Short term energy consumption prediction using bio-inspired fuzzy systems

This paper presents a new particle swarm optimization based fuzzy inference approach to implement short term load forecasting (STLF). Fuzzy logic algorithm is widely employed for modeling highly nonlinear systems and for handling uncertainties of current control systems. However, conventional fuzzy logic systems are incapable of handling complex problems with many input variables because of fixed rule sets and fixed membership function (MF) parameters. This work therefore presents a model-based technique to optimize the fuzzy system's membership functions using particle swarm optimization (PSO) algorithm. The PSO scheme is used for identification of fuzzy models from the input-output data. The results obtained demonstrate that the developed model has better prediction capabilities than a conventional fuzzy model for the same system with heuristically defined MFs. This therefore suggests the proposed method is an effective technique for short-term load forecasting.

[1]  G. Gross,et al.  Short-term load forecasting , 1987, Proceedings of the IEEE.

[2]  T. Funabashi,et al.  Next day load curve forecasting using hybrid correction method , 2005, IEEE Transactions on Power Systems.

[3]  Mo-Yuen Chow,et al.  Application of fuzzy logic technology for spatial load forecasting , 1996, Proceedings of 1996 Transmission and Distribution Conference and Exposition.

[4]  P. Mastorocostas,et al.  Fuzzy modeling for short term load forecasting using the orthogonal least squares method , 1999 .

[5]  S. Vemuri,et al.  Neural network based short term load forecasting , 1993 .

[6]  Abul Hasan Siddiqi,et al.  Wavelet transforms of meteorological parameters and gravity waves , 2005 .

[7]  Avelino J. Gonzalez,et al.  Short-term electrical load forecasting using a fuzzy ARTMAP neural network , 1998, Defense, Security, and Sensing.

[8]  K. Adamson,et al.  Methodologies for Load Forecasting , 2006, 2006 3rd International IEEE Conference Intelligent Systems.

[9]  A. C. Liew,et al.  Demand forecasting using fuzzy neural computation, with special emphasis on weekend and public holiday forecasting , 1995 .

[10]  S. Muto,et al.  Regression based peak load forecasting using a transformation technique , 1994 .

[11]  J. Theocharis,et al.  A novel approach to short-term load forecasting using fuzzy neural networks , 1998 .

[12]  W. Charytoniuk,et al.  Nonparametric regression based short-term load forecasting , 1998 .

[13]  Robert J. Marks,et al.  Electric load forecasting using an artificial neural network , 1991 .

[14]  Joe H. Chow,et al.  Applied mathematics for restructured electric power systems : optimization, control, and computational intelligence , 2005 .

[15]  K. K. Aggarwal,et al.  A Matlab Implementation of Swarm Intelligence based Methodology for Identification of Optimized Fuzzy Models , 2006, Swarm Intelligent Systems.

[16]  S. J. Kiartzis,et al.  A neural network short term load forecasting model for the Greek power system , 1996 .

[17]  J. Kennedy.  Social interaction is a powerful optimiser: The particle swarm , 2008 .

[18]  A. Germond,et al.  Heterogeneous artificial neural network for short term electrical load forecasting , 1995 .

[19]  Maurice Clerc,et al.  The particle swarm - explosion, stability, and convergence in a multidimensional complex space , 2002, IEEE Trans. Evol. Comput..

[20]  T. Hesterberg,et al.  A regression-based approach to short-term system load forecasting , 1989, Conference Papers Power Industry Computer Application Conference.

[21]  James Kennedy,et al.  Particle swarm optimization , 2002, Proceedings of ICNN'95 - International Conference on Neural Networks.