This paper addresses the problem about how to deploy different protection strategies in the multi-layer network to use
resource efficiently and give protections perfectly. Generally, every protection strategy has its own merits and demerits.
How to use the merits of the protections efficiently and avoid the demerits as much as possible. For this aim, giving
different protections to different LSP requests is a good selection. In this paper, we define different classes of LSP
requests in terms of transmission delay and give different protections to different classes of LSP requests. Then, we
propose a novel QoS-aware multi-layer protection scheme which consider the o-e-o conversion and the hop for the high
priority requests at the same time and only consider the hop for the low priority requests. Moreover, we present a new
inter-class backup resource sharing strategy within the scheme. It allows low priority requests to use the backup space of
high priority services and also allows the high priority request use all of the resource of the network firstly as the
blocking probability increasing. A complete set of experiments proves that this scheme can effectively decrease the
blocking probability and end-to-end delay, comparing with the multi-layer protection scheme without inter-class backup
At present, the video stream scheme based on Unicast is adopted in VOD systems. It not only increases network load and delay, but also causes user's QoS to be limited by network transmission bandwidth. And networks congestion caused by characteristic of IP networks affects video applications seriously. So a design of network structure of VOD system base on IP Multicast is proposed in the paper. And this system has a predominant scheduler algorithm to Multicast transmission of video stream. At the same time, design and performance of the system's video sever are analyzed. Further, The ways of coding technology and runoff control are proposed, so that QoS will be improved. The main propositions are as follows:1. Propose a design of network structure of VOD system base on IP Multicast. 2. Analyze the design of access sever for system users. including analysis of the most users, analysis of network transmission for users in different regions demanding the same program, and how to access user severs nonblocking for users in different networks, and so on. 3. Propose a way of realizing system QoS, including network optimization, runoff and congestion control of the network, and prior control of different service in the network.
In this paper,architecture of grid audio/video communication environment based on optical layer multicast is introduced. First, architecture of optical layer multicast communication environment is analyzed. Then, scheme of large capability optical routing is presented. Last, condition of non-blocking multicast communication over WDM(wavelength division multiplexing) grid network is analyzed.
Recently, people pay more attention to the grid technology. It can incorporate high-speed network, high performance computer, large database, sensor and remote equipment etc. Moreover, it can not only connect all kinds of resources in the network and also put them into a super transparent computing environment for customers. In which it can realize meta-computing for the shared resources. However, traditional parallel computing system such as SMP and MPP use multi-processors to upgrade computing by closed coupler. Doing like that, the flexible and scalable performance of the system will be limited so that the system can't meet the requirement of the grid technology.
In this paper, the architecture of cluster computing system applying in grid nodes is introduced. It mainly includes the following aspects. First, the network architecture is analyzed and designed. Second, it forms virtual computers with distributing computing including divided computing and shared computing. Last, it discusses the communication problems between the grid nodes. In other words, it discusses the realization of single map in order to meet all the requirements of customers sent to the grid nodes.