A MPPT Control Algorithm Based on Extreme Learning Machine in PV System

Abstract:

At present, there are many commonly used maximum power point tracking (MPPT) control methods for solar photovoltaic system which have different degrees of output fluctuations. In order to solve the problem and improve the response speed further, a novel MPPT algorithm based on the extreme learning machine was put forward in this paper. Using the extreme learning machine which has small error, fast speed and simple structure train a mathematical model with the environmental temperature and light intensity as input and the maximum power point as output, the model can be used as the controller of the photovoltaic cells. The simulation results show that the error of the model meets the requirements, when the ambient temperature and light intensity change, it can respond quickly so as to photovoltaic cells work at the maximum power point and operate stably.

• Periodical: Advanced Materials Research (Volumes 791-793)
• Pages: 1214-1219
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.791-793.1214
• Online since: September 2013
• Authors: Jie Wang, Kai Zhang
• Keywords: Extreme Learning Machine, MPPT, Photovoltaic (PV), Rapid, Simulink

References

[1] Chen Danping. Simulation and analysis of commonly using Mppt algorithm of photovoltaic power generation system [J]. Application of power supply technology, 2012, 15 (7): 9-13.

[2] Song Liang, Wang Xiaodong, Liu Wen et al. Research status of photovoltaic battery MPPT disturbance observation method [J]. Semiconductor optoelectronics, 2012, 33 (4): 455-462.

[3] Li Lan, Tong Yi. The maximum power point tracking of photovoltaic cells variable-step incremental conductance method In photovoltaic power generation [J]. Electric technology, 2012 (6): 37-40.

[4] Zhu Minglian, Li Chensong et al. Application of the variable step perturbation and observation method in the photovoltaic system MPPT [J]. Power electronics, 2010, 44 (1): 20-22.

[5] Wu Junjuan, Jiang Yida et al. A improved photovoltaic system MPPT control algorithm [J]. Journal of solar energy, 2010, 33 (3): 478-484.

[6] Li Xingpeng, Shi Qingjun et al. Application of double fuzzy control method in the photovoltaic power generation system MPPT [J]. Electric power automation equipment, 2012, 32 (8): 113-117.

[7] Zhao Zhengming, Liu Jianzheng et al. Solar photovoltaic power generation and its application [M]. Beijing: Science Press, 2010: 20-28.

[8] S. Tamura, M. Tateishi. Capability and storage capacity of a four-layered feedforward neural network [J]. IEEE Transaction on Neural Network, 2011, 8(2): 251-255.

DOI: 10.1109/72.557662

[9] G-B Hang. Learning capability and storage capacity of two-hidden-layer feedforward networks [J]. IEEE Transaction on Neural Network, 2012, 14(2): 274-281.

DOI: 10.1109/tnn.2003.809401

[10] Huang GB, Zhu QY and Siew CK. Extreme learning machine：theory and applications [J]. Neurocomputing, 2011(7): 489-501.

[11] Chang Yuqing, Li Yuzhao, Wang Fuli et al. The biochemical processes of soft measurement modeling based on extreme learning machine [J]. System simulation, 2011, 19 (23): 5587-5590.