As the general mobile edge computing (MEC)scheme cannot adequately handle the emergency communicationrequirements in vehicular networks, unmanned aerial vehicle(UAV)-assisted vehicular edge computing networks (VECNs) areenvisioned as the reliable and cost-efficient paradigm for themobility and flexibility of UAVs. UAVs can perform as thetemporary base stations to provide edge services for road vehicleswith heavy traffic. However, it takes a long time and huge energyconsumption for the UAV to fly from the stay charging stationto the mission areas disorderly. In this paper, we design a predispatchUAV-assisted VECNs system to cope with the demandof vehicles in multiple traffic jams. We propose an optimalUAV flight trajectory algorithm based on the traffic situationawareness. The cloud computing center (CCC) server predictsthe real-time traffic conditions, and assigns UAVs to differentmission areas periodically. Then, a flight trajectory optimizationproblem is formulated to minimize the cost of UAVs, while boththe UAV flying and turning energy costs are mainly considered. Inaddition, we propose a deep reinforcement learning(DRL)-basedenergy efficiency autonomous deployment strategy, to obtain theoptimal hovering position of UAV at each assigned mission area. Simulation results demonstrate that our proposed method canobtain an optimal flight path and deployment of UAV with lowerenergy consumption.