共查询到19条相似文献,搜索用时 140 毫秒
1.
2.
光突发交换网络中支持业务区分的多路由机制研究 总被引:1,自引:1,他引:0
针对光突发交换(OBS)网络的多路由机制多是考虑一种业务而对多业务区分的多路由机制研究偏少这种现状,提出了一种支持业务区分的多路由(MRSD)机制。在发送各个服务等级的业务之前,首先在没有共享风险链路的多条路由上发送请求包获得各条路由上的多种优先级业务的负载情况,然后根据爱尔兰固定点近似分析法计算各种优先级业务在不同路由上的丢包率,并为每种优先级业务选择一条使本业务丢包率最小的路由;在一个核心节点内,则采用基于额外偏置时间的业务区分方法实现不同优先级业务的区分,将各种业务根据链路状态信息分配到没有共享风险链路的多条路由上去传输,从而在减少突发丢失率(BLP)的同时实现了多种优先级业务在路由上的区分。仿真结果表明,这种多路由机制能够有效降低网络的BLP,实现区分服务。 相似文献
3.
光突发交换网络(OBS)是一种IP over WDM的光交换技术,能很好地支持突发业务。OBS系统采用单向波长资源预留方式为突发数据分组预留前向数据波长通道,这样提高了传输交换效率、减少了建链时间,但同时因路由连接的非确定性而引起突发分组的易丢失性。所以QoS戍为OBS网络中的最亟需解决的问题。对OBS网络所采取的多种改善其QoS的策略进行了研究。 相似文献
4.
引入广义光突发汇聚(GOBA)概念对传统光突发交换(OBS)进行扩展,形成新的广义OBS(GOBS)网络。针对GOBS的多业务承载目标,提出了一种支持多业务承载的GOBA机制,采用将业务最小时延要求作为汇聚时间的汇聚方式,将多种用户数据业务汇聚到不同粒度的广义数据突发(GDB)中。仿真结果表明,在GOBS环境下,与MSMAP(max burst-size max assembly period)机制相比,GOBA能够在满足较高数据成功接收率的基础上显著地减小约10%的总体数据超时率,同时降低约15%的突发碰撞率,并提高约20%信道利用率。 相似文献
5.
6.
提出一种解决光突发交换(OBS)网络节点中突发数据包冲突的方案.发生冲突时,在OBS层重传被丢弃突发数据包,然后给出评估这种重传机制丢包率的方法,并与偏射路由策略的性能进行比较,结果表明突发重传机制显著改善了丢包率.可以很好地实现服务质量(QoS)机制. 相似文献
7.
光突发交换(OBS)网络被认为是下一代光因特网的典型代表,其中,光突发数据包在节点的竞争问题是OBS网络中需要解决的关键问题之一。该文重点研究了突发数据包之间因争夺链路资源而导致冲突的四种竞争解决方案:波长转换、光缓存、偏射路由和突发包分割,并分析了它们的优缺点。在此基础上,提出了OBS网络中冲突解决方法的发展趋势——... 相似文献
8.
9.
光突发交换(Optcal Burst Switching.OBS)被认为是在下一代光网络中起到至关重要作用的一种交换技术。边缘节点处突发包的组装作为业务接入OBS网络的第一步,是OBS研究的关键课题之一。 该文重点阐述了几种常用的突发组装方案:基于突发长度组装方案、基于组装时间组装方案、混合组装方案及自适应组装方案,并分析了它们的性能和优缺点。最后指出综合考虑网络业务流量、边缘节点的处理速度和信道带宽等因素的更加有效的突发组装算法是重点研究的内容。 相似文献
10.
11.
SuKyoung Lee LaeYoung Kim JooSeok Song David Griffith Kotikalapudi Sriram 《Photonic Network Communications》2005,9(3):347-356
In optical burst-switched networks, one of the most significant issues is contention resolution. There have been several deflection routing techniques as contention resolution. While contention is resolved by traditional deflection routing, it cannot guarantee that the control packet will reserve all the wavelengths successfully to the destination on the alternate path, especially when traffic load in a network is high. Therefore, in this paper, we propose a Deflection Routing with Virtual Wavelength Assignment (DR-VWA) algorithm in order to provide a higher resource guarantee for loss-sensitive traffic bursts. The proposed DR-VWA scheme (1) dynamically decides the alternate path with the least traffic load and (2) allows high-priority bursts in terms of loss to be assigned available wavelengths over the path virtually. The proposed scheme is evaluated through simulation, and it is shown that significant improvement with regard to burst loss and wavelength conversion cost can be achieved.This work was supported in part by the Korea Science and Engineering Foundation (KOSEF) through OIRC project and by the US National Communications System (NCS). 相似文献
12.
光突发交换技术是最具发展潜力的光交换技术之一,而减少突发丢失是其首要问题。传统的静态路由机制不能随着网络负载的变化而更改路由,不能有效应对动态业务。为此,在研究现有动态负载平衡路由机制的基础上,提出了一种基于蚁群探测的路由机制。蚁群根据节点出度链路上的负载变化选择下一跳节点,当转发到目的节点时收集蚁群探测到的所有备选路径,然后根据备选路径中记录的链路负载选择可使丢包最小的路径,通过选择更加合理的路由,达到减少突发丢失率的目的。仿真结果表明,与其他算法相比,所提出的机制表现出比较好的性能,有效降低至少15%突发丢失率。 相似文献
13.
This paper proposes a dynamic burst discarding scheme for deflection routing in optical burst switching networks. In general, deflection routing is effective in lightly loaded situations, whereas it has a contrary effect in congested networks because deflected bursts accelerate network congestion. Thus deflection routing should be employed in lightly loaded networks. Incoming traffic, however, varies in time and location, so that temporal and/or local congestion cannot be avoided. Our proposed scheme resolves this problem in the following way. Each node autonomously detects congestion with local information, and bursts to be deflected are discarded in a probabilistic manner, based on the degree of detected congestion and the numbers of elapsed and remaining hops of those bursts. Simulation experiments show that when congestion happens temporarily, the proposed scheme reduces the burst loss probability, and it utilizes network resources efficiently when local congestion happens. 相似文献
14.
《AEUE-International Journal of Electronics and Communications》2014,68(1):44-50
In optical burst switching (OBS) networks, burst contentions in OBS core nodes may cause data loss. To reduce data loss, retransmission scheme has been applied. However, uncontrolled retransmission may increase network load significantly and data loss probability defeating the retransmission purpose. In addition, in a priority traffic existing OBS network, OBS nodes may apply different retransmission mechanisms to priorities bursts for quality-of-service (QoS) support. This study has developed a controlled retransmission scheme for prioritized burst segmentation to support QoS in OBS networks. Unlike previous works in the literature, we have set a different value to retransmission probability at each contention and propose a retransmission analytical model for burst segmentation contention resolution scheme. In addition, we have applied the proposed retransmission scheme to the prioritized burst segmentation for QoS support. We have taken into account the load at each link due to both fresh and retransmitted traffic, and have calculated the path blocking probability and byte loss probability (ByLP) for high-priority and low-priority burst to evaluate network performance. An extensive simulation has been proposed to validate our analytical model. 相似文献
15.
文章分析了偏射路由对网络性能的影响,在分析发送端控制偏射路由技术的基础上,提出了基于阈值检测和数据更新的改进方案.边缘节点快速更新状态信息,并通过特殊控制分组传递链路拥塞的分布特征等信息;交换节点进行阈值检测,动态决定竞争时突发的传送方式,减少偏射路由对网络负荷的影响,进一步降低网络阻塞率,改善网络性能。 相似文献
16.
光突发交换是适合在当前技术条件下的新交换技术,它比电路交换灵活,带宽利用率高,又比光分组交换易于实现,将成为下一代光IP骨干网的核心技术。在光突发交换网络中,偏射路由算法是有效解决突发竞争、提高网络性能的一种重要措施。首先分析了发送端控制的偏射路由技术,在此基础上提出了一种基于阈值检测的偏射路由的改进算法。该算法通过跳数来控制无效偏射路由并通过有条件地丢弃偏射突发来保证正常突发的丢包率,从而减少偏射路由对网络负荷的影响,使整个网络的丢包率得到一定提高,改善网络性能。 相似文献
17.
Multiservice on-demand routing in LEO satellite networks 总被引:2,自引:0,他引:2
Karapantazis S. Papapetrou E. Pavlidou F.-N. 《Wireless Communications, IEEE Transactions on》2009,8(1):107-112
In this paper, a distributed on-demand routing protocol for Low Earth Orbit (LEO) satellite systems, named multiservice on-demand routing (MOR), is proposed and evaluated. The proposed protocol adjusts the routing procedure to the QoS requirements of different traffic classes. The performance of the MOR protocol is compared to the unique proposal for traffic class dependent routing in the literature and the good characteristics of the proposed scheme are corroborated by ample simulation experiments, where significant gains in performance are witnessed. 相似文献
18.
The authors describe a simple adaptive routing scheme for datagram (connectionless) and virtual circuit (connection-oriented) transmission that relieves congestion resulting from nonuniform traffic patterns and network failures. The authors describe a fixed-routing algorithm for dedicated channel ShuffleNets. Based on the fixed routing algorithm, an adaptive routing scheme for datagram transmission is presented followed by performance results for uniform and nonuniform traffic patterns and fault tolerance. The adaptive routing of datagrams uses only the local queue size information available at the network interface units (NIUs) and redistributes the load as congestion develops. Since datagrams are individually routed through the network, they may not arrive at their destination in the order they were generated and may need to be resequenced. The authors compute an upper estimate on the resequencing buffer size for stream traffic. A virtual circuit version of the adaptive routing algorithm eliminates the need for resequencing buffers 相似文献
19.
WANG Ru-yan~ LONG Ke-ping~ WU Wei~ YANG Xiao-long~ ZHU Wei-le~.The College of Electronic Engineering University of Electronic Science Technology of China Chengdu P.R. China .Special Research Centre for Optical Internet & Wireless Information Networks Chongqing Univ of Posts Telecom Chongqing P.R. China 《中国邮电高校学报(英文版)》2005,12(3)
1 Introduction The increase in the demand of transport capacity duetothe explosive growth of the Internet IP-based traffichas fueled the development of high-speed transmissionsystems andthe emergence of Wavelength Division Mul-tiplexing ( WDM) technology[1].Soin the near future ,it will be possible to support hundreds of wavelengths ofseveral Gigabit/s each. A new approach called OpticalBurst Switching (OBS)[2]that combines the best of op-tical circuit switching and optical packet switch… 相似文献