基于遗传算法小波神经网络的光伏微网发电预测  

Application for photovoltaic micro-grid power forecasting using improved wavelet neural networks-based on GA

作　　者：刘爱国[1] 黄泽平[1] 薛云涛 汪硕承 

机构地区：[1]南昌大学信息工程学院,南昌330031

出　　处：《电测与仪表》2017年第7期28-33,共6页Electrical Measurement & Instrumentation

摘　　要：准确预测光伏微网在未来某确定的时段内的发电功率,对电力系统稳定和经济运行有着重要意义。文中通过对比发电功率和气象等历史数据,分析了在光伏发电中天气、太阳辐射及温度等因素对发电功率预测的影响,同时综合遗传算法全局快速寻优特性与小波分析的时频局部特性,建立基于遗传算法的小波神经网络光伏微网发电预测模型。结果表明,基于遗传算法的小波神经网络模型的学习能力和泛化能力更强,同时把气象预测数据作为网络的输入有利于提高模型的预测精度。It is important for the energy conservation and emissions reduction to accurately predicate the power of photovoltaic micro-grid in a certain period of time in the future. In this paper, by comparing the power generation and meteorological history data, analyzes the factors such as weather, solar radiation and temperature in the photovoltaic power generation prediction, meanwhile, based on the global optimization searching performance of the genetic algo- rithm and the time-frequency localization of the wavelet neural networks, micro-grid photovoltaic power generation forecasting model has been established. Through case analysis, the results show that wavelet neural network based on genetic algorithm has better learning ability and generalization ability. And in the aspect of micro-grid photovoltaic power, the forecasting data as the network input is more valuable in improving the prediction precision of the model.

关 键 词：光伏微网 光伏功率预测 气象因子 遗传算法 小波神经网络 

分 类 号：TM77[电气工程—电力系统及自动化]