5G is expected to provide network connectivity to not only classical devices (i.e., tablets, smartphones, etc.) but also to the IoT, which will drastically increase the traffic load carried over the network. 5G will mainly rely on NFV and SDN to build flexible and on-demand instances of functional networking entities via VNFs. Indeed, 3GPP is devising a new architecture for the core network, which replaces point-to-point interfaces used in 3G and 4G by producer/consumer-based communication among 5G core network functions, facilitating deployment over a virtual infrastructure. One big advantage of using VNFs is the possibility of dynamic scaling, depending on traffic load (i.e., instantiate new resources to VNFs when the traffic load increases and reduce the number of resources when the traffic load decreases). In this article, we propose a novel mechanism to scale 5G core network resources by anticipating traffic load changes through forecasting via ML techniques. The traffic load forecast is achieved by using and training a neural network on a real dataset of traffic arrival in a mobile network. Two techniques were used and compared: RNN, more specifically LSTM; and DNN. Simulation results show that the forecast-based scalability mechanism outperforms the threshold-based solutions, in terms of latency to react to traffic change, and delay to have new resources ready to be used by the VNF to react to traffic increase.

中文翻译：

---

改善流量预测以实现5G核心网络可扩展性：一种机器学习方法

预计5G不仅可以为传统设备（例如，平板电脑，智能手机等）提供网络连接，而且还可以为物联网提供网络连接，这将大大增加网络上承载的流量负载。5G将主要依靠NFV和SDN通过VNF构建功能网络实体的灵活和按需实例。确实，3GPP正在为核心网络设计一种新的架构，该架构通过5G核心网络功能之间基于生产者/消费者的通信来替代3G和4G中使用的点对点接口，从而促进了在虚拟基础架构上的部署。使用VNF的一大优势是可以根据流量负载进行动态扩展（例如，当流量负载增加时，将新资源实例化到VNF，而当流量负载减少时，减少资源数量）。在本文中，我们提出了一种通过ML技术进行预测来预测流量负载变化的扩展5G核心网络资源的新颖机制。通过在移动网络中流量到达的真实数据集上使用和训练神经网络，可以实现流量负载预测。使用了两种技术并进行了比较：RNN，更具体地说是LSTM；和DNN。仿真结果表明，基于预测的可伸缩性机制在响应流量变化的延迟和延迟使VNF准备使用新资源以应对流量增加方面均优于基于阈值的解决方案。使用了两种技术并进行了比较：RNN，更具体地说是LSTM；和DNN。仿真结果表明，基于预测的可伸缩性机制在响应流量变化的延迟和延迟使VNF准备使用新资源以应对流量增加方面均优于基于阈值的解决方案。使用了两种技术并进行了比较：RNN，更具体地说是LSTM；和DNN。仿真结果表明，基于预测的可伸缩性机制在响应流量变化的延迟和延迟使VNF准备使用新资源以应对流量增加方面均优于基于阈值的解决方案。