软件定义网络中一种快速无循环路径迁移策略

针对软件定义网络中数据平面转发设备的分布式部署及异步操作导致的路径迁移缓慢及故障等问题,提出了一种快速无循环路径迁移策略。首先,提出了一种基于节点排序的快速循环检测算法。该算法通过对比流的新旧路径上相邻节点的位置差异,可快速判定路径迁移过程中是否存在转发循环以及检测循环发生位置。然后,提出了一种基于节点松弛依赖关系的贪婪更新机制。该机制利用快速循环检测算法发掘出新旧路径上公有交换机之间存在的松弛依赖关系,进而保证了迁移过程每轮更新的交换机数量最大化。仿真实验结果表明,相比于现有迁移方案,所提策略在不同网络状态下均可有效避免迁移循环且获得最佳更新时间开销。     

软件定义WSN规则一致更新研究

遵循控制转发分离思想,软件定义无线传感器网络（Wireless Sensor Network,WSN）数据转发采用基于流的实现方式.因此,软件定义WSN规则更新过程中节点行为可能违背网络属性一致性.针对此,提出每包前向一致性概念,并证明其可保持所有网络属性的更新一致性.在此基础上,通过引入缓存节点与缓存规则简化规则依赖关系,提出一种规则前向一致更新算法,在满足每包前向一致性的同时,支持规则快速并行更新.实验结果表明,算法在规则开销、更新时间和通信开销等关键性能指标上具有较为明显的优势.     

基于代价模型的多平台分析任务流调度优化

分析任务流的调度是人们关注的热点问题之一.在无法提前得知各子任务资源和时间开销以及算子间传输开销的情况下,现有研究缺少较好的调度方法,也无法很好地处理多平台环境下的任务调度.为此,本文提出了一种基于启发式规则优化的拓扑调度算法.该算法通过对同平台任务和后继任务优先选择的规则,对任务流调度顺序进行优化;其次,结合Spark平台下数据分析任务常见的SQL算子和机器学习算子的代价模型,有效对任务的开销做出估计.实验表明,调度优化算法能有效节约时间开销和内存开销,代价模型的估计也较为准确.     

面向数据密集型工作流的能耗感知调度策略

随着数据中心规模的扩大,高能耗问题已经成为高性能计算领域的一个重要问题。针对数据密集型工作流的高能耗问题,提出通过引入“虚拟数据访问节点”的方法来量化评估工作流任务的数据访问能耗开销,并在此基础上设计了一种“最小能耗路径”的启发式策略。在经典的HEFT算法和CPOP算法基础上,通过引入该启发式策略设计并实现了2种具有能耗感知能力的调度算法（HEFT-MECP和CPOP-MECP）。实验结果显示,基于最小能耗路径的启发式调度算法能有效降低数据访问操作的能耗开销,在面对大型的数据密集工作流任务时,该启发式调度策略体现了较好的适应性。     

同步卫星转发器二维时频资源蚁群调度算法

针对地球同步卫星转发器多任务时频资源调度问题,考虑任务执行时间和占用带宽需求,建立了以卫星系统总收益为目标的多约束规划模型,提出了基于任务频率时间窗口更新的蚁群调度算法.该算法综合考虑了任务优先级和时间灵活度,以增强蚁群在状态转移规则下的搜索能力;同时设计了虚拟任务、伪随机状态转移规则和信息素参数,保证算法向最优解逐步收敛.实例仿真表明,该算法相对于传统蚁群算法、遗传算法和启发式算法,在算法结果、寻优能力和稳定性方面具有显著优势.     

增强人工蜂群算法求解半导体最终测试调度问题

本文提出一种增强人工蜂群算法(Enhanced Artificial Bee Colony,EABC),用于最小化半导体最终测试调度问题(Semiconductor Final Testing Scheduling Problem,SFTSP)的最大完工时间.该算法采用混合启发式方法初始化种群,并利用前插式解码策略来提高初始解的质量.在算法搜索阶段设计多种基于问题性质的探索策略和基于贝叶斯网络的概率模型对问题解空间进行深度与宽度的协同搜索.此外,提出基于重启策略的种群更新机制以加强算法跳出局部最优的能力.实验部分构造多种对比算法来验证EABC中各关键环节的有效性.通过基于实例的数值仿真以及与NFOA(Novel Fruit fly Optimization Algorithm)、KMEA(Knowledge-based Multi-agent Evolu-tionary Algorithm)和CCIWO(Cooperative Co-evolutionary Invasive Weed Optimization)的算法比较验证了EABC的有效性和鲁棒性.     

适合于无线传感器网络的混合式组密钥管理方案

针对无线传感器网络中经常出现节点加入或退出网络的情况,提出了一种安全有效的混合式组密钥管理方案.多播报文的加密和节点加入时的组密钥更新,采用了对称加密技术;而系统建立后,组密钥的分发和节点退出后的组密钥更新,采用了基于身份的公钥广播加密方法.方案可抗同谋、具有前向保密性、后向保密性等安全性质.与典型组密钥管理方案相比,方案在适当增加计算开销的情况下,有效降低了节点的存储开销和组密钥更新通信开销.由于节点的存储量、组密钥更新开销独立于群组大小,方案具有较好的扩展性,适合应用于无线传感器网络环境.     

使用多级交换网络进行大容量光纤通道交换机设计

介绍了三级Clos网络拓扑,在此基础上设计了基于Clos网络的大容量光纤通道交换机体系结构.针对三级Clos网络存在的信元调度和路由分配问题,提出了一种新颖的采用流水线并行处理方式的双重匹配帧调度策略.该设计和策略对大容量光纤通道交换机的研制具有一定参考意义.     

网格调度的算法研究及改进

优化网格资源调度算法可以提高网格系统执行效率,给任务安排合理的执行顺序和合适的处理器是优化网格资源调度算法需突破的关键技术.文中研究并实现了（Heterogeneous-Earliest-Finish） HEFT[1]算法和新的（Hierarchical Reliability-Driven Scheduling）HRDS算法.采用DAG[2]任务图生成函数,通过对已有HEFT算法进行研究,采用SimGrid为在分布计算环境下进行分布并行应用调度研究提供一个仿真环境,对HRDS算法进行了改进和验证.验证过程中在HRDS算法中加入了可靠性开销作为调度依据,并把算法分为两层调度,本地可靠性驱动调度和全局可靠性驱动调度.两算法的调度结果在SimGrid网格模拟器中仿真调度,仿真成功并且调度结果在可靠性和性能方面HRDS都比HEFT算法要好.     

基于异构网络小区扩展技术的研究

基于异构网络中的小区扩展技术,提出了一种动态自适应的偏移量设置算法。考虑到用户分布随时间的变化,算法将更新周期规则结合到动态配置过程当中,以实现异构网络各基站的负载均衡。最终根据仿真结果,结合系统开销和系统吞吐量的比较,验证了算法对于实际系统的配置设计具有指导意义。     

高速无线个域网中一种基于效用公平的机会调度算法

基于对无线高速个域网中机会调度的研究,提出了一种适用于WPAN的机会主义时隙调度算法FPTS。该算法充分考虑了信道状态的波动和用户间的公平性,由参数更新模块和调度分配模块组成。参数更新模块根据调度结果更新控制参数,维护用户的公平性和自适应的跟踪信道的变化;调度分配模块负责计算每个用户的公平效用权值,并按照权值向各用户比例分配信道资源。仿真结果表明：所提调度方案能够在保证系统高吞吐量的前提下,获得LLPTS算法更好的公平性和信道使用效率。     

面向云存储的安全密文访问控制方案

存储在云端服务器中的敏感数据的保密和安全访问是云存储安全研究的重要内容.针对真实的云存储环境中云服务提供商不可信的情况,采用基于属性的加密算法,提出了一种安全、高效、细粒度的云存储密文访问控制方案.与现有方案相比,该方案在用户撤销时,通过引入广播加密技术,使得撤销用户即使和云服务提供商共谋,也不能对私钥进行更新,保证了数据的安全性;方案将大部分密文重加密和用户私钥更新工作转移给云服务提供商执行,在保证安全性的前提下,降低了数据属主的计算代价;另外该方案还可支持多用户的同时撤销.最后分析了方案的安全性和计算复杂性,并测试了用户撤销时的运行效率.     

A genetic algorithm‐based flow update scheduler for software‐defined networks

Software‐defined networking (SDN) facilitates network programmability through a central controller. It dynamically modifies the network configuration to adapt to the changes in the network. In SDN, the controller updates the network configuration through flow updates, ie, installing the flow rules in network devices. However, during the network update, improper scheduling of flow updates can lead to a number of problems including overflowing of the switch flow table memory and the link bandwidth. Another challenge is minimizing the network update completion time during large‐network updates triggered by events such as traffic engineering path updates. The existing centralized approaches do not search the solution space for flow update schedules with optimal completion time. We proposed a hybrid genetic algorithm‐based flow update scheduling method (the GA‐Flow Scheduler). By searching the solution space, the GA‐Flow Scheduler attempts to minimize the completion time of the network update without overflowing the flow table memory of the switches and the link bandwidth. It can be used in combination with other existing flow scheduling methods to improve the network performance and reduce the flow update completion time. In this paper, the GA‐Flow Scheduler is combined with a stand‐alone method called the three‐step method. Through large‐scale experiments, we show that the proposed hybrid approach could reduce the network update time and packet loss. It is concluded that the proposed GA‐Flow Scheduler provides improved performance over the stand‐alone three‐step method. Also, it handles the above‐mentioned network update problems in SDN.     

Optimum scheduling and memory management in input queued switches with finite buffer space

The goal of this paper is to design optimal scheduling and memory management so as to minimize packet loss in input queued switches with finite input buffers. The contribution is to obtain closed-form optimal strategies that minimize packet loss in 2/spl times/2 switches with equal arrival rates for all streams. For arbitrary arrival rates, the contribution is to identify certain characteristics of the optimal strategy, and use these characteristics to design a near-optimal heuristic. A lower bound for the cost associated with packet loss for N/spl times/N switches is obtained. This lower bound is used to design a heuristic which attains near-minimum packet loss in N/spl times/N switches with arbitrary N. These policies reduce packet loss by about 25% as compared to the optimal strategy for the infinite buffer case. The framework and the policies proposed here apply to buffer-constrained wireless networks as well.     

切换时延不为零的光交换调度算法

文章针对切换时延不为零的光交换调度提出了一种新算法--2近似启发算法.算法由两部分组成:选择匹配和决策权重.其中,选择匹配是确定光交叉阵列的切换次数,由贪心算法完成;决策权重是决定各个配置的持续时长,它是通过选择一个值以使剩下的业务矩阵的开销估计最优.2近似启发算法的近似因子为2,时间复杂度为O(N2logN).仿真表明这种调度算法更接近最优调度,比DOUBLE[1]和ADJUST[2]算法更能自适应传送来的不同业务模式.     

Location tracking with distributed HLR's and pointer forwarding

Location tracking operations in a personal communications service (PCS) network are expensive. A location tracking algorithm called pointer forwarding has been proposed to reduce the location update cost. The key observation behind forwarding is that if users change PCS registration areas (RAs) frequently, but receive calls relatively infrequently, it should be possible to avoid registrations at the home-location register (HLR) database by simply setting up a forwarding pointer from the previous visitor-location register (VLR). Calls to a given user will first query the user's HLR to determine the first VLR, which the user was registered at, and then follow a chain of forwarding pointers to the user's current VLR. To reduce the “find” cost in call delivery, the PCS provider may distribute HLR databases in the network. This paper integrates the concept of distributed HLRs with pointer forwarding, and the new scheme is referred to as the pointer forwarding with distributed HLR (PFDHLR). Since no registration to the HLR is performed in the pointer forwarding scheme when a user moves to the new locations, the cost of updating multiple HLRs is eliminated in PFDHLR. Our study indicates that PFDHLR may significantly reduce the mobility management cost compared with the single HLR approach     

云存储中数据完整性的聚合盲审计方法

To solve the problem of data integrity in cloud storage,an aggregated privacy-preserving auditing scheme was proposed.To preserve data privacy against the auditor,data proof and tag proof were encrypted and combined by using the bilinearity property of the bilinear pairing on the cloud server.Furthermore,an efficient index mechanism was designed to support dynamic auditing,which could ensure that data update operations did not lead to high additional computation or communication cost.Meanwhile,an aggregation method for different proofs was designed to handle multiple auditing requests.Thus the proposed scheme could also support batch auditing for multiple owners and multiple clouds and multiple files.The communication cost of batch auditing was independent of the number of auditing requests.The theoretical analysis and experimental results show that the proposed scheme is provably secure.Compared with existing auditing scheme,the efficacy of the proposed individual auditing and batch auditing improves 21.5% and 31.8% respectively.     

HQ-Tree:一种基于Hadoop的分布式数据索引(英文)

In this paper,we propose a novel spatial data index based on Hadoop:HQ-Tree.In HQ-Tree,we use PR QuadTrec to solve the problem of poor efficiency in parallel processing,which is caused by data insertion order and space overlapping.For the problem that HDFS cannot support random write,we propose an updating mechanism,called "Copy Write",to support the index update.Additionally,HQ-Tree employs a two-level index caching mechanism to reduce the cost of network transferring and I/O operations.Finally,we develop MapReduce-based algorithms,which are able to significantly enhance the efficiency of index creation and query.Experimental results demonstrate the effectiveness of our methods.     

RPA: a flexible scheduling algorithm for input buffered switches

This paper presents and evaluates a quasi-optimal scheduling algorithm for input buffered cell-based switches, named reservation with preemption and acknowledgment (RPA). RPA is based on reservation rounds where the switch input ports indicate their most urgent data transfer needs, possibly overwriting less urgent requests by other input ports, and an acknowledgment round to allow input ports to determine what data they can actually transfer toward the desired switch output port. RPA must be executed during every cell time to determine which cells can be transferred during the following cell time. RPA is shown to be as simple as the simplest proposals of input queuing scheduling, efficient in the sense that no admissible traffic pattern was found under which RPA shows throughput limitations, and flexible, allowing the support of packet-mode operations and different traffic classes with either strict priority discipline or bandwidth guarantee requirements. The effectiveness of RPA is assessed with detailed simulations in uniform as well as unbalanced traffic conditions and its performance is compared with output queuing switches and the optimal maximum weighted matching (MWM) algorithm for input-buffered switches. A bound on the performance difference between the heuristic weight matching adopted in RPA and MWM is analytically computed