Task unloading method based on intention perception in air-ground integrated Internet of Vehicles

Abstract

The invention provides a task unloading method based on intention perception in an air-ground integrated Internet of Vehicles. The task unloading method comprises the following steps: constructing a system model; refining the model; proposing a high-reliability low-delay constraint and optimization problem; performing conversion of an optimization problem and track similarity estimation. Accordingto the task unloading method based on intention perception, the user experience quality model, the high-reliability low-delay constraint, the trajectory similarity estimation and the reinforcement learning are combined for selecting the edge server, so that the three-dimensional user intention perception of the user experience quality perception, the high-reliability low-delay perception and thetrajectory similarity perception is realized. Tail distribution of the queue length is also considered, the probability of occurrence of extreme events and the conditional mean value and variance of excess backlog under long-term average time are constrained, queue delay is reduced, queue stability is improved, multi-hop forwarding is not needed, end-to-end delay is remarkably reduced, and the number of times of successful task unloading is increased.

Description

Technical field [0001] The invention belongs to the technical field of intelligent transportation, and specifically relates to a task offloading method based on intention perception in the air-ground integrated vehicle networking. Background technique [0002] Air-ground Integrated Vehicular Edge Computing (AGI-VEC) is one of the key technologies of the next generation of intelligent transportation systems (Intelligent Transportation Systems, ITS), which integrates communication and computing in air-based and ground-based networks And storage resources, to meet the growing computing needs of car networking equipment, and provide a new vehicle edge computing architecture. In the space-based network of this architecture, UAVs (Unmanned Aerial Vehicles, UAVs) can be used as edge servers to flexibly provide user vehicles (User Vehicle, UV) with communication and computing services; in the ground-based network, edge computing is equipped The ground base station (Base Station, BS) of ...

AI Technical Summary

Problems solved by technology

[0004] The current task offloading scheme based on Lyapunov optimization needs to offload tasks under the condition of known global information, and the signaling overhead is high, so it is difficult to implement in reality

[0005] The UCB-based task offloading scheme only optimizes the task offloading for a single quality of service performance index (such as throughput, delay or bit error rate), without considering the high reliability and low delay constraints of user intentions and data queues, causing users The quality of vehicle experience is poor, and it is difficult to guarantee high-reliability and low-latency communication requirements

Images