a c m s i g c o m m ABSTRACTVirtualizing and sharing networked resources have become a growing trend that reshapes the computing and networking architectures. Embedding multiple virtual networks (VNs) on a shared substrate is a challenging problem on cloud computing platforms and large-scale sliceable network testbeds.In this paper we apply the Markov Random Walk (RW) model to rank a network node based on its resource and topological attributes. This novel topology-aware node ranking measure reflects the relative importance of the node. Using node ranking we devise two VN embedding algorithms. The first algorithm maps virtual nodes to substrate nodes according to their ranks, then embeds the virtual links between the mapped nodes by finding shortest paths with unsplittable paths and solving the multi-commodity flow problem with splittable paths. The second algorithm is a backtracking VN embedding algorithm based on breadth-first search, which embeds the virtual nodes and links during the same stage using node ranks. Extensive simulation experiments show that the topology-aware node rank is a better resource measure and the proposed RW-based algorithms increase the long-term average revenue and acceptance ratio compared to the existing embedding algorithms.

No abstract

SUMMARYVirtual network (VN) embedding is a major challenge in network virtualization. In this paper, we aim to increase the acceptance ratio of VNs and the revenue of infrastructure providers by optimizing VN embedding costs. We first establish two models for VN embedding: an integer linear programming model for a substrate network that does not support path splitting and a mixed integer programming model when path splitting is supported. Then we propose a unified enhanced particle swarm optimization‐based VN embedding algorithm, called VNE‐UEPSO, to solve these two models irrespective of the support for path splitting. In VNE‐UEPSO, the parameters and operations of the particles are well redefined according to the VN embedding context. To reduce the time complexity of the link mapping stage, we use shortest path algorithm for link mapping when path splitting is unsupported and propose greedy k‐shortest paths algorithm for the other case. Furthermore, a large to large and small to small preferred node mapping strategy is proposed to achieve better convergence and load balance of the substrate network. The simulation results show that our algorithm significantly outperforms previous approaches in terms of the VN acceptance ratio and long‐term average revenue. Copyright © 2012 John Wiley & Sons, Ltd.

No abstract

Network virtualization has caught the attention of many researchers in recent years. It facilitates the process of creating several virtual networks over a single physical network. Despite this advantage, however, network virtualization suffers from the problem of mapping virtual links and nodes to physical network in most efficient way. This problem is called virtual network embedding ("VNE"). Many researches have been proposed in an attempt to solve this problem, which have many optimization aspects, such as improving embedding strategies in a way that preserves energy, reducing embedding cost and increasing embedding revenue. Moreover, some researchers have extended their algorithms to be more compatible with the distributed clouds instead of a single infrastructure provider ("ISP"). This paper proposes energy aware particle swarm optimization algorithm for distributed clouds. This algorithm aims to partition each virtual network request ("VNR") to sub-graphs, using the Heavy Clique Matching technique ("HCM") to generate a coarsened graph. Each coarsened node in the coarsened graph is assigned to a suitable data center ("DC"). Inside each DC, a modified particle swarm optimization algorithm is initiated to find the near optimal solution for the VNE problem. The proposed algorithm was tested and evaluated against existing algorithms using extensive simulations, which shows that the proposed algorithm outperforms other algorithms.

No abstract

No abstract

The intersubspecific hybrids of autotetraploid rice has many features that increase rice yield, but lower seed set is a major hindrance in its utilization. Pollen sterility is one of the most important factors which cause intersubspecific hybrid sterility. The hybrids with greater variation in seed set were used to study how the F1 pollen sterile loci (S-a, S-b, and S-c) interact with each other and how abnormal chromosome behaviour and allelic interaction of F1 sterility loci affect pollen fertility and seed set of intersubspecific autotetraploid rice hybrids. The results showed that interaction between pollen sterility loci have significant effects on the pollen fertility of autotetraploid hybrids, and pollen fertility further decreased with an increase in the allelic interaction of F1 pollen sterility loci. Abnormal ultra-structure and microtubule distribution patterns during pollen mother cell (PMC) meiosis were found in the hybrids with low pollen fertility in interphase and leptotene, suggesting that the effect-time of pollen sterility loci interaction was very early. There were highly significant differences in the number of quadrivalents and bivalents, and in chromosome configuration among all the hybrids, and quadrivalents decreased with an increase in the seed set of autotetraploid hybrids. Many different kinds of chromosomal abnormalities, such as chromosome straggling, chromosome lagging, asynchrony of chromosome disjunction, and tri-fission were found during the various developmental stages of PMC meiosis. All these abnormalities were significantly higher in sterile hybrids than in fertile hybrids, suggesting that pollen sterility gene interactions tend to increase the chromosomal abnormalities which cause the partial abortion of male gametes and leads to the decline in the seed set of the autotetraploid rice hybrids.