COMMUNICATION NETWORKS TRAFFIC PREDICTION USING MACHINE LEARNING
The aim of this project was to examine the structure of communication networks and to introduce a data-driven architecture for the practical applications of machine learning techniques to predict data traffic on a network.
Objectives:
-To examine the existing machine learning implementations in communication networks;
-Processing of the dataset to make it easy to use;
-Implementation of machine learning algorithms;
-Evaluation of accuracy.
Dataset: The Telecom Italia Big Data
This dataset provides information about the telecommunication activity over the city of Milan. The dataset is the result of a computation over the Call Detail Records (CDRs) generated by the Telecom Italia cellular network over the city of Milan. CDRs log the user activity for billing purposes and network management.
https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/EGZHFV
Results:
The links for the codes I utilized are below.
http://globec.whoi.edu/software/saga/fillmiss.m
http://www.ee.ic.ac.uk/hp/staff/dmb/voicebox/mdoc/v_mfiles/v_enframe.html