基于人工神经网络的光伏充电桩有序充电控制系统

Orderly Charging Control System of Photovoltaic Charging Pile Based on Artificial Neural Network

为了节约用户充电成本,保证单位时间内充电车辆数量,设计基于人工神经网络的光伏充电桩有序充电控制系统。在微控制器模块中,基于FPGA设计一种微控制器作为系统发挥控制功能的硬件。设计粒子群算法与极限学习机相结合的区域电动汽车充电短期负荷预测模型,实施电动汽车短期负荷预测。测试结果表明,该系统的短期负荷预测结果与实际负荷结果相近,在系统控制下,用户充电成本得到较大幅度地降低,同时电动汽车充电车辆数量有所提升。

In order to save the charging cost of users and ensure the number of charging vehicles per unit time,an orderly charging control system for photovoltaic charging pile based on artificial neural network is designed.In the microcontroller module,a microcontroller is designed based on FPGA,which is used as the hardware of the system to perform the control function.A regional electric vehicle charging short-term load forecasting model based on particle swarm optimization algorithm and limit learning machine is designed to implement electric vehicle short-term load forecasting.The test results show that the short-term load prediction results of the system are very close to the actual load results.Under the control of the system,the user charging cost is greatly reduced,and the number of electric vehicle charging vehicles is increased.It proves that this experiment is feasible.