Uranus: Congestion-proportionality among Slices based on Weighted Virtual Congestion Control, 2019.

    Dual-structural network of active defense,SCIENTIA SINICA Informationis, 2018.

    Resource Provisioning in the Edge for IoT Applications with Multi-Level Services, 2018. 

     

    Energy-aware Dual-path Geographic Routing to Bypass Routing Holes in Wireless Sensor Networks, 2018.

       

    Enabling collaborative edge computing for software defined vehicular networks, 2018.

       

    Towards optimal request mapping and response routing for content delivery networks, 2018.

    Hyperconnected Network: A Decentralized Trusted Computing and Networking Paradigm, IEEE Network, 2018.

    Towards Optimal Request Mapping and Response Routing for Content Delivery Networks ,IEEE Transactions on Services Computing,2017.(Accepted) 
    主动防御的双结构网络,中国科学 : 信息科学,2018.(已接收)
    Enabling Collaborative Edge Computing for Software Defined Vehicular, Networks  IEEE Network Magazine ,2017.(Accepted)
     

    尹浩, 姜泽勋, 李军, 联接云际:云际网络互联的协同服务机制, 中国计算机学会通讯 ,3,2017.

    目前,热点的互联网应用与服务几乎都离不开云计算,并且逐步向几个重要的云服务平台集中。应用的创新发展和市场需求的变化,使现有云计算服务面临新的挑战,单一云平台难以满足应用全时全域的优质服务需求和灵活多样的个性化定制需求[1]。同时,随着边缘计算和5G等技术的发展,云计算模式也面临从集中式向分布式发展的趋势。

     

     

    X. Zhang, H. Yin, D. OliverWu, H. Huang, G. Min, and Y. Zhang, "SSL: A Surrogate-based Method for Large-scale Statistical Latency Measurement," IEEE Transactions On Service Computing, 2017.

    To address this challenge, we design an indirect method based on widely-distributed clients called SSL (Surrogate-based method for large-scale Statistical Latency measurement).SSL estimates the latency between two arbitrary hosts using the measured latencies from several selected clients near one end   host,which are called the host’s surrogates, to the other end host. To overcome the limited capacity of the volatile clients with unstable CPU, memory, and bandwidth resources, we propose an innovative two-step measurement task assignment mechanism for SSL that can achieve high accuracy measurement results while satisfying the resource constraints simultaneously. Moreover, SSL adopts a sampling technique to reduce the overhead in large-scale measurements, and a resampling technique to determine the confidence interval. Simulation experiments show that SSL can achieve more than 90% accuracy in most situations with 10% client density and 15% sampling rate.

     

     

    史佩昌,王怀民,郑子斌,尹浩,面向云际计算的自主对等协作环境,中国科学,2017,已录用.

    本文提出支持不同云交易参与者之间自主对等交易资源和服务的支撑环境——云际协作环境(JointCloud Cooperation Environment, JCCE),JCCE包括分布云交易、分布云社区、分布云监管以及基于区块链的分布记账系统,JCCE中与信息交换尤其是价值交换相关的支撑技术,利于打破云际协作参与方之间的信息不对称,为参与各方创造多赢机会,实现对云际计算商业模式创新的强有力支撑。论文从云服务消费者、云服务提供者、云服务代理等视角出发,分别提出了JCCE的消费服务模式、供给服务模式和磋商服务模式,便于指导交易各方高效、便捷获取JCCE价值交换支撑服务。论文以云资源交易、数据交易和定制软件服务交易为案例,阐述了JCCE中有关价值交换支撑服务的运行机理。云际协作环境对于构建协作共赢的云际计算生态系统具有十分重要的理论意义和实践价值。

     

     

    H. Yin, X. Zhang, H. H. Liu, Y. Luo, C. Tian, S. Zhao, et al., "Edge Provisioning with Flexible Server Placement," IEEE Transactions on Parallel and Distributed Systems, vol. 28, pp. 1031-1045, Apr 1 2017.

    We show how Tentacle effectively identifies promising edge locations which are close to a collection of users merely with inaccurate network distance estimation methods,e.g., geographic coordinate (GC) and network coordinate systems (NC). We also show how Tentacle comprehensively considers various pragmatic concerns in edge provisioning, such as traffic limits by law or ISP policy, edge site deployment and resource usage cost, over-provisioning for fault tolerance, etc., with a simple optimization model. We simulate Tentacle using real network data at global and county-wide scales. Measurement-driven simulations show that with a given cost budget Tentacle can improve user performance by around 10-45 percent at global scale networks and 15-35 percent at a country-wide scale network.

     

     

    H. Yin, X. Zhang, S. Zhao, Y. Luo, C. Tian, and V. Sekar, "Trade-offs between Cost and Performance for CDN Provisioning Based on Coordinate Transformation," IEEE Transactions on Multimedia, 2017. 

    Our conversations with CDN operators reveal that a new provisioning mechanism is necessary to take advantage of emerging opportunities such as faster speed to roll out new locations and more access networks. In this paper, we present the design of DISC, a decision support system to help CDN operators systematically investigate different design tradeoffs and evaluate what-if scenarios. The key enabler underlying DISC is a network coordinate based data analysis workflow that can flexibly embed different cost, performance, and workload characteristics without sacrificing the fidelity. We describe practical use cases and experiences in applying DISC to a large country-wide deployment. The results show that DISC significantly reduces average latency, deployment cost and inter-domain traffic.

     

     

    H. Huang, H. Yin, G. Min, X. Zhang, W. Zhu, and Y. Wu, "Coordinate-Assisted Routing Approach to Bypass Routing Holes in Wireless Sensor Networks," IEEE Communications Magazine, vol. 55, pp. 180-185, 2017. 

    In this article, we frst survey representative face-based geographic routing approaches, including their design prerequisites and philosophy. Furthermore, we outline the emerging issues to be addressed in the future and illustrate the forming factors behind them in detail. Based on these observations, we then propose a CAGR to address the routing hole problem by employing relative coordinate systems, avoiding  planarizing networks and preserving route optimality properties. Simulation results show that the  proposed approach is superior to existing protocols in terms of packet delivery ratio, control overhead, and delivery delay in WSNs over a variety of communication sessions passing through the  routing holes.

     

     

    Z. Jiang and H. Yin, "Adaptive Routing Algorithm for Joint Cloud Video Delivery," 2017 IEEE 37th International Conference on Distributed Computing Systems Workshops, pp. 316-319, 2017. 

    To employ the potential of Joint Cloud, this paper designs and implements a new request routing algorithm that can make video delivery utilize multiple clouds and servers. On the premise of guaranteeing the quality of video playing, this algorithm minimizes the cost of service resources based on different infrastructures service quality, cost, and cover areas. Based on this algorithm, we implement a practical video delivery system using light-weight, flash-based terminals. And this system provides live video and video-on-demand delivery service for China Future Networks Industry Summit 2014 on June 4th. The actual user data was gathered and analyzed to verify the effectiveness of this algorithm. 90.2% of the total VOD  requests were completed smoothly without pause, and the video traffic was optimized by the algorithm.

     

    L. Jiao, H. Yin, D. Guo, and Y. Lyu, "Heterogeneous Malware Spread Process in Star Network," 2017 IEEE 37th International Conference on Distributed Computing Systems Workshops, pp. 265-269, 2017. 

    The heterogeneous SIS model for virus spread in any finite size graph characterizes the influence of factors of SIS model and could be analyzed by the extended N-Intertwined model introduced in . We specifically focus on the heterogeneous virus spread in the star network in this paper. The  epidemic threshold and the average meta-stable state fraction of infected nodes are derived for virus spread in the star network.Our results illustrate the effect of the factors of SIS model on the  steady state infection.

       

    Y. Wu, Y. Lyu, Q. Fang, G. Zheng, H. Yin, and Y. Shi, "Protecting Outsourced Data in Semi-Trustworthy Cloud: A Hierarchical System," 2017 IEEE 37th International Conference on Distributed Computing Systems Workshops, pp. 300-305, 2017.

    The existing schemes to achieve the security and usability goal usually apply encryption to the data before outsourcing them to the storage service providers (SSP), and disclose the decryption keys only to authorized user. They cannot ensure the security of data while operating data in cloud where the  third-party servicers are usually semi-trustworthy, and need lots of time to deal with the data. We construct a privacy data management system appending hierarchical access control called HAC-DMS, which can not only assure security but also save plenty of time when updating data in cloud. 

     

     

    C. Zha, Y. Lyu, H. Yin, and D. Guo, "UCPR: User Classification and Influence Analysis in Social Network," 2017 IEEE 37th International Conference on Distributed Computing Systems Workshops, pp. 311-315.

    This paper puts forward the design of User Classification PageRank (UCPR) to solve this problem. Firstly,  we classify users according to the content which they forwarded. Then, we use space mapping to set up several subnet. Finally, we analyze user influence in every specific subnet by Domain Mapped Network (DMN) which is based on PageRank algorithm and we improve this algorithm to analyze the user influence in different domains. Through the work of this paper, we used a vector to present user influence rather than a single number and we test and verified the long-tailed distributions of social network in experiments.

       

     

    Edge Provisioning with Flexible Server Placement

    (IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS ’17 Hao Yin, Xu Zhang, Hongqiang Harry Liu, Yan Luo, Member, IEEE,Chen Tian, Shuoyao Zhao, and Feng Li)

    We present Tentacle, a decision support framework to provision edge servers for online services providers (OSPs).Tentacle takes advantage of the increasingly flexible edge server placement, which is enabled by new technologies such as edge computing platforms, cloudlets and network function virtualization, to optimize the overall performance and cost of edge infrastructures.

       

    Data-Driven Information Plane in Software-Defined Networking

    (IEEE Communications Magazine ’17 Haojun Huang, Hao Yin, Geyong Min, Hongbo Jiang, Junbao Zhang, and Yulei Wu)

    In this article, we explicitly propose a data-driven information plane and extending the SDN architecture specifically. We first overview the evolution of SDN, and then illustrate a novel SDN paradigm by introducing a data-driven information plane into the commonly accepted SDN reference architecture. Finally, we outline emerging challenges and discuss future directions for further research triggered by a data-driven information plane.

     

     

     

     

     

     

     

     

     

     

     

     

     

     

     

     

    Copyright © 2018 Network and Big Data Technology R&D Center

    Please publish modules in offcanvas position.