AI model servitization sharing method and system oriented to power grid regulation and control business

A power grid regulation and model technology, applied in the direction of calculation model, program control design, program control device, etc., can solve the problems of model sharing, weak AI model management, etc., achieve fast and smooth model upgrade and expansion, and improve model access efficiency , the effect of reducing the frequency of network transmission

Pending Publication Date: 2022-03-08
NARI TECH CO LTD
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problems of weak AI model management and inability to share models in the prior art, the present invention proposes a service sharing method and system for AI models oriented to power grid regulation business, which performs unified storage and version management on AI models, and through the cluster The system invokes the model to reduce the management cost of the business application AI model, improve management efficiency, and realize the co-construction and sharing of the results of the application of the AI ​​model within the power grid control system

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • AI model servitization sharing method and system oriented to power grid regulation and control business
  • AI model servitization sharing method and system oriented to power grid regulation and control business
  • AI model servitization sharing method and system oriented to power grid regulation and control business

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0052] Below in conjunction with accompanying drawing, technical scheme of the present invention will be further described:

[0053] In order to realize the co-construction and sharing of AI models in the power grid dispatching system, the present invention provides an AI model management method oriented to the field of power grid control, which stores and manages AI models in the field of power grid control with the model set as the granularity, and builds an AI model warehouse , the specific operation is as follows:

[0054] S1. The user creates multiple model sets as needed. Each model set is configured with a unique model set ID. Each model set only stores the same type of AI model. The corresponding relationship between common artificial intelligence algorithm frameworks and model file types is shown in Table 1. Show.

[0055] Table 1

[0056]

[0057]

[0058] S2. Obtain multiple AI models through power grid regulation business training. Each AI model is configured...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a power grid regulation and control business-oriented AI model servitization sharing method and system, and the method comprises the steps: obtaining an AI model warehouse which comprises a plurality of model sets, and storing a plurality of AI models of the same type in each model set; creating a model online service of the AI model in the cluster system by taking the model set in the AI model warehouse as granularity; storing the AI model in the AI model warehouse into a cluster system by starting a model online service; and loading the AI model from the cluster system according to an external request. According to the method, a batch AI model access mode is adopted, the network transmission frequency is reduced, the access efficiency is effectively improved, AI model service integrated release is provided based on Kubernetes, rapid and smooth upgrading and capacity expansion are achieved, the hardware resource utilization rate is improved, convenience, rapidness, safety, reliability and low cost are achieved, and an ecological environment where AI model achievements are co-constructed and shared in a regulation and control system is constructed.

Description

technical field [0001] The invention relates to an AI model service-oriented sharing method and system for power grid regulation and control business, and belongs to the technical field of power grid regulation and control. Background technique [0002] At present, the application of artificial intelligence technology in the field of power grid regulation technology has achieved preliminary results, but various business applications mostly adopt the independent management mode of AI model, and there are redundant construction of underlying resources, insufficient compression and conversion capabilities of various algorithm framework models, and model sources and versions. There are problems such as inability to trace the source, heterogeneous system model deployment and service release capabilities, and the application of AI model results has not formed an ecological environment for co-construction and sharing. [0003] According to the current development trend of power gri...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F9/445G06F16/176G06N20/00G06F9/455G06Q10/06G06Q50/06
CPCG06F9/44505G06F16/176G06N20/00G06F9/45558G06Q10/0631G06Q50/06G06F2009/45562G06F2009/4557G06F2009/45595
Inventor 沈嘉灵李佳阳陈佳佳闫妮张瑞智王宇冬陈子韵徐丽燕李昊季学纯张珂珩劳莹莹
Owner NARI TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products