Web Cache系统的设计与分布技术

1 引言随着因特网技术和应用向广度和深度迅猛发展,人们除了在网上共享信息外,还试图通过无所不在的因特网来大规模地共享计算能力和服务等一切可以共享的资源。但是,由于网络中瓶颈的存在及热点资源的相对集中,这种迅猛发展也带来了一个问题,即人们上网时常常体验到的“World WideWait”问题。要解决这一问题,一种有效的解决办法就是采用Web Caching技术,即将Web上常被人们访问的、热门的信息缓存在Web服务器与最终用户之间的缓存服务器系统中。当前,Web Caching是一个正在迅速发展的领域,无论科研界还是工业界,都在这一方面投入了大量的精力。如果设计和部署得当的话,Web Caching可以带来很多好处,如节约大     

Evaluation of Strong Consistency Web Caching Techniques

The growth of the World Wide Web (WWW or Web) and its increasing use in all types of business have created bottlenecks that lead to high network and server overload and, eventually, high client latency. Web Caching has become an important topic of research, in the hope that these problems can be addressed by appropriate caching techniques. Conventional wisdom holds that strong cache consistency, with (almost) transactional consistency guarantees, may neither be necessary for Web applications, nor suitable due to its high overhead. However, as business transactions on the Web become more popular, strong consistency will be increasingly necessary. Consequently, it is important to have a comprehensive understanding of the performance behavior of these protocols. The existing studies, unfortunately, are ad hoc and the results cannot be compared across different studies. In this paper we evaluate the performance of different categories of cache consistency algorithms using a standard benchmark: TPC-W, which is the Web commerce benchmark. Our experiments show that we could still enforce strong cache consistency without much overhead, and Invalidation, as an event-driven strong cache consistency algorithm, is most suitable for online e-business. We also evaluate the optimum deployment of caches and find that proxy-side cache has a 30–35% performance advantage over client-side cache with regard to system throughput.     

An Effective Cache Replacement Algorithm in Transcoding-Enabled Proxies

In this paper, we address the problem of cache replacement for transcoding proxy caching. Transcoding proxy is a proxy that has the functionality of transcoding a multimedia object into an appropriate format or resolution for each client. We first propose an effective cache replacement algorithm for transcoding proxy. In general, when a new object is to be cached, cache replacement algorithms evict some of the cached objects with the least profit to accommodate the new object. Our algorithm takes into account of the inter-relationships among different versions of the same multimedia object, and selects the versions to replace according to their aggregate profit which usually differs from simple summation of their individual profits as assumed in the existing algorithms. It also considers cache consistency, which is not considered in the existing algorithms. We then present a complexity analysis to show the efficiency of our algorithm. Finally, we give extensive simulation results to compare the performance of our algorithm with some existing algorithms. The results show that our algorithm outperforms others in terms of various performance metrics.     

Web代理服务器缓存置换算法研究

目前Web代理服务器中的缓存机制普遍都以提高缓存命中率为目标,来设计相应的页面置换算法,一般并不考虑命中页面因过期失效而需要额外的验证及更新这一因素。为此,提出了改进的页面缓存效益模型,对包括页面验证更新在内的各种相关因素进行了综合考虑,以缓存效益系统最优为目标提出Web代理服务器中缓存置换算法——PCR;并基于合理的假设证明了该算法的最优性。最后,通过与LRU-K、Hybrid等算法的比较实验,验证了PCR算法的有效性。     

Web缓存的一种新的替换算法

现有的Web缓存器的实现主要是基于传统的内存缓存算法,然而由于Web业务请求的异质性,传统的替换算法不能在Web环境中有效工作.首先给出了问题的一个最优化模型,分析了替换算法的关键在于能正确地体现Web业务的访问模式.在泊松到达模型的基础上,提出一种新的缓存策略--最少正规化代价替换算法(leastnormalized-cost,简称LNC).新的替换算法除了考虑Web文档的平均引用时间、最近流逝时间、文档大小和单位大小价值以外,还考虑了Web业务的访问率动态改变的特征.对轨迹文件所做的性能实验表明,LNC优于其他主要的算法.     

Web缓存技术综述

Web高速缓存(Web Caching)技术实现了Web内容的关键节点(包括本地)存储，它能减少网络带宽的占用，降低硬件成本，改善响应时间，提高了最终用户的效率．本文通过对Web缓存的分类、性能指标、一致性策略以及替换算法几个方面对目前流行的缓存技术作了一个总结．     

语义缓存技术的研究

语义缓存技术一直以来是数据库研究的热点之一。语义缓存是指将用户向服务器端提交的查询语句和查询实际得到的结果数据同一存储在指定的缓存中,因而其不仅包含有数据,还有对数据的相关描述信息,从而可以提高查询效率。在语义缓存之前,还存在页面缓存、元组缓存、块缓存等缓存技术。文中首先介绍语义缓存的模型,然后阐述和分析语义缓存查询匹配算法和缓存替换策略,最后对语义缓存技术进行总结,从而为语义缓存技术的进一步研究提供一定的理论基础。     

一种提高Web响应性能的缓存机制

对于一个日访问量达到万级以上的网站来说,浏览速度将会成为该系统的一个瓶颈。如果能够优化内容发布系统,并把非实时更新的页面转换成静态页面,将会使浏览速度得到显著的提升。本文提出一种基于Java和XML技术、在MVC2架构基础上的三级缓存机制,从静态页面、组件到数据对象分别进行缓存,根据点击率来更新缓存,有效降低了多层体系结构之间的通信量,提高了Web的响应性能。     

Soft Computing Techniques for Rank Aggregation on the World Wide Web

Rank aggregation is the problem of generating a near-consensus ranking for a given set of rankings. When applied to the web, this finds applications in meta-searching, search engine comparison, spam fighting and word association techniques. The rank aggregation obtained by optimizing the Spearman footrule distance is called footrule optimal aggregation (FOA), and it also satisfies the Condorcet property. We find in literature a polynomial time algorithm to compute FOA for full lists. However, when collating the results of the search engines, the lists are almost invariably always the partial ones, as different search engines usually return non-overlapping lists of documents. The FOA for partial lists, however, is NP-hard. This NP-hard nature of partial footrule optimal aggregation problem (PFOA) motivates us to apply genetic algorithm (GA) for the PFOA problem. The GA based technique may take long to compute, but we propose to decide upon the number of generations of GA based on the time limit allowed by the user. We have also considered some positional methods, as they are linear in complexity. A classical positional method is the Borda's method. Since, fuzzy logic has been extensively studied in literature for arriving at consensus in group decision making, the adoption of some fuzzy techniques is also being investigated here for getting an improvement over the Borda's method. We have not only adopted and compared the classical fuzzy rank ordering techniques for web applications, but also proposed three novel techniques that outshine the existing techniques.     

基于内容的Web Caching

提出一个新的 Web Caching结构模型—基于内容的 Web Caching.模型综合考虑了 Proxy的操作信息和 Web文档的内容特性 ,界定了虚拟用户团体和 Proxy个性 ,并利用 Ontology技术来刻画 Proxy的个性 ,模拟实验表明 ,结合内容属性可以使得 Web Caching性能得到进一步提高     

Page Replacement with Multi-Size Pages and Applications to Web Caching

Abstract. We consider the paging problem where the pages have varying size. This problem has applications to page replacement policies for caches containing World Wide Web documents. We consider two models for the cost of an algorithm on a request sequence. In the first (the FAULT model) the goal is to minimize the number of page faults. In the second (the BIT model) the goal is to minimize the total number of bits that have to be read into the cache. We show offline algorithms for both cost models that obtain approximation factors of O(log k) , where k is the ratio of the size of the cache to the size of the smallest page. We show randomized online algorithms for both cost models that are O(log ² k) -competitive. In addition, if the input sequence is generated by a known distribution, we show an algorithm for the FAULT model whose expected cost is within a factor of O(log k) of any other online algorithm.     

信息中心网络中的内置缓存技术研究

互联网的应用方式正从以面向主机的点对点通信为主转向以海量内容获取为主.为适应这一转变,研究界提出了多种以信息/内容为中心的新型网络架构.这类网络架构中最重要的特征之一是利用网络内置缓存提高接收者驱动的内容获取的传输效率和网络资源的利用率.与传统的Web缓存、CDN缓存等相比,ICN缓存系统呈现了缓存透明化、泛在化和细粒度化等新特征,对缓存系统的建模、行为理解和优化方法都提出了新的挑战.在介绍了ICN缓存系统的新特征及带来的挑战后,首先从多方面着重阐述和比较了缓存网络的优化方法,之后对缓存网络系统的理论模型研究现状加以阐述,然后分析了仍待解决的关键问题和未来的研究方向.     

Web缓存命中率与字节命中率关系

在研究Web缓存性能时,一般考虑2个评价指标：命中率HR和字节命中率BHR。目前大多侧重于2个指标之一,或仅通过测试2个指标的数值来评价缓存替换算法优劣,没有从2个指标关系的角度来评价缓存替换算法的性能。该文讨论了Web缓存系统中命中率与字节命中率之间的关系,提出了一种Web缓存性能评价指标——命中比（FBR）,讨论了该指标在Web缓存替换算法及Web预取性能评价中的应用,为度量缓存系统的性能提供了参考依据。     

Integrating Web Prefetching and Caching Using Prediction Models

Web caching and prefetching have been studied in the past separately. In this paper, we present an integrated architecture for Web object caching and prefetching. Our goal is to design a prefetching system that can work with an existing Web caching system in a seamless manner. In this integrated architecture, a certain amount of caching space is reserved for prefetching. To empower the prefetching engine, a Web-object prediction model is built by mining the frequent paths from past Web log data. We show that the integrated architecture improves the performance over Web caching alone, and present our analysis on the tradeoff between the reduced latency and the potential increase in network load.     

WWW浏览导航与结构优化技术

In this paper,we introduce some typical WWW navigation systems and Web site optimizationsystems,analyse the properties of navigation and optimization techniques, present some key problemsand techniques that are valuable to pay special attention and discuss the future works.     

内容中心网络中一种改进型缓存机制

内容中心网络( CCN)作为一种主要的未来网络架构,以命名的内容作为网内的主要元素之一,在网络研究中受到广泛关注。针对已有的CCN缓存方案内容副本替换严重的问题,提出一种内容热门度与节点中介中心度约束的缓存机制PopBetw。在基于节点中心度的基础上,从内容本身的属性热门度出发,避免非热门内容的不必要缓存,降低每个节点的缓存负荷,提高网络缓存性能。仿真结果表明,通过评估缓存大小和内容热门度对缓存性能的影响,PopBetw缓存策略可取得比LCE,LCPro和EgoBetw方案更高的缓存命中率和更小的路径延展度,明显降低网内缓存替换数量,有效减少网内节点中介中心性较大节点群的缓存替换数,达到整体性能最优化。     

Cache技术在万维网上的应用

虽然Cache技术是一种传统的技术,但是在应用到网络新环境时,就需要在原有的技术上进行改进。文中详细地介绍整个网络中各个节点(用户端、代理端、服务器端)对用户事件的网络行为,说明在WWW上使用Cache技术的原因和介绍了如何在网络的不同节点上应用该技术的问题,并比较了现有的主要的有关网络缓存的各种不同协议。还介绍了这一技术中两个重要的问题:缓存替换策略和如何使缓存中的动态对象和原始的Web服务器中相应的对象保持一致。     

En-Route Transcoding缓存的优化放置和替换

对en-route transcoding缓存中的缓存路由和协同放置及替换问题进行了研究.提出了CCRA(cost-aware cache routing algorithm)缓存路由算法,能以可控的探测开销来发现潜在的、具有最小访问开销的缓存对象.在此基础上,建立了en-route transcoding缓存的分析模型,将缓存放置和替换问题形式化为一个最优化问题,并利用一种基于动态规划的方法来求解最佳缓存放置策略.仿真结果表明,与已有的元算法放置策略相比,该协同放置和替换策略可以获得更好的CSR性能.     

一种基于分散协作的Web缓存集群体系结构

Web对象缓存技术是一种减少Web访问通信量和访问延迟的重要手段，该文通过分析现有的各种Web缓存系统，提出了一种基于分散协作的Web缓存集群体系结构。该体系结构克服了集中式系统需要额外配备一台管理服务器的缺陷，消除了管理服务器瓶颈失效造成系统瘫痪的危险，减少由于管理服务器带来的延迟；同时消除了分散系统的缓存不命中情况下的多级转发的延迟和缓存内容重叠，提高了资源利用率和系统效率，具有良好的可扩展性和健壮性。     

Evolutionary design of Evolutionary Algorithms

Manual design of Evolutionary Algorithms (EAs) capable of performing very well on a wide range of problems is a difficult task. This is why we have to find other manners to construct algorithms that perform very well on some problems. One possibility (which is explored in this paper) is to let the evolution discover the optimal structure and parameters of the EA used for solving a specific problem. To this end a new model for automatic generation of EAs by evolutionary means is proposed here. The model is based on a simple Genetic Algorithm (GA). Every GA chromosome encodes an EA, which is used for solving a particular problem. Several Evolutionary Algorithms for function optimization are generated by using the considered model. Numerical experiments show that the EAs perform similarly and sometimes even better than standard approaches for several well-known benchmarking problems.