无线传感器网络中数据汇聚技术的研究

无线传感器网络能量和计算资源严重受限，数据汇聚技术是减少能耗、消除数据冗余、增加从源节点到基站的有用信息流、延长网络寿命的重要方法。数据汇聚可以集成在路由协议中，也可以实现与路由协议紧密交互的独立的协议(或技术)。首先介绍了无线传感器网络中数据汇聚协议的背景；然后分析和综述了主要的数据汇聚技术，包括汇聚路由、聚集函数、数据挖掘；最后提出了这个快速发展领域的研究方向。     

利用地理网格簇增强定向扩散协议

定向扩散协议是一种用于无线传感器网络的数据分发协议.在定向扩散中,兴趣和探测数据采用泛洪的方法在网络中散布,这将引起广播风暴导致网络能量的大量消耗.在网络中通过形成簇结构可以缓解广播风暴问题,每个节点利用本身的地理位置信息自组织形成虚拟地理网格簇,簇中仅有一个节点负责兴趣和探测数据的广播.模拟试验表明,这种方法有效地降低了网络的能量消耗.     

无线传感器网络基于数据汇聚的路由

提出了一种针对无线传感器网络的路由协议,该路由采用最小传输成本生成树的数据汇聚机制。具体方法是首先将传感区域内的传感器节点采集的数据传送给传感区域内离汇聚点最近的节点,将这些数据进行汇聚操作后,将汇聚的结果通过最短路径传递给网络汇聚点。仿真结果显示,采用最小传输代价生成树的路由协议能减少数据传输量50%-80%,并具有较小的传输时延。     

无线传感器网络中基于区域再生树汇聚的路由算法

传感器网络具有严格的能量限制,冗余的低速数据流和多对一的通信方式等不同于传统Ad Hoc网络的特点,针对这些特点,提出一种区域再生树汇聚的路由算法。算法中将传感区域内部的所有传感器节点采集的数据沿区域再生树的父子关系层层汇聚到传感区域内离Sink点最近的区域汇聚点,再将汇聚的数据通过全局路由树形成的最短路径传递给Sink节点。仿真结果显示区域再生树的数据汇聚能够减少数据传输量,并具有较小的传输时延。     

无线传感器网络环境下时-空查询处理方法

在无线传感器网络环境中,观察者感兴趣的是由传感器网络监测得到的与时间-空间相关的事件,而不是传感器本身或者大量无关的观察数据.观察者会经常提出与事件相关的时-空查询,例如:“网络覆盖的某地理区域R中10:00~11:00发生了哪些事件?”.由于每个传感器节点只有有限的能量,因此,研究能量有效性的时-空查询处理算法成为一个重要的研究课题.给出了一种以数据为中心的时-空查询处理算法.针对3种不同的存储策略:以数据为中心的存储、外部存储和节点本地存储,分析比较了节点的能量消耗.系统地研究了在3种不同的数据存储策略下,事件发生的概率,节点密度,事件类型数目,查询数目,时-空查询地理区域的大小以及时-空查询时间窗口的大小对节点能量消耗的影响.理论与实验结果表明,在多数情况下,这种以数据为中心的时-空查询处理算法的能量消耗少于基于外部存储和本地存储的时-空查询处理算法.     

无锁同步的细粒度并行介度中心算法

通过结合体系结构和算法进行研究发现,基于锁的同步机制是细粒度并行介度中心(betweenness centrality,简称BC)算法在现有多核平台上高效执行的主要瓶颈.提出了一种消除锁同步的数据驱动(data-centric)并行算法,在AMD 32核SMP和Intel8核SMP两个平台上获得了2倍左右的加速比.     

A Performance Evaluation of a Novel Energy-Aware Data-Centric Routing Algorithm in Wireless Sensor Networks

In this paper, we present a novel Energy-Aware Data-Centric Routing algorithm for wireless sensor networks, which we refer to as EAD. We discuss the algorithm and its implementation, and report on the performance results of several workloads using the network simulator ns-2. EAD represents an efficient energy-aware distributed protocol to build a rooted broadcast tree with many leaves, and facilitate the data-centric routing in wireless micro sensor networks. The idea is to turn off the radios of all leaf nodes and let the non-leaf nodes be in charge of data aggregation and relaying tasks. The main contribution of this protocol is the introduction of a novel approach based on a low cost backbone provisioning within a wireless sensor network in order to turn off the non backbone nodes and save energy without compromising the connectivity of the network, and thereby extending the network lifetime. EAD makes no assumption on the network topology, and it is based on a residual power. We present an extensive simulation experiments to evaluate the performance of our EAD forwarding-to-parent routing scheme over a tree created by a single EAD execution, and compare it with the routing scheme over a regular Ad hoc On-Demand Distance Vector (AODV) Protocol. Last but not least, we evaluate the performance of our proposed EAD algorithm and compare it to the Low-Energy Adaptive Clustering Hierarchy (LEACH) protocol, a cluster-based, energy-aware routing protocol specifically designed for sensor networks. Our results indicate clearly that EAD outperforms AODV and LEACH in energy conservation, throughput, and network lifetime extension.Dr. A. Boukerche was partially supported by NSERC, Canada Research Program, Canada Foundation for Innovation, and Ontario Innovation Funds/Ontario Distinguished Research Award.Azzedine Boukerche is a Full Professor and holds a Canada Research Chair Position at the University of Ottawa. He is also the Founding Director of PARADISE Research Laboratory at Ottawa U. Prior to this, he hold a faculty position at the University of North Texas, USA, and he was working as a Senior Scientist at the Simulation Sciences Division, Metron Corporation located in San Diego. He was also employed as a Faculty at the School of Computer Science McGill University, and taught at Polytechnic of Montreal. He spent a year at the JPL-California Institute of Technology where he contributed to a project centered about the specification and verification of the software used to control interplanetary spacecraft operated by JPL/NASA Laboratory.His current research interests include wireless networks, mobile and pervasive computing, wireless multimedia, QoS service provisioning, wireless ad hoc and sensor networks, distributed systems, distributed computing, large-scale distributed interactive simulation, and performance modeling. Dr. Boukerche has published several research papers in these areas. He was the recipient of the best research paper award at PADS’97, and the recipient of the 3rd National Award for Telecommunication Software 1999 for his work on a distributed security systems on mobile phone operations, and has been nominated for the best paper award at the IEEE/ACM PADS’99, and at ACM MSWiM 2001. Dr. A. Boukerche serves as an Associate Editor and on the editorial board for ACM/Springer Wireless Networks, the Journal of Parallel and Distributed Computing, The Wiley Journal of Wireless Communication and Mobile Computing. He served as a Founding and General Chair of the first Int’l Conference on Quality of Service for Wireless/Wired Heterogeneous Networks (QShine 2004), ACM/IEEE MASCOST 1998, IEEE DS-RT 1999-2000, ACM MSWiM 2000; Program Chair for ACM/IFIPS Europar 2002, IEEE/SCS Annual Simulation Symposium ANNS 2002, ACM WWW’02, IEEE/ACM MASCOTS 2002, IEEE Wireless Local Networks WLN 03-04; IEEE WMAN 04-05, ACM MSWiM 98–99, and TPC member of numerous IEEE and ACM conferences. He served as a Guest Editor for JPDC, and ACM/kluwer Wireless Networks and ACM/Kluwer Mobile Networks Applications, and the Journal of Wireless Communication and Mobile Computing.Dr. Boukerche serves as a Steering Committee Chair for ACM MSWiM, IEEE DS-RT, and ACM PE-WASUN Conferences.Xiuzhen Cheng is an Assistant Professor in the Department of Computer Science at the George Washington University. She received her MS and Ph.D. degrees in Computer Science from University of Minnesota—Twin Cities in 2000 and 2002, respectively. Her current research interests include localization, data aggregation services, and data storage in sensor networks, routing in mobile ad hoc networks, and approximation algorithm design and analysis. She is a member of the ACM and IEEE.Joseph Linus has recently graduated with a MSc Degree from the Department of Computer Sciences, University of North Texas. His current research interests include wireless sensors networks, and mobile ad hoc networks.     

I/O Acceleration via Multi-Tiered Data Buffering and Prefetching

Modern High-Performance Computing(HPC)systems are adding extra layers to the memory and storage hierarchy,named deep memory and storage hierarchy(DMSH),to increase I/O performance.New hardware technologies,such as NVMe and SSD,have been introduced in burst buffer installations to reduce the pressure for external storage and boost the burstiness of modern I/O systems.The DMSH has demonstrated its strength and potential in practice.However,each layer of DMSH is an independent heterogeneous system and data movement among more layers is significantly more complex even without considering heterogeneity.How to efficiently utilize the DMSH is a subject of research facing the HPC community.Further,accessing data with a high-throughput and low-latency is more imperative than ever.Data prefetching is a well-known technique for hiding read latency by requesting data before it is needed to move it from a high-latency medium(e.g.,disk)to a low-latency one(e.g.,main memory).However,existing solutions do not consider the new deep memory and storage hierarchy and also suffer from under-utilization of prefetching resources and unnecessary evictions.Additionally,existing approaches implement a client-pull model where understanding the application's I/O behavior drives prefetching decisions.Moving towards exascale,where machines run multiple applications concurrently by accessing files in a workflow,a more data-centric approach resolves challenges such as cache pollution and redundancy.In this paper,we present the design and implementation of Hermes:a new,heterogeneous-aware,multi-tiered,dynamic,and distributed I/O buffering system.Hermes enables,manages,supervises,and,in some sense,extends I/O buffering to fully integrate into the DMSH.We introduce three novel data placement policies to efficiently utilize all layers and we present three novel techniques to perform memory,metadata,and communication management in hierarchical buffering systems.Additionally,we demonstrate the benefits of a truly hierarchical data prefetcher that adopts a server-push approach to data prefetching.Our evaluation shows that,in addition to automatic data movement through the hierarchy,Hermes can significantly accelerate I/O and outperforms by more than 2x state-of-the-art buffering platforms.Lastly,results show 10%-35%performance gains over existing prefetchers and over 50%when compared to systems with no prefetching.     

C-cast: 传感器网络中无位置数据分发和发现技术

在无线传感器网络中,基于对等节点的数据分发和发现技术是一项关键的工作和研究问题。现有的研究技术和协议设计多数依赖于节点的位置信息,但是在传感器网络中节点获取位置信息需要精确的定位算法和大量的计算、通信开销。为满足在没有位置信息的情况下,节点依然能够有效地进行数据分发和发现工作,本文提出了C-cast协议。C-cast协议不仅不依赖于精确的物理位置信息和大功耗的定位服务,而且节点不需要存储维护太多的全局拓扑信息。本文证明了在稠密网络的理想模型下,C-cast协议能够达到100%的数据查询成功率;在随机模型下,通过选择跳步距离适当的两个信标节点,C-cast协议能够达到80%以上的实际数据查询成功率。本文测试了C-cast协议的三种性能,包括数据查询成功率、存储代价和负载均衡。测试结果显示C-cast协议达到甚至超过基于位置信息的协议性能。     

DoDAF V2.0在军事信息系统建设中的应用分析

为借鉴和应用DoDAF V2.0的最新理念,总结了该体系结构框架的核心思想,分析了8个视角之间的相互关系以及DM2（DoDAF Meta-Model）数据组与各视角的映射关系.对DoDAF V2.0中体现的以数据为中心的体系结构开发进行了初步探索,提出了应用该体系结构框架需注意的问题以及对军事信息系统建设的启示和建议.这对我军事信息系统的建设有一定的理论指导意义.