Unlock instant, AI-driven research and patent intelligence for your innovation.

A method and system for cluster link detection based on deep learning

A technology of link detection and deep learning, applied in neural learning methods, transmission systems, climate sustainability, etc., can solve problems such as undetectable link detection methods, link packet loss, slow data transmission, etc.

Active Publication Date: 2022-06-07
INSPUR SUZHOU INTELLIGENT TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, when the cluster system processes computing requests, it often encounters the problem of link packet loss or slow data transmission, so link status detection is particularly important
There is randomness in the link problem. In the existing technology, the link detection method cannot be detected by the existing general means, and can only be based on the empirical knowledge of the specific cluster system as the basis for detection.

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
  • A method and system for cluster link detection based on deep learning
  • A method and system for cluster link detection based on deep learning
  • A method and system for cluster link detection based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] Embodiment 1 of the present invention proposes a cluster link detection method based on deep learning. The combination of deep learning and cluster system uses the empirical learning of deep learning methods (such as convolutional neural networks) to generate link detection of cluster systems. model, and provide judgment basis for link optimization and path aggregation.

[0026] like figure 1 This is a schematic diagram of a link detection model in a deep learning-based cluster link detection method proposed in Embodiment 1 of the present invention.

[0027] First, the state values ​​of the cluster link nodes are obtained, and the experiential learning of deep learning methods (such as convolutional neural networks) is used to train the model on the massive data of the state values ​​of the cluster link nodes, and the training is stopped after the model converges. Then, according to the converged model, through routers, the states of cluster link nodes are arbitrated a...

Embodiment 2

[0044] Based on the present invention, a deep learning-based cluster link detection method is proposed, and a deep learning-based cluster link detection system is also proposed, such as image 3 This is a schematic diagram of a deep learning-based cluster link detection system proposed in Embodiment 2 of the present invention.

[0045] The system includes: a training module and a judgment module; the training module is used to use the cluster link state value as the input feature value of the convolutional neural network; the convolutional neural network trains the massive data of the cluster link state value, and when the training model converges After that, the training is stopped; the judgment module is used for link reservation for the links that meet the threshold according to the converged model, and link merging for the links that do not meet the threshold.

[0046] The process performed by the training module is: quantitatively collect the cluster link status value and...

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 present invention proposes a cluster link detection method and system based on deep learning. The method includes the following steps: using the cluster link state value as the input feature value of the convolutional neural network; After the training model converges, the training is stopped; according to the converged model, links that meet the threshold are retained, and links that do not meet the threshold are merged. The cluster link state value includes link bandwidth, link throughput and link transmission delay. Based on the present invention, a cluster link detection method is proposed, and a deep learning-based cluster link detection system is also proposed. The present invention makes full use of the characteristics of automatic tuning of the convolutional neural network, and performs specific processing on the characteristics of different clusters. The detection model obtained through training can maximize the utilization of each node resource in the cluster system, thereby improving the automation and computing performance of the cluster system.

Description

technical field [0001] The invention belongs to the technical field of distributed cluster detection, and in particular relates to a deep learning-based cluster link detection method and system. Background technique [0002] Distributed clusters have become the key technology of high-performance computing today. In many fields, distributed clusters have played a very important role. By building high-performance clusters, it is possible to solve the problems of small computing volume and long computing cycles for a single computer. [0003] However, when the cluster system processes computing requests, the problem of link packet loss or slow data transmission is often encountered. Therefore, link status detection is particularly important. The link problem is random. In the prior art, the link detection method cannot be detected by existing general means, and can only be detected based on the empirical knowledge of a specific cluster system. SUMMARY OF THE INVENTION [000...

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 Patents(China)
IPC IPC(8): H04L41/14H04L41/0823H04L41/042G06N3/04G06N3/08
CPCH04L41/145H04L41/0823H04L41/042G06N3/08G06N3/045Y02D10/00
Inventor 葛晨
Owner INSPUR SUZHOU INTELLIGENT TECH CO LTD