The existing active queue management （AQM） algorithm acts on subscribers and edge routers only, it does not support differentiate-serve （Diffserv） quality of service （QoS）, while the existing diffserv QoS has no...The existing active queue management （AQM） algorithm acts on subscribers and edge routers only, it does not support differentiate-serve （Diffserv） quality of service （QoS）, while the existing diffserv QoS has not considered the link capacities between edge routers and connected core routers. When a core router in a two layers’ network experiences congestion, the connected edge routers have no ability to adjust their access data rates. Thus, it is difficult to achieve the congestion control for the large scale network with many edge routers and core routers. To solve these problems, two difffserve AQM algorithms are proposed for the congestion control of multilayer network. One diffserv AQM algorithm implements fair link capacities of edge routers, and the other one implements unequal link capacities of edge routers, but it requires the core routers to have multi-queues buffers and Diffserv AQM to support. The proposed algorithms achieve the network congestion control by operating AQM parameters on the conditions of proposed three theorems for core and edge routers. The dynamic simulation results demonstrate the proposed control algorithms for core and edge routers to be valid.展开更多
传感器网络节点通信能力有限,当数据到达速率持续超过节点转发能力时网络会发生拥塞;传感器网络是任务型网络,对不同优先级的信息具有不同的服务质量要求.针对传感器网络信息传输的上述特性,提出了一种新的拥塞避免与控制算法FAQM(Fuzzy...传感器网络节点通信能力有限,当数据到达速率持续超过节点转发能力时网络会发生拥塞;传感器网络是任务型网络,对不同优先级的信息具有不同的服务质量要求.针对传感器网络信息传输的上述特性,提出了一种新的拥塞避免与控制算法FAQM(Fuzzy Active Queue Management).该算法在综合考虑数据包的随机指数标记概率和优先级权值的基础上,建立了模糊逻辑推理系统,并以数据包丢弃因子作为参量来实现数据流的智能调控.NS2仿真实验结果表明:FAQM算法能减少高优先级数据包的丢弃率和节点间链路的时延,稳定节点队列长度,在有效避免与控制拥塞网络的同时提升网络整体QoS(Quality of Service)性能.展开更多
针对TCP(Transmission Control Protocol,传输控制协议)网络的拥塞控制问题,基于T-S(Takagi-Sugeno)模糊模型,采用滑模控制理论提出了一种新的AQM(Active Queue Management,主动队列管理)算法。考虑到TCP网络中存在的不确定和时变时滞因...针对TCP(Transmission Control Protocol,传输控制协议)网络的拥塞控制问题,基于T-S(Takagi-Sugeno)模糊模型,采用滑模控制理论提出了一种新的AQM(Active Queue Management,主动队列管理)算法。考虑到TCP网络中存在的不确定和时变时滞因素,首先利用T-S模糊模型对网络进行建模,然后利用线性矩阵不等式设计了一个渐近稳定的滑模面,而且还给出了一种能够明显减小滑模面附近抖振的趋近律,基于该趋近律设计的控制律能够有效地抑制路由器中队列长度的振荡,并使其快速收敛于期望值。仿真结果表明,该算法与普通的滑模控制算法相比具有更好的稳定性和鲁棒性,能够很好地适应复杂多变的TCP网络环境。展开更多
基金supported by the Beijing Natural Science Foundation (4102050)NSFC-KOSEF Joint Research Project of China and Korea(60811140343), and the CDSN, GIST.
文摘The existing active queue management （AQM） algorithm acts on subscribers and edge routers only, it does not support differentiate-serve （Diffserv） quality of service （QoS）, while the existing diffserv QoS has not considered the link capacities between edge routers and connected core routers. When a core router in a two layers’ network experiences congestion, the connected edge routers have no ability to adjust their access data rates. Thus, it is difficult to achieve the congestion control for the large scale network with many edge routers and core routers. To solve these problems, two difffserve AQM algorithms are proposed for the congestion control of multilayer network. One diffserv AQM algorithm implements fair link capacities of edge routers, and the other one implements unequal link capacities of edge routers, but it requires the core routers to have multi-queues buffers and Diffserv AQM to support. The proposed algorithms achieve the network congestion control by operating AQM parameters on the conditions of proposed three theorems for core and edge routers. The dynamic simulation results demonstrate the proposed control algorithms for core and edge routers to be valid.
文摘传感器网络节点通信能力有限,当数据到达速率持续超过节点转发能力时网络会发生拥塞;传感器网络是任务型网络,对不同优先级的信息具有不同的服务质量要求.针对传感器网络信息传输的上述特性,提出了一种新的拥塞避免与控制算法FAQM(Fuzzy Active Queue Management).该算法在综合考虑数据包的随机指数标记概率和优先级权值的基础上,建立了模糊逻辑推理系统,并以数据包丢弃因子作为参量来实现数据流的智能调控.NS2仿真实验结果表明:FAQM算法能减少高优先级数据包的丢弃率和节点间链路的时延,稳定节点队列长度,在有效避免与控制拥塞网络的同时提升网络整体QoS(Quality of Service)性能.
文摘针对TCP(Transmission Control Protocol,传输控制协议)网络的拥塞控制问题,基于T-S(Takagi-Sugeno)模糊模型,采用滑模控制理论提出了一种新的AQM(Active Queue Management,主动队列管理)算法。考虑到TCP网络中存在的不确定和时变时滞因素,首先利用T-S模糊模型对网络进行建模,然后利用线性矩阵不等式设计了一个渐近稳定的滑模面,而且还给出了一种能够明显减小滑模面附近抖振的趋近律,基于该趋近律设计的控制律能够有效地抑制路由器中队列长度的振荡,并使其快速收敛于期望值。仿真结果表明,该算法与普通的滑模控制算法相比具有更好的稳定性和鲁棒性,能够很好地适应复杂多变的TCP网络环境。
