Intelligent cloud coordination method and device based on platform service type

Abstract

The invention discloses an intelligent cloud coordination method and device based on a platform service type, and relates to the field of cloud computing. A full knowledge graph based on the service type is constructed, a demand sub-graph comprising a service type part is formed through similarity matching, and the demand sub-graph of the service type part is matched with the full knowledge graph; obtaining a matching rule and scheduling resources in sequence through a graph search matching algorithm, obtaining an optimal decision according to the obtained task total energy consumption, task completion total cost and task completion total time, and calculating a power consumption value of a processor core of the multi-edge node according to the optimal decision and the network environment parameters, and scheduling and coordinately distributing resources according to the power consumption value, and finally deploying user requirements in actual equipment to realize service online. According to the invention, through matching the appropriate resource scheduling, the request scheduling resource and service of the edge device are responded at any time, the utilization rate and the calling efficiency of the edge node processor resource are improved, and the user experience is greatly improved.

Description

technical field [0001] The invention relates to the field of cloud computing, in particular to an intelligent cloud coordination method and device based on a platform service type. Background technique [0002] Because the computing power resources of edge nodes are very limited, and AI services and video services connected to edge nodes are highly bursty, the fixed computing power allocation method is difficult to meet the performance requirements during peak business hours, and the business is idle. It will also cause waste of edge computing resources. [0003] Meanwhile, the Dialogue System is a human-computer interaction system based on natural language. Through the dialogue system, people can use natural language and computers to interact in multiple rounds to complete specific tasks, such as information query, service acquisition, etc. The dialogue system provides a more natural and convenient way of human-computer interaction, and is widely used in car, home, custom...

AI Technical Summary

Problems solved by technology

However, users have various requirements for virtual machine scheduling policies, while the existing virtualization platforms provide fixed virtual machine scheduling policies, do not support policy templates and customization of policy templates, and cannot customize virtual machines according to user needs The scheduling strategy cannot meet the user's advanced requirements for virtual machine scheduling

[0006] At present, most of the research focuses on the description protocol of traditional cloud resources or specific applications in the field of Internet of Things, and cannot fully describe the resource demand model of human-machine-thing applications.

In particular, there is no effective mapping between the resource requirements of human-machine-thing applications and specific entities, and there is no effective association between entities at different levels. quality of service, application types are also difficult to expand

[0007] Moreover, the virtual machine scheduling decision-making method has the following defects: it does not support policy templates and the customization of policy templates, and cannot meet the diverse needs of users for virtual machine scheduling policies

Images