A network controller deployment method adapting to dynamic network structure

Abstract

The invention proposes a network controller deployment method adapting to the dynamic network structure. The invention establishes a distance parameter model in the process of node movement; utilizes clustering ideas to cluster nodes with similar moving trajectories, and finds the cluster center in the entire network node as the deployment position of the controller; establishes a network model of the controller, through Switch to controller communication cost, inter-domain controller synchronization communication cost and controller deployment cost calculate the total controller deployment communication cost. The advantage of the present invention is that the mobility characteristics of the nodes in the network can be fully combined through the neighbor propagation algorithm based on the similarity of moving trajectories, so that the finally selected controller deployment position can well adapt to the network dynamics and maintain stable performance.

Description

technical field [0001] The invention belongs to the technical field of wireless networks, and in particular relates to a method for deploying a network controller adapting to a dynamic network structure. Background technique [0002] Software-defined networking is a new network concept proposed in recent years. It realizes flexible control of network traffic by separating the control layer from the data layer. As the most critical component in the software-defined network, the controller plays a role in controlling the entire network. In the case of a given network topology, a reasonable deployment of the controller can reduce the delay of information exchange, reduce the energy consumption of nodes, and improve the efficiency of the entire network. In the existing controller deployment algorithm, the entire network is divided into regions by judging the positional relationship between nodes, and a controller is deployed in each sub-domain, and each switch node is kept conn...

AI Technical Summary

Problems solved by technology

Since any node in the network is always moving, the network topology is no longer fixed. As time goes by, the deployment position of the controller judged at a certain moment becomes unreasonable.

The Euclidean distance in the traditional controller deployment algorithm is no longer able to describe the relationship between two moving nodes, so the existing algorithm cannot be well adapted to this dynamic network structure.

Images