代理缓存一致性策略和替换策略的研究

针对代理缓存的一致性策略和替换策略还没有很好地结合起来,从而影响了代理缓存系统的整体性能的现状,分别探讨了基于Internet的代理缓存一致性策略和替换策略的处理流程、性能评价指标和研究现状,进而给出将这两种策略结合起来的一致性一替换算法的处理流程,并提出陈旧命中比是其主要性能评价指标,能很好地衡量代理缓存的各种算法的优劣和代理缓存系统的整体性能。     

Token-ordered LRU: an effective page replacement policy and its implementation in Linux systems

Most computer systems use a global page replacement policy based on the LRU principle to approximately select a Least Recently Used page for a replacement in the entire user memory space. During execution interactions, a memory page can be marked as LRU even when its program is conducting page faults. We define the LRU pages under such a condition as false LRU pages because these LRU pages are not produced by program memory reference delays, which is inconsistent with the LRU principle. False LRU pages can significantly increase page faults, even cause system thrashing. This poses a more serious risk in a large parallel systems with distributed memories because of the existence of coordination among processes running on individual node. In the case, the process thrashing in a single node or a small number of nodes could severely affect other nodes running coordinating processes, even crash the whole system. In this paper, we focus on how to improve the page replacement algorithm running on one node.

After a careful study on characterizing the memory usage and the thrashing behaviors in the multi-programming system using LRU replacement. we propose an LRU replacement alternative, called token-ordered LRU, to eliminate or reduce the unnecessary page faults by effectively ordering and scheduling memory space allocations. Compared with traditional thrashing protection mechanisms such as load control, our policy allows more processes to keep running to support synchronous distributed process computing. We have implemented the token-ordered LRU algorithm in a Linux kernel to show its effectiveness.     

基于预测的Web缓存替换算法

为了提高Web缓存的性能,在缓存替换算法GDSF的基础上引入了预测机制,提出了基于预测的缓存替换算法PGDSF.先利用Web日志构造预测模型,再用预测模型对当前的用户访问序列进行预测,形成用户可能要访问的预测对象集.当缓存空间不能满足新请求对像时,则利用替换策略GDSF,将权值最小的且不属于预测对象集的对像进行替换.该算法综合考虑了各项因素对Web对象的影响,仿真实验结果表明,在一定的缓存空间内相对于GDSF替换算法有较高的文档命中率和字节命中率.     

基于最小延迟代价的Web缓存替换算法研究

命中率、字节命中率和延迟时间是Web缓存系统中最重要的性能指标,但是却难以准确、合理地度量不同大小的Web对象的访问延迟.引入字节延迟的概念,为不同的对象延迟建立了一个比较合理的评价标准.提出最小延迟代价的Web缓存替换算法LLC,使用户访问的延迟时间尽可能缩短.实验结果表明,与常用的缓存替换算法相比,LLC算法在有效减少用户感知的访问延迟方面具有较好的性能表现.     

面向网络流量的缓存替换算法比较与分析

缓存替换算法对优化网络处理应用的性能起到关键作用，但目前面向网络流量的缓存替换算法研究主要集中在算法设计和领域应用方面，较少有文献对现有的缓存替换算法在网络环境下的性能进行分析比较。对此，本文针对主要的6种缓存替换算法进行分析和比较。通过分析网络流量的新近度与频度特征，为基于最近最少使用(Least Recently Used, LRU)和最近最不常使用(Least Frequently Used, LFU)的缓存替换算法给出实际依据。对仿真环境和实际系统的实验结果表明，类LRU算法较LFU算法更适用于网络流量，而缓存空间较大时，随机替换算法较LRU算法更适用于多核环境。     

基于协作小小区与流行度预测的在线热点视频缓存更新策略

针对无线移动设备数量的指数增长使得异构协作小小区（SBS）将承载大规模的流量负载问题，提出了一种基于协作SBS与流行度预测的在线热点视频缓存更新方案（OVCRP）。首先，分析在线热点视频的流行度在短期内变化情况；然后，构建k近邻模型进行在线热点视频流行度的预测；最后，确定在线热点视频的缓存更新位置。为了选择合适的位置存放在线热点视频，以最小化总体传输时延为目标，建立数学模型，设计整数规划优化算法。仿真实验结果显示，与随机缓存（RANDOM）、最近最少使用（LRU）、最不经常使用（LFU）方案相比，OVCRP在平均缓存命中率和平均访问时延方面具有明显的优势，因此减轻了协作SBS的网络负担。     

基于经济的网格cache接受策略研究

为了减少客户端延迟,又满足本地代理总效益最大的要求,在网格cache的接受策略中引入经济模型,对其进行基于经济的优化,以市场经济的方式计算缓存某资源带来的效益变化,解决其中的利益冲突,模拟实验证明了其有效性。     

基于Web访问特性的缓存替换策略

在分析Web轨迹的基础上,找出用户访问Web内容的访问特性:访问再次到达的概率和访问内容大小分布,并建立相应的代价公式,利用这些代价作为计算Web内容价值的要素.根据这些特性判断用户访问内容被再次访问的可能性,提出内容分发网络缓存替换策略.最后通过数值仿真计算与现有替换策略进行比较,说明了该替换策略的优越性.     

基于预测的Web缓存替换策略

为提高Web缓存性能，在缓存替换算法的基础上加入预测机制，提出了基于预测的Web替换策略P-Re。预测算法采用PPM上下文模型，当缓存空间不够用来存放新的对象时，P-Re选择键值较小且未被预测到的对象进行替换。实验表明，基于预测的Web缓存替换算法P-Re相对于传统替换算法而言具有较高的命中率和字节命中率。     

自适应一致性替换算法的设计与实现

针对代理缓存的一致性策略和替换策略还没有很好地结合起来的技术现状,基于最优化模型,提出、设计和实现了一种新的优化代理缓存的自适应一致性--替换算法(即 ACR算法).这种算法包括一致性策略和替换策略两部分,一致性策略采用自适应TTL机制,替换策略是基于成本/价值模型的算法.通过Trace-Driven模拟实验,结果表明ACR算法在陈旧命中比上均优于传统的几个替换算法.     

On‐demand data co‐allocation with user‐level cache for grids

Conventional remote data access middlewares usually provide client applications with either a pre‐staging scheme or an on‐demand access scheme to fetch data. The pre‐staging scheme uses parallel downloads to fetch a completed input file from multiple data sources, even when only a tiny file fragment is required. Such a transfer scheme consumes unnecessary data transmission time and storage space. In contrast, the on‐demand scheme downloads only the required data blocks from a single data source and does not fully utilize the downstream bandwidth of the computing nodes. This paper presents a middleware called ‘Spigot’ that facilitates legacy (grid‐unaware) applications to transparently access remote data by using native I/O function calls. Spigot uses the on‐demand concept to avoid unnecessary data transfer and adopts a co‐allocation download algorithm to improve the data transfer performance. Moreover, it uses the pre‐fetching strategy to reduce the data waiting time by overlapping data acquisition and data processing. It also provides the client application with its own user‐level cache, which is advantageous since a larger cache space is available in comparison with the kernel‐level cache. Further, it is easy to maintain data consistency between Spigot nodes. The experimental results indicate that Spigot achieves superior performance in reducing the data waiting time than the pre‐staging and the on‐demand access schemes. Copyright © 2010 John Wiley & Sons, Ltd.     

Extended optimal replacement policy for a two-unit system with failure rate interaction and external shocks

This study presents an extended replacement policy for a two-unit system which is subjected to shocks and exhibits failure rate from interaction. The external shocks that affect the system are of two types. A type I shock causes a minor failure of unit-A and the damage that is caused by such a failure affects unit-B, whereas a type II shock causes a total failure of the system (catastrophic failure). All unit-A failures can be recovered by making minimal repairs. The system also exhibits the interaction between the failure rates of units: a failure of any unit-A causes an internal shock that increases the failure rate of unit-B, whereas a failure of a unit-B causes instantaneous failure of unit-A. The goal of this study is to derive the long-run cost per unit time of replacement by introducing relative costs as a factor in determining optimality; then, the optimal replacement period, T*, and the optimal number of unit-A failures, n*, which minimise that cost can be determined. A numerical example illustrates the method.     

Age replacement policy in a random environment using systemability

Preventive maintenance is a group of maintenance policies based on preventive actions in order to predate the failure of a component or a system. Usually, these policies are designed using a series of data related to the studied units. All policies do not consider the effect of the environment where the components or systems operate. In this article, one of the most used policies, the age replacement policy, is also discussed taking into consideration the environmental effects using an innovative concept, introduced by Pham, called systemability. Several numerical examples are carried out in order to illustrate the aim of this work. The importance of environmental factors is also demonstrated thanks to the application to a real case.     

Optimal replacement policy for a repairable system with multiple vacations and imperfect fault coverage

The present investigation deals with the reliability analysis of a repairable system consisting of single repairman who can take multiple vacations. The system failure may occur due to two types of faults termed as major and minor. When the system has failed due to minor faults, it is perfectly recovered by the repairman. If the system failure is due to major faults, there are some recovery levels/procedures that recover the faults imperfectly with some probability. However, the system cannot be repaired in ‘as good as new’ condition. It is assumed that the repairman can perform some other tasks when either the system is idle or waiting for recovery from the faults. The life time of the system and vacation time of the repairman are assumed to be exponential distributed while the repair time follows the general distribution. By assuming the geometric process for the system working/vacation time, the supplementary variable technique and Laplace transforms approach are employed to derive the reliability indices of the system. We propose the replacement policy to maximize the expected profit after a long run time. The validity of the analytical results is justified by taking numerical illustrations.     

利用多维分级Cache替换策略减少对PCM内存写回量

寻找新型存储材料代替DRAM内存是当前的一个研究热点。相变存储PCM因其具有低功耗、高存储密度和非易失性的优点受到广泛的关注,然而PCM的可擦写次数有限,要用作内存必须考虑如何减少对其的写操作。针对该问题,一种有效的解决方法是优化Cache替换策略,减少Cache中脏块被替换出的数量。现有研究主要通过在插入和访问命中时给脏块设定较高的保护优先级来达到给脏块额外保护的目的,但是在降级过程中不再对脏块与干净块进行区分,这导致Cache可能在存在大量干净块的情况下仍然先替换脏块。提出一种新型的Cache替换策略MAC,它通过一个多维分级结构在脏块与干净块之间设置了不可逾越的界限,使得脏块能得到更有力的保护。模拟实验表明,相对LRU替换策略,MAC以较低的硬件开销代价平均减少约25.12%的内存写,同时对程序运行性能几乎没有影响。     

Robust optimal tracking control for multiplayer systems by off‐policy Q‐learning approach

In this article, a novel off‐policy cooperative game Q‐learning algorithm is proposed for achieving optimal tracking control of linear discrete‐time multiplayer systems suffering from exogenous dynamic disturbance. The key strategy, for the first time, is to integrate reinforcement learning, cooperative games with output regulation under the discrete‐time sampling framework for achieving data‐driven optimal tracking control and disturbance rejection. Without the information of state and input matrices of multiplayer systems, as well as the dynamics of exogenous disturbance and command generator, the coordination equilibrium solution and the steady‐state control laws are learned using data by a novel off‐policy Q‐learning approach, such that multiplayer systems have the capability of tolerating disturbance and follow the reference signal via the optimal approach. Moreover, the rigorous theoretical proofs of unbiasedness of coordination equilibrium solution and convergence of the proposed algorithm are presented. Simulation results are given to show the efficacy of the developed approach.     

Parents,pre‐schoolers and learning with technology at home: some implications for policy

Schemes that seek to ensure that children have access to technology at home have, so far, been aimed at children over the age of 8. However, there is likely to be an increasing policy interest in extending similar schemes to pre‐school children given widespread commitment to the value of early intervention in children's education and family life. We draw on three research studies conducted by the authors to discuss the range of technologies that children encounter at home, the different forms their learning takes and family support for learning. We use these findings to provide starting points for considering the implementation of similar schemes for pre‐school children and their parents in the future, identifying several questions to consider when developing policy on home access to technology for pre‐schoolers: which technologies are most appropriate? Will access to technology at home lead to increased use? What roles do parents play in supporting learning? Which forms of learning are most likely to be promoted?     

A cache‐efficient implementation of the lattice Boltzmann method for the two‐dimensional diffusion equation

The lattice Boltzmann method is an important technique for the numerical solution of partial differential equations because it has nearly ideal scalability on parallel computers for many applications. However, to achieve the scalability and speed potential of the lattice Boltzmann technique, the issues of data reusability in cache‐based computer architectures must be addressed. Utilizing the two‐dimensional diffusion equation, , this paper examines cache optimization for the lattice Boltzmann method in both serial and parallel implementations. In this study, speedups due to cache optimization were found to be 1.9–2.5 for the serial implementation and 3.6–3.8 for the parallel case in which the domain decomposition was optimized for stride‐one access. In the parallel non‐cached implementation, the method of domain decomposition (horizontal or vertical) used for parallelization did not significantly affect the compute time. In contrast, the cache‐based implementation of the lattice Boltzmann method was significantly faster when the domain decomposition was optimized for stride‐one access. Additionally, the cache‐optimized lattice Boltzmann method in which the domain decomposition was optimized for stride‐one access displayed superlinear scalability on all problem sizes as the number of processors was increased. Copyright © 2004 John Wiley & Sons, Ltd.     

Learning automata based multi‐agent system algorithms for finding optimal policies in Markov games

Markov games, as the generalization of Markov decision processes to the multi‐agent case, have long been used for modeling multi‐agent systems (MAS). The Markov game view of MAS is considered as a sequence of games having to be played by multiple players while each game belongs to a different state of the environment. In this paper, several learning automata based multi‐agent system algorithms for finding optimal policies in Markov games are proposed. In all of the proposed algorithms, each agent residing in every state of the environment is equipped with a learning automaton. Every joint‐action of the set of learning automata in each state corresponds to moving to one of the adjacent states. Each agent moves from one state to another and tries to reach the goal state. The actions taken by learning automata along the path traversed by the agent are then rewarded or penalized based on the comparison of the average reward received by agent per move along the path with a dynamic threshold. In the second group of the proposed algorithms, the concept of entropy has been imported into learning automata based multi‐agent systems to improve the performance of the algorithms. To evaluate the performance of the proposed algorithms, computer experiments have been conducted. The results of experiments have shown that the proposed algorithms perform better than the existing algorithms in terms of speed and accuracy of reaching the optimal policy. Copyright © 2010 John Wiley and Sons Asia Pte Ltd and Chinese Automatic Control Society     

Optimal replacement period of a two-unit system with failure rate interaction and external shocks

In this article, a periodical replacement model for a two-unit system which is both subjected to failure rate interaction and external shocks will be presented. Without external shocks, each unit 1, whenever it fails, will act as an interior shock to affect the failure rate of unit 2 and increase the failure rate of unit 2 to a certain degree, while each unit 2 failure causes unit 1 into instantaneous failure. Besides failure rate interaction between units, the system is also subjected to external shocks which can be divided into two types. Type A shock causes unit 1 into failure and then converts the damage of such a failure to unit 2, while type B shock makes the system total breakdown. All unit 1 failures are corrected by minimal repairs. The aim of this article is to derive the expected cost rate per unit time by introducing relative costs as a criterion of optimality, and then the optimal replacement period which minimizes that cost will be determined. A numerical example is given to illustrate the method.