From MAGGIE

Should you be interested in the research or development of any of the following projects, feel free to contact Dr. Arshad Ali <arshad.ali_at_niit.edu.pk>, Dr. Les Cottrell <cottrell_at_slac.stanford.edu> or Mr. Umar Kalim <umar.kalim_at_niit.edu.pk>

Contents 1 Available Projects 2 Unresolved issues 2.1 Estimate of usable pings 2.2 Landmark Selection for TULIP 2.3 Estimate of Alpha values for TULIP using PingER data

[edit] Available Projects

• Detecting hosts with anomalous performance compared to neighbors
• Maintaining up-to-date sites list and presentation for TULIP
• Real Time PingER Data
• TULIP Visualization
• Mapping PingER Metrics
• Event Detection and Diagnosis

[edit] Unresolved issues

[edit] Estimate of usable pings

To make the number of pings report usable ideally one needs much more coverage and would also need to find the minimum ping ever. One probably has roughly the approximate "minimum ping ever" using the pingtable.pl results from the various monitors for say a recent month or 180 days. Then one needs to measure minimum ping RTTs as a function of number of pings for many pairs (i.e. the pingtable.pl pairs) as you have been doing and come up with some cumulative distribution statistics (#pairs within n% of the minimum ping ever) of difference in the min-RTT say 5, 10, 20, and infinite (minimum ping ever) pings. This may vary depending on monitoring site, region etc. This could be an analysis project in itself and could be worthy of publication if done well. It might be something you want to spin off to a student who is interested in analysis, since I think it is non trivial and worthy of some detailed effort.

[edit] Landmark Selection for TULIP

Currently, TULIP selects three landmarks with the minimum RTT values to calculate the geo-location of the target host. However, the hosts with the minimum RTT values may not always be the best choice. Thus we need to formulate an algorithm to determine which would be the best landmarks to be used to determine the geolocation.

[edit] Estimate of Alpha values for TULIP using PingER data

With TULIP we convert the RTT values to distance in order to estimate the location of the target host. These RTT values are influenced by the type of network infrastructure in a region. The mapping of latency to distance in one region may not be the same for other regions. Here we are not only interested in different mechanisms of estimating distances based on delay measurements, but also in considering the fact that the methods of estimation in one region may not be the same for the other.