A method, device and system for task migration decision-making

Abstract

The present invention provides a method, device and system for task migration decision-making, wherein the method includes: acquiring local experience information uploaded by multiple terminals for at least one time period, integrating multiple local experience information of the same time period to generate a time period The global experience information of the global experience information; the training parameters from different decision-making groups will be selected from the global experience information of multiple periods of time to integrate to generate training experience information, and all online execution networks will be trained according to the training experience information, and each online execution network will be determined. network parameters; according to the grouping information of the terminals, send the network parameters corresponding to the decision-making group to the terminals in the decision-making group. Through the method, device and system for task migration decision-making provided by the embodiments of the present invention, network parameters of a large number of terminals can be updated, the stability of training and the performance of training results are improved, and the effect of task migration decision-making of terminals can be guaranteed.

Description

technical field [0001] The present invention relates to the technical field of wireless communication, in particular, to a method, device and system for task migration decision-making. Background technique [0002] With the development of mobile communication technology, especially the advent of the 5G era, the number of mobile devices is expected to experience explosive growth. At the same time, due to the development of terminal equipment and the increase of user demands, some computing-intensive tasks have emerged as the times require, such as augmented reality (AR), virtual reality (VR), online artificial intelligence, and the Internet of Things. These new types of tasks usually require processing a large amount of data and are sensitive to delay, and the end devices are generally resource-constrained low-power devices. It is difficult to meet the demand only by relying on the limited local computing power of the terminal, so people propose the method of mobile edge com...

AI Technical Summary

Problems solved by technology

[0006] However, neither the traditional algorithm nor the deep reinforcement learning method considers the cooperation and competition between multiple users when learning the migration strategy. It is not necessarily optimal in terms of the total overhead (delay and power consumption) of the system.

When applied to a NOMA (non-orthogonal multiple access)-based MEC system, due to severe interference between users, its migration algorithm may not be able to effectively make decisions or even cause training instability

Images