Smart Scaling of the 5G Core Network: An RNN-Based Approach

Abstract

The upcoming mobile core network, which will be based on Virtual Network Functions (VNF), will face an increase of data traffic on both data and control planes. This is due to the increase of the number of connected devices and the newly 5G supported-services like IoT, Connected Health Care etc. Therefore dynamic and accurate 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. Although provisioning new resources is easier as it is a matter of software deployment, the strategy to use (when to scale and how much to scale) remains complex. In this paper we propose scaling techniques based on neural networks to forecast the upcoming load. Hence scheduling the resource provisioning should be in a manner that all the needed resources will be deployed and active when the load increases. In the same way, it will scalein the unneeded resources when the traffic load decreases. The proposal is tested via discrete event simulations using a traffic load dataset provided by a Network Operator. The results show clearly the robustness of our proposal compared to a thresholdbased scaling technique.

Cellular Traffic Prediction and Classification: A Comparative Evaluation of LSTM and ARIMA

“…On the other hand, the accuracy of prediction by moving from left to right decreases significantly due to the rareness of the burst occurrence events. The right y-axis represents the rational performance of LSTM versus AR (1). Clearly, LSTM outperforms AR(1) significantly, especially when bursts are occurring infrequently.…”

“…Then, given a matrix X m (t) and a binary indicator vector s, we define X s m (t) the submatrix of X m (t), such that all respective rows, for which s indicates a zero value, are removed. For example, let Then, X s m (t) = [1,2]. Now, the research question in Section 1 could be rewritten as:…”

“…Then, as part of the solution to this problem, one may first predict the application(s) in use and behaviour of the user, and then use them as extra features in the solution. This approach for solving (1) has been illustrated in Fig. 3.…”

“…Indeed, in cellular networks with limited and highly expensive time-frequency radio resources, precise prediction of user traffic arrival can contribute significantly in improving the resource utilization [5]. As a result, in recent years, there has been an increasing interest in leveraging machine learning tools in analyzing the aggregated traffic served in a service area for optimizing the operation of the network [1,28,30,32]. Scaling of fronthaul and backhaul resources for 5G networks has been investigated in [1] by leveraging methods from recurrent neural networks (RNNs) for traffic estimation.…”

AMF Optimal Placement based on Deep Reinforcement Learning in Heterogeneous Radio Access Network

“…To overcome the above threshold configuration problem, machine learning (ML) based approach is used [18][19][20]. In [18], [19] and [20], the traffic load of AMF is forecasted by Convolutional Neural Network (CN-N), Deep Neural Network (DNN) and Long Short Term Memory Network (LSTM) based on real datasets in mobile network, respectively. With the forecast traffic result, AMF instances are optimally scaled.…”