Task unloading optimization method for fixed path AGV in industrial Internet of Things environment

Abstract

The invention discloses a fixed path AGV task unloading optimization method in an industrial Internet of Things environment. On the basis of a traditional model-free reinforcement learning method based on value function updating, optimization is conducted on the task unloading scheduling problem under the AGV-assisted edge computing scene, and on the basis, a load balancing algorithm and an improved DQN algorithm are combined. And finally, under the constraints of task processing delay sensitivity, path, efficiency and the like, the problem of shortest and optimal unloading processing time of multiple AGV and multiple server nodes in the Internet of Things environment is solved. According to the method, excessive priori knowledge and close-range task unloading transmission are not needed, the requirement for data security is met, and the method has good reusability in similar application scenes and is high in practical value.

Description

technical field [0001] The invention belongs to the field of edge computing, and in particular relates to a reinforcement learning method for unloading and optimizing fixed-path AGV tasks in an industrial Internet of Things environment. Background technique [0002] At present, a large number of sensors are deployed in the Industrial Internet of Things, and it is full of time-sensitive data calculations and execution decisions. The complete cloud-centered computing model can no longer meet actual needs. Therefore, the edge computing model is applied to industrial scenarios to distribute data computing tasks from the centralized cloud to edge devices closer to the data source. By being closer to the target, the edge server provides users with cloud computing capabilities at close range, which is extremely It well solves the real-time processing requirements of industrial Internet of Things applications. Among them, task unloading scheduling optimization problem is the focus ...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the problem that the AGV trolley unloads tasks based on a given path in the edge computing scenario of the Industrial Internet of Things, so as to minimize the task completion time

Images