Communication network robustness assessment method based on complex network and in combination with big data

Abstract

The invention provides a communication network robustness assessment method based on a complex network and in combination with big data. A communication network is abstracted into the complex networkthrough building a communication network model; a data mining algorithm is used for processing fault data; simulation modeling is performed on the model, analysis data is loaded into a simulation platform, a forwarding capacity, a caching capacity and a forwarding load are set and adjusted, and a routing strategy is changed, and thus a truer, more reliable and more accurate simulation assessment result is acquired. The network model of a real world complex system is built based on a complex network technology, system performance such as robustness, security and reliability are assessed and anoptimization scheme is provided by using a random simulation technology and operation and maintenance big data of the system; a cascade spreading and diffusion problem after a fault occurs in the communication network is found, weak links, including fault equipment and a fault spreading path, affecting the security and reliability of the whole network are found, and the optimization scheme is further provided based on a network topological structure.

Description

technical field [0001] The invention belongs to the technical field of robustness evaluation of communication networks, in particular to a communication network robustness evaluation method based on the combination of complex network theory and big data. Background technique [0002] In recent years, complex network theory has been fully developed, and more and more researchers are involved in it. After Barabasi and Albert proposed the BA scale-free network with power-law distribution, complex network theory was applied to various fields in the real world. Inetnet, mobile communication network, large power network, rail transit network, etc. are all BA scale-free networks that obey the power law distribution. With the development of science and technology, people study more and more on complex networks, including the statistical characteristics of complex networks, various dynamic behaviors on complex networks (virus propagation and cascading faults on the network, etc.). ...

AI Technical Summary

Problems solved by technology

The disadvantage of this scheme is that it depends on the physical structure of the specific high-speed train, which is quite different from the communication equipment network; in addition, this scheme also does not consider the impact of human factors on network robustness

This scheme also does not simulate the network model, but abstracts the physical structure of the train based on the complex network theory, and combines the abstracted network node degree and equipment failure frequency as the input data of the SVM, without using the system over-dimensional Big data to get accurate fault parameters

[0008] The communication network system is a very complex system, and the unreasonable design of the network structure or the uneven distribution of network load will lead to failures

Traditional solutions to network failures can only solve local and small-scale problems, and structural problems cannot be solved fundamentally

Images