Coordinated Prediction Model of Microgrid Power Generation with Electric Vehicle Participation Based on LSTM and Kalman Filtering Algorithm

Inhalt:
With the development of power storage technology, a huge breakthrough has been made in the ability to shave peaks and fill valleys. When the charging and discharging function of electric vehicles is introduced, with the continuous optimization of technology and algorithms, a considerable number of users will choose to use the charging and discharging characteristics to reduce the cost of daily car use. However, the flow of this power supply method is unstable. For this unstable power supply source, how to use it reasonably is a difficult problem for microgrid scheduling. In this paper, LSTM long short-term memory neural network and Kalman filter algorithm are introduced. According to the historical data of power generation provided by various power generation methods and power consumption, combined with the popularization progress of electric vehicles, a coordinated prediction model of microgrid power generation is constructed. And compared with the traditional LSTM neural network prediction model and the back-propagation neural network prediction model. The experimental results show that the prediction results of this method have good accuracy and stability.