There may exist system operational risks and the risks of losing the revenue because of the generating uncertainty of the stochastic units during the operational process of the virtual power plant (VPP),which contains multiple large scale stochastic units. To solve these problems existing in VPP,a two-stage bi-level decentralized planning (BLDP) model incorporating the conditional value-at-risk (CVaR) based on the characteristics of hierarchical control in the multi-agent system is built. Multi objective programming (MOP) model is selected and compared with the BLDP model constructed in this paper to verify the effectiveness of the BLDP model. It indicates that when VPP participates in the market independently and trades with other VPPs under the BLDP scenario,the system will achieve higher profits and be affected less by the risk levels. Meanwhile,the system can get higher yield rate under BLDP scenario than that under MOP scenario under different trading mechanisms,when VPP participates the power market independently without mutual dealing,results obtained under the BLDP scenario are 103% higher than that under the MOP scenario,while when it takes part in both the market and mutual dealing,the results under the BLDP scenario are 147% higher than that under the MOP scenario. The results have demonstrated the availability of the proposed model under different risk levels.