Datathons Solutions

Datathon Telenor Solution – Exploratory Data & Predictive Analytics -Analogy of Game of Thrones With Telenor Telecommunications

Posted srikanthnarapusetty, balavignesh95, amarnathreddy, saiaditya-g, kabilarasan, liad, theminer, pepe Mentors: drsubhabahapal

->This datasets is regarding the time series analysis on the failure rate of RAVENS sending the messages from kings landing to the north.
It depicts the analogy of Telenor communication  and Game of Thrones.
-> Sending ravens is one of the most fundamental parameters in mobile communications engineering.
For land-based mobile communications, the received raven variation is primarily the result of multipath fading caused by obstacles such as buildings (or clutter) or terrain irregularities; the distance between link end points; predatory animals, and interference among multiple transmissions, for example wars.
This inevitable raven variation is the cause of communication dropping, one of the most significant quality of service measure in operative communication. For this reason, various techniques and schemes are employed in the planning, design and optimization of raven networks to combat these propagation effects.
This normally covers the network physical configuration which include all aspects of network infrastructure deployment such as locations of base nests; additional food; sometimes guards, etc.
A typical example of these schemes and techniques is the use of models for flight prediction based on measured data.
Based on one month data with flight fails, the participants have to make time-series analysis and predict the future amount of fails.

0
votes

Final Submission:-Find the attachments in the above link

Note: Research has been performed on both Python and R programming

The Telenor Case – Flight failures Kings Landing to the North

Abstract:Inrtro

  • Sending ravens is one of the most fundamental parameters in mobile communications engineering.
  • For land-based mobile communications, the received raven variation is primarily the result of multipath fading caused by obstacles such as buildings (or clutter) or terrain irregularities; the distance between link end points; predatory animals, and interference among multiple transmissions, for example wars.
  • This inevitable raven variation is the cause of communication dropping, one of the most significant quality of service measure in operative communication. For this reason, various techniques and schemes are employed in the planning, design and optimization of raven networks to combat these propagation effects.

Problem Statement:

This datasets is regarding the time series analysis on the failure rate of RAVENS sending the messages from kings landing to the north.
This case study is an analogy of Telenor communication  and Game of Thrones

Dataset Dimension Descriptions:

There are 16 columns and 30091754 rows out of which 11 columns are numerical data which resembles the delay in transmission.

Rest of the columns are categorical columns and Date column

Unit Row Defintion:

As per the given dataset each row represents the message that passes through (For land-based mobile communications).

Assumptions:

Failure Instance: Any delay greater than zero (for sum of all the columns or any column greater than zero) is considered as a failure.

Successful Instance: If every column that represents delay has a value, equal to zero then it is considered to be as success.

Analogy between Telenor Communications and Game of Thrones:

Raven:  Raven is considered to be the communication protocol thread/instance which makes communication from kings landing to the north.

I.e. Each thread in the communication refers to the message. If the columns tends to be ‘0’ then it is considered as ‘SUCCESS’

Understanding what are different delays columns:

  • FIRST_GET_RESPONSE_SUCCESS_DELAY: First Get Response Delay measures the time from when a user first interacts with your site (i.e. when they click a link, tap on a button)
  • PAGE_BROWSING_DELAY: Time needed to receive the first byte from the web server when loading a web page
  • TCP_SETUP_TOTAL_DELAY: Time Delay to create a TCP connection to the web server
  • PAGE_CONTENT_DOWNLOAD_TOTAL_DELAY: Total Time delay that had taken place for the connection to download the total content of the page
  • FIRST_DNS_RESPONSE_SUCCESS_DELAY: First response Time delay that had taken while fetching the ip address successfully from the series of DNS servers
  • DNS_RESPONSE_SUCCESS_DELAY: Total response Time delay that had taken while fetching the ip address successfully from the series of DNS servers
  • FIRST_TCP_RESPONSE_SUCCESS_DELAY: Time Delay to get success acknowledgement, once a TCP connection to the web server is created.
  • PAGE_SR_DELAYS: page sender report delay
  • SYN_SYN_DELAY: synchronisation 3 way handshake /acknowledgement delay in the connection
  • TCP_CONNECT_DELAY: total tcp connection delay
  • PAGE_BROWSING_DELAYS: Time delay that had taken place while browsing a page, to downloaded the contents in the page are yet to be downloaded

Rest of the columns Description:

DATETIME: this column consists of date and time stamp of the event.

NETWORK: this column consists which network is used to communicate or the send the message.

RAVEN: This consists of raven name that is used transmit the message.

FAMILY: This consists of the Family Name that is sending the message.

Standard unit followed in these columns is Milliseconds

Steps followed on Tasks:

  1. Top 10 RAVEN with Fail:

– Check, whether the message transmission is success (‘0’)  or  not ( i.e)  if there is no delay in       transmission, then we need to ignore them in order to find the failed records.

-Then group the data by RAVEN_NAME and sort the count in the Descending order

-From the above sorted list, we have taken the top 10 RAVEN_NAME to find the fail count.

  1. Top 10 RAVEN without fail:

-Check, whether the message transmission is success (0) or  not ( i.e)  if there is no delay in       transmission.

-Then group the data by RAVEN_NAME and sort the count in the Descending order

-From the above sorted list, we have taken the top 10 RAVEN_NAME to find the success count.

  1. The Family with the most fails:

-Group the data by FAMILY_NAME, DATETIME and sort the data in descending order

– From the above sorted list, we have taken the top FAMILY_NAME to find the fail count.

  1. The family with the least fails:

-Group the data by FAMILY_NAME, DATETIME and sort the data in Ascending order

– From the above sorted list, we have taken the top FAMILY_NAME to find the Success count.

  1. The family member with most fails:

-Group the data by MEMBER_NAME, DATETIME and sort the data in descending order

– From the above sorted list, we have taken the top MEMBER_NAME to find the fail count.

  1. The family member  with least fails:

-Group the data by MEMBER_NAME, DATETIME and sort the data in ascending order

– From the above sorted list, we have taken the top MEMBER_NAME to find the success count.

 

 

TELENOR-CASE STUDY

Share this

One thought on “Datathon Telenor Solution – Exploratory Data & Predictive Analytics -Analogy of Game of Thrones With Telenor Telecommunications”

  1. 0
    votes

    Hi guys, you’re doing a great work and on the right direction, don’t give up 😉
    Don’t forget to write your results – which MEMBER_NAME, FAMILY_NAME, etc. and will be even nicer if you add some charts and tables/numbers to prove your findings

Leave a Reply