Recently, Vehicular edge computing (VEC) has been widely acknowledged as a promising solution for provisioning on-demand computational services to mobile users. However, because edge network resources are usually placed and interconnected through unreliable communications in a highly dynamic environment, it remains a great challenge to achieve high fault tolerance when faults and errors are unavoidable at different levels of VEC. In this paper, we propose a fault-tolerant scheduling approach with structured applications in hybrid three-tier VEC environments. The proposed approach synthesizes PB(Primary Backup) fault-tolerance model and DDQN algorithm with a Lyapunov optimization for yielding fault tolerance schedules. The simulation results show that our proposed approach outperforms traditional methods in multiple performance metrics.