Abstract
Electrical load forecasting plays a vital role in the operation, scheduling, maintenance and planning of electrical power generation and distribution companies. A novel hybrid system based on the neural implementation of fuzzy logic models of the nonlinear and chaotic electrical load time series is presented in this chapter. Being a universal function approximator, the hybrid neural-fuzzy system can very accurately capture the nonlinearity and chaotic behavior of electrical load series. A hybrid network’s performance is further largely improved from the application of moving average filter and fuzzy clustering on electrical load data along with least square error estimation of rules’ consequents. This, in turn, makes the short-term and mid-term forecasting of electrical load feasible. The results presented at the end confirm the efficacy of the neural-fuzzy system as a good electrical load forecaster.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Box, G.E.P., Jenkins, J.M.: Time Series Analysis: Forecasting and Control, Revised edn. Holden-Day, San Francisco (1976)
Jang, J.S.R.: ANFIS: Adaptive network based fuzzy inference system. IEEE Trans. System, Man and Cybernetics 23(3), 665–685 (1993)
Khotanzad, A., Afkhami-Rohani, R., Lu, T.L., Abaye, A., Davis, M., Maratukulam, D.J.: ANNSTLF – A neural-network based electric load forecasting system. IEEE Trans. on Neural Networks 8(4), 835–845 (1997)
Mamdani, E.H.: Application of fuzzy logic to approximate reasoning using linguistic systems. Fuzzy Sets and Systems 26, 1182–1191 (1977)
Palit, A.K., Babuška, R.: Efficient training algorithm for Takagi-Sugeno type neuro-fuzzy network. In: Proc. of FUZZ-IEEE, Melbourne, Australia, vol. 3, pp. 1538–1543 (2001)
Palit, A.K., Doeding, G., Anheier, W., Popovic, D.: Backpropagation based training algorithm for Takagi-Sugeno network to forecast electrical load time series. In: Proc. of FUZZ-IEEE, Honolulu, Hawaii, USA, vol. 1, pp. 86–91 (2002)
Palit, A.K., Popovic, D.: Computational Intelligence in Time Series Forecasting, Theory and Engineering Applications. Springer, London (2005)
Park, D.C., El-Sharkawi, M.A., Marks II, R.J., Atlas, L.E., Damborg, M.J.: Electric load forecasting using an artificial neural network. IEEE Trans. on Power Systems 6(2), 442–449 (1991)
Pedrycz, W.: An identification algorithm in fuzzy relational systems. Fuzzy Sets and Systems 13, 153–167 (1984)
Setnes, M., Babuška, R., Kaymark, U.: Similarity measures in fuzzy rule base simplification. IEEE Trans. System, Man and Cybernetics 28, 771–778 (1998)
Wang, L.X., Mendel, J.M.: Back-propagation fuzzy system as nonlinear dynamic system identifiers. Proc. of FUZZ-IEEE 2, 1409–1418 (1992)
Xiaosong, D., Popovic, D., Schulz-Ekloff, G.: Oscillation resisting in the learning of backpropagation neural networks. In: Proc. of 3rd IFAC/IFIP workshop on algorithm and architectures for real-time control (AARTC), Ostend, Belgium, pp. 21–25 (1995)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Palit, A.K., Anheier, W., Popovic, D. (2009). Electrical Load Forecasting Using a Neural-Fuzzy Approach. In: Chiong, R., Dhakal, S. (eds) Natural Intelligence for Scheduling, Planning and Packing Problems. Studies in Computational Intelligence, vol 250. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-04039-9_6
Download citation
DOI: https://doi.org/10.1007/978-3-642-04039-9_6
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-04038-2
Online ISBN: 978-3-642-04039-9
eBook Packages: EngineeringEngineering (R0)