Software Defined Networking （SDN） is an emerging networking paradigm that assumes a logically centralized control plane separated from the data plane. Despite all its advantages, separating the control and data plan...Software Defined Networking （SDN） is an emerging networking paradigm that assumes a logically centralized control plane separated from the data plane. Despite all its advantages, separating the control and data planes introduces new challenges regarding resilient communications between the two. That is, disconnec- tions between switches and their controllers could result in substantial packet loss and performance degradation. This paper addresses this challenge by studying the issue of control traffic protection in SDNs with arbitrary numbers of controllers. Specifically, we propose a control traffic protection scheme that combines both local rerouting and constrained reverse path forwarding protections, through which switches can locally react to fail- ures and redirect the control traffic using standby backup forwarding options. Our goal is then to find a set of primary routes for control traffic, called protected control network, where as many switches as possible can benefit from the proposed protection scheme. We formulate the protected control network problem, prove its NP-hardness, and develop an algorithm that reconciles proteetability and performance （e.g., switch-to-control latency）. Through extensive simulations based on real topologies, we show that our approach significantly im- proves protectability of control traffic. The results should help further the process of deploying SDN in real-world networks.展开更多
Network virtualization provides a powerful way of sharing substrate networks. Efficient allocation of network resources for multiple virtual networks( VNs) has always been a challenging task. Especially under the ever...Network virtualization provides a powerful way of sharing substrate networks. Efficient allocation of network resources for multiple virtual networks( VNs) has always been a challenging task. Especially under the everincreasing demand of customized VN requests,many problems arise as network conditions change constantly.Particularly with the emergance of resource conflict alongside the development of VNs,service provider( SP) needs to provide a faster and more effective solution. Recently,software defined network( SDN) has emerged as a new networking paradigm,SDN’s centralized control and customizable routing features present new opportunities for convenient and flexible embedding VNs in the network. However,due to the limitations of SDN,replacing all legacy devices in current operational networks by SDN-enabled switches in a short span of time is impractical.Thus,in our study,we focus on the scenario of VN embedding( VNE) in software-defined hybrid networks. In this work,first of all,we propose partially deploying SDN nodes; and then,we use the characteristics of SDN to allocate resources for VN requests,and redirect the path for requests conflict in hybrid SDN network. We formulate the problems and provide simple algorithms to solve them. Simulation results show that our scheme has high ratio in responsiveness and acceptance.展开更多
基金supported in part by National High-tech R&D Program of China(863 Program)(Grant Nos.2013AA0133012015AA016101)
文摘Software Defined Networking （SDN） is an emerging networking paradigm that assumes a logically centralized control plane separated from the data plane. Despite all its advantages, separating the control and data planes introduces new challenges regarding resilient communications between the two. That is, disconnec- tions between switches and their controllers could result in substantial packet loss and performance degradation. This paper addresses this challenge by studying the issue of control traffic protection in SDNs with arbitrary numbers of controllers. Specifically, we propose a control traffic protection scheme that combines both local rerouting and constrained reverse path forwarding protections, through which switches can locally react to fail- ures and redirect the control traffic using standby backup forwarding options. Our goal is then to find a set of primary routes for control traffic, called protected control network, where as many switches as possible can benefit from the proposed protection scheme. We formulate the protected control network problem, prove its NP-hardness, and develop an algorithm that reconciles proteetability and performance （e.g., switch-to-control latency）. Through extensive simulations based on real topologies, we show that our approach significantly im- proves protectability of control traffic. The results should help further the process of deploying SDN in real-world networks.
基金supported by the National Natural Science Foundation of China ( 61602051)the Fundamental Research Funds for the Central Universities ( 2017RC11)
文摘Network virtualization provides a powerful way of sharing substrate networks. Efficient allocation of network resources for multiple virtual networks( VNs) has always been a challenging task. Especially under the everincreasing demand of customized VN requests,many problems arise as network conditions change constantly.Particularly with the emergance of resource conflict alongside the development of VNs,service provider( SP) needs to provide a faster and more effective solution. Recently,software defined network( SDN) has emerged as a new networking paradigm,SDN’s centralized control and customizable routing features present new opportunities for convenient and flexible embedding VNs in the network. However,due to the limitations of SDN,replacing all legacy devices in current operational networks by SDN-enabled switches in a short span of time is impractical.Thus,in our study,we focus on the scenario of VN embedding( VNE) in software-defined hybrid networks. In this work,first of all,we propose partially deploying SDN nodes; and then,we use the characteristics of SDN to allocate resources for VN requests,and redirect the path for requests conflict in hybrid SDN network. We formulate the problems and provide simple algorithms to solve them. Simulation results show that our scheme has high ratio in responsiveness and acceptance.
