This paper focuses on predicting downlink (DL) traffic volume in mobile networks while minimizing overprovisioning and meeting a given service-level agreement (SLA) violation rate. We present a multivariate, multi-step, and SLA-driven approach that incorporates 20 different radio access network (RAN) features, a custom feature set based on peak traffic hours, and handover-based clustering to leverage the spatiotemporal effects. In addition, we propose a custom loss function that ensures the SLA violation rate constraint is satisfied while minimizing overprovisioning. We also perform multi-step prediction up to 24 steps ahead and evaluate performance under both single-step and multi-step prediction conditions. Our study makes several contributions, including the analysis of RAN features, the custom feature set design, a custom loss function, and a parametric method to satisfy SLA constraints.
翻译:本文旨在预测移动网络中的下行(DL)流量,并最大程度地减少超额配置并满足给定的服务级别协议(SLA)违规率。我们提出了一种多元、多步和基于SLA驱动的方法,其中包括20种不同的无线电接入网络(RAN)特征,基于高峰交通时间的自定义特征集,并利用基于切换的聚类来利用时空效应。此外,我们提出了一种自定义损失函数,确保满足SLA违规率限制的同时最小化超额配置。我们还进行了多步预测,最多可以预测24步,并评估在单步和多步预测条件下的性能。我们的研究做出了多种贡献,包括RAN特征分析,自定义特征集设计,自定义损失函数以及满足SLA约束的参数方法。