Reducing the singling overhead for tracking and mobile paging devices is a challenging issue in the study of location management of cellular networks. Cellular networks have become massive generators of data, and in the forthcoming years, this data is expected to increase drastically. Big data-based intelligence and analytics can improve network operational efficiency and user service quality. This work proposes to exploit massive handover and paging data from cellular networks to minimize singling due to user mobility. In this paper, we offer a new holistic tracking area lists (TAL) management methodology, considering group user mobility behavior and paging characteristics. Firstly, a series of graphs showing the evolution of user mobility and traffic is built from handover and paging statistics in the network management system (NMS). Then, the TAL allocation problem is formulated as a classical graph partitioning problem, which is then solved by detecting overlapping communities algorithm based on game theory. Results show that the proposed method can effectively reduce the location management singling overhead and improve the TAL configuration efficiency.

在蜂窝网络的位置管理研究中，减少跟踪和移动寻呼设备的单一开销是一个具有挑战性的问题。蜂窝网络已经成为大量的数据生成器，并且在未来几年中，预计该数据将急剧增加。基于大数据的情报和分析可以提高网络运营效率和用户服务质量。这项工作建议利用来自蜂窝网络的大量切换和寻呼数据，以最大程度地减少由于用户移动性而产生的单个事件。在本文中，我们提供了一种新的整体跟踪区域列表（TAL）管理方法，其中考虑了组用户的移动行为和寻呼特征。首先，根据网络管理系统（NMS）中的切换和寻呼统计数据，建立了一系列显示用户移动性和流量演变的图形。然后，TAL分配问题被公式化为经典的图划分问题，然后通过基于博弈论的重叠社区检测算法来解决。结果表明，该方法可以有效减少位置管理的单开销，提高TAL配置效率。