Edge node calculation unloading method with performance and demand matching capability

Abstract

The invention discloses an edge node calculation unloading method with performance and demand matching capability. The method comprises the following steps: establishing a cooperative computing network system with a plurality of mobile edge node devices; constructing and initializing a node performance estimation model and a task demand estimation model, and initializing required operation variables; carrying out online selection of unloading targets by using a reinforcement learning method based on an adversarial dobby machine; unloading the task to the selected target, and observing the actual unloading delay; updating a node performance estimation model by using the actual delay of the unloading; the central equipment using the updated node performance estimation model as a behavior basis for next unloading; whether a new unloading request exists or not being judged, if yes, online selection of the unloading target is carried out again, and if not, the new unloading request continues to be waited. According to the method, the traditional single unloading delay is deconstructed into independent double-variable unloading delay to be considered, and the method is better in line with the actual application scene of the Internet of Things equipment.

Description

technical field [0001] The invention belongs to the technical field of application of the Internet of Things, and in particular relates to an edge node computing unloading method with performance and demand matching capabilities. Background technique [0002] With the rapid development of the Internet of Things, more and more devices are connected through the Internet of Things technology and generate massive data and demands. However, most IoT devices have very limited computing resources, which cannot meet the increasingly complex application requirements, and edge computing is considered as a promising computing paradigm to solve this critical problem. There are two collaborative computing methods in edge computing. One is to deploy computing resources close to devices, such as smart gateways, access points, base stations, etc., and integrate them as edge servers. feature, utilizing the computing resources of other idle IoT devices near a certain device. Through the abo...

AI Technical Summary

Problems solved by technology

The common disadvantage of the above two algorithms is that they regard the unloading delay as a whole, and use the complete unloading delay as the choice of feedback update algorithm

[0006] At present, there are some common problems in the existing task offloading selection algorithms among nodes in edge computing: the existing offloading selection algorithms mainly regard the calculation delay as a whole, and do not consider that some components of the calculation delay are relatively independent , and these independent parts are related to the performance configuration of edge nodes, such as computing speed and transmission speed are two relatively independent performance indicators

When the former is unloaded, computing power will be more important than transmission capacity, while the latter is the opposite. This feature makes it difficult for traditional task offloading algorithms to truly select edge nodes suitable for a certain task.

Images