Computing unloading and resource management method in edge calculation based on deep reinforcement learning

Abstract

The invention discloses a computing unloading and resource management method in edge computing based on deep reinforcement learning, which comprises the following steps: constructing an edge computing communication model based on a partially observable Markov decision process, the edge computing communication model comprising M + N agents, the M agents being edge nodes, and the N agents being users; setting a target optimization function according to a user cost minimization target and an edge node utility maximization target; setting a time slot length, a time frame length, an initialization time slot and a time frame; enabling the edge node and the user to respectively use the partial observable Markov decision process to obtain a resource allocation strategy and a task unloading strategy; according to the task unloading strategy and the resource allocation strategy, optimizing a target optimization function by utilizing a participant-criminator model; and dividing and processing the computing task according to the optimized target optimization function. According to the invention, different interest pursues between the edge device and the user are solved, and respective interests are ensured to the maximum extent.

Description

Technical field [0001] The present invention belongs to the field of edge calculation, and in particular to calculating unloading and resource management methods based on edge calculations based on deep strengthening learning. Background technique [0002] With the continuous advancement of science and technology and industrial production capacity, the calculation and communication capacity of mobile devices continues to improve, but all kinds of new mobile applications have put forward higher business needs for mobile devices. In a cluster of a multilateral edge, the user can choose to calculate or uninstall the task locally or unload to the edge device. To respond to innovative applications and user experience growing demand, the uninstallation will calculate the intensive task from the user to the edge. The calculation capability of the edge device is generally stronger than the user, so the user may obtain some time delay and power consumption by uninstalling the calculation ...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the problem that the existing technology cannot well determine resource allocation and computing offloading decisions, the present invention proposes a computing offloading and resource management method in edge computing based on deep reinforcement learning

Images