Tracking Of The Multi-peak PV Module's Maximum Power Point Based On The Genetic Neural Network

As the result of the lacking traditional resources (such as coal, oil natural gas, etc.) and the nuclear security crisis cased by Japanese earthquake, people begin to pay more and more their attentions to clean, renewable solar energy. So in the future, the applications of photovoltaic cells have good development of prospects. However, a low conversion efficiency of photovoltaic cells, and the higher prices have been a serious obstacle to the promotion and application of PV systems. There is a method to maximize using the power generated by PV cells: making PV cells output maximum power to reduce the circuit loss. So in this article the method of maximum power point tracking makes the PV cells working at the maximum power point to obtain the maximum output power, which will be focused research.This paper studied the structure and principle of photovoltaic battery, deeply discussed the composition of the photovoltaic system and the characteristics of system's outputs especially in non-uniform lighting conditions. Because of the nonlinear characteristics of the photovoltaic system, the neural network based on the back propagation (BP) neural network was applied in the tracking the maximum power point. The BP algorithm is the local search method based on the gradient descent, to overcome the local search character,the genetic algorithm was applied to optimize the BP neural network. This paper also established the milt-peak simulation model based on Proteus software.As for the research of the characteristics of PV modules in the non-uniform conditions, it is concluded the component I-V equation and P-V equation. And the simulation shows its output's characteristic curves, these studies lay the foundation of the tracing the maximum power.As for the research of the basic principle of the BP neural network and the system's characteristics and the neural network based on the back propagation (BP) neural network was applied in tracking the maximum power point.Because of the shortage of the BP algorithm, the genetic algorithm is put forward to optimize the neural network weigh coefficient. The experiment shows that the genetic algorithm optimizing neural network can combine with the global search character of genetic algorithm and local search character of BP algorithm. The genetic neural network can accelerate the speed of convergence (the iterative number descended form 122 to 10) and improve the accuracy(the average error descended from 0.156 to0.0021 respectively).The multi-summit PV module basing on the Proteus software is established in the non-illumination lighting conditions. Basing on the multi-summit model, we can design a multi-summit MPPT algorithm that can work under uniform isolation and non-uniform isolation.