How does the recursive undns algorithm affect the accuracy of an IP geolocation system?

IP geolocation services are playing an increasingly important role in Web applications. Landmark-based IP geolocation can gain better IP geolocation performance. However, the accuracy of landmarks is still an urgent issue to address. The paper proposes a filtering landmark mechanism to guarantee the accuracy of landmarks. First, a Ping-Delay Coarse Filtering Landmark algorithm (PCFL) is proposed to coarsely filter landmarks. Second, a recursive undns model is presented to make full use of undns. Third, a Recursive Undns Evaluating Landmark algorithm (RUEL) is proposed to accurately evaluate the accuracy of landmarks. The experimental results and analyses show that using the filtering landmark mechanism proposed in this paper, the accuracy of landmarks can be increased, which in turn makes the median error distance of the IP geolocation system reduced to a certain extent.

[1]  Branko Ristic,et al.  Internet Host Geolocation Using Maximum Likelihood Estimation Technique , 2010, 2010 24th IEEE International Conference on Advanced Information Networking and Applications.

[2]  Emin Gün Sirer,et al.  Octant: A Comprehensive Framework for the Geolocalization of Internet Hosts , 2007, NSDI.

[3]  Dan Li,et al.  IP-Geolocation Mapping for Moderately Connected Internet Regions , 2013, IEEE Transactions on Parallel and Distributed Systems.

[4]  Charmain Cilliers,et al.  Proceedings of the 2008 annual research conference of the South African Institute of Computer Scientists and Information Technologists on IT research in developing countries: riding the wave of technology , 2008 .

[5]  Dana S. Richards,et al.  Statistical Geolocation of Internet Hosts , 2009, 2009 Proceedings of 18th International Conference on Computer Communications and Networks.

[6]  Scott Hazelhurst,et al.  Scientific computing using virtual high-performance computing: a case study using the Amazon elastic computing cloud , 2008, SAICSIT '08.

[7]  Ratul Mahajan,et al.  Measuring ISP topologies with rocketfuel , 2002, TNET.

[8]  David Wetherall,et al.  Towards IP geolocation using delay and topology measurements , 2006, IMC '06.

[9]  Shanika Karunasekera,et al.  GeoWeight: internet host geolocation based on a probability model for latency measurements , 2010, ACSC.

[10]  Paul Barford,et al.  A Learning-Based Approach for IP Geolocation , 2010, PAM.

[11]  Aleksandar Kuzmanovic,et al.  Towards Street-Level Client-Independent IP Geolocation , 2011, NSDI.