Computational Modelling Technique for Short-Term Electric Load Forecasting

Main Article Content

A. R. Iyanda
O. A. Odejobi


One of the major crises facing developing countries of which Nigeria is not an exception is the problem of epileptic power supply. Fifty years after supposedly seeing the light of independence, Nigerians are still literarily living in the dark. This is due to such factors as poor and insufficient power infrastructure resulting from poor funding, mismanagement of the available power resources (both human and material), vandalism, etc contribute to the above problem. This problem has invariably led to stagnation in the kinds of investments in the country, as power is a crucial component of sustainable development. Hence, the need for developing a computational model that will help to produce a 24-hour forecast of electric load. The design was done using coloured petri net tool and implemented using fuzzy logic tool in Matlab 7. Result showed that percentage electric load consumption for raining season is lower than the one consumed in harmattan, therefore more focus should be given to generating more power during harmattan than during raining season for adequate management of the generated electric power.

Article Details



Beckman, T. J. Selecting expert system applications. AI Expert, 6(2):42–48, 1991.
BPE. Power sector frequently asked questions. Bureau of Public Enterprise, 2006. Available from Visited: May 2008
Caudill, M. Expert networks. Byte, 16 (10):108–110, 1991.
CIA. CIA world factbook 2014. Available online at, 2014. Visited April, 2014.
Dash, P. K., Liew, A. C., and Rahman, S. Peak load forecasting using fuzzy neural network. Electrical Power Systems Research, 13:19–23, 1995.
EL-Naggar, K. M. and AL-Rumaih, K. A. Electric load forecasting using genetic based algorithm, optimal filter estimator and least error squares technique: Comparative study. Transactions on Engineering, Computing and Technology, 6:138–142, 2005.
Faleye, A. Development of a computational intelligent system for short-term electric load forecasting. Master's thesis, Obafemi Awolowo University, Ile-Ife, Nigeria, 2008.
Feinberg, E.A. and Genethliou, D. Load Forecasting: Chapter 12. Available from, 2006. Date Assessed: 18/Sept/2006
Haque, M. T. and Kashtiban, A. M. Application of neural networks in power systems: A review. Transactions on Engineering, Computing and Technology Journal, 6:53–57, 2005
Iyanda, A. R., Odejobi, O. A., and Komolafe, O. A. Short-term electric load forecasting in uncertain domain: A fuzzy decision tree approach. INFOCOMP, 10:29–39, 2011.
Iyanda, A. R., Odejobi, O. A., and Ume, C. N. Development of a Web-Based Road Traffic Tutoring System for Igbo.
International Journal of Traffic and Transportation Engineering, 3(4):175–183, 2014.
Jackson, P. Introduction to Expert System., volume 3. Addison Wesley Longman Ltd., Edinburgh Gate., 3rd. ed edition, 1999.
Jeng, B., Jeng, Y., and Liang, T. Film: a fuzzy inductive learning method for automated knowledge acquisition. Decision Support Systems, 21:61–73, 1997.
KPMG (2013). A Guide to the Nigerian Power Sector. Date assessed: February, 2016.
Sun, J., Qin, S.-Y., and hua Song, Y. Fault diagnosis of electric power systems based on fuzzy petri nets. IEEE Transactions on Power Systems, 19(4):2053–2059, Nov 2004.
Tamimi, M. and Egbert, R. Short term electric load forecasting via fuzzy neural collaboration. Electrical Power Systems Research, 56:243–248, 2000.
Wu, J.S. A petri-net algorithm for multiple contingencies of distribution system operation. IEEE Transactions on Power Systems, 13(3):1164–1171, Aug 1998.
Zurawski, R. and Zhou, M. Petri nets and industrial applications: A tutorial. Industrial Electronics, IEEE Transactions on, 41(6):567–583, Dec 1994.