An Efficient and Lightweight Load Forecasting for Proactive Scaling in 5G Mobile Networks

The number of connected devices is increasing with the emergence of new services and trends. This phenomenon is leading to a traffic growth over both the control and the data planes of the mobile core network. It is expected that the traffic will increase more and more with the installation of the new generation of mobile networking (5G) as it offers more services that are intended to be connected over the same network, in addition to the legacy ones. Therefore, the 3GPP group has rethought the architecture of the New Generation Core (NGC) by defining its components as Virtualized Network Functions (VNF). However, scalability techniques should be envisioned in order to answer the needs, in term of resource provisioning, without degrading the Quality Of Service (QoS) already offered by hardware based core networks. Neural networks, and in particular deep learning, having shown their effectiveness in predicting time series, could be good candidates for predicting traffic evolution. In this paper, we propose a novel solution to generalize neural networks while accelerating the learning process by using $K$-means clustering, and a Monte-Carlo method. We benchmarked multiple types of deep neural networks using real operator's data in order to compare their efficiency in forecasting the upcoming network load for dynamic and proactive resources' provisioning. The proposed solution allows obtaining very good predictions of the traffic evolution while reducing by 50% the time needed for the learning phase.

[1]  Kamel Mohamed Faraoun,et al.  Neural Networks Learning Improvement using the K-Means Clustering Algorithm to Detect Network Intrusions , 2007 .

[2]  Tarik Taleb,et al.  Dynamic Cloud Resource Scheduling in Virtualized 5G Mobile Systems , 2016, 2016 IEEE Global Communications Conference (GLOBECOM).

[3]  Fulvio Risso,et al.  An adaptive scaling mechanism for managing performance variations in network functions virtualization: A case study in an NFV-based EPC , 2017, 2017 13th International Conference on Network and Service Management (CNSM).

[4]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[5]  Yoshua Bengio,et al.  Convolutional networks for images, speech, and time series , 1998 .

[6]  Qmn Tran.  Open-source Cloud Computing , 2020 .

[7]  Gerardo Rubino,et al.  Sensitivity analysis of echo state networks for forecasting pseudo-periodic time series , 2015, 2015 7th International Conference of Soft Computing and Pattern Recognition (SoCPaR).

[8]  Adlen Ksentini,et al.  On the scalability of 5G core network: The AMF case , 2018, 2018 15th IEEE Annual Consumer Communications & Networking Conference (CCNC).

[9]  Marco De Nadai,et al.  A multi-source dataset of urban life in the city of Milan and the Province of Trentino , 2015, Scientific Data.

[10]  Jürgen Schmidhuber,et al.  Applying LSTM to Time Series Predictable through Time-Window Approaches , 2000, ICANN.

[11]  Adlen Ksentini,et al.  On evaluating different trends for virtualized and SDN-ready mobile network , 2017, 2017 IEEE 6th International Conference on Cloud Networking (CloudNet).

[12]  Andrew W. Senior,et al.  Long short-term memory recurrent neural network architectures for large scale acoustic modeling , 2014, INTERSPEECH.