ANFIS and Multi Linear Regression to Estimate the LTLF for the Kingdom of Bahrain

<- Back to VIII. Economics & Management Vol. 5

Cite the paper

Mohamed Y. Al-Hamad & Isa S. Qamber (2016). ANFIS and Multi Linear Regression to Estimate the LTLF for the Kingdom of Bahrain. Mechanics, Materials Science & Engineering, Vol 5. doi:10.13140/RG.2.1.3552.1524

AuthorsMohamed Y. Al-Hamad, Isa S. Qamber

ABSTRACTIn the present study, Multiple Linear Regression Method and Adaptive Neuro-Fuzzy Inference System (ANFIS) are designed for output estimated Long Term Estimated Load for the Kingdom of Bahrain. Three variables used as inputs, which are Present Peak Load, Gross Domestic Product (GDP) and Population versus years. Obtaining the estimated Peak Loads calculated using the multi linear regression and ANFIS. The MATLAB Simulink 7.10 package used to obtain the estimated peak load for the Kingdom of Bahrain. The models obtained using the multi linear regression and Neuro-Fuzzy techniques. Bahrain Population and GDP used in the Multiple Linear Regression Model. Different GDP growth scenario based on development in the country used and taken in consideration. The results used for the Peak Demand will compared with actual peaks data. The average percentage of error for each model calculated based on data used to generate the model, where the less average error model presented and recommended for the long-term load forecast for the peak load demand.

Keywords: ANFIS, GDP, MATLAB, Bahrain, LTEL

DOI 10.13140/RG.2.1.3552.1524


[1] GCC Electrical Interconnection Grid – Market Study Report 2004 – GIC / SNC Lavalin Int. / White & Case LLP, March 2004.

[2] Ahmed A. AL-Ebrahim (2005) “Towards Creating Competitive Electricity Markets in the Middle East” – 23rd Arab Engineering Conference – Bahrain – March 2005.

[3] Nayef S. Al-Haddad, & Mohamed Y. Al-Hamad, “Power trading through the Interconnector: Initiation of a local GCC Power market and overcoming challenges”, 21-24 April, session 215, LISBON 2013.

[4] Isa S. Qamber, M. Al-Hamad, and A. Al-Jamea, “Kingdom of Bahrain Load Forecasting Using Neuro-Fuzzy”, Second IEEE-GCC Conference and Exhibition, 23-25 November, 2004, Manama, Kingdom of Bahrain.

[5] E. Kyriakides, M. Polycarpou (2007) “Short term electric load forecasting” A tutorial.In: Chen, K., Wang, L. (Eds.), Trends in Neural Computation, Studies in Computational Intelligence, vol. 35. Springer, P. 391-418 (Chapter 16).

[6] J. Yang, Power system short-term load forecasting. PhD Thesis, 2006, TU Darmstadt.

[7] H. Heiko, M. Silja, Stefan Pickl. (2009) “Electric load forecasting methods- tools for decision making”, ELSEVIER, European Journal of Operational Research, 199, P. 902-907.  doi:10.1016/j.ejor.2009.01.062

[8] E. Gonzalez-Romera, M. A. Jaramillo-Moran, D. Carmona-Fernandez (2006) “Monthly electric energy demand forecasting based on trend extraction”. IEEE Transactions on Power Systems 21 (4), P. 1946–1953. doi:10.1109/TPWRS.2006.883666

[9] E. A. Feinberg, D. Genethliou. Load forecasting. In: Chow, J.H., Wu, F.F., Momoh, J.J. (Eds.) (2005) “Applied Mathematics for Restructered Electric Power Systems” Optimization, Control and Computational Intelligence, Power Electronics and Power Systems. Springer, US, P. 269–285.

[10] Toly Chen, Yu-Cheng Wang (2012) “Long-term load forecasting by a collaborative fuzzy-neural approach”, International Journal of Electrical Power & Energy Systems, Volume 43, Issue 1, December 2012, P. 454–464.  doi:10.1016/j.ijepes.2012.05.072

[11] Bayram Akdemir and Nurettin Çetinkaya (2012) “Long-term load forecasting based on adaptive neural fuzzy   inference system using real energy data”, Energy Procedia, 2011 2nd International Conference on Advances in Energy Engineering (ICAEE),Volume 14, P. 794–799. 

[12] Soliman A. Soliman, Ahmad M. Al-Kandari (2010) “Electrical Load Forecasting: Modeling and Model Construction”, Chapter 3 “Load Modeling for Short-Term”, Elsevier Inc., P. 79-97.

[13] H.L. Willis, L.A. Finley, M.J. Buri (1995) “Forecasting electric demand of distribution system in rural and sparsely populated regions”, IEEE Trans. Power Syst. 10 (4), P. 2008–2013. doi:10.1109/59.477100

[14] P.H. Henault, R.B. Eastvedt, J. Peschon, L.P. Hajdu (1970) “Power system long term planning in the presence of uncertainty”, IEEE Trans. Power Apparatus Syst. PAS-89, P. 156–164. doi:  10.1109/TPAS.1970.292684

[15] Soliman A. Soliman, Ahmad M. Al-Kandari (2010) “Electrical Load Forecasting: Modeling and Model Construction”, Chapter 9 “Load Modeling for Long-Term”, Elsevier Inc., P. 353-407.

[16] Central Information Organization, website address, Kingdom of Bahrain.

Creative Commons Licence
Mechanics, Materials Science & Engineering Journal by Magnolithe GmbH is licensed under a Creative Commons Attribution 4.0 International License.
Based on a work at