Integrated Space-Terrestrial Network (ISTN) can effectively improve the global communication coverage and SDN framework in ISTN has emerged as a promising solution to guarantee the Quality of Service (QoS). At present, the researches on routing algorithm are mainly focused on the QoS parameters about resource availability and do not consider the impact of the network attacks comprehensively, such as DDoS attack. Plenty of available resources will be occupied by network attacks and normal traffic may be blocked incorrectly by attack defense solutions. In this paper, we propose a Trusted Routing (TR) model based on Trusted Resource Matrix (TRM) to protect the normal traffic from network attacks in ISTN. In the process, the SDN controller constructs the characteristic matrices by collecting the state information of each routing node and the entropy estimation method which describes the changes of traffic characteristics is used to determine whether a routing node is suffering from network attacks. Corresponding trust values are allocated to the routing nodes for constructing TRM and trusted transmission paths are discovered by the TR model. Based on the comprehensive consideration of available and trusted resources, a Hybrid Routing (HR) model is proposed, taking into account the traditional QoS parameters and TRM. In the simulation experiments, the TR and HR models-based algorithms are evaluated. The experimental results show that TR and HR algorithms can effectively avoid the routing nodes suffering from network attacks and improve the communication QoS. When considering a scenario of a single attacked node under resource constraints, the average packet pass rate of HR algorithm is about 7.0% higher than that of TR algorithm and about 52.1% higher than that of traditional QoS algorithm.

Virtualization makes virtual machine placement (VMP) one of the most important technology in cloud computing. An effective VMP algorithm can significantly improve resource utilization of physical machines (PMs) in cloud datacenters. In this paper, we propose a VMP algorithm based on weighted PageRank (WPRVMP), which pursued to minimize the number of active PMs and improve the total resource utilization of all PMs in cloud datacenters. The impact of unplaced virtual machines (VMs) in the VMP process on the placement results, and the impact of VMP on the total resource utilization of all PMs are considered in this algorithm, to avoid the algorithm to fall into local optimal solution. In the process of selecting PM for each VM, the number of unplaced VMs of different types in the VMP process is considered in WPRVMP by weighted. The weighted PageRank algorithm is used to measure the possibility of a PM making full use of resources under different VMP conditions. The algorithm then ranks PMs according to the impact of the given VM is placed on each PM on the maximum resource utilization of all PMs, and places the VM based on the ranking results. Experimental results show that our algorithm is superior to other algorithms in reducing the number of active PMs and improving the resource utilization of PMs.

Energy efficiency is a hot topic in the research of virtual machine placement (VMP). As the network equipment energy consumption problem has become increasingly prominent, many studies through resource aggregation to save energy, which can easily lead to resource competition and SLA violations. In this paper, we present a virtual machine placement algorithm based on graph partitioning (GPVMP) to achieve energy optimization. For the virtual machine (VM) group submitted by the user, we reconstruct the VM associated graph according to the traffic and load correlation between VMs, and partition the graph using the improved multilevel k-way partitioning algorithm. Combined with the data center topology, the two-layer mapping relationship of VMs and physical machines (PMs) is determined by extending PM clusters. The experimental results show that our proposed algorithm can guarantee better resource utilization, control SLA violation and offer a significant savings of energy compared with other related algorithms.

The limited computation resource of the centralized controller and communication bandwidth between the control and data planes become the bottleneck in forwarding the packets in Software-Defined Networking (SDN). Denial of Service (DoS) attacks based on Transmission Control Protocol (TCP) can exhaust the resources of the control plane and overload the infrastructure of SDN networks. To mitigate TCP DoS attacks, DoSDefender is proposed as an efficient kernel-mode TCP DoS prevention framework in the data plane for SDN. It can prevent TCP DoS attacks from entering SDN by verifying the validity of the attempts to establish a TCP connection from the source, migrating the connection, and relaying the packets between the source and the destination in kernel space. DoSDefender conforms to the de facto standard SDN protocol, the OpenFlow policy, which requires no additional devices and no modifications in the control plane. Experimental results show that DoSDefender can effectively prevent TCP DoS attacks in low computing consumption while maintaining low connection delay and high packet forwarding throughput.