Ultra-dense network is the key technology of 5G. It provides mobile users with high transmission rates and efficient radio resource management. However, due to the dense deployment of base stations and the small coverage of a single base station in the ultra-dense network, user equipment may have to perform handovers more frequently. The current handover mechanism is more like a “passive handover” triggered by objective conditions. So frequent handover may degrade the user experience and affect the overall performance of the network. Therefore, it is necessary to predict the trajectory of the mobile user, and then take the prediction results into account to perform a more positive and intelligent handover. In response to this problem, in this paper, we propose an LSTM model that can predict a mobile user’s next location based on his historical trajectory and which cell he should connect to at the next moment. We use real mobile user trajectory data for training and testing. Reassuringly, it is best to achieve a prediction accuracy of 92.155% in the scenario we assumed.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Mobile User Trajectory Prediction Based on Machine Learning


    Contributors:
    Liu, Ya (author) / Yang, Hongwen (author) / Huang, Rui (author)


    Publication date :

    2022-06-01


    Size :

    1600243 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Poster: Mobile Gossip Learning for Trajectory Prediction

    Dinani, Mina Aghaei / Holzer, Adrian / Nguyen, Hung et al. | IEEE | 2020


    A Machine Learning Approach to Trajectory Prediction

    de Leege, Arjen / van Paassen, Marinus / Mulder, Max | AIAA | 2013


    Vehicle trajectory prediction through manual setting and machine learning

    Liu, Xinyu / Jiang, Ruixuan / Nie, Yulong et al. | VDE-Verlag | 2022


    Trajectory Flight-Time Prediction based on Machine Learning for Unmanned Traffic Management

    Conte, Claudia / Accardo, Domenico / Rufino, Giancarlo | IEEE | 2020