Abstract:With the rapid development of electric vehicles, accurately identifying the working status of electric vehicles can enable the power grid to fully mobilize electric vehicles as a distributed resource, thereby achieving goals such as power grid scheduling. Therefore, this article proposes a parameter identification technology for electric vehicle charging models based on intelligent algorithms. Firstly, this article constructs a corresponding electric vehicle charging model based on the charging characteristics of electric vehicles. Secondly, the least squares method and ensemble learning algorithm are used to identify the parameters of electric vehicle charging efficiency in both constant and dynamic states. Finally, the identified parameters were substituted into the electric vehicle charging model to generate the time series differential sequence of the electric vehicle''s state of charge, which was compared with the time series differential sequence of the state of charge in the original data for error evaluation, verifying the accuracy of the identified parameters.