Authors :
Prof Aarti Sawant, Yash Kumar, Shreya Badia
Volume/Issue :
Volume 6 - 2021, Issue 4 - April
Google Scholar :
http://bitly.ws/9nMw
Scribd :
https://bit.ly/3t7Io6Q
Abstract :
An optimum machine learning model that
used cell tower statistics such as usage, customer count,
etc., was instructed to project the kind of congestion that
might occur. The accuracy of the model was appreciable
and proper measures were taken to make it robust. As
per further analysis carried out with respect to all
possible algorithms like linear regression, support vector
machine and neural network its found that the major
factors causing congestions were byte usage and
subscribers. Hence, vendors should look for beefing up
their hardware’s to serve more subscribers at the same
time with increased byte rate. Also, in case of congestion,
they can come up with a scheme to prioritize network
traffic i.e., giving critical bytes usage like communication
more priority over less critical bytes usage.
Keywords :
Linear Regression, Machine Learning Model Support Vector Machine ,Neural Network, Congestion.
An optimum machine learning model that
used cell tower statistics such as usage, customer count,
etc., was instructed to project the kind of congestion that
might occur. The accuracy of the model was appreciable
and proper measures were taken to make it robust. As
per further analysis carried out with respect to all
possible algorithms like linear regression, support vector
machine and neural network its found that the major
factors causing congestions were byte usage and
subscribers. Hence, vendors should look for beefing up
their hardware’s to serve more subscribers at the same
time with increased byte rate. Also, in case of congestion,
they can come up with a scheme to prioritize network
traffic i.e., giving critical bytes usage like communication
more priority over less critical bytes usage.
Keywords :
Linear Regression, Machine Learning Model Support Vector Machine ,Neural Network, Congestion.
