Aiming at the solidity of code and the difficulty of upgrades of existing Virtual Data Center (VDC) management platform, a VDC management platform based on Software Defined Network (SDN) was proposed. The proposed platform was composed of VDC Management subsystem (VDCM), VDC Computing Resources Control subsystem (VDCCRC) and VDC Network Resources Control subsystem (VDCNRC). A loosely coupled architecture was built by RESTful API interaction between subsystems. VDCNRC managed data center network by SDN controller, VDCCRC managed computing resources of data center by open source cloud computing platform, and a VDC management algorithm framework was built in VDC management subsystem to develop rapidly VDC management algorithm suitable for production environment. By utilizing Mininet, Openstack and Floodlight to set up test environment, the results show the proposed platform can support running, migrating or deleting virtual machines by Openstack, implement bandwidth resource isolation between VDCs by Openflow controller, and support the operations of creating, deleting, or updating VDC.

For the potential link congestion problem during traffic migration caused by IP network updates, a Congestion Avoidance and Fast Traffic Migration based on Multi-Topology Routing (CAFTM-MTR) algorithm was proposed. Firstly, the link capacity constraints and the timing characteristic of source node traffic migration were considered, and a congestion avoidance migration sequence that each moves one source node was gotten. Secondly, to shorten the migration finishing time, the algorithm was improved based on the sequence independence of traffics to make each batch move multiple sequence independent traffics. By using typical topologies and Waxman topologies to validate the proposed algorithm, the proposed algorithm improved the success rate of avoiding congestion from 20%-60% to 100% in the comparison experiments with Non-Congestion Avoidance and Fast Traffic Migration based on MTR (NonCAFTM-MTR) method, and obtained less than 8-round migration sequence. In addition, the proposed algorithm had an adaptability of dynamic traffic and was able to accommodate the traffic growth ranging from 5% to 284%. The simulation results show that CAFTM-MTR algorithm can effectively improve the success rate of congestion avoidance, and meanwhile make the traffic migration fast.

This paper proposed a method for analyzing the survivability of interdependent networks with incomplete information. Firstly, the definition of the structure information and the attack information were proposed. A novel model of interdependent network with incomplete attack information was proposed by considering the process of acquiring attack information as the unequal probability sampling by using information breadth parameter and information accuracy parameter in the condition of structure information was known. Secondly, with the help of generating function and the percolation theory, the interdependent network survivability analysis models with random incomplete information and preferential incomplete information were derived. Finally, the scale-free network was taken as an example for further simulations. The research result shows that both information breadth and information accuracy parameters have tremendous impacts on the percolation threshold of interdependent network, and information accuracy parameter has more impact than information breadth parameter. A small number of high accuracy nodes information has the same survivability performance as a large number of low accuracy nodes information. Knowing a small number of the most important nodes can reduce the interdependent network survivability to a large extent. The interdependent network has far lower survivability performance than the single network even in the condition of incomplete attack information.

By introducing the current research progress of Virtual Data Center (VDC) embedding, and in accordance with the reliability requirement of VDC, a new heuristic algorithm to address reliability-aware VDC embedding problem was proposed. It restricted the number of Virtual Machines (VMs) which can be embedded onto the same physical server to guarantee the VDC reliability, and then regarded reduction of the bandwidth consumption and energy consumption as main objective to embed the VDC. Firstly, it reduced bandwidth consumption of data center by consolidating the virtual machines, which had high communication services, into the same group and placed them onto the same physical server. Secondly, the consolidated groups were mapped onto the powered physical servers to decrease the number of powered servers, thus reducing the power consumption of servers. The results of experiment conducted on fat tree topology show that, compared with 2EM algorithm, the proposed algorithm can satisfy VDC reliability requirement, and effectively reduce a maximum of 30% bandwidth consumption of data center without increasing extra energy consumption.

When a link weight changes in network with Internet Protocol (IP), routing loops may occur. Such loops increase the network latency and cause packet losses, which cannot meet the needs of high-level real-time service. A fast routing micro-loop avoidance algorithm using a weight sequence was proposed. The link weights were reallocated according to the weight sequence so that no loops would occur during convergence phase. In order to calculate the weight sequence, a safety weight interval was defined to describe the condition for avoiding loops, then the safety interval was used to search a set of safety weight ranges. During calculation, the prunning technology was used to reduce search range and improve efficiency. At last, the final weight sequence was obtained from these ranges. The simulation test results using typical network topology algorithm show that in average five times of link weight reallocation can successfully avoid loops in 87% of topologies. In addition, compared with other existing algorithms using iterative adjustment link weights to solve the routing micro-loop, the computational complexity of the proposed algorithm was greatly reduced by an order of magnitude and the computational efficiency was improved by 30%-80%. The proposed algorithm can greatly shorten the calculation time and more efficiently solve the problem of routing micro-loop, which will avoid network latency and packet loss to provide a high level of service quality.