基于改进神经网络的一种新型光伏发电MPPT预测方法
|
摘要
为了解决光伏系统太阳能利用效率低,最大功率点追踪不够快速准确,局部阴影等问题,提出了一种基于改进遗传算法优化的BP神经网络最大功率点跟踪(MPPT)算法,在总结现有研究成果的基础上,提出了一种线性度更好的预测指标。经Matlab仿真验证,该新型算法有效缩短了MPPT的跟踪时间,并明显的提高了预测精度。
In order to solve the problems such as low efficiency of solar energy utilization, fast and accurate maximum power point tracking and local shadow, an improved genetic algorithm(MPPT) for BP neural network is proposed. In order to overcome the shortcomings of the traditional BP neural network prediction algorithm, this algorithm uses the gradient descent method and the Gauss Newton method to improve the convergence speed, and avoids getting into the local minimum value by BP neural network optimized by genetic algorithm. On the basis of summarizing the existing research results, a better linearity predictor is proposed. The simulation results show that the new algorithm can effectively shorten the MPPT tracking time and improve the prediction accuracy.
In order to solve the problems such as low efficiency of solar energy utilization, fast and accurate maximum power point tracking and local shadow, an improved genetic algorithm(MPPT) for BP neural network is proposed. In order to overcome the shortcomings of the traditional BP neural network prediction algorithm, this algorithm uses the gradient descent method and the Gauss Newton method to improve the convergence speed, and avoids getting into the local minimum value by BP neural network optimized by genetic algorithm. On the basis of summarizing the existing research results, a better linearity predictor is proposed. The simulation results show that the new algorithm can effectively shorten the MPPT tracking time and improve the prediction accuracy.
引文
[1]赵争鸣,陈剑,孙晓瑛.太阳能光伏发电最大功率点跟踪技术[M].北京:电子工业出版社,2011.
[2]杨小煜,周孝信,李立新.利用混合块消去算法的电压稳定负荷裕度灵敏度计算[J].中国电机工程学报,2012,32(31):134-142.
[3]胥芳,张任,吴乐彬,等.自适应BP神经网络在光伏MPPT中的应用[J].太阳能学报,2012, 33(3):468-472.
[4]刘昇,徐政,华文,等.用于在线预测静态电压稳定性的SIPSS-Lasso-BP网络[J].中国电机工程学报,2014,34(34),6032-6041.
[5]刘晓楠,王胜辉,金月新.基于附加动量的小波神经网络风电功率短期预测[J].沈阳工程学院学报,2015(2):101-106.
[6]马宁,马光,李长明.BP网络局部极小值的修正算法[J].北华航天工业学院学报,2007,17(5):24-27.
[7]马斌,马艳丽.一种基于径向基神经网络的短期风电功率直接预测方法[J].电力系统保护与控制,2015, 43(19):78-82.
[8]钱军,李欣然,王玲,等.面向负荷的光伏电池和燃料电池建模及其等效描述[J].电网技术,2011(4):135-142.
[2]杨小煜,周孝信,李立新.利用混合块消去算法的电压稳定负荷裕度灵敏度计算[J].中国电机工程学报,2012,32(31):134-142.
[3]胥芳,张任,吴乐彬,等.自适应BP神经网络在光伏MPPT中的应用[J].太阳能学报,2012, 33(3):468-472.
[4]刘昇,徐政,华文,等.用于在线预测静态电压稳定性的SIPSS-Lasso-BP网络[J].中国电机工程学报,2014,34(34),6032-6041.
[5]刘晓楠,王胜辉,金月新.基于附加动量的小波神经网络风电功率短期预测[J].沈阳工程学院学报,2015(2):101-106.
[6]马宁,马光,李长明.BP网络局部极小值的修正算法[J].北华航天工业学院学报,2007,17(5):24-27.
[7]马斌,马艳丽.一种基于径向基神经网络的短期风电功率直接预测方法[J].电力系统保护与控制,2015, 43(19):78-82.
[8]钱军,李欣然,王玲,等.面向负荷的光伏电池和燃料电池建模及其等效描述[J].电网技术,2011(4):135-142.