A Model Based Approach for Improving Geolocation *
description
Transcript of A Model Based Approach for Improving Geolocation *
![Page 1: A Model Based Approach for Improving Geolocation *](https://reader036.fdocuments.in/reader036/viewer/2022062322/56814524550346895db1ea8d/html5/thumbnails/1.jpg)
A Model Based Approach for Improving Geolocation*
Péter HágaEötvös Loránd University
Budapest, Hungary
* ”A Model Based Approach for Improving Router Geolocation”accepted for publication in Computer Networks, 2010.
![Page 2: A Model Based Approach for Improving Geolocation *](https://reader036.fdocuments.in/reader036/viewer/2022062322/56814524550346895db1ea8d/html5/thumbnails/2.jpg)
Outline
• Measurement based geolocation• Detailed path latency model
– To localize internal routers
• Case studies– To localize end hosts
• Spotter framework
![Page 3: A Model Based Approach for Improving Geolocation *](https://reader036.fdocuments.in/reader036/viewer/2022062322/56814524550346895db1ea8d/html5/thumbnails/3.jpg)
• Location information can be useful to both private and corporate users– Targeted advertising on the web– Restricted content delivery– Location-based security check– Web statistics
• Scientific applications– Measurement visualization– Network diagnostics
Motivation
![Page 4: A Model Based Approach for Improving Geolocation *](https://reader036.fdocuments.in/reader036/viewer/2022062322/56814524550346895db1ea8d/html5/thumbnails/4.jpg)
Geolocation in General
• Passive geolocation– Extracting location information from domain names– DNS and WhoIS databases– Commercial databases
• MaxMind, IPligence, Hexasoft
– Large and geographically dispersed IP blocks can be allocated to a single entity
• Active geolocation– Active probing– Measurement nodes with known locations– Constraint based techniques
![Page 5: A Model Based Approach for Improving Geolocation *](https://reader036.fdocuments.in/reader036/viewer/2022062322/56814524550346895db1ea8d/html5/thumbnails/5.jpg)
• Network Delays – with active measurements• Delays can be transformed to geographic distance
– Round Trip Time (ping)– One-way delay (measured in the ETOMIC Infrastucture)
• Effects of delay underestimation• Effects of delay overestimation
Measurement Based Geolocation
![Page 6: A Model Based Approach for Improving Geolocation *](https://reader036.fdocuments.in/reader036/viewer/2022062322/56814524550346895db1ea8d/html5/thumbnails/6.jpg)
Modeling Packet Delays
• A packet delay (d) can be divided into…– Queuing delay (Dq)
– Processing delay (Dpc)
– Transmission delay (Dtr)
– Propagation delay (Dpg)
• The overall packet delay for a network path:
n0 n1 n2 nH…
Only the propagation component has role in the
geolocation
• A given path:
![Page 7: A Model Based Approach for Improving Geolocation *](https://reader036.fdocuments.in/reader036/viewer/2022062322/56814524550346895db1ea8d/html5/thumbnails/7.jpg)
How to Estimate Propagation Delays
• Assumptions used in the model– No queuing: Dq = 0
– The per-hop processing and transmission delays can be approximated by a global constant:dh = Dpc + Dtr
– Based on the literature and our observations dh = 100s
• The one-way propagation delay along a given path:
![Page 8: A Model Based Approach for Improving Geolocation *](https://reader036.fdocuments.in/reader036/viewer/2022062322/56814524550346895db1ea8d/html5/thumbnails/8.jpg)
Distance Approximation
• An upper approximation of geographical distance from source s to destination d:
• where r is the velocity of signal propagation in network [in c units]
s
d
• Physical properties• Length • cable curvatures
• in copper: ~0.7• in fiber : 0.65
![Page 9: A Model Based Approach for Improving Geolocation *](https://reader036.fdocuments.in/reader036/viewer/2022062322/56814524550346895db1ea8d/html5/thumbnails/9.jpg)
1. Round-Trip Time Constraint
• Using path-latency model– Round-trip propagation delay from a landmark
• Upper approximation of one-way propagation delay
L
t
The nodeto be localized
Landmark with known location
![Page 10: A Model Based Approach for Improving Geolocation *](https://reader036.fdocuments.in/reader036/viewer/2022062322/56814524550346895db1ea8d/html5/thumbnails/10.jpg)
2. Per-link Distances
• Link latency estimation– For a symmetric link e
– For real links
L1
ni-1
ni
Internet
RTT1 – RTT2
ni-1
nie
L1
L2
![Page 11: A Model Based Approach for Improving Geolocation *](https://reader036.fdocuments.in/reader036/viewer/2022062322/56814524550346895db1ea8d/html5/thumbnails/11.jpg)
3. One-way Delay Constraint
• Limits the geographic length of a given network path• Requires OWD measurements
L1 n1
L2n2
n3
![Page 12: A Model Based Approach for Improving Geolocation *](https://reader036.fdocuments.in/reader036/viewer/2022062322/56814524550346895db1ea8d/html5/thumbnails/12.jpg)
Localizing internal routers
![Page 13: A Model Based Approach for Improving Geolocation *](https://reader036.fdocuments.in/reader036/viewer/2022062322/56814524550346895db1ea8d/html5/thumbnails/13.jpg)
Localizing internal routers
![Page 14: A Model Based Approach for Improving Geolocation *](https://reader036.fdocuments.in/reader036/viewer/2022062322/56814524550346895db1ea8d/html5/thumbnails/14.jpg)
Localizing internal routers
Based on one way delays:
![Page 15: A Model Based Approach for Improving Geolocation *](https://reader036.fdocuments.in/reader036/viewer/2022062322/56814524550346895db1ea8d/html5/thumbnails/15.jpg)
Performance Analysis
![Page 16: A Model Based Approach for Improving Geolocation *](https://reader036.fdocuments.in/reader036/viewer/2022062322/56814524550346895db1ea8d/html5/thumbnails/16.jpg)
Extensions
• latency vs. distance distribution for each landmark• calibrated to the other landmarks• flat disks -> probability distributions
Figure is from the Octant paper.
![Page 17: A Model Based Approach for Improving Geolocation *](https://reader036.fdocuments.in/reader036/viewer/2022062322/56814524550346895db1ea8d/html5/thumbnails/17.jpg)
Case study I. – Where are your YouTube videos?
![Page 18: A Model Based Approach for Improving Geolocation *](https://reader036.fdocuments.in/reader036/viewer/2022062322/56814524550346895db1ea8d/html5/thumbnails/18.jpg)
Case study I.– Where are your YouTube videos?
• Where are YouTube’s content delivery servers?• MaxMind result is: Mountain View, CA• Geoloc based on active measurement:
– The IP range: 74.125.0.0/16– 8127 accessible IP addresses– 8127 nodes to be localized
• Landmarks: 300 PlanetLab nodes
![Page 19: A Model Based Approach for Improving Geolocation *](https://reader036.fdocuments.in/reader036/viewer/2022062322/56814524550346895db1ea8d/html5/thumbnails/19.jpg)
Case study I.– Where are the YouTube servers?
![Page 20: A Model Based Approach for Improving Geolocation *](https://reader036.fdocuments.in/reader036/viewer/2022062322/56814524550346895db1ea8d/html5/thumbnails/20.jpg)
Case study I. – Where are the YouTube servers?
![Page 21: A Model Based Approach for Improving Geolocation *](https://reader036.fdocuments.in/reader036/viewer/2022062322/56814524550346895db1ea8d/html5/thumbnails/21.jpg)
Case study I. – Where are the YouTube servers?
London
Amsterdam, ???
Dortmund,Frankfurt,
???
Moscow
Stockholm
Bremen, Hamburg
Dresden
???
![Page 22: A Model Based Approach for Improving Geolocation *](https://reader036.fdocuments.in/reader036/viewer/2022062322/56814524550346895db1ea8d/html5/thumbnails/22.jpg)
Case study I. – Where are the YouTube servers?
![Page 23: A Model Based Approach for Improving Geolocation *](https://reader036.fdocuments.in/reader036/viewer/2022062322/56814524550346895db1ea8d/html5/thumbnails/23.jpg)
Case study I. – Where are the YouTube servers?
Seattle
San Francisco
Los Angeles
Chicago
Minneapolis
Toronto
New York
Baltimore,Washington
???
Atlanta
Charlestown,Savannah
![Page 24: A Model Based Approach for Improving Geolocation *](https://reader036.fdocuments.in/reader036/viewer/2022062322/56814524550346895db1ea8d/html5/thumbnails/24.jpg)
Case study I. – Where are the YouTube servers?
• N=1
• 2<=N<10
• 10<=N
Hong Kong
Singapure
Tokyo
Taipei
![Page 25: A Model Based Approach for Improving Geolocation *](https://reader036.fdocuments.in/reader036/viewer/2022062322/56814524550346895db1ea8d/html5/thumbnails/25.jpg)
Case study II. – Where do the Hungarians live?
![Page 26: A Model Based Approach for Improving Geolocation *](https://reader036.fdocuments.in/reader036/viewer/2022062322/56814524550346895db1ea8d/html5/thumbnails/26.jpg)
Case study II. – Where do the Hungarian live?
• target IPs: – google/yahoo/baidu/bing web search – 10 words from the 100 most frequent hungarian words– 4359 globally accessible IP addresses– 4359 nodes to be localized
• Landmarks: 300 PlanetLab nodes
![Page 27: A Model Based Approach for Improving Geolocation *](https://reader036.fdocuments.in/reader036/viewer/2022062322/56814524550346895db1ea8d/html5/thumbnails/27.jpg)
Case study II. – Where do the Hungarian live?
![Page 28: A Model Based Approach for Improving Geolocation *](https://reader036.fdocuments.in/reader036/viewer/2022062322/56814524550346895db1ea8d/html5/thumbnails/28.jpg)
Case study II. – Where do the Hungarian live?
![Page 29: A Model Based Approach for Improving Geolocation *](https://reader036.fdocuments.in/reader036/viewer/2022062322/56814524550346895db1ea8d/html5/thumbnails/29.jpg)
Case study II. – Where do the Hungarian live?
![Page 30: A Model Based Approach for Improving Geolocation *](https://reader036.fdocuments.in/reader036/viewer/2022062322/56814524550346895db1ea8d/html5/thumbnails/30.jpg)
Spotter geolocation framework
![Page 31: A Model Based Approach for Improving Geolocation *](https://reader036.fdocuments.in/reader036/viewer/2022062322/56814524550346895db1ea8d/html5/thumbnails/31.jpg)
• Engine:– to evaluate the measurement data– To visualize the result (confidence regions)– store raw and evaluated date in nmVO
Framework
• active probing based on Planetlab nodes• Management layer:
– to reserve nodes– to execute probing– to collect measurement data
![Page 32: A Model Based Approach for Improving Geolocation *](https://reader036.fdocuments.in/reader036/viewer/2022062322/56814524550346895db1ea8d/html5/thumbnails/32.jpg)
• Calls the framework• http://nm.vo.elte.hu/spotter• http://nm.vo.elte.hu/spotter/test_version
• Feedbacks are welcome!
Prototype – nm.vo.elte.hu/spotter
• C# ASP based implementation• Under development, current release is „unstable”• define targets• Filtering:
– Landmarks - Planetlab sources– Results – number of „closest” data sources to evaluate
![Page 33: A Model Based Approach for Improving Geolocation *](https://reader036.fdocuments.in/reader036/viewer/2022062322/56814524550346895db1ea8d/html5/thumbnails/33.jpg)
Prototype – nm.vo.elte.hu/spotter
![Page 34: A Model Based Approach for Improving Geolocation *](https://reader036.fdocuments.in/reader036/viewer/2022062322/56814524550346895db1ea8d/html5/thumbnails/34.jpg)
Prototype – nm.vo.elte.hu/spotter
![Page 35: A Model Based Approach for Improving Geolocation *](https://reader036.fdocuments.in/reader036/viewer/2022062322/56814524550346895db1ea8d/html5/thumbnails/35.jpg)
Prototype – nm.vo.elte.hu/spotter
![Page 36: A Model Based Approach for Improving Geolocation *](https://reader036.fdocuments.in/reader036/viewer/2022062322/56814524550346895db1ea8d/html5/thumbnails/36.jpg)
Thank you for your attention!