Distributed network measurement method based on hierarchical coordination multi-agent system

Abstract

The invention relates to a distributed network measurement method based on a hierarchical coordination multi-agent system. By adopting the method, the distributed network measurement can be realized by a cooperative multi-agent system consisting of a plurality of measurement nodes. The measurement nodes are divided into different logical levels according to the network position per se; the measurement nodes form clusters according to the physical topology, wherein the measurement nodes in the clusters are adjacent in the physical topology and each cluster is provided with a cluster head; the nodes in the cluster are only used for measuring chain information of other measurement nodes which are positioned at the same cluster with the measurement nodes; the cluster heads can be respectivelypositioned in two clusters; the roles in the bottom layer cluster are used as the cluster heads; and the roles in the upper layer cluster are used as general nodes in the cluster. Therefore, the real-time chain state information of two adjacent layers of network can be acquired by implementing the measurement on the nodes of the cluster nodes. Meanwhile, the network measurement data of two adjacent layers can be relayed by using the nodes of the cluster heads as a bridge for information interaction of measurement nodes in two adjacent nodes, thereby ensuring that the measurement nodes in the layers can get the state information of the network outside the layers.

Description

technical field [0001] The invention relates to the field of computer network management, in particular to a distributed network measurement method based on a hierarchical cooperative multi-subject system. Background technique [0002] Network measurement models are generally divided into centralized measurement models and distributed measurement models. [0003] Traditional network measurement systems are mostly based on centralized measurement models. figure 1 Measure model diagrams for traditional centralized networks. Such as figure 1 As shown, the measurement system generally includes a central server, a measurement node, a central database and an analysis server. The central server is responsible for managing the entire network measurement process, including active measurement and passive measurement. The measurement nodes are responsible for performing specific test tasks and sending the collected data to the central database for statistics and analysis. This mea...

AI Technical Summary

Problems solved by technology

[0021] The centralized network measurement model adopts the C / S structure. The biggest disadvantage of this model is that the tasks of each measurement node in the system are initiated and managed by the central server, which can easily cause the task load of the central server to be too heavy and become the bottleneck of the system. Data communication cannot be directly performed between measurement nodes, resulting in low efficiency of the entire system, and it is difficult to adapt to a large-scale network environment

Similarly, for centralized analysis servers and central databases, there are also problems of heavy load and low efficiency

[0022] Although distributed network measurement solves the bottleneck problem of the central server, it also has certain limitations

First of all, the test goal of distributed network measurement is often to measure the end-to-end link performance between nodes. Since the end-to-end link spans multiple sub-links, and the status of the sub-links changes in real time, the end-to-end The end-to-end measurement results cannot accurately reflect the real-time link status; secondly, the end-to-end link measurement cannot obtain the performance data of each sub-link, so the measurement results cannot locate the bottleneck area of ​​the end-to-end link; finally, due to the end-to-end The link contains multiple sub-links, so multiple end-to-end links have overlapping sub-links, so when performing end-to-end measurement, the overlapping sub-links are repeatedly measured, causing problems such as increased network burden

Images