Virtual power plant（VPP）, as an aggregated energy system, is faced with a difficult problem that the uncertain wind power and solar power and the random charging behavior of electric vehicles affect its economy. Therefore, a virtual power plant bidding strategy that takes into account diverse un-certainties is proposed, which can improve the absorption capacity of renewable energy and in-crease the income level. Firstly, the particle swarm optimization（PSO）-long term memory（LSTM）algorithm is used to convert the wind power and EV charging demand into deterministic scenarios based on the real data and the charging capacity boundaries. Then, considering the uncertainty of group loads of renewable energy and electric vehicles, a bidding strategy model of virtual power plant is established based on the output deviation variables and the Cournot game. Finally, a numerical example is given to verify the effective-ness of the proposed model.