User Mobility Prediction in 5G Networks Using Recurrent Neural Networks

The use of new possibilities introduced by 5G networks also creates new problems and concerns, specifically in the field of user mobility in wireless communication systems. In this paper, the Authors investigate the effectiveness of Recurrent Neural Networks (RNNs) in the mobility prediction context in order to exploit the temporal component in the users movement data for improved prediction performance. To drive this process, the input datasets are obtained from the GeoLife GPS Trajectories dataset, then follow the data pre-processing steps, constructing an LSTM-based RNN model, and using Python with TensorFlow and Keras. From the analyses, we detected that the accomplishment of using LSTM and hybrid RNN-CNN is significant and higher than the traditional approaches of EN, RFM, and CL. The test results demonstrate that the LSTM model can reduce the MAE and RMSE values by 19. 49% and 14. 82%, respectively. However, the execution of these models has some issues that include compute time, instantaneous prediction that is needed in many real-world applications, and case. Such problems can be solved with the help of such approaches as edge computing and distributed processing. Besides, it is pivotal to put measures in place to maintain the confidentiality and security of user information. This paper highlights the applicative potential of RNNs in redesigning user mobility prediction in 5G networks, and thus helping toward a better ownership of the network players and assets.