Node fault model training method, detection method, equipment, medium and product

Abstract

The embodiment of the invention discloses a node fault model training method, a detection method, equipment, a medium and a product. The method comprises the following steps: acquiring sampling correctable error (CE) data of a sampling node before a sampling moment, sampling fault data of the sampling node after the sampling moment and sampling static configuration information of the sampling node; performing feature extraction according to the sampling static configuration information and the sampling CE data to obtain sampling CE features; and obtaining a to-be-sampled node fault model, and training the to-be-sampled node fault model by taking the sampling CE features as input and the node fault data as output to obtain a target node fault model. According to the scheme, the target node fault model used for predicting whether the corresponding node has the node fault can be obtained, the accuracy of predicting whether the node has the fault is improved, fault response measures can be taken for the node, and the reliability of the node can be improved.

Description

technical field [0001] The present disclosure relates to the field of network technology, and in particular to a node fault model training method, detection method, equipment, medium and product. Background technique [0002] With the continuous development of computer technology, people can obtain rich resources through nodes with data processing functions such as computers and servers in daily life. The hardware components of nodes usually include calculators, controllers, memories, input devices and output devices. The device, in which the memory can be divided into memory and external memory. The memory is generally used to store the programs and data that the node is currently using, or uses at any time. When a memory error or failure occurs, it may cause the node to become unresponsive or go down, which is a node failure. Currently, errors in node memory can be checked and corrected based on Error Correcting Code (ECC) technology. Among them, when a correctable error...

AI Technical Summary

Problems solved by technology

[0004] Although the above scheme can predict the emergence of UCE, with the increasing rise of cloud services and cloud computing, more and more user applications are deployed on cloud computing systems. Due to the complexity of cloud computing environments, cloud computing systems Nodes in , even when UCE is not present, may experience node failures due to other types of errors or failures in memory in the nodes

Images