Deriving traffic demands for operational IP networks: methodology and experience

By Anja Feldmann, Albert G. Greenberg, Carsten Lund, N. Reingold, Jennifer Rexford, Fred True. TNET, 2001

623 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/71e928184942280b37a25a06596c59a94ed0ac63

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

In Electrical and Electronic Engineering

Citations in the corpus

One Sketch to Rule Them All: Rethinking Network Flow Monitoring with UnivMon (2016, background): “Network management is multi-faceted and encompasses a range of tasks including trafﬁc engineering [11, 32], attack and anomaly detection [49], and forensic analysis [46].”
Packet classification in large ISPs: design and evaluation of decision tree classifiers (2005, methodology): “The methods used to derive the ingress interface from a ﬂow record is described in [12].”
OpenTM: Traffic Matrix Estimator for OpenFlow Networks (2010, methodology): “Previous works infer the TM (a) indirectly from link loads [2,3], (b) directly from sampled flow statistics (e.g., using Cisco NetFlow) [4, 5], or (c) using a combination of both [1].”
Traffic matrix estimation: existing techniques and new directions (2002, methodology): “The data used in [6] came from Netflow measurements, routing tables and routing configuration files.”
Walking the tightrope: responsive yet stable traffic engineering (2005, background): “Offline Oblivious Optimizers: Instead of estimating traffic matrices accurately [13], the MPLS Oblivious optimizer [6] fin ds a routing that balances load independent of the traffic matrix , i.”
New directions in traffic measurement and accounting (2001, methodology): “[9] deals with correlating measurements taken at various points to nd spatial traÆc distributions; the techniques in our paper can be used to complement their methods.”
Making intra-domain routing robust to changing and uncertain traffic demands: understanding fundamental tradeoffs (2003, background): “We arrive at a surprising conclusion: it is possible to obtain a robust routing that guarantees a nearly optimal utilization with a fairly limited knowledge of the applicable tra.c demands.”
A Genetic Algorithm for the Weight Setting Problem in OSPF Routing (2002, background): “An estimation of future demands can be based, as in the case of the AT&T Worldnet backbone , on concrete measures of flow between source-destination pairs [10] [11].”
Providing public intradomain traffic matrices to the research community (2006, neutral): “Providing Public Intradomain Traf.c Matrices to the Research Community Steve Uhlig1, Bruno Quoitin Jean Lepropre2 , Simon Balon2 Computing Science and Engineering Research Unit in Networking Department University of Liege, Belgium University of Louvain-la-Neuve, Belgium {lepropre,balon}@run.monte”
Data streams: algorithms and applications (2005, background): “AT&T gave me the opportunity to build systems with SNMP data, AWS cellular CDRs, and Intellectual property—patent data, and a national system for location-based services in wireless networks.”
Building a better NetFlow (2004, neutral): “In Section 2.3 we give an example of how a router manufacturer could con(cid:12)gure ANF to ensure that router memory and processing power are not exhausted under any possible tra(cid:14)c mix .”
SIMPLE-fying middlebox policy enforcement using SDN (2013, background): “Such inputs are typically already collected in network management systems [17].”
Design and Implementation of a Consolidated Middlebox Architecture (2012, background): “The NetworkSpec for routing and traffic information is collected for other network management applications [20].”
Heavy-Hitter Detection Entirely in the Data Plane (2016, background): “Many network management applications can bene t from nding the set of ows contributing signi cant amounts of tra c to a link: for example, to relieve link congestion [5], to plan network capacity [18], to detect network anomalies and attacks [23], or to cache forwarding table entries [36].”
Characterization of network-wide anomalies in traffic flows (2004, methodology): “We augmented the routing tables with conﬁguration ﬁles in order to resolve customer IP addresses that do not appear in the BGP tables.”