摘要：Information centric networking(ICN) is a new network architecture that is centred on accessing content. It aims to solve some of the problems associated with IP networks, increasing content distribution capability and improving users' experience. To analyse the requests' patterns and fully utilize the universal cached contents, a novel intelligent resources management system is proposed, which enables effi cient cache resource allocation in real time, based on changing user demand patterns. The system is composed of two parts. The fi rst part is a fi ne-grain traffi c estimation algorithm called Temporal Poisson traffi c prediction(TP2) that aims at analysing the traffi c pattern(or aggregated user requests' demands) for different contents. The second part is a collaborative cache placement algorithm that is based on traffic estimated by TP2. The experimental results show that TP2 has better performance than other comparable traffi c prediction algorithms and the proposed intelligent system can increase the utilization of cache resources and improve the network capacity.

摘要：为了针对不同的应用和流量提供服务质量保障和差异化服务,负载均衡和多优先级队列技术被广泛地应用于网络中。在传统网络中,网络管理员经常使用"traceroute"和"ping"工具来检测负载均衡机制或者服务质量策略是否正常工作。然而,由于这些工具并不被现有的OpenFlow交换机所支持,所以还不能够应用于软件定义网络中。此外,traceroute和ping依靠主动发送探测包来探测路径。然而,当负载均衡机制把探测包和所需追踪流的数据包均衡到不同路径时,这些工具将无法探测出流的真实转发路径,更无法测量出真实的路径时延。因此,为了准确的测量链路时延,测量工具必须能够提前找出数据包的真实转发路径。基于此发现,我们提出了一套新的软件定义网络中的流追踪机制"FlowTrace",利用它来追踪任意流量的转发路径以及测量数据流所经历的链路时延。该工具通过收集交换机的流表来计算流的转发路径。然而,如果直接从交换机中查询流表会产生很大的数据平面流量,从而带来巨大的开销。因此,我们提出了一种被动的零开销的流表收集方法来解决该问题。在获得流的真实转发路径后,我们提出了一种新的测量方法来测量不同流的网络时延。最后,实验结果显示我们设计的方法可以准确的找出流的真实转发路径并测量出不同种类流所经历的时延。