Intelligent computing unloading method under a vehicle-mounted network

Abstract

The invention discloses an intelligent computing unloading method under a vehicle-mounted network, which combines a deep reinforcement learning algorithm with vehicle edge computing, studies the optimization problem of task scheduling and resource allocation in the vehicle-mounted network, and gives a computing unloading method. On the basis of the limited Markov chain, the intelligent unloading model under the vehicle-mounted network is constructed, and the service experience quality of a user is considered while the profit of a network operator is maximized. According to the invention, the joint optimization problem of initial task scheduling and resource allocation is decomposed into two sub-optimization problems. For the first sub-problem, a utility function is designed to measure theservice experience quality grade of a user, and then a task scheduling algorithm based on a bilateral matching model is provided to solve the sub-problem. Based on an improved deep reinforcement learning algorithm, a reinforcement learning model under a vehicle-mounted network unloading system is constructed, and a resource allocation algorithm is provided to solve a second sub-problem. Experimental results prove the high efficiency of the algorithm provided by the invention.

Description

technical field [0001] The invention relates to an intelligent computing offloading method under the vehicle Internet, in particular to a computing offloading method based on a bilateral matching model and a deep reinforcement learning algorithm. Background technique [0002] The rapid development in the field of artificial intelligence has led to the emergence of new in-vehicle applications. While providing a safer and more comfortable environment for drivers and passengers, how to run computing-intensive applications in the in-vehicle system is always facing a huge challenge. The emergence of Mobile Cloud Computing (MCC) has relieved the load of some vehicle systems, but the demand for real-time feedback is still not satisfied. Compared with MCC, mobile edge computing (MEC) based on vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) transmission architecture can provide low-latency communication guarantee. More efficient task scheduling and intelligent unloading...

AI Technical Summary

Problems solved by technology

The emergence of Mobile Cloud Computing (MCC) has relieved the load of some vehicle systems, but the demand for real-time feedback is still not satisfied

Images