Research And Implementation Of Network Traffic Control System Based On SDN

With the rapid development of Internet and the increasing expansion of the network scale,the network is becoming more and more overburdened.The traditional network uses traffic control to reduce the network load,but the implementation of the global network topology in traffic control is complex,reducing the network performance.As a hot spot of current network research,software defined network(SDN)has the characteristics of separating the data plane and control plane of the device,obtaining the state information of the global network by the centralized state controller,and having the flexible programmable ability of the application layer.In this paper,a network traffic control system based on SDN was designed for the above characteristics.The system can eliminate a large number of manual configuration processes,introduce flexibility,and increase the overall view of the whole network so as to realize the practical significance of traffic control.In this paper,aiming at the research of architecture network and traffic control in SDN,a path optimization algorithm is proposed to solve the big data flow causing network congestion,and a network traffic control system based on SDN is designed and implemented.First,in view of the current research status of SDN network traffic control,it is found that the current SDN network traffic control is mainly to improve the network performance.Then,aiming at the analysis of SDN network characteristic,this paper proposes that the implementation of network traffic control is based on SDN,which adds network traffic monitoring module and path calculation module in Floodlight controller.The network traffic monitoring module is mainly used to monitor the large data flow that causes the network congestion,then the path calculation module is used to calculate the path of the large data flow.Based on the analysis above,it can be seen that the improvement of traffic control in network performance is mainly determined by the performance of path computation.Therefore,this paper proposes an improved particle swarm optimization algorithm(IVPSO)based on SDN for path calculation.The IVPSO algorithm is based on the topology characteristics of SDN to dynamically change the inertia weight,thereby improving the convergence of the algorithm and changing the global extreme value to solve the local extreme value problem of the algorithm.Simulation experiment was carried out on IVPSO algorithm and standard particle swarm algorithm.The results show that IVPSO algorithm has better effect on path optimization in terms of convergence and local extreme value.In the end of the paper,the network traffic control system based on SDN was implemented;a network traffic monitoring module and a path calculation module were implemented in the controller and the IVPSO proposed in this paper were used in path calculation module;the client of the system in the application layer is based on the REST interface provided by the Floodlight controller to obtain the information required by the system.The experiment results show that the traffic control can avoid network congestion and improve network performance.The research in this paper has practical significance for SDN network traffic control.Moreover,the IVPSO can solve the problem of path computation,and it also has application value in SDN network.