Mobile traffic data in urban regions shows differentiated patterns during
different hours of the day. The exploitation of these patterns enables highly
accurate mobile traffic prediction for proactive network management. However,
recent Deep Learning (DL) driven studies have only exploited spatiotemporal
features and have ignored the geographical correlations, causing high
complexity and erroneous mobile traffic predictions. This paper addresses these
limitations by proposing an enhanced mobile traffic prediction scheme that
combines the clustering strategy of daily mobile traffic peak time and novel
multi Temporal Convolutional Network with a Long Short Term Memory (multi
TCN-LSTM) model. The mobile network cells that exhibit peak traffic during the
same hour of the day are clustered together. Our experiments on large-scale
real-world mobile traffic data show up to 28% performance improvement compared
to state-of-the-art studies, which confirms the efficacy and viability of the
proposed approach.

提出了一种增强型移动流量预测方案，该方案结合了每日移动流量高峰时间的聚类策略和新颖的多时间卷积网络与长短期记忆模型 (multi TCN-LSTM)，实验结果显示与最先进技术相比，性能提升达到 28％，证实了该方法的功效和可行性。

基于区域相关性的时空深度学习辅助移动流量预测

Regional Correlation Aided Mobile Traffic Prediction with Spatiotemporal  Deep Learning

Mobile traffic prediction is of great importance on the path of enabling 5G
mobile networks to perform smart and efficient infrastructure planning and
management. However, available data are limited to base station logging
information. Hence, training methods for generating high-quality predictions
that can generalize to new observations on different parties are in demand.
Traditional approaches require collecting measurements from different base
stations and sending them to a central entity, followed by performing machine
learning operations using the received data. The dissemination of local
observations raises privacy, confidentiality, and performance concerns,
hindering the applicability of machine learning techniques. Various distributed
learning methods have been proposed to address this issue, but their
application to traffic prediction has yet to be explored. In this work, we
study the effectiveness of federated learning applied to raw base station
aggregated LTE data for time-series forecasting. We evaluate one-step
predictions using 5 different neural network architectures trained with a
federated setting on non-iid data. The presented algorithms have been submitted
to the Global Federated Traffic Prediction for 5G and Beyond Challenge. Our
results show that the learning architectures adapted to the federated setting
achieve equivalent prediction error to the centralized setting, pre-processing
techniques on base stations lead to higher forecasting accuracy, while
state-of-the-art aggregators do not outperform simple approaches.

本文研究联邦学习应用于基站聚合 LTE 数据的时序预测的有效性。我们使用 5 种不同的神经网络架构在联邦设置下进行一步预测，结果表明：适应联邦设置的学习架构与集中式设置具有相当的预测误差，基站的预处理技术导致更高的预测准确性，而现代聚合器并不比简单的方法好。