On-line neural network training for maximum power point tracking of PV power plant

Abstract

The paper presents a new method to achieve maximum power point tracking (MPPT) for practical grid-connected PV panels. The method employs the radial basis function neural network (RBFNN) to predict the PV plant's maximum power points corresponding to different weather conditions. The RBFNN model can be trained on-line, autonomously, using a simplified genetic algorithm (SGA). The method has been verified by modelling the MPP points for practical PV panels located in Southampton and Leeds, respectively. The Leeds model has been used to control a prototype PV-grid-connected power generation system. The on-line RBFNN training scheme is discussed in detail and experimental results are presented which compared favourably with the conventional perturbation and observation (P&O) technique.

Keywords

genetic algorithm maximum power point tracking photovoltaic power generation radial basis function neural network

Get full access to this article

View all access options for this article.

References

Al-Amoudi, A.O. and Zhang, L. 2000: Application of radial basis function networks for solar-array modelling and maximum power point prediction. IEE Proceedings of Generation, Transmission and Distribution 147, 310—16.

Bai, Y.F. 2003: Internet based modelling and control for grid-connected photovoltaic power generation systems using artificial neural networks. PhD thesis, University of Leeds.

Chen, S. , Wu, Y. and Luk, B.L. 1999: Combined genetic algorithm optimization and regularized orthogonal least squares learning for radial basis function networks. IEEE Transactions on Neural Networks 10, 1239—43.

dSpace. 2000: DS1102 DSP controller board installation and configuration guide.

Gow, J.A. and Manning, C.D. 1999: Development of a photovoltaic array model for use in power electronics simulation study. IEEE Proceedings on Electric Power Applications 146, 193—200.

Haykin, S. 1994: Neural networks: a comprehensive foundation. Prentice Hall.

Hiyama, T. , Kouzuma, S. and Imakubo, T. 1995: Identification of optimal operating point of PV modules using neural network for real time maximum power tracking control. IEEE Transactions on Energy Conversion 10, 360—66.

Hiyama, T. and Kitabayashi, K. 1997: Neural network based estimation of maximum power generation from PV module using environmental information. IEEE Transactions on Energy Conversion 12, 241—47.

Hua, C. , Lin, O. and Shen, C. 1998: Implementation of a DSP-controlled photovoltaic system with peak power tracking. Industrial, IEEE Transactions on Electronics 45, 99—107.

10.

Hussein, K. , Muta, I. , Hoshino, T. and Osakada, M. 1995: Maximum photovoltaic power tracking: an algorithm for rapidly changing atmospheric condition. IEE Proceedings of Generation, Transmission and Distribution 142, 59—64.

11.

Kuo, Y. , Liang, T. and Chen, J. 2001: Novel maximum power point tracking controller for photovoltaic energy conversion system. IEEE Transactions on Industrial Electronics 48, 594—601.

12.

Merwe, L. and Merwe, G. 1998: Maximum power point tracking — implementation strategies . Proceedings ISIE '98. IEEE International Symposium Vol. 1, 214—17.

13.

Murphy, J.M.D. and Turnbull, F.G. 1990: Power electronic control of AC motors. Pergamon Press.

14.

Winter, G. 1995: Genetic algorithm in engineering and computer science . Wiley.

15.

Zhang, L. and Bai, Y.F. 2005: Genetic algorithm-trained radial basis function neural networks for modelling photovoltaic panels. Engineering Application of Artificial Intelligence 18, 833—44.

16.

Zhang, L. , Watthanasarn, C. and Hardan, F. 1994: An efficient microprocessor-based pulse width modulation using space vector modulation strategy. IEEE IECON 94 Conference, 5—9 September, Bologna, 91—96.