Extension of feature selection with a ML algorithm for wireless network traffic prediction

The release of 5G network in near future will provide reliable connectivity, higher throughput, better service quality, and more efficient signaling. The network traffic load will continuously rise with more and more mobile users using the internet services. There is a need to forecast wireless network traffic load to manage network resources efficiently and provide better quality of service. This network traffic dataset is complex and nonlinear in nature that contains large number of variables. The proposed research will combine the feature selection techniques with an advanced machine learning (ML) method to handle this network traffic dataset, which employing 4 feature selection techniques to extremely reduce the data size with keeping significant features in the dataset, and further result in the increasing of the prediction accuracy for the ML model. The feature selection aids in better prediction accuracy of machine learning algorithm on wireless network traffic with overall interpretability of the prediction model.

Faculty Supervisor:

Wei Peng

Student:

Surya Pusapati

Partner:

Discipline:

Engineering

Sector:

University:

University of Regina

Program:

Accelerate