基于BP神经网络的并网光伏电站有功功率控制
Active Power Control of Grid Connected Photovoltaic Power Plants Based on BP Neural Network
张雪萍 1邹欢 1阮解琼 1杨彦鑫1
作者信息
- 1. 云南农业大学机电工程学院,云南 昆明 650000
- 折叠
摘要
光伏电站的输出功率受到天气等环境因素的影响,具有不确定性,提出一种大型地面并网光伏电站有功功率控制方法.利用BP神经网络对大型地面并网光伏电站输出功率展开预测,通过学习光伏电站发电单元组件的功率输出特性,获取各个组件的最大输出功率,利用递归的方式依次对光伏逆变器展开计算,获取逆变器的运行数.根据计算结果向光伏电站内的逆变器下发相应的动作指令,当光伏电站内所含逆变器全部完成指令动作后,实现对大型地面并网光伏电站有功功率控制.经实验验证表明,所提方法可以对不同环境下的光伏电站输出功率展开准确预测,且全时刻发电达标率较高.
Abstract
The output power of photovoltaic power stations is affected by environmental factors such as weather and has uncertainty.Therefore,this paper proposed a method for controlling active power of large ground grid-con-nected photovoltaic power station.Firstly,BP neural network was used to predict the output power of PV power plants.After learning the power output characteristics of the power generation unit components in the PV power plant,we ob-tained the maximum output power of component.Then,the photovoltaic inverter was calculated in a recursive manner to obtain the number of operations of the inverter.According to the calculation results,corresponding action commands were issued to the inverter in the PV power plant.When all the inverters in the PV power plant had completed the ac-tion commands,the active power control was achieved.The experimental results show that the proposed method can accurately predict the output power of PV power plant in different environments,and always has a high standard-reac-hing rate.
关键词
光伏电站/有功功率控制/功率预测/光伏逆变器Key words
Photovoltaic power plants/Active power control/Power prediction/Photovoltaic inverter引用本文复制引用
出版年
2024
NETL
NSTL
万方数据