摘要
微电网下新能源的使用促使了人们对能量优化调度的研究,储能装置是其中的关键一部分,准确识别其存储容量是实现微电网电力优化调度的任务之一。为实现对微电网下储能装置的实时容量在线识别,利用BP神经网络结构建立了储能装置容量识别模型,并引入了优化的粒子群算法PSO,实现了储能装置的实时容量在线识别。通过对比传统的BP神经网络识别结果,采用PSO-BP神经网络识别模型的容量误差在0.3%~2.4%之间,传统的BP神经网络误差范围为1.0%~21%,表明采用PSO-BP神经网络识别模型明显优于传统的BP神经网络识别模型。
The use of new energy under the micro-grid has prompted the research on energy optimal scheduling. The energy storage device is the key part,and the accurate identification of its storage capacity is one of the tasks to realize the optimal dispatching of micro-grid power. The capacity identification model of energy storage device is established by means of the structure of BP neural network,so as to realize the on-line identification of the real-time capacity of energy storage device under the microgrid;and the optimized particle swarm optimization(PSO)algorithm is introduced to realize the on-line identification of the real-time capacity of energy storage device. In comparison with the recognition results of traditional BP neural network,the capacity error of the recognition model based on PSO-BP neural network is 0.5%~13%,and the error range of the traditional BP neural network is 1.0%~21%. The recognition model using PSO-BP neural network is obviously better than that of the traditional BP neural network recognition model.
作者
吕磊
王红蕾
LU Lei;WANG Honglei(College of Electrical Engineering,Guizhou University,Guiyang 550025,China)
出处
《现代电子技术》
北大核心
2020年第12期69-73,共5页
Modern Electronics Technique
基金
国家自然科学基金资助项目(51667007)。
关键词
容量识别
储能装置
识别建模
BP神经网络
粒子群算法
在线识别
capacity identification
energy storage device
identification modeling
BP neural network
particle swarm optimization
on-line identification
