Joint Route Selection And Resource Allocation Algorithms In Software-Defined Networking

Software-defined networking(SDN)is expected to dramatically simplify network control processes,enable the convenient deployment of sophisticated networking functions,and support user applications with guaranteed quality of service(QoS).To achieve data packet transmission between two non-adjacent switches in SDN,efficient route selection algorithms should be designed.In addition,to stress the problem of resource competition among various user flows,reasonable resource allocation schemes should be designed which can improve the utilization of network resources under the premise of meeting the needs of user requirements of efficient and reliable communications.In this thesis,joint routing and resource allocation algorithm for SDN will be discussed.The following issues are mainly discussed.Firstly,the concept,the structure and the key technologies of SDN are introduced.The current research works on routing algorithms and resource allocation algorithms for SDN are summarized.Moreover,the difficulties and challenges of SDN routing and resource allocation are analyzed.Secondly,we study the data transmission of multiple user flows over SDN.Under the assumption that flow splits at intermediate switches are allowed,we jointly design the route selection and flow allocation algorithm.To stress the problem of resource competition among various user flows,we propose a virtual network architecture applying network virtualization technology.Jointly considering the transmission performance of multiple user flows and stressing the importance of energy consumption at transmission links and switches,we formulate the jointly route selection and flow allocation scheme as the optimization problem that minimizes the total energy consumption,subject to data transmission and service requirement constraints of the flows.Because the formulated optimization problem is an NP-complete problem that cannot be conveniently solved,we transform it into a minimum-cost commodity flow problem and solve the problem by using an N-algorithm.Numerical results demonstrate the effectiveness of the proposed algorithm.Finally,in the network scenario where multi-user flows transmit simultaneously,a delay optimization based joint route selection and resource allocation algorithm is proposed for SDN.Jointly considering constraints such as QoS requirements of users,the transmission performance of network,the route selection and flow allocation of user flows,we formulate the problem of joint route selection and resource allocation as the optimization problem that minimizes the total delay subject to these constraints.We solve the problem by using a heuristic algorithm.Firstly,for each user flow,applying Dijkstra algorithm to obtain the minimum delay path,then determining whether there are shared nodes and links among multi-user flows.If yes,the joint optimization of processing resources of nodes and bandwidth resources of link allocation strategies is achieved,which aims to optimize the network delay while guaranteeing user QoS requirements.The simulation results show that the proposed algorithm is capable of achieving the total delay optimization of the network and guaranteeing user QoS requirements as well.