A Queueing-based Performance Model Of OpenFlow Networks

At present,under the wave of Internet,all industries want to catch up fast-growing technology.Enterprises and individuals are increasingly inseparable from Internet in daily production.With the addition of new business and new protocols in the way of "patching",traditional networks,which only have some single functions,becoming increasingly complex.As an innovative network architecture decoupling data forwarding and control logic,and opening underlying programming interfaces,Software-Defined Networking(SDN)provides a novel solution to reduce deployment and operation costs and improve business application performance in networks.However,logically centralized control plane under the SDN architecture is prone to performance bottlenecks,and increases packet forwarding delay.Thus it is necessary to understand the characteristics of its packet forwarding performance.To this end,this thesis models performance of OpenFlow networks according to traffic characteristics of the software-defined mobile networks and software-defined core networks.(1)this thesis proposes a queuing theory-based performance model of Packet-in message processing process in software-defined mobile networks.We first introduce typical deployment scenarios of software-defined mobile networks,and analyze packet flow arrival process in its data plane and SDN controller processing of Packet-in messages.Then,the queuing process of the Packet-in message in the controller is modeled as the M/M/1/m queuing model.On this basis,we derive the average waiting queue length,average waiting time and average sojourn time of Packet-in message and sojourn time's cumulative distribution function.Finally,experimental evaluation in virtue of the controller performance measurement tool OFsuite_Performance shows that our proposed M/M/1/m model can accurately estimate actual performance of controller compared with M/G/1 and Mk//M/1 models,which provides effective references for practical deployments of software-defined mobile networks.(2)this thesis proposes a queuing theory-based performance model of OpenFlow packet forwarding in software-defined core networks.We first introduce typical deployment scenarios of software-defined core networks,and analyze Packet-in message arrival process in its control plane and packet arrival process in its data plane.Then the M/M/n/m and M/M/1/m queuing models are respectively applied to depict Packet-in message processing process of its controller clusters and packet processing process of its OpenFlow switches.On this basis,we establish a prioritized queuing model of OpenFlow packet forwarding,and derive packet forwarding delays of different priorities and its cumulative distribution function.Finally,experimental evaluation in virtue of the controller performance measurement tool OFsuite_Performance shows that our proposed M/M/n/m model can accurately estimate actual performance of controller clusters compared with existing models.Meanwhile,we contrast packet forwarding delays of different priorities in various situations and their CDF curves by numerical analysis,which provides effective references for practical deployments of software-defined core networks.