Network topology inference method and system based on convolutional neural network

Abstract

The invention discloses a network topology inference method and system based on a convolutional neural network, and the method comprises the steps: judging three paths of sub-topology structures through the convolutional neural network, taking the information as an input, and inferring a network topology through employing a topology inference algorithm in the invention. The topology inference algorithm is the same as that of most traditional topology inference algorithms. According to the algorithm provided by the invention, the topology is constructed by determining the positions of the branch nodes and the nodes connected to the branch nodes; the difference is that three paths of sub-topological structure information are input into the algorithm, and compared with similar measurement type quantitative data input in a traditional method, the qualitative data is higher in error tolerance degree, and therefore better robustness is achieved.

Description

technical field [0001] The present invention relates to the field of network tomography, and more specifically, relates to a convolutional neural network-based network topology inference method and system. Background technique [0002] The external measurement technology based on router cooperation initiates the measurement process at the edge of the network, and obtains the parameters to be measured through the feedback of internal nodes to the detection data. Among them, the more common tools include ping for diagnosing network connectivity, traceroute for obtaining network topology, and pathchar for measuring performance parameters such as link bandwidth and delay. Such methods will fail when internal nodes do not support collaboration due to factors such as network security. In addition, most of these methods use ICMP (Internet Control Measurement Protocol) packets as detection data, but the priority of ICMP packets in actual networks is low, so the measured performance...

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention is to propose a three-way sub-topology inference method and system based on a convolutional neural network in view of the above-mentioned technical defects of low robustness inference using quantitative data. After the three-way sub-topology measurement data, use the convolutional neural network and the algorithm in the present invention to infer the network topology

Images