Applying Machine Learning to LTE Traffic Prediction: Comparison of Bagging, Random Forest, and SVM
Nikolai Stepanov, Daria Alekseeva, Aleksandr Ometov, Elena Simona Lohan
Abstract
Today, a significant share of smartphone applications use Artificial Intelligence (AI) elements that, in turn, are based on Machine Learning (ML) principles. Particularly, ML is also applied to the Edge paradigm aiming to predict and optimize the network load conventionally caused by human-based traffic, which is growing each year rapidly. The application of both standard and deep ML techniques is expected to improve the networks' operation in the most complex heterogeneous environment. In this work, we propose a method to predict the LTE network edge traffic by utilizing various ML techniques. The analysis is based on the public cellular traffic dataset, and it presents a comparison of the quality metrics. The Support Vector Machines method allows much faster training than the Bagging and Random Forest that operate well with a mixture of numerical and categorical features.