This paper proposes a collaborative scheduling strategy for computing resources of the Internet of vehicles considering location privacy protection in the mobile edge computing environment. Firstly, a multi area multi-user multi MEC server system is designed, in which a MEC server is deployed in each area, and multiple vehicle user equipment in an area can offload computing tasks to MEC servers in different areas by a wireless channel. Then, considering the mobility of users in Internet of vehicles, a vehicle distance prediction based on Kalman filter is proposed to improve the accuracy of vehicle-to-vehicle distance. However, when the vehicle performs the task, it needs to submit the real location, which causes the problem of the location privacy disclosure of vehicle users. Finally, the total cost of communication delay, location privacy of vehicles and energy consumption of all users is formulated as the optimization goal, which take into account the system state, action strategy, reward and punishment function and other factors. Moreover, Double DQN algorithm is used to solve the optimal scheduling strategy for minimizing the total consumption cost of system. Simulation results show that proposed algorithm has the highest computing task completion rate and converges to about 80% after 8000 iterations, and its performance is more ideal compared with other algorithms in terms of system energy cost and task completion rate, which demonstrates the effectiveness of our proposed scheduling strategy.

中文翻译：

---

在移动边缘计算环境中考虑位置隐私保护的IoV计算资源的协作调度策略

本文提出了一种在移动边缘计算环境中考虑位置隐私保护的车辆互联网计算资源协作调度策略。首先，设计了一种多区域多用户多MEC服务器系统，在每个区域中部署了一个MEC服务器，一个区域中的多个车辆用户设备可以通过无线信道将计算任务分流到不同区域的MEC服务器中。然后，考虑到用户在车联网中的移动性，提出了一种基于卡尔曼滤波的车距预测方法，以提高车距的准确性。然而，当车辆执行任务时，需要提交真实位置，这导致了车辆用户位置隐私泄露的问题。最后，总的通信延迟成本 将车辆的位置隐私和所有用户的能源消耗确定为优化目标，其中要考虑系统状态，操作策略，奖惩功能等因素。此外，采用Double DQN算法来求解最优调度策略，以最小化系统的总消耗成本。仿真结果表明，该算法具有最高的计算任务完成率，经过8000次迭代收敛到80％左右，在系统能耗，任务完成率等方面，与其他算法相比，其性能更为理想。建议的调度策略。奖惩功能等因素。此外，采用Double DQN算法来求解最优调度策略，以最小化系统的总消耗成本。仿真结果表明，该算法具有最高的计算任务完成率，经过8000次迭代收敛到80％左右，在系统能耗，任务完成率等方面，与其他算法相比，其性能更为理想。建议的调度策略。奖惩功能等因素。此外，采用Double DQN算法来求解最优调度策略，以最小化系统的总消耗成本。仿真结果表明，该算法具有最高的计算任务完成率，经过8000次迭代收敛到80％左右，在系统能耗，任务完成率等方面，与其他算法相比，其性能更为理想。建议的调度策略。