基于遗传优化BP神经网络算法的光伏系统最大功率点跟踪研究  

Research on the maximum power point tracking of the photovoltaic system based on the genetic optimization BP neural network algorithm

作　　者：林虹江 周步祥[1] 冉伊[1] 詹长杰[1] 杨昶宇 

机构地区：[1]四川大学电气信息学院,成都610065

出　　处：《电测与仪表》2015年第5期35-40,共6页Electrical Measurement & Instrumentation

摘　　要：针对恒压控制法中采用BP神经网络预测最大功率点处电压存在较大误差的情况,提出了用遗传算法来优化BP神经网络,然后用优化后的算法来预测光伏系统最大功率点之处的电压,并以此值代替基于恒电压的光伏发电系统MPPT控制算法中的恒电压参数;同时结合恒电压控制法建立了基于GA-BP神经网络学习算法的改进恒压型光伏系统MPPT控制的仿真模型。最后算例仿真结果证明所提的基于GA-BPNN的光伏系统MPPT控制算法能够快速准确地进行光伏最大功率点跟踪,并且相比于BP神经网络算法、干扰观察法及FUZZY控制算法其稳定性更好、精度更高。In the constant pressure control method , there is a big error when the BP neural network is adopted to pre-dict the voltage at the maximum power point .In view of this problem , the genetic algorithm was proposed in this paper to optimize the BP neural network , and then the optimized algorithm was used to predict the voltage at the maximum power point ofthe photovoltaic system and this value was substituted for the constant voltage parameter of the MPPT control algorithm for the photovoltaic power generation system based on constant voltage .At the same time , in combi-nation with the constant voltage control method , a simulation model of the improved constant voltage photovoltaic sys-tem MPPT control based on the GA-BP neural network learning algorithm was built .Finally the simulation results of examples proved that the proposed photovoltaic system MPPT control algorithm based on GA-BPNN could track down the photovoltaic maximum power point quickly and accurately , and compared with the BP neural network algorithm , the perturbation and observation method and the FUZZY control algorithm , the MPPT control algorithm had better sta-bility and higher precision .

关 键 词：恒压控制法 最大功率点跟踪 遗传算法 BP神经网络 干扰观察法 

分 类 号：TM93[电气工程—电力电子与电力传动]