Search: onr:"swepub:oai:DiVA.org:hkr-20591" >
Web metrics for the...
Web metrics for the next generation performance enhancing proxies
-
- Arvidsson, Åke, 1957- (author)
- Högskolan Kristianstad,Forskningsmiljön för datavetenskap (RECS),Avdelningen för datavetenskap
-
- Grinnemo, Karl-Johan (author)
- Karlstads universitet
-
- Chen, Eric Zhi (author)
- Högskolan Kristianstad,Avdelningen för datavetenskap,Forskningsmiljön för datavetenskap (RECS)
-
show more...
-
- Wang, Qinghua (author)
- Högskolan Kristianstad,Forskningsmiljön för datavetenskap (RECS),Avdelningen för datavetenskap
-
- Brunström, Anna (author)
- Karlstads universitet
-
show less...
-
(creator_code:org_t)
- IEEE, 2019
- 2019
- English.
-
In: 2019 27TH INTERNATIONAL CONFERENCE ON SOFTWARE, TELECOMMUNICATIONS AND COMPUTER NETWORKS (SOFTCOM). - : IEEE. - 9789532900880 ; , s. 171-176
Abstract
Subject headings
Close
- The fast growth of Internet traffic, the growing importance of cellular accesses and the escalating competition between content providers and network operators result in a growing interest in improving network performance and user experience. In terms of network transport, different solutions ranging from tuning TCP to installing middleboxes are applied. It turns out, however, that the practical results sometimes are disappointing and we believe that poor testing is one of the reasons for this. Indeed, many cases in the literature limit testing to the simple and rare use case of a single file download, while common and complex use cases like web browsing often are ignored or modelled only by considering smaller files. To facilitate better testing, we present a broader view which includes domain counts, flow counts and different forms of concurrency to better characterise the complexity around web pages, and from which the potential for different optimisation techniques can be estimated. We also derive numerical values of these metrics for a small set of popular web pages and study similarities and differences between pages with the same kind of content (newspapers, e-commerce and video) and between pages designed for the same platform (computer and smartphone).
Subject headings
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (datalogi) (hsv//swe)
- NATURVETENSKAP -- Data- och informationsvetenskap (Datateknik) (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences (hsv//eng)
Keyword
- Performance enhancing proxy
- web metrics
- traffic model
- flow concurrency
- congestion control
Publication and Content Type
- ref (subject category)
- kon (subject category)