EC-DDPG: DDPG-Based Task Offloading Framework of Internet of Vehicle for Mission Critical Applications

With the development of the Internet of Vehicles (IoV) technology and mission critical requirements, users' demand for computation resources is expanding. It is still a huge challenge to perform large computing tasks in vehicles with limited resources. To solve the above problems, this paper proposes a task offloading framework EC-DDPG based on the Deep Deterministic Policy Gradient (DDPG) algorithm, it obtains the service requirements of users' vehicles by interacting with the edge computing server. Through multiple rounds of training, it will evaluate and obtain the optimal task offloading strategy after the neural network converges. The simulation results based on existing traffic data show that compared with typical algorithms, the proposed architecture can offload computation tasks more effectively. It can be deployed in the network security field to reduce the resource consumption of intelligent network security system construction.