基于效用最优化的多路径网络资源公平分配

网络资源最优分配除了要提高资源的利用率外,还应该实现面向服务、以用户为中心的资源分配目标,从而达到网络资源的公平分配,最大程度的满足用户的满意度.为了实现上述分配目标,文中考虑了多路径网络的资源公平分配问题,将多路径网络效用最大化模型分解为3个独立的子问题,而每个子问题其实对应于互联网体系结构的一层,并阐述了各个子问题的经济学含义.分析了用户所支付的价格和路径所收取的价格之间的关系,并提出了一类流量控制算法,通过该算法可以得到网络资源的最优公平分配.同时,考虑了算法在实际网络中的具体实现,并提出了基于窗口的流量控制机制.     

数据密集作业在GPU集群上的调度算法研究

数据密集型作业包含大量的任务,使用GPU设备来提高任务的性能是目前的主要手段.但是,在解决数据密集型作业之间的GPU资源公平共享以及降低任务所需数据在网络间的传输代价方面,现有的研究方法没有综合考虑资源公平与数据传输代价的矛盾.分析了GPU集群资源调度的特点,提出了一种基于最小代价最大任务数的GPU集群资源调度算法,解决了GPU资源的公平分配与数据传输代价较高的矛盾.将调度过程分为两个阶段：第1阶段为各个作业按照数据传输代价给出自己的最优方案;第2阶段为资源分配器合并各个作业的方案,按照公平性给出全局的最优方案.首先,给出了GPU集群资源调度框架的总体结构,各个作业给出自己的最优方案,资源分配进行全局优化;第二,给出了网络带宽估计策略以及计算任务的数据传输代价的方法;第三,给出了基于GPU数量的资源公平分配的基本算法;第四,提出了最小代价最大任务数的资源调度算法,描述了资源非抢夺、抢夺以及不考虑资源公平策略的实现策略;最后,设计了6种数据密集型计算作业,对所提出的算法进行了实验.通过实验验证,最小代价最大任务数的资源调度算法对于资源公平性能够达到90%左右,同时亦能保证作业并行运行时间最小.     

异构云系统中基于智能优化算法的多维资源公平分配

资源分配策略的研究一直是云计算领域研究的热点和难点,针对异构云计算环境下多维资源的公平分配问题,结合基因算法（GA）和差分进化算法（DE）,分别给出了两种兼顾分配公平性和效率的资源分配策略,改进了解矩阵表达式使异构云系统中的主资源公平分配（DRFH）模型转化成为整数线性规划（ILP）模型,并提出了基于最大任务数匹配值（MTM）的初始解产生机制和使不可行解转化为可行解的修正操作,以此提高算法的收敛速度,使其能够快速有效地得到最优分配方案。实验结果表明,基于GA和DE算法的多维资源公平分配策略可以得到近似最优解,在最大化最小主资源份额目标值和资源利用率方面明显优于Best-Fit DRFH和Distributed-DRFH,而且针对不同任务类型的资源需求,具有较强的自适应能力。     

云联盟中收益最优化算法

云联盟环境下,资源提供者旨在协作地向用户提供资源,以获取更多的经济收益。通过联盟博弈研究了云资源提供者的群体合作行为,基于任务执行时间和执行代价最优化问题,定义了资源提供者组建资源联盟的依据,并设计了两种任务调度算法PMTC和TMPC。同时,对联盟收益进行内部分配时,提出了基于Shapley值的联盟收益分配算法,该算法充分考虑了联盟成员对联盟总收益的贡献度,使得联盟总收益在其个体成员间的分配更加均衡与合理。算例分析结果表明,云资源联盟不仅可以改进任务执行效率和资源提供者收益,而且Shapley值可以实现收益的公平分配。     

适应异构集群的Mesos多资源调度DRF增强算法

云计算集群环境下多资源分配的公平性是考量资源调度子系统最重要的指标之一,DRF作为通用的多资源公平分配算法,在异构异质的集群环境下可能有失公平性。在研究Mesos框架中DRF多资源公平分配算法的基础上,设计并实现了增加机器性能评估影响因子的meDRF分配算法。将计算节点的机器性能得分,作为DRF主导份额计算的因子,使得计算任务有均等的机会获得优质计算资源和劣质计算资源。通过选取K-means、Bayes及PageRank等多种作业进行实验,实验结果表明:meDRF较DRF分配算法更能体现多资源分配的公平性,且资源分配具有更好的稳定性,能有效提高系统资源的利用率。     

WSN中满足公平性的时分复用调度算法

如果网络中的节点不能及时公平地共享信道资源,会造成数据传输延时的增加和节点能量的浪费。为解决这种信道分配不均问题,提出一种基于TDMA的调度算法TSFA。该算法分为网络分簇、节点染色、独立集调度3个步骤,主要思想是在分布式顶点染色算法DVCA的基础上得到最大独立集,其根据每个独立集内的数据流量大小分配时隙。仿真结果表明,TSFA避免了相邻节点间的通信干扰,减少了网络的通信延时,提高了网络的吞吐量,实现了信道分配的公平性。     

虚拟时钟调度算法研究

FIFO队列调度算法由于实现简单、执行效率高而在网络中得到大量的应用，但FIFO队列无法实现对资源的分配；男种调度算法公平队列调度则可以实现对带宽资源的公平分配，但是它存在可扩展性问题。而基于虚拟时钟的算法在实现对资源进行公平分配的同时具备良好的可扩展性，从而能够满足QoS控制中对于分组调度算法的需求。本文主要对一些基于虚拟时钟的度算法进行了分析和讨论，这也是进行QoS控制研究的基础。     

基于负载基尼系数的服务网络公平均衡调度

针对组织结构较为稳定的区域内服务网络,提出了一种有监督的公平均衡负载调度算法。该算法受到经济学领域的收入分配基尼系数的启发,通过对网络负载分配基尼系数的监控,最终完成区域内服务任务的公平调度。给出了实现公平任务调度所需的系统结构和算法步骤,并通过仿真结果验证了该方法能有效完成服务网络任务均衡调度,具有较好的全局公平性。     

云环境下公平性优化的资源分配方法

针对云数据中心资源分配不均、效率不高、资源错位等问题,为了满足不同用户的需求,达到多种资源分配的公平性,实现资源的高效利用,提出了全局优势资源公平（GDRF）分配算法。GDRF算法采用多轮分配方式,即先通过用户已分配资源量确定分配资格,每轮再通过全局优势资源共享比和全局优势资源权重来确定具体的分配用户,分配过程充分考虑了资源的匹配情况,采用了max-min fairness思想的渐进填充方式,并且将多资源分配公平性统一度量模型运用到了算法中。实验基于一个Google集群数据模型与基于占优资源的多资源联合公平分配算法作了比较。实验结果表明,GDRF算法分配的虚拟机总量提高了12%,资源总利用率提高了0.5个百分点,公平评估值提高了约15%,并且该算法的资源组合分配的适应度较高,使得用户需求和供给更匹配。     

负载均衡的主导资源公平分配算法

随着使用云计算并行且可靠地处理计算问题成为一种趋势,各种云计算平台应运而生,在这些平台中,保证多种资源调度策略的公平性非常重要。主导资源公平分配算法DRF有效地实现了多种资源环境中的公平分配,但在资源分配过程中容易出现集群负载不均的情况。因此,提出在使用DRF算法分配资源过程中,通过集群中各节点的资源利用率情况对节点进行K-means聚类分析,根据聚类结果将资源分配给任务来提高集群负载均衡的能力。基于CloudSim 4.0实现了改进DRF算法的仿真实验,实验结果表明,负载均衡的DRF算法比原始的DRF算法以及基于层次分析法(AHP)改进的DRF算法更能有效地改善集群整体的负载均衡。     

Fair Scheduling Algorithms in Grids

In this paper, we propose a new algorithm for fair scheduling, and we compare it to other scheduling schemes such as the earliest deadline first (EDF) and the first come first served (FCFS) schemes. Our algorithm uses a max-min fair sharing approach for providing fair access to users. When there is no shortage of resources, the algorithm assigns to each task enough computational power for it to finish within its deadline. When there is congestion, the main idea is to fairly reduce the CPU rates assigned to the tasks so that the share of resources that each user gets is proportional to the users weight. The weight of a user may be defined as the users contribution to the infrastructure or the price he is willing to pay for services or any other socioeconomic consideration. In our algorithms, all tasks whose requirements are lower than their fair share CPU rate are served at their demanded CPU rates. However, the CPU rates of tasks whose requirements are larger than their fair share CPU rate are reduced to fit the total available computational capacity in a fair manner. Three different versions of fair scheduling are adopted in this paper: the simple fair task order (SFTO), which schedules the tasks according to their respective fair completion times, the adjusted fair task order (AFTO), which refines the SFTO policy by ordering the tasks using the adjusted fair completion time, and the max-min fair share (MMFS) scheduling policy, which simultaneously addresses the problem of finding a fair task order and assigning a processor to each task based on a max-min fair sharing policy. Experimental results and comparisons with traditional scheduling schemes such as the EDF and the FCFS are presented using three different error criteria. Validation of the simulations using real experiments of tasks generated from 3D image- rendering processes is also provided. The three proposed scheduling schemes can be integrated into existing grid computing architectures.     

On-Line Edge-Coloring with a Fixed Number of Colors

We investigate a variant of on-line edge-coloring in which there is a fixed number of colors available and the aim is to color as many edges as possible. We prove upper and lower bounds on the performance of different classes of algorithms for the problem. Moreover, we determine the performance of two specific algorithms, First-Fit and Next-Fit . Specifically, algorithms that never reject edges that they are able to color are called fair algorithms. We consider the four combinations of fair/ not fair and deterministic/ randomized. We show that the competitive ratio of deterministic fair algorithms can vary only between approximately 0.4641 and 1/2, and that Next-Fit is worst possible among fair algorithms. Moreover, we show that no algorithm is better than 4/7-competitive. If the graphs are all k -colorable, any fair algorithm is at least 1/2-competitive. Again, this performance is matched by Next-Fit while the competitive ratio for First-Fit is shown to be k/(2k-1) , which is significantly better, as long as k is not too large.     

Strong Fairness and Full Abstraction for Communicating Processes

We construct several denotational semantics for communicating processes that incorporate assumptions of strong (process) fairness. Strong fairness is the guarantee that every process enabled infinitely often will make progress infinitely often. Modeling fairness compositionally requires care: generally speaking, the fair computations of a command cannot be defined only in terms of the fair computations of its component commands. For this reason, we introduce the notion of parameterized fairness, which generalizes fairness sufficiently to admit a compositional characterization. In each of these semantics, a command's meaning is simply the set of fair traces representing its fair computations; each fair trace records the steps made along a computation as well as additional information made explicit by the definition of parameterized fairness. Each semantics obtains full abstraction with respect to a natural notion of strongly fair program behavior: two terms are given identical meanings precisely when they exhibit the same behaviors in all program contexts.     

Fair webs

Fair webs are energy-minimizing curve networks. Obtained via an extension of cubic splines or splines in tension to networks of curves, they are efficiently computable and possess a variety of interesting applications. We present properties of fair webs and their discrete counterparts, i.e., fair polygon networks. Applications of fair curve and polygon networks include fair surface design and approximation under constraints such as obstacle avoidance or guaranteed error bounds, aesthetic remeshing, parameterization and texture mapping, and surface restoration in geometric models.     

Petri网的依赖关系

为了分析变迁不处于公平关系或弱公平关系时在运行中的依赖关系,本文提出了公平依赖和弱公平依赖的概念。研究了伪可重复向量的性质及在判断公平依赖关系时起的作用。给出了判断变迁处于公平依赖关系和弱公平依赖关系的充分必要条件。     

A formal model of fair exchange protocols

1 Background Electronic commerce over open networks has been growing rapidly over the last dec- ade. Usually commercial transactions involve parties who mutually distrust each other, so protecting one legitimate party from another is as important as protecting legitimate parties from intruders. Therefore the fairness property of an exchange protocol is vital. Generally, a typical fair exchange protocol has a main protocol and several sub-protocols. It has a much bigger size than the classical…     

一种基于非完全公正方的P2P网络公证协议

在系统地分析传统的基于完全公正方的公证协议的基础上，针对P2P网络的特点，提出了一种基于非完全公正方的P2P网络公证协议。该协议采用混合密码体制作为执行载体，协议双方充分掌握通信的主动权，不需要对公正方绝对信任，公正方的执行权限受协议的限制，执行行为亦受协议双方的监控。给出了该协议的交互过程，分析了它的执行效率、安全性能和适用性。分析结果表明，该协议优于基于完全公正方的公证协议。     

Analysis of temporal and throughput fair scheduling in multirate WLANs

The IEEE 802.11e Wireless Local Area Network (WLAN) provides controlled access features that can be used in conjunction with scheduling algorithms to provide guaranteed per-session services. However, the multirate operation of the WLAN complicates the design of scheduling and Quality of Service (QoS) provisioning algorithms. We propose a new solution based on Controlled Access Phase Scheduling (CAPS) framework, introduced for fixed rate WLANs in our earlier works, and employ a new fair central scheduler to achieve guaranteed fair services in a WLAN. We examine the fairness issues involved in designing such an algorithm and study several fair scheduling algorithms that can be used with CAPS. We present a modified start time fair queuing based scheduler as our choice and analyze its performance under dynamic and static multirate operation. The algorithm is then evaluated through several simulation experiments. We show that the enhanced CAPS is able to adapt to multirate environments and provide both temporal and throughput fair services in 802.11e WLANs.     

一种基于连接的增强拥塞控制机制

文中针对越来越多的网络应用不采用端拥塞控制机制而导致非公平占用网络带宽问题,介绍了在路由器内部实现基于连接调度的增强拥塞控制方法。路由器使用公平排队调度算法代替传统的先来服务调度算法,可隔离和保护基于漏桶控制的连接。但采用基于窗口反馈拥塞控制机制ＴＣＰ连接会对数据包丢失敏感,路由器使用公平排队调度算法还需要结合相应的缓冲管理方法,才能保证ＴＣＰ连接获取公平的吞吐量。文中还讨论了基于连接的排队数据包     

Individual and Social Learning

We use adaptive models to understand the dynamics that lead to efficient and fair outcomes in a repeated Battle of the Sexes game. Human subjects appear to easily recognize the possibility of a coordinated alternation of actions as a mean to generate an efficient and fair outcome. Yet such typical learning models as Fictitious Play and Reinforcement Learning have found it hard to replicate this particular result. We develop a model that not only uses individual learning but also the “social learning” that operates through evolutionary selection. We find that the efficient and fair outcome emerges relatively quickly in our model. JEL classification: B52, D83 An erratum to this article can be found at