Zihou Wang

Virtual network embedding by exploiting topological information

Network virtualization provides a powerful way to run multiple heterogeneous virtual networks (VNs) at the same time on a shared substrate network. A major challenge in network virtualization is the efficient virtual network embedding: mapping virtual nodes and virtual edges onto substrate networks. Previous researches have presented several heuristic algorithms, which fail to consider the topology attributes of substrate and virtual networks. However, the topology information affects the performance of the embedding obviously. In this paper, for the first time, we exploit the topology attributes of substrate and virtual networks, introduce network centrality analysis into the virtual network embedding, and propose virtual network embedding algorithms based on closeness centrality. Due to considering the topology information, our study is more reasonable than the existing work in coordinating node and edge embedding. In addition, with the guidance of topology quantitative evaluation, the proposed network embedding approaches largely improve the network utilization efficiency and decrease the embedding complexity. Experimental results demonstrate the usability and feasibility of the proposed approach.

A novel cache size optimization scheme based on manifold learning in Content Centric Networking

Content Centric Networking (CCN) is an emerging network architecture, shifting from an end-to-end connection to a content centric communication model. Each router in CCN has a content store module to cache the chunks passed by, and is arranged in an arbitrary network topology. It is important to allocate an appropriate cache size to each router in order to both improve the network performance and reduce the economic investment. Previous works have proposed several heterogeneous cache allocation schemes, but the gain brought by these schemes is not obvious. In this paper, we introduce a data mining method into the cache size allocation. The proposed algorithm uses manifold learning to analyze the regularity of network traffic and user behaviors, and classify routers based on their roles in the content delivery. Guided by the manifold learning embedding results, a novel cache size optimization scheme is developed. Extensive experiments have been performed to evaluate the proposed scheme. Simulation results show that the proposed scheme outperforms the existing cache allocation schemes in CCN.

A dominating-set-based collaborative caching with request routing in content centric networking

Content Centric Networking (CCN) is a new emerging network architecture, shifting from an end-to-end connection to a content-centric communication model. A number of content-oriented characteristics, such as name-based routing, arbitrary topology and ubiquitous caching make caching in CCN different from the previous works. In this paper, we focus on the collaborative caching in CCN and propose a dominating-set-based collaborative caching mechanism, which jointly considers the content placement and request routing in a tightly-couple manner. Extensive experiments have been performed to evaluate the proposed scheme. Simulation results show that the proposed CollaCache proposal outperforms the existing caching and routing mechanisms in CCN.

Topology-aware virtual network embedding based on closeness centrality

Network virtualization aims to provide a way to overcome ossification of the Internet. However, making efficient use of substrate resources requires effective techniques for embedding virtual networks: mapping virtual nodes and virtual edges onto substrate networks. Previous research has presented several heuristic algorithms, which fail to consider that the attributes of the substrate topology and virtual networks affect the embedding process. In this paper, for the first time, we introduce complex network centrality analysis into the virtual network embedding, and propose virtual network embedding algorithms based on closeness centrality. Due to considering of the attributes of nodes and edges in the topology, our studies are more reasonable than existing work. In addition, with the guidance of topology quantitative evaluation, the proposed network embedding approach largely improves the network utilization efficiency and decreases the embedding complexity. We also investigate our algorithms on real network topologies (e.g., AT&T, DFN) and random network topologies. Experimental results demonstrate the usability and capability of the proposed approach.

An adaptive per-application storage management scheme based on manifold learning in information centric networks

Abstract Information Centric Network (ICN) is an emerging network paradigm centered around the named contents rather than the host-to-host connectivity. The common characteristic of ICN leverages in-network caching to achieve an efficient and reliable content distribution but also brings challenges. The in-network caching technique equips all ICN routers with cache storage. However, no existing works focus on the cache storage sharing mechanism among different applications to satisfy the line speed requirements and diversity of applications in ICN. In this paper, we formulate the per-application storage management problem into an optimized resource allocation problem and introduce a manifold learning method to classify the priority of applications. Dynamic programming is adopted to solve the formulated problem and an adaptive per-application storage management scheme is proposed on the basis of the optimal solutions. Extensive experiments have been performed to evaluate the proposed scheme and show that our approach is superior to static partitioning and shared storage schemes.

Minimizing Bandwidth Cost of CCN: A Coordinated In-Network Caching Approach

To reduce data access latency, network traffic volume and server load, in-network caching was proposed and has become an intrinsic component of the content-centric network (CCN) architecture. The content-oriented characteristics of in-network caching, such as arbitrary topology, volatile content locations and line speed requirements, make routers content-aware and supportive of fast content distribution. Meanwhile, they also raise new challenges in content placement and request routing, namely, how to optimally make content storage decisions and provision individual routers bandwidth to serve user requests, so as to minimize the bandwidth cost under storage and link capacity limit. To address this problem, we build a distributed in-network caching model to formulate the content placement and request routing in CCN, aiming at minimizing the bandwidth cost with strict storage and bandwidth constraints. Based on the proposed model, we design a scalable, adaptive and low-complexity in-network caching scheme for content placement and request routing and analyze the performance gains via simulations on a real ISP network topology and traffic traces. The experimental results show the proposed model and scheme are superior. Compared with the existing works, we also observe significant performance enhancements in terms of hit ratio of requests, reduction of server load, and bandwidth cost.

Request routing through collaborative in‐network caching for bandwidth optimization: a methodology

To reduce data access latency, network traffic volume and server load, in-network caching was proposed and has become an intrinsic component of the content-centric network (CCN) architecture. The content-oriented characteristics of in-network caching, such as arbitrary topology and volatile content locations, make routers content-aware and supportive of fast content distribution. Meanwhile, they also raise new challenges in content placement and request routing, namely, how to optimally make content storage decisions and forward user requests towards a ‘best’ (e.g. closest) available content replicas, so as to minimize the bandwidth cost under storage and link capacity limit. To address this problem, we build a distributed in-network caching model to formulate the content placement and request routing in CCN, aiming at minimizing the bandwidth cost with strict storage and bandwidth constraints. Based on the proposed model, we design a scalable, adaptive and low-complexity in-network caching scheme for content placement and request routing and analyse the performance gains via simulations on a real Internet Service Provider (ISP) network topology and traffic traces. The experimental results show the proposed model and scheme are superior. Compared with the existing works, we also observe significant performance enhancements in terms of hit ratio of requests, reduction of server load and bandwidth cost. Copyright

Adaptive virtual resource clustering and monitoring through nonlinear dimensionality reduction

Network virtualization provides a promising way to overcome the ossification of current Internet. One important issue in network virtualization is the problem of real-time monitoring of resource usage information. In this paper we investigate a novel method for clustering virtual resources inspired by the nonlinear dimensionality reduction method. Then a clustering algorithm extending the k-means method with the isometric feature mapping (Isomap) is used to analyze the relationships of substrate nodes and links in different time slots. By replacing the classical Euclidean distance with the geodesic distance, we can preserve the intrinsic geometry of the high-dimensional data and discover the regularities and irregularities in the substrate network. Simulation results demonstrate that the proposed method can classify the real-time states of virtual resources and provide accurate VN mapping guidance and resource management.

A distributed framework for inter-domain virtual network embedding

Network virtualization has been a promising technology for overcoming the Internet impasse. A main challenge in network virtualization is the efficient assignment of virtual resources. Existing work focused on intra-domain solutions whereas inter-domain situation is more practical in realistic setting. In this paper, we present a distributed inter-domain framework for mapping virtual networks to physical networks which can ameliorate the performance of the virtual network embedding. The distributed framework is based on a Multi-agent approach. A set of messages for information exchange is defined. We design different operations and IPTV use scenarios to validate the advantages of our framework. Use cases shows that our framework can solve the inter-domain problem efficiently.

A novel cognitive management scheme for the virtual network resources

As a long term solution to the gradual Internet ossification problem, virtual networks can guarantee on-demand requirements of diverse end user on a global level. Clearly it is a major challenge to achieve the automation and optimization of network management like virtual resources or QoS to ensure the personalized user satisfaction. In this article, we propose a novel cognitive management architecture to meet the future needs under a heterogeneous network environment. The architecture introduces a cognitive management cycle to the virtual network resources to ensure flexibility. We also focus on the efficient virtual network resource allocation and scheduling algorithms. Based on the complex network centrality analysis, we solve the virtual network resources allocation problem with consideration of the topology structure and statistical analysis. Finally we evaluate the efficiency and effectiveness of our algorithm on common benchmarks including the acceptance, revenue and cost.