Centre for Applied Network Research takes its inspiration from PingER, IEPM and NLANR

e.g. anomaly detection   

Following are brief descriptions of selected projects conducted under MAGGIE - Measurement and Analysis of the Global Grid and Internet End-to-End Performance.

Legend

Project Details Project Details Project Details Documentation Project Details Executables / Binaries Project Details Source Code

 

TULIP - Trilateration Utility for Locating IP Addresses

TULIP is a Java application being developed by the MAGGIE-NS team from the National University of Sciences and Technology (NUST) Institute of Information Technology (NIIT) and the Stanford Linear Accelerator Center (SLAC) Internet End-to-end Performance Monitoring (IEPM) project. TULIP's purpose is to geolocate a specified target host (identified by IP name or address) using ping RTT delay measurements to the target from reference landmark hosts whose positions are well known. Knowing the speed of light in fiber or copper (roughly 0.6*c, we use 1ms. is equivalent to 100km), the minimum ping RTT measurement from each landmark site gives a rough estimate of the fibre + copper cable distance of the landmark from the target host. Lateration is applied on these distance estimates to estimate the position of the specified host on the globe.

ViPER - Visualization for PingER

ViPER (Visualization for PingER) is an interactive Java application being developed by the MAGGIE-NS team from the National University of Sciences and Technology (NUST) Institute of Information Technology (NIIT) and the Stanford Linear Accelerator Center (SLAC) Internet End-to-end Performance Monitoring (IEPM) project. ViPER's purpose is to visually present the location of all the PingER nodes on the world map, show links between PingER Monitoring and Remote nodes and provide visual representation of all the data monitored by PingER.

Federation - SmokePing PingER Integration

The main goals of this project are to build a federation of measurement infrastructures so that latency measurements (historical and recent) can be shared, best practices among several measurement infrastructures can be adopted, the need for sites to deploy multiple infrastructures to gain all the available benefits be reduced and different analysis and visualization techniques be applied to yield more ubiquitous coverage and new insights. This project "Federation-SmokePing, PingER Integration" serves the main 'MAGGIE Project' and deals with the integration of two network latency measurement tools namely SmokePing and PingER. The objectives of the project include:

  1. Study and evaluate SmokePing and PingER to understand how they work, and their pros and cons.
  2. Extend the capability of SmokePing to derive parameters/metrics not currently supported such as ping unreachability, jitter, derived TCP throughput, etc.
  3. Provide the ability to select and visualize these new metrics. Feed the modifications to SmokePing back into the development base.
  4. Modify PingER to enable it to utilize the SmokePing time series visualization tool.
  5. Evaluate and provide the ability to feed SmokePing data to the Pinger analysis/visualization toolkit, so we can use the PingER aggregation techniques to characterize performance by regions, or affinity groups.

Network Weather Forecasting

Distributed applications are increasingly dependant on the reliability and performance of networks. This issue is prominent over international collaborations. Computer networks often suffer with sudden change in performance due to various reasons. The current approach of network measurement and diagnosis is generally reactive by manually viewing graphs and tables of analyzed measures and results. We assume that an automated approach to forecast and detect events can serve network engineers and administrators better to identify network problems. Thus we aim to forecast values of network performance into future with reasonable confidence by employing techniques of autoregressive moving average (ARMA) models, sometimes called Box-Jenkins models (ARMA).

Toplogical Analysis and Network Performance Visualization

The project is to contribute to production software packages that will facilitate the identification of network performance scheduling , monitoring, event detection and visualization. In particular, PathNeck (an opensource tool developed jointly by AT&T and CMU ) has been identified as a useful network monitoring tool that we wish to implement and extrapolate information from. It combines traceroute information with throughput information from packet train deductions.

 

Anomaly Detection and (Event) Diagnosis

Event Diagnosis is the next step after Event Detection. IEPM group has established a large infrastruture for network performance measurment all over the world. This infrasture provides near real time network performance related data. IEPM group has developed analysis techniques and tools that detect drop in performance. Event Diagnosis project is aimed at finding out the cause of performance drop. So it is a sub-system under IEPM-BW being developed over Event Detection. Current work is being carried out by a team of researchers at SLAC but given the nature and evident benfits of project it is expected to expand quickly.

Netflow Presentation Frontend

To develop, test and document a flexible web based frontend for the netflow data. This will involve expanding and developing new code to improve the API and performance of the existing perl/cgi server side scripts and the client end javascripts.

The server side code is primarily a means to dynamically gather and present base components of the frontend; for example to display the statistics of from the BNL site to say SLAC. Much work needs to be conducted to expand the presentation consistency and to iron the bugs in the implementation.

Using the above prototype as a framework, learn and use AJAX technologies and methodologies to improve the user experience of the netflow visualisation and offer suggestions of how to better represent the netflow data.

 

Image

PingER Route Visualizer using Traceroutes

Visualizing topology graphs can be very useful for seeing and demonstrating how direct or indirect routing is between countries (often routing between countries close to one another in developing regions can go via Europe or the US). It is also useful to discover hosts whose location is not properly known. This script generates topology graphs of traceroute data of a particular region/group of countries in the Guthrie database.

Image

PingER Host Searcher

Increasing the coverage of PingER in developing countries has been difficult so far because it is hard to find hosts which are geographically located within those countries and do not block pings. The usual method of searching for hosts on Google using the top level domain of such countries has proven to be tedious and time consuming task. The PingER host searcher is an attempt to solve this problem.

Image

PerfSONAR Visualization

PerfSONAR is a distributed network monitoring protocol that utilises the power of XML and Web-services. In this realm, it is very important that network managers and users can get a feel for the data that the the services provide.

This project focusses on developing advanced visualisation tools that will leverage the power of PerfSONAR such that Network Operation Centers, Network Managers and others can quickly, efficiently and logically drill down to understand network performances etc.

Image

AMP PingER Integration

This project aims to develop a script that allows the conversion of AMP data to PingER and vice versa. This is to faciliate analysis that may be performed using tools developed for either of the formats.

Image

Web based visualization for PingER

This project deals with the visualization of PingER monitoring, These sites are mapped as circles on a world map according to their latitude and longitude values, when any of the them is clicked a webpage showing the detailed information about the node is dynamically generated using the script dbprac.pl. Green circles represent remote sites,blue sites represent beacon sites and red circles represent monitoring sites.

Documentation

Image

PingER Executive Plots

The aim of this project is to create long-term summary plots of PingER historical data. These plots may be bar charts, line charts or trend line charts of PingER data overtime

The PingER project has been gathering historical data for various countries/regions for over 7 years. There was a need to design a software which could provide summary plots of this data. These plots need to be dynamic and adjustable in order to enable the user to analyze the data as he desires. In addition the software must be extendable to include new capabilities and functionalities as required. The software developed has been categorized into loss-quality and trendlines.

Documentation Loss Quality Trendlines

Image

PingER Management

The aim of the PingER management project is to create an application, that can automatically test the pingER software and report errors to the administrators.

Documentation Binary - Executable