基于连通支配集的OBS网络多粒度业务疏导机制  

Connected dominating set-based multi-granularity traffic grooming mechanism for OBS networks

在线阅读下载全文

作  者:阳小龙[1,2] 周静[1] 刘真[3] 黄琼[3] 隆克平[2] 

机构地区:[1]重庆邮电大学计算机科学与技术学院,重庆400065 [2]电子科技大学光互联网与移动信息网络研究中心,四川成都611731 [3]重庆邮电大学通信与信息工程学院,重庆400065

出  处:《光电子.激光》2011年第5期701-705,共5页Journal of Optoelectronics·Laser

基  金:国家"973"计划资助项目(2007CB310706);国家"863"计划资助项目(2009AA01Z215;2009AA01Z254);国家自然科学基金资助项目(60725104;60873263);四川省青年基金资助项目(09ZQ026-032);教育部新世纪优秀人才计划资助项目

摘  要:针对目前光网络核心节点的交换速度无法匹配单波长的传输速度难以满足大量的业务请求而拥塞,为了提高核心节点交换效率使其具有大容量数据交换的能力,本文提出了一种基于连通支配集(CDS)的光突发交换(OBS)网络稀疏节点疏导机制(CDS-TG)。主要思路是:首先在OBS核心网络中根据改进的连通支配集算法选取疏导节点;其次在疏导节点中根据多粒度虚拟汇聚算法将多个数据突发包(DB)逻辑汇聚成更大粒度的虚拟突发在网络中传送,减少核心节点业务请求次数,降低核心节点对BCP的处理开销,以达到提高核心节点的交换效率的目的。仿真结果表明,与边缘节点疏导机制相比,CDS-TG能有效地使核心节点处理BCP的数量在不同负载下平均减少了约25%,链路利用率平均提高约18%,丢包率降低约0.2%。The rate of processing in core node is still not matching the rate of transmission for optical burst switching(OBS).In order to improve capabilities of high-speed and high-capacity data exchange in core node,a traffic grooming mechanism which is called CDS-TG is proposed in optical burst switching networks.First of all,according to the advanced connected dominating set(CDS) algorithm,the grooming nodes were chosen from the OBS core networks; then in grooming nodes based on the multi-granularity virtual assembly algorithm,arriving data bursts(DBs) in different granularities were assembled into a virtual burst which is with bigger granularity than before assembling,reducing the core node number of the service requests and BCP processing overhead in core nodes,with the purpose of improving the exchange efficiency.Experiments show that the average number of BCP processing in the core node is reduced by approximately 25% under different loads,the average link utilization is increased by about 18%,and the packet loss rate is decreased by about 0.2%.

关 键 词:连通支配集(CDS) 多粒度 光突发交换(OBS) 业务疏导 虚拟突发 

分 类 号:TN915[电子电信—通信与信息系统]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象