Full-scene edge calculation method, device and system

Abstract

The invention discloses a full-scene edge calculation method, device and system, and the full-scene edge calculation method comprises the following steps: receiving a calculation request of a user, generating a full-scene edge calculation task, and generating a mirror image file dockerfile by a resource scheduling node; obtaining an indifference calculation program executed by the edge calculationnode or compiling the program by utilizing a source code; and selecting an edge scheduling algorithm, selecting available edge computing nodes according to the edge scheduling algorithm, splitting the edge computing task into working tasks which can be executed by the edge computing nodes, and distributing the working tasks. According to the full-scene edge calculation method, device and system,a distributed architecture is adopted; the physical cost is lower; the computing power of any scale can be accessed; and stronger computing power service is provided for the outside. The full-scene edge calculation method is operated in a parallel mode; and data reading efficiency and the calculation efficiency are higher. The platform supports multi-scene computing; different edge computing nodesare packaged in a unified mode; a user does not need to configure or know the running environment of a server; and the user can pay more attention to service functions.

Description

technical field [0001] The invention belongs to the technical field of edge computing, and relates to a full-scene edge computing method, device and system. Background technique [0002] Edge computing refers to an open platform that integrates network, computing, storage, and application core capabilities on the side close to the source of objects or data, and provides the nearest end services. Its applications are launched on the cloud and run on the edge side, resulting in faster network service response, meeting the needs of the industry in real-time business, application intelligence, security and privacy protection. Edge computing adopts a distributed computing architecture, moving data and computing from the central node of the network to the edge node for processing. The process of edge computing is to decompose large-scale services that were originally handled by central nodes, cut them into smaller and easier-to-manage parts, and disperse them to edge nodes for pr...

AI Technical Summary

Problems solved by technology

[0004] In foreign countries, some edge computing open source projects have emerged, but most of them are edge computing of the Internet of Things. However, the diversity of software, hardware and access methods of the Internet of Things brings difficulties to the data access function and affects the deployment of edge computing applications.

[0005] At present, edge computing is mainly network equipment information communication technology and server virtualization technology, and focuses on specific industry applications. Different solutions are adopted in different scenarios, and there is no unified overall support for multiple scenarios (multiple scenarios are specific but not limited to: AI training) , AI applications, big data storage and analysis, Internet of Things, rendering, streaming media, etc.) computing edge computing framework

Images