中国邮电高校学报(英文) ›› 2019, Vol. 26 ›› Issue (3): 15-21.doi: 10.19682/j.cnki.1005-8885.2019.0018

• Wireless • 上一篇    下一篇

Hierarchical mobility prediction in the future heterogeneous networks for the tradeoff between accuracy and complexity

刘振亚1,李曦1,纪红2,张鹤立1   

  1. 1. 北京邮电大学
    2. 北邮199信箱
  • 收稿日期:2018-07-03 修回日期:2019-04-12 出版日期:2019-06-30 发布日期:2019-06-30
  • 通讯作者: 刘振亚 E-mail:liuzhenya@bupt.edu.cn
  • 基金资助:
    This work was supported by the National Science and Technology Major Project of China (2017ZX03001014) and the National Natural Science Foundation of China (61771070).

Hierarchical mobility prediction in the future heterogeneous networks for the tradeoff between accuracy and complexity

Zhen-Ya LIUXi LI 2,Zhang Heli   

  • Received:2018-07-03 Revised:2019-04-12 Online:2019-06-30 Published:2019-06-30
  • Contact: Zhen-Ya LIU E-mail:liuzhenya@bupt.edu.cn

摘要: Mobility prediction is one of the promising technologies for improving quality of service (QoS) and network resource utilization. In future heterogeneous networks (HetNets), the network topology will become extremely complicated due to the widespread deployment of different types of small-cell base stations (SBSs). For this complex network topology, traditional mobility prediction methods may cost unacceptable overhead to maintain high prediction accuracy. This problem is studied in this paper, and the hierarchical mobility prediction scheme (HMPS) is proposed for the future HetNets. By dividing the entire process into two prediction stages with different granularity, the tradeoff between prediction accuracy and computation complexity is investigated. Before performing prediction of user mobility, some frequently visited locations are identified from the user’s trajectory, and each location represents an important geographic area (IGA). In the coarse-grained prediction phase, the next most possible location to be visited is predicted at the level of the possible geographic areas by using a second-order Markov chain with fallback. Then, the fine-grained prediction of user position is performed based on hidden Markov model (HMM) from temporal and spacial dimensions. Simulation results demonstrate that, compared with the existing prediction methods, the proposed HMPS can achieve a good compromise between prediction accuracy and complexity.

关键词: mobility prediction, heterogeneous networks, prediction accuracy and complexity, Markov chain, HMM

Abstract: Mobility prediction is one of the promising technologies for improving quality of service (QoS) and network resource utilization. In future heterogeneous networks (HetNets), the network topology will become extremely complicated due to the widespread deployment of different types of small-cell base stations (SBSs). For this complex network topology, traditional mobility prediction methods may cost unacceptable overhead to maintain high prediction accuracy. This problem is studied in this paper, and the hierarchical mobility prediction scheme (HMPS) is proposed for the future HetNets. By dividing the entire process into two prediction stages with different granularity, the tradeoff between prediction accuracy and computation complexity is investigated. Before performing prediction of user mobility, some frequently visited locations are identified from the user’s trajectory, and each location represents an important geographic area (IGA). In the coarse-grained prediction phase, the next most possible location to be visited is predicted at the level of the possible geographic areas by using a second-order Markov chain with fallback. Then, the fine-grained prediction of user position is performed based on hidden Markov model (HMM) from temporal and spacial dimensions. Simulation results demonstrate that, compared with the existing prediction methods, the proposed HMPS can achieve a good compromise between prediction accuracy and complexity.

Key words: mobility prediction, heterogeneous networks, prediction accuracy and complexity, Markov chain, HMM