Internet-of-Vehicles data-driven task unloading system and method based on mobile edge computing

Abstract

The invention discloses an Internet-of-Vehicles data-driven task unloading system and method based on mobile edge computing. The system comprises an application layer, a vehicle layer, an MEC layer and a cloud layer. The application layer comprises data perception management, ITS service management and road safety management; and the vehicle layer includes a sensing vehicle and a computing vehicle. The sensing vehicle collects various traffic data and unloads the traffic data to the computing server for computing, and the computing vehicle provides computing service for sub-tasks in the V2V communication range; the MEC layer comprises an MEC server and an RSU, and the MEC server serves as a computing server and a local scheduler to be deployed near the RSU; and the cloud layer comprises acloud server and a backbone network, and the vehicle can unload its subtasks to the cloud server through a cellular interface. The system and method have the advantages that the service delay and theservice cost of the data-driven task are reduced, the task unloading architecture is distributed, the decision time of task unloading scheduling can be effectively shortened, and the utilization rateof resources is increased.

Description

technical field [0001] The present invention relates to the technical field of Internet of Vehicles, in particular to a data-driven task offloading system and method for Internet of Vehicles based on mobile edge computing. Background technique [0002] At present, with the rapid development of Internet of Things technology and 5G wireless communication technology, a large number of new applications have emerged in the field of Internet of Vehicles, such as autonomous driving, video surveillance and traffic control. These applications related to intelligent transportation systems first need to collect a large amount of environmental data, such as road network information, real-time traffic information, vehicle driving information, etc., and then on the basis of these data, the vehicle or other sensing devices perform corresponding processing, such as Face recognition, object detection, traffic prediction, etc., so these applications are data-driven and computationally intensi...

AI Technical Summary

Problems solved by technology

[0007] 1. The precision of the particle swarm optimization algorithm is low, and it is easy to diverge;

[0008] 2. If the acceleration coefficient, maximum speed and other parameters are too large, the particle swarm may miss the optimal solution, and the algorithm will not converge;

[0009] 3. In the case of convergence, since all the particles are flying towards the optimal solution, the particles tend to be homogenized (diversity is lost), which makes the later convergence speed significantly slower. At the same time, when the algorithm converges to a certain accuracy, It is impossible to continue to optimize, and the accuracy that can be achieved is not high

[0010] 4. It cannot adapt to the dynamically changing task offloading environment, and the algorithm needs to be re-run during each task offloading scheduling process, which has high time complexity and low efficiency

[0016] 3. The heuristic algorithm cannot adapt to the dynamically changing task offloading environment, and the algorithm needs to be re-run during each task offloading scheduling process, which is inefficient

Images