论文标题
5G长期和大规模移动流量预测
5G Long-Term and Large-Scale Mobile Traffic Forecasting
论文作者
论文摘要
对于服务提供商来说，要在大规模的蜂窝网络中理解和预测移动流量至关重要，以便管理和管理基本站放置，负载平衡和网络计划的机制。本文的目的是从已安装在不同大都市地区的14,000多个牢房中提取和模拟交通模式。为此，我们创建，实现和评估一种方法，其中首先根据其感兴趣的点对细胞进行分类，然后根据每个区域中细胞的时间分布进行聚类。提出的模型已使用现实世界中的5G移动流量数据集进行了测试，该数据集在各个城市中收集了31周内。我们发现，我们提出的模型在预测移动流量模式方面表现良好，最多提前2周。我们的模型在大多数感兴趣领域的基础模型都优于基本模型，与幼稚的方法相比，预测误差通常少15％。这表明我们的方法可以有效预测大型蜂窝网络中的移动流量模式。
It is crucial for the service provider to comprehend and forecast mobile traffic in large-scale cellular networks in order to govern and manage mechanisms for base station placement, load balancing, and network planning. The purpose of this article is to extract and simulate traffic patterns from more than 14,000 cells that have been installed in different metropolitan areas. To do this, we create, implement, and assess a method in which cells are first categorized by their point of interest and then clustered based on the temporal distribution of cells in each region. The proposed model has been tested using real-world 5G mobile traffic datasets collected over 31 weeks in various cities. We found that our proposed model performed well in predicting mobile traffic patterns up to 2 weeks in advance. Our model outperformed the base model in most areas of interest and generally achieved up to 15\% less prediction error compared to the naïve approach. This indicates that our approach is effective in predicting mobile traffic patterns in large-scale cellular networks.
