ScienceDirect - Computer Networks : p2pWeb: An open, decentralized infrastructure of Web servers for sharing ephemeral Web content

Rerun your search for "p2pweb " on ScienceDirect. Search

Font Size:

A web content manipulation technique based on page Frag...
Journal of Network and Computer Applications

A web content manipulation technique based on page Fragmentation Original Research Article
Journal of Network and Computer Applications, Volume 30, Issue 2, April 2007, Pages 563-585
Bouras Christos, Kounenis Giorgos, Misedakis Ioannis

Abstract

Web portals today offer a variety of content and services to their users. This content can be split into various categories and usually content semantically related is placed in the same area. In this paper, a software technique is presented that allows the viewers of web sites to build their own personalized portals, using specific areas of their preferred sites. This technique saves users’ time and reduces the cost of browsing the web by minimizing the volume of data that has to be downloaded. It is based on an algorithm, which fragments a web page in discrete fragments using the page's internal structure. Users utilize a web interface to define which parts of selected web pages they desire to appear in their personalized portal. No additional software needs to be installed on the users’ personal computers, since this technique is designed to function centrally as a data source for a Web Server. In addition, usage of this technique reduces user perceived latency during browsing sessions, since less data must be transferred to users’ personal computers.

Purchase article PDF (790 K)

A content-based load balancing algorithm with admission...
Future Generation Computer Systems

A content-based load balancing algorithm with admission control for cluster web servers Original Research Article
Future Generation Computer Systems, Volume 24, Issue 8, October 2008, Pages 775-787
Saeed Sharifian, Seyed A. Motamedi, Mohammad K. Akbari

Abstract

With the growing demands for web-based applications, cluster web servers emerged as a reliable and leading resource in internet infrastructure. Managing performance of the cluster web servers under heavy load conditions is a critical task specifically when it comes to the advent of dynamic contents and database-driven applications. In this paper we propose a new load balancing algorithm namely IQRD (Intelligent Queue-based Request Dispatcher) for web-switches of the cluster web servers which operates at layer-7. The IQRD aims to achieve better load balancing with the help of request classification, performance isolation and dynamic remaining capacity estimation mechanisms. For this, a queuing model was employed for each class of requests in each node of the cluster to provide an estimation regarding the node remaining capacity. This value is used as a load descriptor (index) in the load balancing algorithm and also used by the admission control mechanism. The implementation results with synthetic and realistic workloads confirm that IQRD effectively balances loads among servers in the cluster and achieves better response time and throughput compared to other load balancing algorithms. However, the IQRD algorithm offered more processing overheads both in the web-switch and the web servers, but presented a better load balancing among web servers, even when the request rates were beyond the cluster capacity.

Purchase article PDF (1506 K)

Evaluating IA-32 web servers through simics: a practica...
Journal of Systems Architecture

Evaluating IA-32 web servers through simics: a practical experience Original Research Article
Journal of Systems Architecture, Volume 51, Issue 4, April 2005, Pages 251-264
F.J. Villa, M.E. Acacio, J.M. García

Abstract

Nowadays, the use of multiprocessor systems is not just limited to typical scientific applications, but these systems are increasingly being used for executing commercial applications, such as databases and web servers. Therefore, it becomes essential to study the behavior of multiprocessor architectures under commercial workloads. To accomplish this, we need simulators able to model not only the CPU, memory and interconnection network but also other aspects that are critical in the execution of commercial workloads, such as I/O subsystem and operating system. In this paper, we present our first experiences using Simics, a simulator which allows full-system simulation of multiprocessor architectures covering all the topics previously mentioned. Using Simics we carry out a detailed performance study of a static web content server, showing how changes in some architectural parameters, such as number of processors and cache size, affect final performance. The results we have obtained corroborate the intuition of increasing performance of a dual-processor web server opposite to a single-processor one, and at the same time, allow us to check out Simics limitations. Finally, we compare these results with those that are obtained on real machines.

Purchase article PDF (336 K)

An optimization model for Web content adaptation
Computer Networks

An optimization model for Web content adaptation Original Research Article
Computer Networks, Volume 50, Issue 7, 15 May 2006, Pages 953-965
Rong-Hong Jan, Ching-Peng Lin, Maw-Sheng Chern

Abstract

This paper considers Web content adaptation with a bandwidth constraint for server-based adaptive Web systems. The problem can be stated as follows: Given a Web page P consisting of n component items d₁, d₂, … , d_n and each of the component items d_i having J_i versions d_i₁,d_i₂,…,d_{i_{J_i}}, for each component item d_i select one of its versions to compose the Web page such that the fidelity function is maximized subject to the bandwidth constraint. We formulate this problem as a linear multi-choice knapsack problem (LMCKP). This paper transforms the LMCKP into a knapsack problem (KP) and then presents a dynamic programming method to solve the KP. A numerical example illustrates this method and shows its effectiveness.

Purchase article PDF (594 K)

Adaptive job routing and scheduling
Engineering Applications of Artificial Intelligence

Adaptive job routing and scheduling Original Research Article
Engineering Applications of Artificial Intelligence, Volume 17, Issue 7, October 2004, Pages 855-869
Shimon Whiteson, Peter Stone

Abstract

Computer systems are rapidly becoming so complex that maintaining them with human support staffs will be prohibitively expensive and inefficient. In response, visionaries have begun proposing that computer systems be imbued with the ability to configure themselves, diagnose failures, and ultimately repair themselves in response to these failures. However, despite convincing arguments that such a shift would be desirable, as of yet there has been little concrete progress made towards this goal. These challenges are naturally suited to machine learning methods. Hence, this article presents a new network simulator designed to study the application of machine learning methods from a system-wide perspective. Also, learning-based methods for addressing the problems of job routing and CPU scheduling in the simulated networks are introduced. Experimental results verify that methods using machine learning outperform reasonable heuristic and hand-coded approaches on example networks designed to capture many of the complexities that exist in real systems.

Purchase article PDF (659 K)

View more related articles

Related reference work articles e.g. encyclopedias

Web Searching
Encyclopedia of Language & Linguistics

Web Searching
Encyclopedia of Language & Linguistics, 2006, Pages 527-538
R. Baeza-Yates, C. Castillo

Abstract

In just a few years, the World Wide Web has become the largest cultural endeavor of all times. The Web is a distributed repository of information without a central point of control, and thus can be viewed as a vast, diverse, rapidly changing and unstructured database. The low cost of publishing information on the Web is a key part of its success, but implies that searching for information on the Web will always be inherently more difficult than searching for information in traditional, closed repositories.

Purchase article PDF (330 K)

Internet-Based Measurement
International Encyclopedia of Human Geography

Internet-Based Measurement
International Encyclopedia of Human Geography, 2009, Pages 569-579
M. Dodge, M. Zook

Abstract

Internet-based measurement is a set of methods applied to quantitatively describe the structure, workload, and use of the Internet. They provide a practical means of doing a kind of virtual ‘fieldwork’ on the Internet using online tools and network monitoring techniques to gather fine-scale primary data. Internet-based measurement as a methodology for human geography is important because it (1) provides insight to the underlying structural processes of the Internet and Internet-based activities; (2) allows users to explore and analyze the Internet for themselves; and (3) allows researchers to aggregate data spread across multiple websites to analyze offline phenomenon. After outlining the five distinct kinds of geographical locations associated with an Internet-based resource (lexical, hardware, production, ownership, and use), this article outlines a range of tools and techniques for exploring these geographies. These include IP address geo-coding, domain name whois lookups, website rankings, ping, and traceroute. These tools can provide an understanding of the topological structures and geographies of the Internet, and allows users to construct information firsthand and critically question network operations directly.

Purchase article PDF (4041 K)

Abstract

Nowadays, we are witnessing an increasing growth of Web 2.0 content such as micronews, blogs and RSS feeds. This trend exemplified by applications like Twitter and LiveJournal is starting to slow down not only by the limitations of existing services – proprietary and centralized, but also by the cumbersome process of discovering and tracking interesting content. This content is generally ephemeral and thus difficult to index by conventional Web search technology. This problem is exacerbated by the passive role adopted by Web content providers: it is surprising that Web servers publish information and expect that thousands of other servers (search engines, Web-based aggregators like GoogleNews, etc.) advertise their content to the world.

In this work we propose p2pWeb, an open, decentralized infrastructure to enable Web servers to use their spare capacity to filter out, aggregate and disseminate Web content in a scalable and timely manner. p2pWeb is flexible enough to support a broad variety of services. The main property of p2pWeb is that all communication abstractions, including aggregation and multicast, are implemented hierarchically and using the HTTP protocol. Simulation results certify the viability of our approach.

Keywords: Distributed systems; Web technology; Peer-to-peer computing; Publish/subscribe

Article Outline

Introduction: 1.1. Contributions

Related work: 2.1. p2p Publish–subscribe (pub/sub) systems; 2.2. Micropublishing systems

The p2pWeb infrastructure

3.1. Basic architecture

3.1.1. Data model

3.1.2. Network model

3.2. Hierarchical publish/subscribe

3.2.1. Dissemination tree construction
3.2.1.1. Default tree construction
3.2.1.2. Tree construction analysis
3.2.1.3. Aggregating dissemination network status
3.2.1.4. Tree construction with scoped subscriptions
3.2.1.5. Vertical subscriptions
3.2.1.6. Horizontal subscriptions

3.2.2. Dissemination procedure
3.2.2.1. Default dissemination procedure
3.2.2.2. Dissemination procedure analysis
3.2.2.3. Scoped dissemination procedure
3.2.2.4. Dissemination analysis

3.2.3. Complexity analysis
3.2.3.1. Subscription complexity
3.2.3.2. Dissemination complexity

3.3. Aggregation

Evaluation

Conclusions

Acknowledgements

Hierarchical publish/subscribe algorithms

Implementation issues

B.1. HTTP based overlay

B.1.1. Sequentiality issues

B.1.2. Routing issues

B.1.3. Hierarchical issues

B.1.4. Detecting dead links

References

Vitae

Corresponding author. Tel.: +34 977 559677; fax: +34 977 559710.

Vitae

Marc Sànchez-Artigas is an assistant professor at URV (Tarragona, Spain) in the Department of Computer Engineering and Maths. In 2009, he received his Ph.D. with European Mention from UPF (Barcelona, Spain). During his Ph.D. studies, he worked at EPFL under the supervision of professor Karl Aberer. He received the Best Paper Award from IEEE LCN’07. Contact him at marc.sanchez@urv.cat.

Jordi Pujol-Ahulló obtained on September 2002 his B.S. degree in Computer Science Engineering (Software speciality). On June 2005 he obtained his M.S. degree in Computer Science Engineering. Both degrees were attained at Universitat Rovira i Virgili. He obtained his Ph.D. in January 2010 in the University of Murcia about data management and content distribution services on structured peer-to-peer networks, under the guidance of Dr. Pedro García-López and Dr. Antonio F. Gómez-Skarmeta. During his Ph.D. he also worked in the University of Trento (Italy) with Alberto Montresor. His research topics are distributed systems, peer-to-peer networks, distributed middleware and collaborative solutions.

Lluis Pamies-Juarez is a Ph.D. student in the Department of Computer Engineering and Mathematics at Universitat Rovira i Virgili, Spain. His research interests include distributed storage systems and peer-to-peer infrastructures. He has a BS and a MS in computer science from Universitat Rovira i Virgili. Department of Computer Engineering and Mathematics (DEIM), Office 144, Campus Sescelades, Avinguda dels Països Catalans, 26, Tarragona, Spain.

Pedro García-López is professor at the Computer Engineering and Mathematics Department at the University Rovira i Virgili (Spain) and IEEE Member. He obtained his Ph.D. in 2003 in the University of Murcia about Collaborative Distributed Systems under the guidance of Antonio F. Gomez Skarmeta. During his Ph.D. he also worked in the University of Ghent (Belgium) with Hans Vangheluwe and in Fraunhofer-FIT Bonn (Germany) with Wolfgang Appelt (BSCW team). His research topics are distributed systems, peer-to-peer, software architectures and middleware and collaborative environments. He has published more than 30 papers and participated in several Spanish and European research projects. He currently leads in Tarragona the “Architectures and Telematic Services” research group and coordinates the URV team in the project P2PGRID (Self-Adjusting P2P and Grid Systems). Furthermore, he chairs the IEEE Collaborative Peer-to-Peer Systems Workshop (COPS) and is member of the Program Committee of the IEEE P2P Conference. Contact him at pedro.garcia@urv.cat.

Purchase

$ 31.50

Computer Networks
Volume 54, Issue 12, 26 August 2010, Pages 1968-1985
P2P Technologies for Emerging Wide-Area Collaborative Services and Applications

doi:10.1016/j.comnet.2010.03.021 \| How to Cite or Link Using DOI Copyright © 2010 Elsevier B.V. All rights reserved.	Cited By in Scopus (0)
Permissions & Reprints