Research On QOS Guarantee For Streaming Media Services Over Software Defined Networks

With the rapid expansion of network scale and the continuous enrichment of video service applications,online video has become the mainstream of current Internet streaming media.Its low delay(jitter),high throughput,low packet loss rate and other parameters are very important to guarantee the quality of video transmission service,which puts forward higher demand for network resources.However,attempts to secure QoS have been unsuccessful because the existing network architecture has exposed many drawbacks while meeting application demands.How to guarantee the QoS quality of video transmission and the efficiency of network routing has become a hot research topic in the industry,as well as an urgent problem to be solved in multimedia video streaming transmission.A new future network architecture represented by SDN/OpenFlow improves the flexibility and reliability of network management by breaking the vertical integration,separating the control logic of the network from the underlying routers and switches,promoting the centralization of network control,and introducing the ability to program the network.Therefore,this paper takes full advantage of the advantages of SDN to study the QoS optimization problem of multimedia transmission video and the related issues of traffic scheduling.The maj or study context in this paper includes those:1)Aiming at the inefficiency of multi-path scheduling algorithms and the fluctuation of end-to-end delay in multimedia applications,these two problems seriously affect the quality of video transmission.A dynamic and adaptive QoS guarantee algorithm for multi-path video transmission based on SDN is proposed.The architecture of the algorithm is an extension of the existing SDN architecture,and makes full use of the advantages of SDN to dynamically manage the dynamic nodes in the network to meet the requirements of QoS guarantee for video transmission.In this paper,a QoS path optimization algorithm with multiple constraints is proposed to obtain the QoS parameters of the underlying network devices in real time through the controller,and these parameters are used as the input parameters of multi-constraint cost function,so as to realize the calculation of routing.2)Aiming at the network congestion caused by the occupied bandwidth for a long time in multimedia networks,an adaptive bandwidth adjustment mechanism based on multi-level feedback queue in SDN architecture is proposed in this paper.This method determines the degree of link congestion and the priority of queues according to the congestion state of network links,and adjusts the bandwidth supporting specific traffic by preempting the bandwidth of other queues to ensure the transmission quality of specific traffic.Thus,it can make full use of the resources in the network.Experimental results show that this method can effectively avoid the network congestion or loss of a large number of packets caused by malicious flow transmission with the occupied bandwidth for a long time,thus ensuring the accurate arrival of high-priority messages.Additionally,the proposed method can carry out multi-level scheduling of streams,which can meet the requirements of various flows and the anti-interference ability of each queue is relatively strong.3)Aiming at implementing different QoS guarantee of different priority strategy for different priority traffic,this paper proposes a dynamic multipath priority-aware algorithm based on SDN,which realize the QoS guarantee for the designated traffic.Moreover,the proposed algorithm fully considers the priority and real-time multimedia stream link status and link load,and provides a link cost on this basis.By considering the link cost,the impact between services can be minimized to allocate bandwidth resources reasonably.