SUPPORT VECTOR LEARNING BASED MODELING OF A SOLAR POWER PLANT

Abstract Modeling and control of a solar power plant using support vector learning is considered in this work. The model is based on a radial basis function network architecture and uses subtractive clustering and support vector learning to find the parameters and size of the network. To achieve a more interpretable structure the proposed method proceeds in two phases. Firstly, the input-output data is clustered according to the subtractive clustering method. Secondly, the support vector learning algorithm finds the number and location of centers and the weights of the network. This approach will improve the interpretability analysis and reduces the complexity of the problem. The proposed learning scheme is applied to the distributed collector field of a solar power plant. An internal model control scheme is also suggested, in which the proposed strategy proves to be effective in modeling the plant dynamics and the corresponding inverse.

[1]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[2]  John C. Platt,et al.  Fast training of support vector machines using sequential minimal optimization, advances in kernel methods , 1999 .

[3]  James C. Bezdek,et al.  Pattern Recognition with Fuzzy Objective Function Algorithms , 1981, Advanced Applications in Pattern Recognition.

[4]  R. Yager,et al.  Approximate Clustering Via the Mountain Method , 1994, IEEE Trans. Syst. Man Cybern. Syst..

[5]  Stephen L. Chiu,et al.  Fuzzy Model Identification Based on Cluster Estimation , 1994, J. Intell. Fuzzy Syst..

[6]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[7]  John Yen,et al.  Constructing optimal fuzzy models using statistical information criteria , 1999, Proceedings Mexico-USA Collaboration in Intelligent Systems Technologies..

[8]  Chuen-Tsai Sun,et al.  Functional equivalence between radial basis function networks and fuzzy inference systems , 1993, IEEE Trans. Neural Networks.

[9]  Daniel Sbarbaro,et al.  Neural Networks for Nonlinear Internal Model Control , 1991 .

[10]  M. Berenguel,et al.  Nonlinear neural model-based predictive control of a solar plant , 1997, 1997 European Control Conference (ECC).

[11]  M. Berenguel,et al.  Incremental fuzzy PI control of a solar power plant , 1997 .

[12]  Robert Babuska,et al.  Fuzzy Modeling for Control , 1998 .

[13]  Si Wu,et al.  Improving support vector machine classifiers by modifying kernel functions , 1999, Neural Networks.

[14]  Thorsten Joachims,et al.  Making large-scale support vector machine learning practical , 1999 .

[15]  Alberto Cardoso,et al.  Supervision and c-Means clustering of PID controllers for a solar power plant , 1999, Int. J. Approx. Reason..

[16]  Martin Brown,et al.  Neurofuzzy adaptive modelling and control , 1994 .