The intense demands for higher data rates and ubiquitous network coverage have raised the stakes on developing new network topologies and architectures to meet these ever-increasing demands in a cost-effective manner. The telecommunication industry and international standardization bodies have placed considerable attention on the deployment of ultra-dense heterogeneous small-scale cells over existing cellular systems. Those small-scale cells, although they provide higher data rates and better indoor coverage by reducing the distance between BSs and end users, have raised severe configuration concerns. As the deployments are becoming irregular and flexible, inappropriate configurations occur frequently and undermine the network reliability and service quality. We envision that the fine-grained characterization of user traffic is a key pillar to diagnosing inappropriate configurations. In this article, we investigate the fine-grained traffic patterns of mobile users by analyzing the network data containing millions of subscribers and covering thousands of cells in a large metropolitan area. We characterize traffic patterns and mobility behaviors of users and geospatial properties of cells, and discuss how the heterogeneity of these characteristics affects network configurations and diagnosis in future ultra-dense small cells. Based on these observations from our measurements, we investigate possible models and corresponding challenges, and propose a heterogeneity-aware scheme that takes into account the disparity of user mobility behaviors and geospatial properties among small cells.

中文翻译：

---

超密集异构网络的配置和诊断：从经验测量到技术解决方案

对更高数据速率和无处不在的网络覆盖范围的强烈需求使开发新的网络拓扑和体系结构以符合成本效益的方式满足这些不断增长的需求的风险增加了。电信行业和国际标准化机构已将相当多的注意力放在了现有蜂窝系统上超密集异构小规模小区的部署上。这些小型小区虽然通过减少BS与最终用户之间的距离来提供更高的数据速率和更好的室内覆盖，却引起了严重的配置问题。随着部署变得不规则和灵活，不适当的配置经常发生，并破坏了网络的可靠性和服务质量。我们设想用户流量的细粒度表征是诊断不适当配置的关键支柱。在本文中，我们将通过分析包含数百万个订户并覆盖大都市圈中数千个小区的网络数据来研究移动用户的细粒度流量模式。我们表征了用户的流量模式和移动行为以及小区的地理空间特性，并讨论了这些特性的异质性如何影响未来超密集小型小区的网络配置和诊断。基于我们的测量中的这些观察，我们研究了可能的模型和相应的挑战，并提出了一种异构感知方案，该方案考虑了用户移动行为的差异和小型小区之间的地理空间特性。