Research Papers: Energy Systems Analysis

An Artificial Neural Network in Short-Term Electrical Load Forecasting of a University Campus: A Case Study

[+] Author and Article Information
David Palchak

Department of Mechanical Engineering,
Colorado State University,
Fort Collins, CO 80523
e-mail: jd.palchak@gmail.com

Siddharth Suryanarayanan

Department of Electrical & Computer Engineering,
Colorado State University,
Fort Collins, CO 80523
e-mail: sid@colostate.edu

Daniel Zimmerle

Engines & Energy Conversion Laboratory,
Colorado State University,
Fort Collins, CO, 80523
e-mail: Dan.Zimmerle@colostate.edu

1Corresponding author.

Contributed by the Advanced Energy Systems Division of ASME for publication in the JOURNAL OF ENERGY RESOURCES TECHNOLOGY. Manuscript received February 16, 2012; final manuscript received February 7, 2013; published online May 24, 2013. Assoc. Editor: Kau-Fui Wong.

J. Energy Resour. Technol 135(3), 032001 (May 24, 2013) (6 pages) Paper No: JERT-12-1033; doi: 10.1115/1.4023741 History: Received February 16, 2012; Revised February 07, 2013

This paper presents an artificial neural network (ANN) for forecasting the short-term electrical load of a university campus using real historical data from Colorado State University. A spatio-temporal ANN model with multiple weather variables as well as time identifiers, such as day of week and time of day, are used as inputs to the network presented. The choice of the number of hidden neurons in the network is made using statistical information and taking into account the point of diminishing returns. The performance of this ANN is quantified using three error metrics: the mean average percent error; the error in the ability to predict the occurrence of the daily peak hour; and the difference in electrical energy consumption between the predicted and the actual values in a 24-h period. These error measures provide a good indication of the constraints and applicability of these predictions. In the presence of some enabling technologies such as energy storage, rescheduling of noncritical loads, and availability of time of use (ToU) pricing, the possible demand-side management options that could stem from an accurate prediction of energy consumption of a campus include the identification of anomalous events as well the management of usage.

Copyright © 2013 by ASME
Your Session has timed out. Please sign back in to continue.


Abu-El-Magd, M. A., and Sinha, N. K., 1982, “Short-Term Load Demand Modeling and Forecasting: A Review,” IEEE Trans. Syst. Man Cybern., 12(3), pp. 370–382. [CrossRef]
Shahidehpour, M., Yamin, H., Li, Z., 2002, Market Operations in Electric Power Systems Forecasting, Scheduling, and Risk Management, Wiley-IEEE Press, New York.
Soliman, S. A., Al-Kandari, A. M., 2010, Electrical Load Forecasting Modeling and Model Construction, Butterworth-Heinemann, Washington, DC.
Gibson, F. J., and Kraft, T. T., 1993, “Electric Demand Prediction Using Artificial Neural Network Technology,” ASHRAE J., 35(3), pp. 60–68.
Kalogirou, S. A., and Bojic, M., 2000, “Artificial Neural Networks for the Prediction of the Energy Consumption of a Passive Solar Building,” Energy, 25(5), pp. 479–491. [CrossRef]
Krarti, M., 2003, “An Overview of Artificial Intelligence-Based Methods for Building Energy Systems,” ASME J. Solar Energy Eng., 125(3), pp. 331–342. [CrossRef]
Plummer, J., Oatman, E., and Gupta, P. K., 1985, Strategic Management and Planning for Electric Utilities, Prentice-Hall, Englewood Cliffs, NJ.
Energy Independence and Security Act of 2007, Public Law 110–140, 110th Congress, (December 19, 2007).
Cherkassky, V., Chowdhury, S. R., Landenberger, V., Tewari, S., and Bursch, P., 2011, “Prediction of Electric Power Consumption for Commercial Buildings,” in The 2011 International Joint Conference on Neural Networks (IJCNN), pp. 666–672.
Cagno, E., and Trianni, A., 2012, “Analysis of the Most Effective Energy Efficiency Opportunities in Manufacturing Primary Metals, Plastics, and Textiles Small- and Medium-Sized Enterprises,” ASME J. Energy Resourc. Technol., 134(2), p. 021005. [CrossRef]
Loughran, D. S., and Kulick, J., 2004, “Demand-Side Management and Energy Efficiency in the United States,” Energy25(1), pp. 19–44.
“SmartMeterTM – See Your Power,” http://www.pge.com/myhome/customerservice/smartmeter/ (Accessed: February 3, 2012).
“CPS Energy to Pilot Advanced Meters,” http://www.cpsenergy.com/Services/Generate_Deliver_Energy/Energy_Delivery/AMI/index.asp (Accessed: February 3, 2012).
“Automated Meters.” http://www.austinenergy.com/Customer%20Care/Billing/AM/index.htm (Accessed: February 3, 2012).
“The Smart Grid in Ontario,” http://www.ieso.ca/imoweb/siteShared/ontarios_smart_grid.asp?sid=md (Accessed: February 3, 2012).
“Meters and More – European initiatives – Smart Grids – Innovation – Enel.com,” http://www.enel.com/en-GB/innovation/smart_grids/european_initiatives/meters_more/index.aspx (Accessed: February 3, 2012).
“ComEd – An Exelon Company | Real-time Pricing,” https://www.comed.com/sites/homesavings/pages/hsrealtimepricing.aspx (Accessed: February 3, 2012).
“NYSEG | Time-of-Use Service Rate,” http://www.nyseg.com/YourHome/pricingandrates/timeofuserate.html (Accessed: February 3, 2012).
“Time-of-Use Rate,” http://www.oru.com/programsandservices/incentivesandrebates/timeofuse.html (Accessed: February 3, 2012).
Obara, S., and Tanno, I., 2009, “Installation Plan of a Fuel Cell Microgrid System Optimized by Maximizing Power Generation Efficiency,” ASME J. Energy Resourc. Technol., 131(4), p. 042601. [CrossRef]
Himelic, J. B., and Kreith, F., 2011, “Potential Benefits of Plug-In Hybrid Electric Vehicles for Consumers and Electric Power Utilities,” ASME J. Energy Resourc. Technol., 133(3), p. 031001. [CrossRef]
Gross, G., and Galiana, F. D., “Short-Term Load Forecasting,” Proc. IEEE, 75(12): pp. 1558–1573. [CrossRef]
Lu, C.-N., Wu, H.-T., and Vemuri, S., 1993, “Neural Network Based Short Term Load Forecasting,” IEEE Trans. Power Syst.8(1), pp. 336–342. [CrossRef]
Hippert, H. S., Pedreira, C. E., and Souza, R. C., 2001, “Neural Networks for Short-Term Load Forecasting: A Review and Evaluation,” IEEE Trans. Power Syst.16(1), pp. 44–55. [CrossRef]
Zhang, G. P., 2007, “Avoiding Pitfalls in Neural Network Research,” IEEE Trans. Syst. Man Cybern., Part C Appl. Rev.37(1), pp. 3–16. [CrossRef]
Park, D. C., El-Sharkawi, M. A., Marks, R. J., Atlas, L. E., and Damborg, M. J., 1991, “Electric Load Forecasting Using an Artificial Neural Network,” IEEE Trans. Power Syst.6(2), pp. 442–449. [CrossRef]
Osman, Z. H., Awad, M. L., and Mahmoud, T. K., 2009, “Neural Network Based Approach for Short-Term Load Forecasting,” Power Systems Conference and Exposition, Paper No. PSCE’09. IEEE/PES, pp. 1–8.
Zhang, G., Eddy Patuwo, B., and Hu, M. Y., 1998, “Forecasting With Artificial Neural Networks: The State of the Art,” Int. J. Forecast., 14(1), no. 1, pp. 35–62. [CrossRef]
Haykin, S., Neural Networks a Comprehensive Foundation ( Prentice Hall, Upper Saddle River, NJ, 1999).
“GPS Coordinates Of Colorado State University Located In Fort Collins, Colorado - Latitude And Longitude Of Colorado State University,” http://www.thegpscoordinates.com/colorado/fort-collins/colorado-state-university/ (Accessed: February 4, 2012).
“Colorado State University – Facts and Figures,” http://www.colostate.edu/features/facts-figures.aspx (Accessed: February 4, 2012).
“Fort Collins, CO – Climate Summary,” http://www.wrcc.dri.edu/cgi-bin/cliMAIN.pl?co3005 (Accessed: February 7,2012).
“Fort Collins Weather Station,” http://climate.colostate.edu/∼autowx/ (Accessed: February 3, 2012).
Samarasinghe, S., Neural Networks for Applied Sciences and Engineering From Fundamentals to Complex Pattern Recognition ( Auerbach, Boca Raton, FL, 2007).
“Utilities: City of Fort Collins, 2009 Energy Policy,” http:// www.fcgov.com/utilities/what-we-do/light-power. (Accessed: February 5, 2012).
Beale, M. H., Hagan, M. T., and Demuth, H. B., 2011, Neural Network Toolbox User's Guide, R2011b ed., The Mathworks Inc., Natick, MA.
Ranaweera, D. K., Karady, G. G., and Farmer, R. G., 1996, “Effect of Probabilistic Inputs on Neural Network-Based Electric Load Forecasting,” IEEE Trans. Neural Netw., 7(6), pp. 1528–1532. [CrossRef] [PubMed]
Giacone, E., Mancò, S., and Gabriele, P., 2008, “Energy Management Techniques for Small- and Medium-Sized Companies,” ASME J. Energy Resourc. Technol., 130, p. 012002. [CrossRef]


Grahic Jump Location
Fig. 1

Monthly climatic data for Fort Collins, CO [33]

Grahic Jump Location
Fig. 2

Typical weekday and weekend load profiles

Grahic Jump Location
Fig. 3

Architecture of the ANN

Grahic Jump Location
Fig. 4

(a) MAPE versus number of neurons in the hidden layer of the ANN. (b) A zoom-in of 0-5% MAPE versus number of neurons in the hidden layer of the ANN

Grahic Jump Location
Fig. 5

Error in peak hour prediction of the 121 test days

Grahic Jump Location
Fig. 6

Typical load profile and forecast for 24-hour period

Grahic Jump Location
Fig. 7

MAPE over 242 test days



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