On network-aware clustering of Web clients

By Balachander Krishnamurthy, Jia Wang. Conference on Applications, Technologies, Architectures, and Protocols for Computer Communication, 2000

442 citations recorded by the source corpus.

Being able to identify the groups of clients that are responsible for a significant portion of a Web site's requests can be helpful to both the Web site and the clients. In a Web application, it is beneficial to move content closer to groups of clients that are responsible for large subsets of requests to an origin server. We introduce clusters---a grouping of clients that are close together topologically and likely to be under common administrative control. We identify clusters using a ``network-aware" method, based on information available from BGP routing table snapshots.

Subfields: Computer Networks and Communications

View Paper: https://www.semanticscholar.org/paper/1423e1dc928d7870a463bb5c11deecc17072f7e4

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

Citations in the corpus

Defense Against Spoofed IP Traffic Using Hop-Count Filtering (2007, methodology): “Based on the BGP routing table information, a network-aware clustering technique [26] has been proposed to identify a group of Web clients that are topologically close to each other and”
An investigation of geographic mapping techniques for internet hosts (2001, methodology): “Thus knowledge of the address pre xes (APs) used by the routing protocol enables us to identify topological clusters, as observed in [12].”
An analysis of live streaming workloads on the internet (2004, background): “AS clustering amongst clients accessing the same web-site has also been studied [14].”
Distributing streaming media content using cooperative networking (2002, background): “In our evaluation, peers are close if they belong in the same BGP prefix domain [9].”
Constrained mirror placement on the Internet (2001, background): “Ideally, a mirror can be placed where there is a large concentration of clients interested in the content of a server [3].”
Should internet service providers fear peer-assisted content distribution? (2005, methodology): “Such locality solutions could be implemented with small modifications to BitTorrent trackers and could consider algorithms based on simple prefix rules, domain names, or more sophisticated hierarchical prefix matching rules, network-aware clustering [13] or routing table lookups (the two latter case”
Community detection in graphs (2009, background): “Biological, social, technological, and information networks can be studied as graphs, and graph analysis has become crucial to understand the features of these systems.”
Topologically-aware overlay construction and server selection (2002, background): “One might also imagine centralized solutions [14] wherein a single site gathers network topology and routing information to infer the relative proximity of hosts.”
Finding Hierarchical Heavy Hitters in Data Streams (2003, background): “Knowledge of busy clusters can be very useful for packet forwarding in routers, QoS differentiation, proxy positioning, and server replication [18].”
AS relationships: inference and validation (2006, background): “…make our results easily accessible and practically useful for the community, we open an AS relationship repository where we archive, on a weekly basis, and make publicly available the complete Internet AS-level topology annotated with AS relationship information for every pair of AS neighbors.”
Prefix-preserving IP address anonymization: measurement-based security evaluation and a new cryptography-based scheme (2002, background): “, routing performance analysis, or clustering of endsystems [3]).”
On the placement of Web server replicas (2001, background): “to potential replica sites) about the number of requests generated by all the popular clusters, where clusters are identified using the approach proposed in [15].”
Deriving traffic demands for operational IP networks: methodology and experience (2001, background): “The traffic statistics could be aggregated to the client prefix level [14] to predict the outbound demands for the new access link.”
Characterizing the Internet hierarchy from multiple vantage points (2002, background): “fixes and ASes responsible for a large portion of the traffic from the site [5].”