A deep learning-based model for High-Speed Users’ Mobility Prediction in Small Cell and Femtocell Networks

Abstract

Users’ mobility has a huge impact on the performance of cellular networks. Particularly in the networks which are deployed with small cells, by predicting the next positions of the users, it can determine the nearby cells to the users before they arrive and prepare the connection, and estimate the mobile resources for them. In this paper, we proposed a model to predict the users' next location based on Recurrent Neural Network (RNN) with Long-Short Term Memory (LSTM) cell, a Deep learning neural network. We use Simulation of Urban MObility (SUMO) to create our own users’ trajectory datasets to train and test the models. To prove the effectiveness of the model, we compare its performance with Deep Neural Network (DNN), and Gated Recurrent Unit (GRU) models, Baseline model (BL), and Linear regression model (LR).