The DDPG-Based Joint Optimization of Task Offloading and Content Caching in UAV-Assisted IoV
Jingpan Bai, Jiahui Luo, Yuan Chen, Yuming Tang, Li Jin, Shi Yan, Bo Yang, Houling Ji
Abstract
In the unmanned aerial vehicle (UAV) assisted Internet of Vehicles (IoV) scenario, with the advantages of rapid deployment and line-of-sight communication, UAVs are widely adopted to provide the computation, communication and storage service for vehicles. However, existing research often overlooks the impact of content caching on task latency and UAV resource optimization in UAV assisted IoV. Hence, this paper explores the relationship between computation offloading and content caching, and formulates a joint optimization problem to reduce task delays in UAV assisted IoV environment. Especially, each computation task is modeled as a directed acyclic graph, in which the subtasks are interdependence. Furthermore, the joint optimization problem is the non-linear integer programming problem, and the Deep Deterministic Policy Gradient algorithm is used to solve the joint optimization problem, regarding the decision variables, available resources and the optimal objective as the action space, the state space and the reward function, successively. Finally, extensive simulation experiments demonstrate the algorithm’s effectiveness on task processing delay in UAV assisted IoV environments.