云数据中心光电混合网络流调度
Hybrid Optical and Electrical Network Flows Scheduling in Cloud Data Centres
摘要:
近年来,具有光电能力的混合数据中心内网络吸引了研究兴趣。这归因于新的带宽贪婪应用和新颖的计算范例的出现。在这种类型的网络中做出的关键决策是选择和放置合适的流以用于电路网络中的交换。在这里,我们提出了一种有效的策略,适合混合云内数据中心网络的流选择和放置。我们进一步提出的技术,调查在一个分组网络中的瓶颈和电路网络中切换流的选择。在软件定义网络(SDN)实验平台上验证了该瓶颈技术。我们还实现了这里提出的技术在一个可扩展的模拟实验,调查流选择对网络性能的影响。可扩展的仿真实验结果表明,该算法在平均吞吐量、配置延迟和分流稳定性等方面都有较大的提高
英文摘要:
Hybrid intra-data centre networks, with optical and electrical capabilities, are attracting research interest in recent years. This is attributed to the emergence of new bandwidth greedy applications and novel computing paradigms. A key decision to make in networks of this type is the selection and placement of suitable flows for switching in circuit network. Here, we propose an efficient strategy for flow selection and placement suitable for hybrid Intra-cloud data centre networks. We further present techniques for investigating bottlenecks in a packet networks and for the selection of flows to switch in circuit network. The bottleneck technique is verified on a Software Defined Network (SDN) testbed. We also implemented the techniques presented here in a scalable simulation experiment to investigate the impact of flow selection on network performance. Results obtained from scalable simulation experiment indicate a considerable improvement on average throughput, lower configuration delay, and stability of offloaded flows
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。