Dynamically selecting optimal distribution strategies for Web documents

Pierre, Guillaume; Steen, Maarten van; Tanenbaum, Andrew S.

doi:10.1109/tc.2002.1009149

Cited by 58 publications

(47 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A decentralized solution should solve these problems and automatically determine the appropriate parameters for each page. Classifying pages and determining per-page strategies has already been shown to be a solvable, yet nontrivial problem [26].…”

Section: Htmlmentioning

confidence: 99%

Wikipedia workload analysis for decentralized hosting

2009

View full text Add to dashboard Cite

a b s t r a c tWe study an access trace containing a sample of Wikipedia's traffic over a 107-day period aiming to identify appropriate replication and distribution strategies in a fully decentralized hosting environment. We perform a global analysis of the whole trace, and a detailed analysis of the requests directed to the English edition of Wikipedia. In our study, we classify client requests and examine aspects such as the number of read and save operations, significant load variations and requests for nonexisting pages. We also review proposed decentralized wiki architectures and discuss how they would handle Wikipedia's workload. We conclude that decentralized architectures must focus on applying techniques to efficiently handle read operations while maintaining consistency and dealing with typical issues on decentralized systems such as churn, unbalanced loads and malicious participating nodes.

show abstract

Section: Htmlmentioning

confidence: 99%

Wikipedia workload analysis for decentralized hosting

2009

View full text Add to dashboard Cite

show abstract

“…As opposed to replica placement algorithms proposed for CDNs and P2P networks [2,7,14,15,16], which are often complex, the behavior algorithm of agents in our framework is simple and easy to design, yet demonstrates through simulations that the service performance improves with evolutionary adaptation. An additional simulation study will be done focusing on specific network services or applications.…”

Section: Discussionmentioning

confidence: 99%

“…Such network services may include content distribution networks [2,7,14,15,16], content services networks [11] and peer-to-peer file sharing networks [13]. Analogous to those applications inspired by swarm intelligence, agents are simply designed using only local information without relying on global knowledge, and collectively provide adaptive and scalable network services.…”

Section: Introductionmentioning

confidence: 99%

Adaptive and Evolvable Network Services

Nakano

Suda

2004

Genetic and Evolutionary Computation – GECCO 2004

View full text Add to dashboard Cite

Abstract. This paper proposes an evolutionary framework where a network service is created from a group of autonomous agents that interact and evolve. Agents in our framework are capable of autonomous actions such as replication, migration, and death. An evolutionary mechanism is designed using genetic algorithms in order to evolve the agent's behavior over generations. A simulation study is carried out to demonstrate the ability of the evolutionary mechanism to improve the network service performance (e.g., response time) in a decentralized and self-organized manner. This paper describes the evolutionary mechanism, its design and implementation, and evaluates it through simulations.

show abstract

“…SU50 (Server Update): The primary server maintains copies at the 50 most relevant intermediate servers. 6 i.e., there is only one document in each group, our method is the same as the method in [21]. Therefore, the method proposed in [21] can be viewed as a special case of our method.…”

Section: Delayed Verification (Cdv)mentioning

confidence: 99%

Dynamically Selecting Distribution Strategies for Web Documents According to Access Pattern

Qu¹,

Wu²,

Li³

et al. 2005

Embedded and Ubiquitous Computing – EUC 2005

View full text Add to dashboard Cite

SummaryWeb caching and replication are efficient techniques for reducing Web traffic, user access latency, and server load. In this paper, we first propose an improved GreedyDual* (GD*) cache replacement algorithm, which considers update frequency as a factor in its utility function. Second, we present a group-based method for dynamically selecting distribution strategies for web documents according to access patterns. The documents are divided into groups according to access patterns and the documents in each group are assigned to the same distribution strategy. Our group-based model combines performance metrics with the different weights assigned to each of them. Finally, we use both trace data and statistical data to simulate our methods. The experimental results show that our improved GD*algorithm can outperform the existing GD* algorithm over the performance metrics considered, and our group-based method for document distribution strategy selection can improve several performance metrics, while keeping others almost the same.

show abstract

Dynamically selecting optimal distribution strategies for Web documents

Cited by 58 publications

References 29 publications

Wikipedia workload analysis for decentralized hosting

Wikipedia workload analysis for decentralized hosting

Adaptive and Evolvable Network Services

Dynamically Selecting Distribution Strategies for Web Documents According to Access Pattern

Contact Info

Product

Resources

About