Modeling and Empirical Evaluation of Machine Learning Based Load Forecasting Models for Pakistan
Abstract
Electric load forecasting (LF) deals with predicting futuristic energy demand of consumers. It is the foremost and important step of energy distribution and generation planning. Machine learning based statistical and artificial intelligence techniques are widely used for LF. Among these, artificial neural networks (ANN) and support vector machines (SVM) emerge as competitive modeling approaches for LF. To further improve the performance of these models, optimization techniques are being used to formulate hybrid LF models. Availability of modern approaches motivated authors to solve the issues with power planning in Pakistan. Hence, we contribute towards proposing machine learning based accurate model of LF on Pakistan power system data set. Several forecasting models are formed using hybrid optimization and model development techniques, which are ranked against their forecasting accuracy and performance. SVM based models performed well and achieved 98.91% accuracy of forecasts. On the other hand, ANN based models showed comparable performance achieving 98.34% accuracy with added ability to avoid over-fitting, and efficiency with improved results.References
L. Suganthiand A.A Samuel, Renewable and Sustainable Energy
Reviews 16 (2012) 1223.
H.K.Alfares and M.Nazeeruddin, Int. J. Sys. Sci. 33 (2010) 23.
H.Hahn, S.Meyer-Nieberg and S.Pickl, European Journal of
Operational Research 199 (2009) 902.
C. Xia, J. Wang and K. McMenemy, International Journal of
Electrical Power & Energy Systems 32 (2010) 743.
E.E. Elattar, J. Goulermas and Q.H. Wu, IEEE Transactions on
Applications and Reviews 40 (2010) 438.
N. Amjady and F. Keynia, Energies 4 (2011) 488.
J. Che, J. Wang and G. Wang, Energy 37 (2012) 657.
A. Kavousi-Fard, Journal of Experimental & Theoretical Artificial
Intelligence 25 (2013) 543.
S. Haykin, Neural Networks: A Comprehensive Foundation, Chapter
-7, 2nd edn. Prentice Hall PTR, NJ, USA (1999) 190.
V.N.Vapnik, The Nature of Statistical Learning Theory, Chapter 5-6,
Springer-Verlag, NY, USA (1995) 131.
O. Chapelle, V. Vapnik, O. Bousquet and S. Mukherjee, Machine
Learning 46 (2002) 131.
S. Sra, S. Nowozin and S.J. Wright, Optimization for Machine
Learning, Chapter 1, MIT Press (2011) 5.
A.S. Ahmad, M.Y. Hassan, M.P. Abdullah, H.A. Rahman,
F. Hussin, H. Abdullah and R. Saidur, Renewable and Sustainable
Energy Reviews 33 (2014) 102.
G. OÄŸcu, O.F. Demirel and S. Zaim, Social and Behavioral Sciences
(2012) 1576.
L.J. Soares and M.C. Medeiros, Int. J. Forecast. 24 (2008) 630.
J.W.Taylor, and P.E. McSharry, IEEE Transactions on Power
Systems 22 (2007) 2213.
B.M.Wilamowski and H.Yu, IEEE Transactions on Neural
Networks 21 (2010) 930.
L.M.Saini and M.K. Soni, Generation, Transmission and
Distribution, IEEE Proceedings 149 (2002) 578.
H.A.O. Junior, L. Ingber, A. Petraglia, M.R. Petraglia and M.A.S.
Machado, Adaptive Simulated Annealing, Stochastic Global
Optimization and Its Applications with Fuzzy Adaptive Simulated
Annealing 35 (2012) 33, Springer.
P.-F.Pai and W.C.Hong, Energy Conversion and Management 46
(2005) 2669.
J. Kennedy, Particle Swarm Optimization, Encyclopedia of Machine
Learning (2010) 760.
Y. Huang, D. Li, L. Gao and H. Wang, Proc. IEEE Conf. on Control
and Decision 1 (2009) 1448.
L.M. Saini, Electric Power Systems Research 78 (2008) 1302.
X.-S.Yang, S.S.S. Hosseini and A.H.Gandomi, Applied Soft
Computing 12 (2012) 1180.
D. Karaboga and C. Ozturk, Applied Soft Computing 11 (2011) 652.
W.-C.Hong, Energy 36 (2011) 5568.
Z. Hu, Y. Bao and T. Xiong, The Scientific World Journal 1
(2013)10.
A.U. Haque, P. Mandal, J. Meng and R.L. Pineda, Procedia
Computer Science 12 (2012) 320.
R.J. Hyndman and A.B. Koehler, Int. J. Forecast. 22 (2006) 679.