Content Adaptation Architectures Based on Squid Proxy Server

Abstract

The overwhelming popularity of Internet and the technology advancements have determined the diffusion of many different Web-enabled devices. In such an heterogeneous client environment, efficient content adaptation and delivery services are becoming a major requirement for the new Internet service infrastructure. In this paper we describe intermediary-based architectures that provide adaptation and delivery of Web content to different user terminals. We present the design of a Squid-based prototype that carries out the adaptation of Web images and combines such a functionality with the caching of multiple versions of the same resource. We also investigate how to provide some form of cooperation among the nodes of the intermediary infrastructure, with the goal to evaluate to what extent the cooperation in discovering, adapting, and delivering Web resources can improve the user-perceived performance.

Resource Management Strategies for Mobile Web-Based Services

“…For the current scenario, the service times to dynamically generate a textbased resource follow an empirical distribution obtained by preliminary experiments, with a median of 220 ms. For multimedia resources, the service times are based on [3]. Since the time to adapt a multimedia resource is proportional to the resource size [6], [13], we consider a service time for MB, that is 730 ms for images and 1054 ms for audio/video. To model future server infrastructures with more powerful CPU, we assume that the server computational power will continue to increase according to the Moore Law for the next five years.…”

“…These approaches may be integrated with caching strategies [22], [6], [13] that typically exploit a sort of utility function to determine whether or not it is convenient to cache an adapted version of a certain resource. However, all these proposals consider a traditional Web scenario, with a limited amount of multimedia resources and a small fraction of requests that come from mobile devices and, consequently, require adaptation.…”

“…For example, photo and video sharing services (e.g., YouTube, Flickr) are causing an explosion of demand for multimedia content. These trends will determine a future mobile Web scenario characterized by a large amount of heterogeneous contents, mainly consisting of multimedia resources (e.g., [1], [2], [3]), that will have to be tailored to user preferences and to device capabilities on-thefly at the moment of the client request [4], [5], [6]. Designing server architectures that will support future Mobile Web-based services requires an initial evaluation of the workload and computational impact.…”

A Two-level distributed architecture for the support of content adaptation and delivery services

“…For these reasons, supporting efficient content adaptation and delivery services is a complex task that requires intervention at the software level, modification of existing protocols, and even accurate design of the server infrastructures that represent the focus of this paper. Any content provider should address the high computational cost of the adaptation and the augmented storage requirements due to the presence of multiple resource versions, hence the most practicable solution is to rely on intermediary architectures consisting of multiple geographically distributed servers interposed in the path from the client to the origin server [5,17,23,27]. This type of architectures opens the possibility of sharing the load of computationally expensive services, increases the storage capacity and improves content delivery.…”

“…The motivation is that content partitioning has the effect of preserving request access locality and avoiding content replication. The proposed architecture is innovative because it addresses present and future issues for scalability and performance that are not solved by available solutions based on geographically distributed architectures [5]. We compare the Two-level architecture with alternative flat architectures through several experiments based on prototype systems.…”