多路径传输控制协议(multipath TCP,MPTCP)利用设备的多个网络接口传输数据,通过聚合带宽来提高传输效率。在进行路径选择时MPTCP通常使用不相交路径选择算法,由于优先选择负载小的路径,这种贪心策略容易造成网络拥塞和带宽利用率不足...多路径传输控制协议(multipath TCP,MPTCP)利用设备的多个网络接口传输数据,通过聚合带宽来提高传输效率。在进行路径选择时MPTCP通常使用不相交路径选择算法,由于优先选择负载小的路径,这种贪心策略容易造成网络拥塞和带宽利用率不足。轮盘赌轮选择通过概率的方式,在路径选择时加入随机性和动态性,能够克服该贪心策略造成的问题。为此,设计了一种基于轮盘赌轮选择的MPTCP路径选择算法,称作基于轮盘赌轮的MPTCP路径选择(roulette wheel based MPTCP path selection,RWSMPS)。RWSMPS通过软件定义网络(software defined network,SDN)控制器监控和分析网络状态信息,基于轮盘赌轮方式进行子流路径选择,用分组检查将子流分配到路径上,充分利用所有可用路径,并保证路径间的负载平衡。在Mininet平台上的实验证明,相比于广泛使用的等价多路径路由(equal cost multi path,ECMP)算法和链路不相交算法,RWSMPS的吞吐量分别提高了43.9%和41.8%,抖动分别减少了41.6%和40.7%。展开更多
软件定义网络(Software Defined Network,SDN)作为一种新型网络架构,通过分离数据平面与控制平面来简化网络管理逻辑,是下一代网络的研究热点。但是,由于频繁的链路故障等因素,SDN网络的可靠性成为公认的业界难题。当前已有的SDN链路故...软件定义网络(Software Defined Network,SDN)作为一种新型网络架构,通过分离数据平面与控制平面来简化网络管理逻辑,是下一代网络的研究热点。但是,由于频繁的链路故障等因素,SDN网络的可靠性成为公认的业界难题。当前已有的SDN链路故障恢复模型存在恢复时延过长、消耗过多流表项、忽视故障恢复后链路拥塞的问题。为了解决这些问题,提出了一种基于段路由(Segment Routing,SR)的单链路故障恢复模型(Loop Free Alternates-Congestion Aware,LFA-CA)。该模型包含了两个启发式算法BPF和BPU,分别用于在网络初始化时计算无环的备份路径,和在运行过程中更新拥塞避免的备份路径,实现了针对单链路故障的快速恢复和故障恢复后的拥塞避免。大量仿真实验证明了LFA-CA相比当前的SDN单链路故障恢复模型消耗了更少的转发规则,且具有更好的故障后负载均衡能力。展开更多
Large-scale and diverse businesses based on the cloud computing platform bring the heavy network traffic to cloud data centers.However,the unbalanced workload of cloud data center network easily leads to the network c...Large-scale and diverse businesses based on the cloud computing platform bring the heavy network traffic to cloud data centers.However,the unbalanced workload of cloud data center network easily leads to the network congestion,the low resource utilization rate,the long delay,the low reliability,and the low throughput.In order to improve the utilization efficiency and the quality of services(QoS)of cloud system,especially to solve the problem of network congestion,we propose MTSS,a multi-path traffic scheduling mechanism based on software defined networking(SDN).MTSS utilizes the data flow scheduling flexibility of SDN and the multi-path feature of the fat-tree structure to improve the traffic balance of the cloud data center network.A heuristic traffic balancing algorithm is presented for MTSS,which periodically monitors the network link and dynamically adjusts the traffic on the heavy link to achieve programmable data forwarding and load balancing.The experimental results show that MTSS outperforms equal-cost multi-path protocol(ECMP),by effectively reducing the packet loss rate and delay.In addition,MTSS improves the utilization efficiency,the reliability and the throughput rate of the cloud data center network.展开更多
针对6LoWPAN(IPv6 over Low-Power Wireless Personal Area Networks)分层路由算法存在的控制消息冗余、父节点选取不合理以及未解决下行路径修复等问题,提出了一种基于负载均衡的分层路由算法(a Load Balanced Hierarchical Routing Pr...针对6LoWPAN(IPv6 over Low-Power Wireless Personal Area Networks)分层路由算法存在的控制消息冗余、父节点选取不合理以及未解决下行路径修复等问题,提出了一种基于负载均衡的分层路由算法(a Load Balanced Hierarchical Routing Protocol for 6LoWPAN,LB-HiLow)予以解决。LBHiLow算法主要提出了两个改进机制:一个是最优父节点选取机制,通过减少控制消息的冗余以及增加选择的参数从而保持网络的负载平衡,可以更好地提高网络的生存时间;另一个是路径修复机制,通过判断失效节点与其上一跳节点的关系然后针对性地进行路径修复,从而提升数据传输成功率。仿真结果表明,文中算法在节点存活率、平均端到端时延和平均传输成功率等性能指标方面均有明显改善。展开更多
文摘多路径传输控制协议(multipath TCP,MPTCP)利用设备的多个网络接口传输数据,通过聚合带宽来提高传输效率。在进行路径选择时MPTCP通常使用不相交路径选择算法,由于优先选择负载小的路径,这种贪心策略容易造成网络拥塞和带宽利用率不足。轮盘赌轮选择通过概率的方式,在路径选择时加入随机性和动态性,能够克服该贪心策略造成的问题。为此,设计了一种基于轮盘赌轮选择的MPTCP路径选择算法,称作基于轮盘赌轮的MPTCP路径选择(roulette wheel based MPTCP path selection,RWSMPS)。RWSMPS通过软件定义网络(software defined network,SDN)控制器监控和分析网络状态信息,基于轮盘赌轮方式进行子流路径选择,用分组检查将子流分配到路径上,充分利用所有可用路径,并保证路径间的负载平衡。在Mininet平台上的实验证明,相比于广泛使用的等价多路径路由(equal cost multi path,ECMP)算法和链路不相交算法,RWSMPS的吞吐量分别提高了43.9%和41.8%,抖动分别减少了41.6%和40.7%。
基金supported by the National Key Research and Development Program of China(2018YFB1003702)the National Natural Science Foundation of China(61472192)the Scientific and Technological Support Project(Society)of Jiangsu Province(BE2016776)
文摘Large-scale and diverse businesses based on the cloud computing platform bring the heavy network traffic to cloud data centers.However,the unbalanced workload of cloud data center network easily leads to the network congestion,the low resource utilization rate,the long delay,the low reliability,and the low throughput.In order to improve the utilization efficiency and the quality of services(QoS)of cloud system,especially to solve the problem of network congestion,we propose MTSS,a multi-path traffic scheduling mechanism based on software defined networking(SDN).MTSS utilizes the data flow scheduling flexibility of SDN and the multi-path feature of the fat-tree structure to improve the traffic balance of the cloud data center network.A heuristic traffic balancing algorithm is presented for MTSS,which periodically monitors the network link and dynamically adjusts the traffic on the heavy link to achieve programmable data forwarding and load balancing.The experimental results show that MTSS outperforms equal-cost multi-path protocol(ECMP),by effectively reducing the packet loss rate and delay.In addition,MTSS improves the utilization efficiency,the reliability and the throughput rate of the cloud data center network.
文摘针对6LoWPAN(IPv6 over Low-Power Wireless Personal Area Networks)分层路由算法存在的控制消息冗余、父节点选取不合理以及未解决下行路径修复等问题,提出了一种基于负载均衡的分层路由算法(a Load Balanced Hierarchical Routing Protocol for 6LoWPAN,LB-HiLow)予以解决。LBHiLow算法主要提出了两个改进机制:一个是最优父节点选取机制,通过减少控制消息的冗余以及增加选择的参数从而保持网络的负载平衡,可以更好地提高网络的生存时间;另一个是路径修复机制,通过判断失效节点与其上一跳节点的关系然后针对性地进行路径修复,从而提升数据传输成功率。仿真结果表明,文中算法在节点存活率、平均端到端时延和平均传输成功率等性能指标方面均有明显改善。
