Computing resource management scheduling method for industrial edge nodes

Abstract

The invention relates to a computing resource management scheduling method for industrial edge nodes, and belongs to the field of Internet of Things. The method comprises the following steps: S1, constructing a computing resource virtualization architecture for industrial edge nodes; s2: scheduling computing resources. The invention provides an industrial edge node-oriented computing resource virtualization architecture, which comprises an industrial physical layer, a virtual resource layer and a control layer, and realizes unified management of computing resources. Meanwhile, a computing resource scheduling strategy is provided by predicting the computing resource use condition of the edge node at the future moment and combining the industrial computing priority and the overload conditionof the edge node, so that the problem of unbalanced load of the edge node in an industrial environment is solved.

Description

technical field [0001] The invention belongs to the field of the Internet of Things, and relates to a computing resource management scheduling method for industrial edge nodes. Background technique [0002] At present, the computing resource management and scheduling of edge computing at home and abroad mainly focus on task offloading. However, in industrial scenarios, offloading tasks to other remote edge nodes may not meet the low-latency requirements of industrial computing tasks, and at the same time, comprehensive sharing and unified management of computing resources cannot be realized among industrial edge nodes. Regarding the status quo of computing resource management and scheduling of industrial edge nodes, the following problems may exist at present: [0003] (1) Computing resources of edge nodes cannot be fully shared and managed in a unified manner: edge nodes are the core of carrying edge computing tasks, but there are various types of products and large differ...

AI Technical Summary

Problems solved by technology

[0003] (1) Computing resources of edge nodes cannot be fully shared and managed in a unified manner: edge nodes are the core of carrying edge computing tasks, but there are various types of products and large differences in the underlying hardware, resulting in the inability to fully share computing resources; at the same time, there is a lack of corresponding The controller manages the computing resources of the edge nodes;

[0004] (2) In the industrial scene, there are multiple edge nodes computing overload, which cannot meet the dynamic changing requirements of industrial computing tasks: According to the arrangement of the production plan, there may be cases where multiple edge nodes are computing overloaded and the rest of the edge nodes are idle. The load is unbalanced, resulting in low overall computing efficiency of the task

[0009] ZiY et al. focus on server load prediction, judge the overloaded server by predicting the load of the physical server at the next moment, and migrate the container in the overloaded server to other servers, but this algorithm ignores the changes of the container itself , which will cause the load to become unbalanced again after a period of time

Images