artificial neural network (ANN) models, two regression analysis models, and one autoregressive integrated moving average (ARIMA) model are developed based on the historical data from 1950 to 2013. While ANN model 1 and regression model 1 use gross domestic product (GDP), gross national product (GNP), and per capita personal income as independent input factors, ANN model 2 and regression model 2 employ GDP, GNP, and population (POP) as the predictive factors. The forecasted values resulted from these models are compared with the forecast made by the U.S. Energy Information Administration (EIA) for the period of 2014–2019. The forecasted results of ANN models and regression model 1 are close to those of the U.S. EIA; however, the results of regression model 2 and ARIMA model are significantly different from the forecast made by the U.S. EIA. Finally, a comparison of the forecasted values resulted from three efficient models showed that the energy demand would vary between 95.51 and 100.08 quadrillion British thermal unit (btu) for the period of 2014–2019. In addition, we have discussed the possibility of self-sufficiency of the United States in terms of energy generation based on the information of current available technologies nationwide.

Copyright © 2016 by ASME
Your Session has timed out. Please sign back in to continue.


EIA, “ International Energy Statistics,” U.S. Energy Information Administration, Washington, DC, http://www.eia.gov/cfapps/ipdbproject/IEDIndex3.cfm?tid=44&pid=44&aid=2
EIA, “ Annual Energy Review,” U.S. Energy Information Administration, Washington, DC, www.eia.gov/totalenergy/data/annual/index.cfm#summary
Dincer, I. , and Dost, S. , 1996, “ Energy Intensities for Canada,” J. Appl. Energy, 53(3), pp. 283–298. [CrossRef]
Bianco, V. , Manca, O. , and Nardini, S. , 2009, “ Electricity Consumption Forecasting in Italy Using Linear Regression Models,” J. Energy, 34(9), pp. 1413–1421. [CrossRef]
Mohamed, Z. , and Bodger, P. , 2005, “ Forecasting Electricity Consumption in New Zealand Using Economic and Demographic Variables,” J. Energy, 30(10), pp. 1833–1843. [CrossRef]
Ranjan, M. , and Jain, V. K. , 1999, “ Modelling of Electrical Energy Consumption in Delhi,” J. Energy, 24, pp. 351–361. [CrossRef]
Sözen, A. , and Arcaklioglu, E. , 2007, “ Prediction of Net Energy Consumption Based on Economic Indicators (GNP and GDP) in Turkey,” J. Energy Policy, 35(10), pp. 4981–4992. [CrossRef]
Sözen, A. , Arcaklioglu, E. , and Özkaymak, M. , 2005, “ Turkey's Net Energy Consumption,” J. Appl. Energy, 81(2), pp. 209–221. [CrossRef]
Sözen, A. , 2009, “ Future Projection of the Energy Dependency of Turkey Using Artificial Neural Network,” J. Energy Policy, 37(11), pp. 4827–4833. [CrossRef]
Geem, Z. W. , and Roper, W. E. , 2009, “ Energy Demand Estimation of South Korea Using Artificial Neural Network,” J. Energy Policy, 37(10), pp. 4049–4054. [CrossRef]
Geem, Z. W. , 2011, “ Transport Energy Demand Modeling of South Korea Using Artificial Neural Network,” J. Energy Policy, 39(8), pp. 4644–4650. [CrossRef]
Ekonomou, L. , 2010, “ Greek Long-Term Energy Consumption Prediction Using Artificial Neural Networks,” J. Energy, 35(2), pp. 512–517. [CrossRef]
Kankal, M. , Akpinar, A. , Kömürcü, M. I. , and Özsahin, T. S. , 2011, “ Modeling and Forecasting of Turkey's Energy Consumption Using Socio-Economic and Demographic Variables,” J. Appl. Energy, 88(5), pp. 1927–1939. [CrossRef]
Islam, S. M. , Al-Alawi, S. M. , and Ellithy, K. A. , 1995, “ Forecasting Monthly Electric Load and Energy for a Fast Growing Utility Using an Artificial Neural Network,” J. Electr. Power Syst. Res., 34(1), pp. 1–9. [CrossRef]
Pao, H. , 2006, “ Comparing Linear and Nonlinear Forecasts for Taiwan's Electricity Consumption,” J. Energy, 31(12), pp. 2129–2141. [CrossRef]
Pao, H. T. , 2009, “ Forecasting Energy Consumption in Taiwan Using Hybrid Nonlinear Models,” Energy, 34(10), pp. 1438–1446. [CrossRef]
Wang, X. , and Meng, M. , 2012, “ A Hybrid Neural Network and ARIMA Model for Energy Consumption Forecasting,” J. Comput., 7(5), pp. 1184–1190.
Avami, A. , and Boroushaki, M. , 2011, “ Energy Consumption Forecasting of Iran Using Recurrent Neural Networks,” J. Energy Sources, Part B, 6(4), pp. 339–347. [CrossRef]
Lise, W. , and Montfort, K. V. , 2005, “ Energy Consumption and GSP in Turkey: Is There a Co-Integration Relationship?,” International Conference on Policy Modeling (EcoMod2005), Istanbul, Turkey, June 29–July 2.
Soytas, U. , and Sari, R. , 2003, “ EC and GDP: Causality Relationship in G-7 Countries and Emerging Markets,” J. Energy Econ., 25(1), pp. 33–37. [CrossRef]
Paul, S. , and Bhattacharya, R. N. , 2004, “ Causality Between Energy Consumption and Economic Growth in India: A Note on Conflicting Results,” J. Energy Econ., 26(6), pp. 977–983. [CrossRef]
Yang, H.-Y. , 2000, “ A Note on the Causal Relationship Between Energy and GDP in Taiwan,” J. Energy Econ., 22(3), pp. 309–317. [CrossRef]
Ozturk, I. , and Acaravci, A. , 2010, “ The Causal Relationship Between Energy Consumption and GDP in Albania, Bulgaria, Hungary and Romania: Evidence From ARDL Bound Testing Approach,” J. Appl. Energy, 87(6), pp. 1938–1943. [CrossRef]
Egelioglu, F. , Mohamad, A. A. , and Guven, H. , 2001, “ Economic Variables and Electricity Consumption in Northern Cyprus,” J. Energy, 26(4), pp. 355–362. [CrossRef]
Soytas, U. , and Sari, R. , 2006, “ Energy Consumption and Income in G-7 Countries,” J. Policy Model., 28(7), pp. 739–750. [CrossRef]
Asafu-Adjaye, J. , 2000, “ The Relationship Between Energy Consumption, Energy Prices and Economic Growth: Time Series Evidence From Asian Developing Countries,” J. Energy Econ., 22(6), pp. 615–625. [CrossRef]
Mozumder, P. , and Marathe, A. , 2007, “ Causality Relationship Between Electricity Consumption and GDP in Bangladesh,” J. Energy Policy, 35(1), pp. 395–402. [CrossRef]
Kialashaki, A. , and Reisel, J. R. , 2013, “ Modeling of the Energy Demand of the Residential Sector in the United States Using Regression Models and Artificial Neural Networks,” J. Appl. Energy, 108, pp. 271–280. [CrossRef]
Ediger, V. S. , Akar, S. , and Ugurlu, B. , 2006, “ Forecasting Production of Fossil Fuel Sources in Turkey Using a Comparative Regression and ARIMA Model,” J. Energy Policy, 34(18), pp. 3836–3846. [CrossRef]
Ediger, V. S. , and Akar, S. , 2007, “ ARIMA Forecasting of Primary Energy Demand by Fuel in Turkey,” J. Energy Policy, 35(3), pp. 1701–1708. [CrossRef]
Saab, S. , Badr, E. , and Nasr, G. , 2001, “ Univariate Modeling and Forecasting of Energy Consumption: The Case of Electricity in Lebanon,” J. Energy, 26(1), pp. 1–14. [CrossRef]
Hang, Y. , Deyun, X. , and Zhentao, L. , 2009, “ Regional Energy Demand Modeling and Forecasting,” 6th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD '09), Tianjin, China, Aug. 14–16, pp. 599–603.
Kialashaki, A. , and Reisel, J. R. , 2014, “ Development and Validation of Artificial Neural Network Models of the Energy Demand in the Industrial Sector of the United States,” J. Energy, 76, pp. 749–760. [CrossRef]
McCulloch, W. , and Pitts, W. , 1943, “ A Logical Calculus of the Ideas Immanent in Nervous Activity,” Bull. Math. Biophys., 5(4), pp. 115–133. [CrossRef]
Song, J. , 1998, “ Neural Network Applications in Determining the Fatigue Crack Opening Load,” Int. J. Fatigue, 20(1), pp. 57–69. [CrossRef]
Moriasi, D. N. , Arnold, J. G. , Van Liew, M. W. , Bingner, R. L. , Harmel, R. D. , and Veith, T. L. , 2007, “ Model Evaluation Guidelines for Systematic Quantification of Accuracy in Watershed Simulations,” Trans. ASABE, 50(3), pp. 885–900. [CrossRef]
Chen, T.-L. , and Lu, H.-C. , 2012 “ Stochastic Multi-Site Capacity Planning of TFT–LCD Manufacturing Using Expected Shadow-Price Based Decomposition,” J. Appl. Math. Model., 36(12), pp. 5901–5919. [CrossRef]
EIA, 2015, “Primary Energy Consumption by Source,” U.S. Energy Information Administration, Washington, DC, http://www.eia.gov/totalenergy/data/monthly/pdf/sec1_7.pdf
EIA, 2015, “Primary Energy Production by Source,” U.S. Energy Information Administration, Washington, DC, http://www.eia.gov/totalenergy/data/monthly/pdf/sec1_5.pdf
Jacobson, M. Z. , and Delucchi, M. A. , 2011, “ Providing all Global Energy With Wind, Water, and Solar Power, Part I: Technologies, Energy Resources, Quantities and Areas of Infrastructure, and Materials,” J. Energy Policy, 39(3), pp. 1154–1169. [CrossRef]
Miller, J. S. , Stakenborghs, B. , and Tsai, R. , 2011, “ Improving Nuclear Power Plant's Operational Efficiencies in the USA,” 19th International Conference on Nuclear Engineering (ICONE19), Chiba, Japan, May 16–19, Paper No. ICONE19-43791.
Bagher, A. M. , Vahid, M. , Mohsen, M. , and Parvin, D. , 2015, “ Hydroelectric Energy Advantages and Disadvantages,” Am. J. Energy Sci., 2(2), pp. 17–20.
Wong, K. V. , 2014, “ Engineering Solutions to the Greenhouse Gases Generated by Hydroelectric Plants,” ASME J. Energy Resour. Technol., 136(2), p. 024701. [CrossRef]
Wong, K. V. , and Tan, N. , 2015, “ Feasibility of Using More Geothermal Energy to Generate Electricity,” ASME J. Energy Resour. Technol., 137(4), p. 041201. [CrossRef]
Fthenakis, V. , Mason, J. E. , and Zweibel, K. , 2009, “ The Technical, Geographical, and Economic Feasibility for Solar Energy to Supply the Energy Needs of the US,” J. Energy Policy, 37(2), pp. 387–399. [CrossRef]
Gupta, A. K. , 2015, “ Efficient Wind Energy Conversion: Evolution to Modern Design,” ASME J. Energy Resour. Technol., 137(5), p. 051201. [CrossRef]
Guell, B. M. , Sandquist, J. , and Sorum, L. , 2012, “ Gasification of Biomass to Second Generation Biofuels: A Review,” ASME J. Energy Resour. Technol., 135(1), p. 014001. [CrossRef]
Dhungana, A. , Basu, P. , and Dutta, A. , 2012, “ Effects of Reactor Design on the Torrefaction of Biomass,” ASME J. Energy Resour. Technol., 134(4), p. 041801. [CrossRef]
Dean, J. , Braun, R. , Penev, M. , Kinchin, C. , and Munoz, D. , 2011, “ Leveling Intermittent Renewable Energy Production Through Biomass Gasification-Based Hybrid Systems,” ASME J. Energy Resour. Technol., 133(3), p. 031801. [CrossRef]
EIA, 2015, “Primary Energy Imports by Source,” U.S. Energy Information Administration, Washington, DC, http://www.eia.gov/totalenergy/data/monthly/pdf/sec1_10.pdf
EIA, “ Primary Energy Exports by Source and Total Net Imports,” http://www.eia.gov/totalenergy/data/monthly/pdf/sec1_11.pdf


Grahic Jump Location
Fig. 1

A typical architecture of a neural network

Grahic Jump Location
Fig. 2

Process flow of the method used

Grahic Jump Location
Fig. 3

(a) Actual data versus predicted values of ANN model 1 and (b) actual data versus predicted values of ANN model 2

Grahic Jump Location
Fig. 4

(a) Actual data versus predicted values of regression model 1 and (b) actual data versus predicted values of regression model 2

Grahic Jump Location
Fig. 5

Historical and forecasted values using ARIMA

Grahic Jump Location
Fig. 6

Graphical comparison of the forecasted values from different models with U.S. EIA data




Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In