摘要
光伏阵列最大功率点预测在光伏发电控制系统具有重要地位,由于光伏阵列受到温度、光强、阴影等非线性因素的影响,传统的解析方法难以获得理想的预测结果。研究了一种基于遗传算法改进的BP网络光伏阵列最大功率点预测模型,利用遗传算法的全局搜索能力,对BP神经网络的权值和阈值进行优化,有效克服了BP网络容易陷入局部最小的问题。仿真表明,基于遗传算法优化的光伏阵列最大功率点预测BP网络具有良好的泛化能力和一定的有效性。
The prediction of maximum power point of the photovoltaic array holds an important position in the photovoltaic control system. As the photovoltaic array is influenced by non-linear factors such as temperature,light intensity and shadow,the traditional analytical method can hardly obtain ideal prediction results. Based on genetic algorithm,this paper presents an improved max. power point prediction model for BP network photovoltaic array,which,by using the global search ability of genetic algorithm,optimizes BP neural network weights and thresholds,thus effectively preventing the BP network from falling into local minimum. Simulation results show that the designed prediction method has good generalization ability and produces certain effect.
出处
《电气自动化》
2014年第3期54-56,70,共4页
Electrical Automation
关键词
太阳能
光伏阵列
BP算法
遗传算法
最大功率点预测
solar power
photovoltaic array
BP algorithm
genetic algorithm
maximum power point prediction
