Page History

...

• Membership of pinger-my in https://groups.google.com

• We are working with Dr Zaidi the new head of SEECS to investigate resources need to continue support of PingER in Pakistan. We communicated first week in August. No word since. Sent a reminder 8/1/2015. We had a rump meeting of Anjum, Hassaan and Les after the previous meeting to discuss the way forward. Hassaan is waiting to hear from HEC about the comments on the proposal. Any Update?

• NETAPPS2015: 
  

  • All four papers were accepted.

  • Thiago has updated the Data Warehouse submission: 

    • Working out details of funding the registration, whether Thiago can be online to answer questions and who will present it.

• 9 students from Amity University near New Delhi in India interested in coming to SLAC for 3 months starting Feb until May. All expenses paid by them.

  • SLAC putting together document on proposed projects, skills needs, setting up chat group

• Joao a Brazillian student identified by Renan is interested in a 3 month internship at SLAC similar to those accomplished by Renan and Thiago.  SLAC we are in communication and he has the a list of what is needed.

• Needed to move this meeting  30 minutes earlier in future to accommodate Johari's schedule. Is this ongoing?

Geolocation Anjum, 

• Anjum believes the TULIP Geolocation application  can be improved significantly. At least there are few ideas that we can try. For this, either a group of undergraduate students or an active masters student is required. The resultant work can easily be the thesis of masters level. Who is interested? 

  • Saqib at Faisalabad has an MS student interested to work on Geolocation project. He requests an initial  paper on the project.  Les has responded to Saqib. He also has some other students. Anjum will contact him. Potential projects/asks include: take over management of PingER monitoring in Pakistan (say 5 monitors/student; case study of how Pakistan's network performance/connectivity has improved over thea years especially as function of funding etc;  geolocation with variable alpha; indoor geolocation

  • Johari will contact Anjum to learn more of the requirements. Update Johari/Adnan

  • See http://www.slac.stanford.edu/comp/net/tulip/. Basically TULIP uses pings to a target from landmarks at known locations and converts the minimum RTTs to estimate the distances. Then uses the distances with mulitlateration to estimate the location of the target

  • To improve TULIP one needs the right selection of landmarks, i.e. good (working landmarks) at the right locations (not too far from the target), straddling the target, and with a a reasonable estimate of the indirectness (directivity or alpha) of the path from the landmark to the target (so we can reasonably accurately estimate the distance). One also needs a reasonable density of landmarks (e.g. number of targets/100,000sq km)

  • The landmarks come from PingER and perfSONAR sites.  We have a reasonable density in the US, Pakistan and Europe. Currently Anjum is getting better than 20km accuracy for Pakistani targets

  • As the number of landmarks goes up so does the accuracy, but so does the time to make the measurements (pings). 

  • One needs to find the optimal density

  • Anjum proposes to speed up the measurements using a cluster for parallelization and also proposes to improve the adaptation of alpha based region. He regards the adaptive geolocation and parallelization as  MS projects. 

  • He is also interested in geolocation in small proximity (e.g.indoors), e.g. using cell tower signals. This is a new area of research. It is possible that the port of PingER to an Android could  be related to this. This is a PhD project

  • Anjum reports he can supervise the students on Geolocation. He will need to know when the students are ready. We can start with a joint meeting involving Les and the students. Later on, Anjum can have the meeting with students every week while Les can join if he has time.

Android - Bebo

• Bebo said Topher would be interested in getting a student to port PingER to an Android. Possibly one of the Indian students. Les put out a version of the PingER MA on Github at https://github.com/iepm/ in 2013 as part of coordinating with Google( which did not get very far). It has been dormant since it was put out there. Les is not a github expert or user so is  unclear how complete it is or who can access it.   Can somebody test and if not available let Les know what to do. 

• Topher  is at home for 2 weeks, he will set up a shareable Github for PingER files. Any progress

Saqib

Saqib has submitted a project with title "A Fundamental Active Internet Performance Monitoring Framework for Pakistan Education & Research Network (PERN) in University of Agriculture, Faisalabad"

• Funding source will accept the projects if it is designed for the development of Agriculture in the University.
• Objective: The active internet performance monitoring framework for the University of   Agriculture, Faisalabad helps in forecasting and detecting the events that cause bottleneck links in the network affecting the overall performance of the University of   Agriculture, Faisalabad.
• Initially the project is accepted. However, I received the following comment
• The PI was advised to include in the project the justification how it will have an impact on agriculture development in the University of Agriculture Faisalabad Pakistan. 
• For justification I have added the following paragraph:
• The aim of this project is to provide the performance analysis and anomaly detection framework for the University of Agriculture, Faisalabad  in order to detect the events that cause bottleneck links in the network affecting the overall performance of the University. Further, It will help to improve the performance of the web applications running in the university.
• Les added: 

  • Internet connectivity is critical to agriculture, especially since agriculture is usually conducted in rural and possibly remote areas. In particular it enables farmers to ascertain the optimum prices for seeds, fertilizers at, the most promising markets etc for their goods, upcoming weather conditions, forecasting yields, providing information for addressing challenges etc. It also supports timely sharing of information between farmers, their customers, and learning of new relevant developments from research and industrial centers such as the universities. This is very important since the adoption of new technologies has always been an important factor in agricultural productivity. See http://pnwsteep.wsu.edu/directseed/conf2k5/pdf/gillis.pdf

     

    Understanding the Internet performance between the University of Agriculture and other areas of Pakistan will enable setting up: information centers at Faisalabad, outreach to agricultural communities (e.g. by social tools etc.),  by setting realistic expectations for connectivity and hence capabilities to various regions of Pakistan for email, web, chat rooms, data sharing etc.

UUM

Fatima  implemented her work (involving HDFS and MapReduce with Pinger Data) on 50MB to 200MB data sets, using a 2-node cluster, and then a 3-node cluster. The work is not completed, but she has obtained some good results and is putting together the presentation for her final viva. She and Ibrahim are using the same cloud/cluster at MYREN.

UM

Ibrahim has extracted the  PingER Zip manually. He is reconstructing 11Gb of data, heas 15GBytes of data there. He is trying to use SPAR to classify the data. He alsop was looking at RDF. the next step si to use MapReduce to organize and reduce the output of dataso can vizualize it. He will be using a teh same techniques he used for looking at 1996-2006 weather data. 

UNIMAS

UTM

Johari will contact Hanan to request someone to support PingER at UTM, now Saqib has left. Johari will try dean to get a replacement for Saqib. However the Dean is new so Johari wants to gather some information first.

 Saqib

Has a student  interested to work on Hadoop and pinger data. Les has sent him information on the SLAC Nebula cluster Cloudera/impala/HDFS Pinger Data warehouse dedveloped by Thiago and Co.

Further he has a few more MS students searching for their research topics. We can also utilize them in our pinger project. They are from software engineering, database and network background. 

MYREN

No update 8/12/2015, no Update 9/2/2015. 

perfsonar-unimas.myren.net.my is back up and running

We have been unable to gather data from pingersonar-utm.myren.net.my  since September 11th, 2015 pingersonar-utm.myren.net.my. It is pingable  however there is no response from http://pingersonar-utm.myren.net.my/cgi-bin/traceroute.pl?function=ping&target=www-wanmon.slac.stanford.edu&options=-i%200.2

NUST

Following the last meeting, Anjum, Hassaan and Les met to discuss the way forward. 

• "Adnan currently is unable to find resources for handling the project. Similarly, there is no progress on hiring of a full time RA by NUST HQ. 
• However, I (Hassaan) checked from HEC about the proposal that I submitted last year. They have informed me that 2 reviewers have asked for revisions while they are waiting for the third review. I am very hopeful about it. If the proposal is accepted then we can easily have a full time RA for the project. I have plans to talk to Dr. Zaidi about hiring an RA on assuming that our proposal will be accepted by HEC. We can then get his salary deducted later from the HEC project. I shall update you very soon in this regard." 

• Hassaan is  waiting to hear from HEC about the comments on the proposal. 

• Moreover, he has asked a student to work on the project for the time being. His name is Mian Anas however he will need few weeks to understand the project. 

PingER at SLAC

• Thiago completed setting up the  PingER data SQL Impala warehouse running on a Nebula/Cloudera cluster using the Hadoop File System (HDFS). Unfortunately it is not currently accessible from outside SLAC. There have been several attempts to provide outside access, but no success yet, we need to engage the subject matter experts. Thiago is now a SLAC associate so he still has an account at SLAC. There was a cyber security alert on the version of java installed with Cloudera. Les has replaced the cloudera version of java which should fix the vulnerability. However the new version has not been tested.

Working on the following hosts to be able to gather data 

Next Meeting

Next meeting:  Wednesday Dec  2nd 7:30pm Pacific Standard Time, Thursday Dec 3rd 2015  8:30am Pakistan time, Thursday Dec 3rd  2015 11:30am  Malaysian time, Thursday Dec 3rd 2015 01:30 am Rio Standard Time.  

...

• This is a proposed project for one of the Indian students.

Android - Bebo

• Bebo said Topher would be interested in getting a student to port PingER to an Android. Possibly one of the Indian students. Les put out a version of the PingER MA on Github at https://github.com/iepm/ in 2013 as part of coordinating with Google( which did not get very far). It has been dormant since it was put out there. Les is not a github expert or user so is  unclear how complete it is or who can access it.   Can somebody test and if not available let Les know what to do. 

• Topher  is at home for 2 weeks, he will set up a shareable Github for PingER files. Any progress

Saqib

Saqib has submitted a project with title "A Fundamental Active Internet Performance Monitoring Framework for Pakistan Education & Research Network (PERN) in University of Agriculture, Faisalabad"

• Funding source will accept the projects if it is designed for the development of Agriculture in the University.
• Objective: The active internet performance monitoring framework for the University of   Agriculture, Faisalabad helps in forecasting and detecting the events that cause bottleneck links in the network affecting the overall performance of the University of   Agriculture, Faisalabad.
• Initially the project is accepted. However, I received the following comment
• The PI was advised to include in the project the justification how it will have an impact on agriculture development in the University of Agriculture Faisalabad Pakistan. 
• For justification I have added the following paragraph:
• The aim of this project is to provide the performance analysis and anomaly detection framework for the University of Agriculture, Faisalabad  in order to detect the events that cause bottleneck links in the network affecting the overall performance of the University. Further, It will help to improve the performance of the web applications running in the university.
• Les added: 

  • Internet connectivity is critical to agriculture, especially since agriculture is usually conducted in rural and possibly remote areas. In particular it enables farmers to ascertain the optimum prices for seeds, fertilizers at, the most promising markets etc for their goods, upcoming weather conditions, forecasting yields, providing information for addressing challenges etc. It also supports timely sharing of information between farmers, their customers, and learning of new relevant developments from research and industrial centers such as the universities. This is very important since the adoption of new technologies has always been an important factor in agricultural productivity. See http://pnwsteep.wsu.edu/directseed/conf2k5/pdf/gillis.pdf

     

    Understanding the Internet performance between the University of Agriculture and other areas of Pakistan will enable setting up: information centers at Faisalabad, outreach to agricultural communities (e.g. by social tools etc.),  by setting realistic expectations for connectivity and hence capabilities to various regions of Pakistan for email, web, chat rooms, data sharing etc.

UUM

Fatima  implemented her work (involving HDFS and MapReduce with Pinger Data) on 50MB to 200MB data sets, using a 2-node cluster, and then a 3-node cluster. The work is not completed, but she has obtained some good results and is putting together the presentation for her final viva. She and Ibrahim are using the same cloud/cluster at MYREN.

UM

Ibrahim has extracted the  PingER Zip manually. He is reconstructing 11Gb of data, heas 15GBytes of data there. He is trying to use SPAR to classify the data. He alsop was looking at RDF. the next step si to use MapReduce to organize and reduce the output of dataso can vizualize it. He will be using a teh same techniques he used for looking at 1996-2006 weather data. 

UNIMAS

UTM

Johari will contact Hanan to request someone to support PingER at UTM, now Saqib has left. Johari will try dean to get a replacement for Saqib. However the Dean is new so Johari wants to gather some information first.

 Saqib

Has a student  interested to work on Hadoop and pinger data. Les has sent him information on the SLAC Nebula cluster Cloudera/impala/HDFS Pinger Data warehouse dedveloped by Thiago and Co.

Further he has a few more MS students searching for their research topics. We can also utilize them in our pinger project. They are from software engineering, database and network background. 

MYREN

No update 8/12/2015, no Update 9/2/2015. 

perfsonar-unimas.myren.net.my is back up and running

We have been unable to gather data from pingersonar-utm.myren.net.my  since September 11th, 2015 pingersonar-utm.myren.net.my. It is pingable  however there is no response from http://pingersonar-utm.myren.net.my/cgi-bin/traceroute.pl?function=ping&target=www-wanmon.slac.stanford.edu&options=-i%200.2

NUST

Following the last meeting, Anjum, Hassaan and Les met to discuss the way forward. 

• "Adnan currently is unable to find resources for handling the project. Similarly, there is no progress on hiring of a full time RA by NUST HQ. 
• However, I (Hassaan) checked from HEC about the proposal that I submitted last year. They have informed me that 2 reviewers have asked for revisions while they are waiting for the third review. I am very hopeful about it. If the proposal is accepted then we can easily have a full time RA for the project. I have plans to talk to Dr. Zaidi about hiring an RA on assuming that our proposal will be accepted by HEC. We can then get his salary deducted later from the HEC project. I shall update you very soon in this regard." 

• Hassaan is  waiting to hear from HEC about the comments on the proposal. 

• Moreover, he has asked a student to work on the project for the time being. His name is Mian Anas however he will need few weeks to understand the project. 

PingER at SLAC

• Thiago completed setting up the  PingER data SQL Impala warehouse running on a Nebula/Cloudera cluster using the Hadoop File System (HDFS). Unfortunately it is not currently accessible from outside SLAC. There have been several attempts to provide outside access, but no success yet, we need to engage the subject matter experts. Thiago is now a SLAC associate so he still has an account at SLAC. There was a cyber security alert on the version of java installed with Cloudera. Les has replaced the cloudera version of java which should fix the vulnerability. However the new version has not been tested.

Working on the following hosts to be able to gather data 

Next Meeting

Next meeting:  Wednesday Dec  2nd 7:30pm Pacific Standard Time, Thursday Dec 3rd 2015  8:30am Pakistan time, Thursday Dec 3rd  2015 11:30am  Malaysian time, Thursday Dec 3rd 2015 01:30 am Rio Standard Time.  

Old Items

Geolocation

Anjum believes the TULIP Geolocation application  can be improved significantly. At least there are few ideas that we can try. For this, either a group of undergraduate students or an active masters student is required. The resultant work can easily be the thesis of masters level. Who is interested? 

• Saqib at Faisalabad has an MS student interested to work on Geolocation project. He requests an initial  paper on the project.  Les has responded to Saqib. He also has some other students. Anjum will contact him. Potential projects/asks include: take over management of PingER monitoring in Pakistan (say 5 monitors/student; case study of how Pakistan's network performance/connectivity has improved over thea years especially as function of funding etc;  geolocation with variable alpha; indoor geolocation

• Johari will contact Anjum to learn more of the requirements. Update Johari/Adnan

• See http://www.slac.stanford.edu/comp/net/tulip/. Basically TULIP uses pings to a target from landmarks at known locations and converts the minimum RTTs to estimate the distances. Then uses the distances with mulitlateration to estimate the location of the target

• To improve TULIP one needs the right selection of landmarks, i.e. good (working landmarks) at the right locations (not too far from the target), straddling the target, and with a a reasonable estimate of the indirectness (directivity or alpha) of the path from the landmark to the target (so we can reasonably accurately estimate the distance). One also needs a reasonable density of landmarks (e.g. number of targets/100,000sq km)

• The landmarks come from PingER and perfSONAR sites.  We have a reasonable density in the US, Pakistan and Europe. Currently Anjum is getting better than 20km accuracy for Pakistani targets

• As the number of landmarks goes up so does the accuracy, but so does the time to make the measurements (pings). 

• One needs to find the optimal density

• Anjum proposes to speed up the measurements using a cluster for parallelization and also proposes to improve the adaptation of alpha based region. He regards the adaptive geolocation and parallelization as  MS projects. 

• He is also interested in geolocation in small proximity (e.g.indoors), e.g. using cell tower signals. This is a new area of research. It is possible that the port of PingER to an Android could  be related to this. This is a PhD project

• Anjum reports he can supervise the students on Geolocation. He will need to know when the students are ready. We can start with a joint meeting involving Les and the students. Later on, Anjum can have the meeting with students every week while Les can join if he has time.

NUST/SEECS Pakistani PingER nodes status

...