基于AHP的云存储负载均衡研究

针对云存储系统节点在数据分布策略和系统响应时间方面的综合负载计算问题,提出了一种云存储系统的负载均衡算法,并对该算法进行了验证。算法基于层次分析法（Analytic Hierarchy Process,AHP）,通过建立综合评估指标体系,从可用存储空间、可用CPU、可用内存和访问热度四个方面,计算各个存储节点的综合负载,并据此对数据存取进行均衡调度。验证结果表明,通过调整不同指标的权重,算法能够很好地满足不同的应用需求,同时,该算法能够很好地反应各节点的综合负载,实现云存储系统整机性能的优化,尤其适用于一些高并发的大数据存储。     

无线传感器网络数据管理技术研究进展

无线传感器网络本质上是一个以数据为中心的网络,它处理的数据为传感器采集的连续不断的数据流.因此,现有的数据管理技术把无线传感器网络看作为来自物理世界的连续数据流组成的分布式数据库.由于传感器节点的计算能力、存储容量、通信能力以及电池能量有限,再加上flash存储器以及数据流本身的特性,给数据管理带来了传统分布式数据库系统没有的一些新挑战.从数据库系统的体系结构、数据存储与索引技术、数据模式、查询处理及优化技术等方面介绍了无线传感器网络的数据管理技术的研究现状.     

WSN中一种负载均衡的动态非均匀分簇方案

无线传感器网络(WSN)是由资源受限的传感器节点构成,节点能耗对网络的性能有着重要影响,对网络进行分簇可以有效地控制节点整体能耗。针对网络实际运行时节点状态和事件位置动态变化等特点,提出了一种负载均衡的动态非均匀分簇方案。方案主体思路是:首先网络利用O-LEACH算法自组织地进行非均匀分簇,接着动态地从簇头中选举出一定数量的决策节点用于网络的数据汇聚,并根据事件发生位置和节点状态变换而动态更改决策节点角色。仿真结果表明,与CAPNet方案相比,该方案均衡了网络能耗,提高了传输效率,延长了网络生命周期。     

Dynamic storage and access load balancing for answering range queries in peer-to-peer networks

Recently, many applications have used Peer-to-Peer (P2P) systems to overcome the current problems with client/server systems such as non-scalability, high bandwidth requirement and single point of failure. In this paper, we propose an efficient scheme to support efficient range query processing over structured P2P systems, while balancing both the storage load and access load. The paper proposes a rotating token scheme to balance the storage load by placing joining nodes in appropriate locations in the identifier space to share loads with already overloaded nodes. Then, to support range queries, we utilize an order-preserving mapping function to map keys to nodes in order preserving way and without hashing. This may result in an access load imbalance due to non-uniform distribution of keys in the identifier space. Thus, we propose an adaptive replication scheme to relieve overloaded nodes by shedding some load on other nodes to balance the access load. We derive a formula for estimating the overhead of the proposed adaptive replication scheme. In this study, we carry simulation experiments with synthetic data to measure the performance of the proposed schemes. Our simulation experiments show significant gains in both storage load balancing and access load balancing.     

支持大规模智能电网的数据存储方法

针对大规模智能电网中的监测数据具有海量性、实时性、动态性等特点,提出一种以数据为中心的支持大规模智能电网的数据存储方法:海量动态数据的分层扩展存储机制。首先,采用扩展哈希编码方法动态增加存储节点,避免突发、频发事件数据的丢失,增强系统的可用性;然后,采用多阈值级别方法将数据分散到多个存储节点上,避免出现存储热点问题,实现负载均衡。实验结果表明,分层扩展存储机制能够最大限度地满足海量数据的存储需求,获得较好的负载均衡,并且使总能耗最低,有效地延长了网络的生命周期。     

面向射频能量捕获传感网的高吞吐量负载均衡的节点接入方案

由于传统无线传感器网络更换传感器电池较为麻烦或不具可行性,其实际应用范围受到很大的限制。考虑具有射频能量捕获能力的无线传感器网络,已知能量源、节点、基站(即汇聚节点)的部署位置,研究如何安排各个节点的接入基站,在满足基站负载平衡约束的情况下最大化整个网络节点的总吞吐量。首先,建立能量捕获传感网的能量捕获模型和信息传输模型,并将该节点接入问题建模为0-1整数规划问题;然后,针对该问题提出一种复杂度较低的算法和一种复杂度略高的贪婪式算法。仿真结果表明,与低复杂度算法相比,贪婪式算法所得到的节点接入方案具有更高的网络总吞吐量,但其复杂度略高,因此可用于节点数目较少的场景,而低复杂度算法可用于节点数目较多的场景。     

雾计算中跨层感知分簇路由协议

传统的以数据为中心的路由协议,往往会导致传感网中出现在大量的“能量空洞”或“热点”现象。为了克服上述现象,借助雾计算理论模型,提出了一种基于雾计算跨层感知分簇路由协议（A Cross-layer-sensing Clustering Routing Protocol Based on Fog Computing,CCRP）。该协议通过跨层映射原理,利用感知事件驱动机制将雾节点映射到传感层,构成功能强大的虚拟控制节点,将传感网分簇路由协议的控制过程上传至雾层,通过雾计算实现事件域节点分布式成簇路由汇聚中心,从而建立以映射雾节点为中心的优化数据聚合路由,取代传感网底层路由中的数据,进一步平衡并减少网络负载。在路由协议优化阶段,利用粒子群优化算法（Particle Swarm Optimizations,PSO）采用无竞争开销方式选举一组最佳节点担任簇首,能有效地均衡全网能量的开销,抑制传感器节点能量的快速消耗,延长了网络生存周期。仿真实验表明,CCRP协议能够有效抑制网络开销的同时还可以高效完成对数据的优化过程。     

Congestion Avoidance Based on Lightweight Buffer Management in Sensor Networks

A wireless sensor network is constrained by computation capability, memory space, communication bandwidth, and above all, energy supply. When a critical event triggers a surge of data generated by the sensors, congestion may occur as data packets converge toward a sink. Congestion causes energy waste, throughput reduction, and information loss. However, the important problem of congestion avoidance in sensor networks is largely open. This paper proposes a congestion-avoidance scheme based on light-weight buffer management. We describe simple yet effective approaches that prevent data packets from overflowing the buffer space of the intermediate sensors. These approaches automatically adapt the sensors' forwarding rates to nearly optimal without causing congestion. We discuss how to implement buffer-based congestion avoidance with different MAC protocols. In particular, for CSMA with implicit ACK, our 1/k{hbox{-}}{rm{buffer}} solution prevents hidden terminals from causing congestion. We demonstrate how to maintain near-optimal throughput with a small buffer at each sensor and how to achieve congestion-free load balancing when there are multiple routing paths toward multiple sinks.     

基于模拟退火算法的资源负载均衡方案

针对大型ERP系统的网络资源负载均衡问题展开研究。在理论上对问题的需求进行建模分析,设计了满足主机和网络性能约束的启发式目标函数,将模型转化为度约束最小生成树问题,设计了一种模拟退火算法对此问题进行处理,提出了基于该算法的资源负载均衡方案LABS。理论分析表明,整个网络执行该方案的时间复杂度为节点规模的平方阶,说明方案具有较强的可用性与可伸缩性。仿真实验结果显示,通过选择适当的启发因子,算法不仅可以吸纳大部分节点协同参与负载均衡操作,还能够显著减少系统中的瓶颈节点数,降低平均资源使用率。     

基于数据库集群的动态负载均衡研究与实现

针对数据库集群负载问题,提出了一种动态负载均衡方法,并进一步设计、实现了包括CPU使用率、磁盘存储量、磁盘响应效率、网络延时、内存使用率等在内的多指标的节点负载测量和实时监控。该算法根据各节点的负载反馈信息进行任务分配,实现了负载均衡。性能分析和实验表明,该算法具有较高的负载均衡度和较低的系统开销。     

动态无线传感网中低延迟高可靠的数据查询机制

查询处理作为大规模无线传感器网络中智能服务的一个重要操作,可以根据用户需求对网络中的感知数据进行检索和回传.然而,部署在恶劣环境中的无线传感网络,节点容易遭受外力破坏,或者自身资源(能量、存储等)有限,可能会导致节点发生位移和故障,从而造成网络拓扑不断改变以及部分节点的感知数据失效.同时,由于节点感知数据容量大、传输带宽有限以及网络链路不可靠等情况,可能会造成网络通信时延大大增加.这些因素使得快速、可靠的数据查询处理成为无线传感网中一个难题.为了解决这个难题,提出一种动态网络中低延迟高可靠的数据查询机制.该机制是一种非聚合随机查询方式,通过将传感节点划分为源节点和查询节点来实现数据查询.首先,根据监测事件将网络划分为若干个子区域,每个子区域中的源节点相互协作,并按照时间顺序依次轮流监听该区域的事件信息;接着,源节点根据预估的平均节点故障概率,计算出一个合理的备份数量,并将源数据按照该数量存储到邻居节点中,以降低源数据的失效概率;然后,为了加快数据查询速度,源节点定期对源数据块进行编码压缩,并选取剩余能量和存储空间较小的多个邻居节点作为下一跳接收节点.这些接收节点基于局部区域中节点个数大小,决定是否接收存储该报文.重复上述过程,直至压缩数据均匀地分布在网络中.另一方面,查询节点接收到查询请求时,也使用负载均衡多路分发方式将查询请求传输到部分节点上.为了避免目标数据的冗余回传,当查询请求成功查询到目标数据时,目标节点先修改访问位,再选取与查询节点距离最近的邻居节点作为下一跳接收节点,迭代执行上述操作,直到用户获得所需要的事件信息.在以上过程中,为了节省节点能量,在保证高成功查询率的条件下,建立通信能耗最小化的优化模型,计算出最优的压缩数据副本数和查询消息副本数,之后,源节点和查询节点分别按照该数量进行副本数据分发.最后,理论分析和实验结果表明,与其它四种查询算法相比,提出的查询机制具有更高的查询成功率、更低的通信能耗和通信时延.     

基于OpenStack的Swift负载均衡算法

为了解决由于OpenStack的负载分发不均衡而引发的存储性能下降、资源利用率降低、I/O响应时长增加等问题,提出对加权最小连接调度算法进行改进. 通过对对象存储的负载均衡调度算法研究,利用存储节点的CPU、内存、硬盘、I/O资源利用率信息,并结合节点任务请求连接数,计算存储节点负载能力、性能和权值. 负载均衡器根据每个存储节点的权值大小判断任务分发方向. 经实验证明改进的负载均衡调度算法能够解决存储读写性能下降的问题,提升数据吞吐率、存储读写性能和系统稳定性.     

基于纠删码技术的云存储数据块部署方案

针对云存储系统中因忽视集群中存储节点之间的差异而引起的存储代价过高、可靠性较低、节点负载能力不足等问题,提出了段排序交换算法（FSSA）.首先对数据块部署问题进行数学建模;然后根据各个节点的负载情况进行分段,并在各个分段中依据数据可靠性的需求对节点进行初步选择;最后根据数学模型中对目标函数的分析在分段选择的结果中选取适当的节点进行数据部署.仿真结果表明,采用FSSA算法可以在保证数据存储可靠性的基础之上,降低数据存储代价、增强系统负载均衡能力.     

Balancing Energy Consumption to Maximize Network Lifetime in Data-Gathering Sensor Networks

Unbalanced energy consumption is an inherent problem in wireless sensor networks characterized by multihop routing and many-to-one traffic pattern, and this uneven energy dissipation can significantly reduce network lifetime. In this paper, we study the problem of maximizing network lifetime through balancing energy consumption for uniformly deployed data-gathering sensor networks. We formulate the energy consumption balancing problem as an optimal transmitting data distribution problem by combining the ideas of corona-based network division and mixed-routing strategy together with data aggregation. We first propose a localized zone-based routing scheme that guarantees balanced energy consumption among nodes within each corona. We then design an offline centralized algorithm with time complexity O(n) (n is the number of coronas) to solve the transmitting data distribution problem aimed at balancing energy consumption among nodes in different coronas. The approach for computing the optimal number of coronas in terms of maximizing network lifetime is also presented. Based on the mathematical model, an energy-balanced data gathering (EBDG) protocol is designed and the solution for extending EBDG to large-scale data-gathering sensor networks is also presented. Simulation results demonstrate that EBDG significantly outperforms conventional multihop transmission schemes, direct transmission schemes, and cluster-head rotation schemes in terms of network lifetime.     

基于特征选择的无线传感器网络路由标识算法

针对无线传感器网络具有节点数量大、分布范围广、以数据为中心进行路由等特点,提出了一种基于特征选择的路由标识算法。该算法首先通过汇节点向传感器节点发送“询问”数据包,收到数据包的各个节点检查自身特征是否与“询问”内容相符,然后发送一个“答复”信息到网络,完成路由的标识。仿真结果证明该算法可以解决传统路由协议中的冗余信息和广播风暴,在生成、接收信息上具有更好的稳定性,并能够有限地减少能耗。     

异构云平台中基于多层架构的动态循环调度方案

针对现有分布式循环自调度方案在异构云平台中存在负载不平衡等问题,提出一种基于多层架构的分层分布式动态循环调度方案。首先,通过HPLS算法来评估计算环境中各Worker节点的计算速度。然后,在传统自调度方案中融入节点计算速度,构建一种能够处理异构环境的调度方案,提高负载平衡能力。最后,将计算系统构建成一个由SuperMaster,Master和Worker节点组成的多层架构,利用层次化方法来解决传统Master-Worker架构中单个Master节点的瓶颈问题,用来提高任务分配效率。仿真实验结果表明,提出的方案能够有效提高云平台的计算效率。     

Hybrid work stealing of locality-flexible and cancelable tasks for the APGAS library

Since large parallel machines are typically clusters of multicore nodes, parallel programs should be able to deal with both shared memory and distributed memory. This paper proposes a hybrid work stealing scheme, which combines the lifeline-based variant of distributed task pools with the node-internal load balancing of Java’s Fork/Join framework. We implemented our scheme by extending the APGAS library for Java, which is a branch of the X10 project. APGAS programmers can now spawn locality-flexible tasks with a new asyncAny construct. These tasks are transparently mapped to any resource in the overall system, so that the load is balanced over both nodes and cores. Unprocessed asyncAny-tasks can also be cancelled. In performance measurements with up to 144 workers on up to 12 nodes, we observed near linear speedups for four benchmarks and a low overhead for cancellation-related bookkeeping.     

Resilience of sink filtering scheme in wireless sensor networks

One of severe security threats in wireless sensor network is node compromise. A compromised node can easily inject false data reports on the events that do not occur. The existing approaches in which each forwarding sensor along a path probabilistically filters out injected false data may not be adequate because such protection may break down when more than a threshold number of nodes are compromised. To solve this problem, we present a sink filtering scheme in clusters of heterogeneous sensor networks. In addition to basic sensors, some powerful data gathering sensors termed as cluster heads (CHs) are added. Each aggregation report generated by a CH must carry multiple keyed message authentication codes (MACs); each MAC is generated by a basic sensor that senses the event. The sink node checks the validity of the carried MACs in an aggregation report and filters out the forged report. We analyze the resilience and overhead of the sink filtering scheme. Both analytical and simulation results show that the scheme is resilient to an increasing number of compromised nodes, with graceful performance degradation. Particularly, we adopt Poisson Approximation to investigate the performance tradeoff between resilience and overall cost, and give some suggestions on how to choose the parameters. The scheme is also scalable and efficient in communication, computation and storage.     

基于Kademlia的负载平衡云存储算法

针对采用主从式结构的主流云存储系统可能出现的性能瓶颈和可扩展问题,基于分布式哈希表(DHT)技术的完全分布式云存储系统成为一种新的选择。解决好节点的负载平衡问题,是此类技术获得推广的关键。研究了Kademlia算法应用于云存储系统的负载平衡性能。考虑到算法在异构环境下负载平衡性能有明显下降,改进算法在Kademlia找出的候选存储节点中根据节点的存储能力来分配负载。仿真结果表明,改进后算法的负载平衡性能有非常明显的提高,在系统模拟运行时间足够长(如1500 h以上)时,过载节点平均下降7.0%(轻载)和33.7%(重载);文件保存成功率平均提高27.2%(轻载)和35.1%(重载),而增加的通信开销可接受。     

一种无线传感器网络预分配密钥管理方案的改进

无线传感器网络在应用二元多项式密钥预分配协议时,通常容易遭受到敌方的合谋攻击。为了更好地解决这一问题,通过减少普通节点共享的密钥个数,改变簇首间建立共享密钥的方式,改进了一种无线传感器网络的密钥预分配管理方案。分析表明,改进后的方案保留了原方案的网络高安全性等优点,而且进一步节省了普通节点的内存空间,减少了节点间的通信量,延长了网络的生存周期,能够有效地抵御敌方的合谋攻击。