On the scalability of 5G core network: The AMF case

Alawe, Imad; Hadjadj‐Aoul, Yassine; Ksentini, Adlen; Bertin, Philippe; Darche, Davy

doi:10.1109/ccnc.2018.8319194

Cited by 41 publications

(27 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We remark the same trend regarding the time needed by a UE to successfully attach to the network, which is presented in Figure 2(b). In this case, we observe that from the same threshold 20 UEs/sec, for the first configuration, and 40 UEs/sec second for the second one, the attach duration is exponentially increasing, which is violating the requirements specified by the 3GPP standard 4 . Obviously, there is a need to have a mechanism to solve this issue, which may consist on either: (i) adding more resources (CPU and memory) to the VM, i.e.…”

Section: A Scalability Issue Of the Amfmentioning

confidence: 80%

“…In [5], [6] and [7] authors have proposed scalability based on thresholds. In the same spirit, we worked also on threshold based scalability in a previous attempt to manage AMF instances in [4]. The main idea is to deploy a new instance (scale-out) when the CPU usage (or other resources) exceeds a certain fixed "scale-out" threshold.…”

Section: B Related Workmentioning

confidence: 99%

“…The information provided by EM, represents the inside VNF service performances, like the number of attach requests or the size of the queue of the AMF, etc. In [4], we proposed that the EM of the AMF reports this information to the VNFM, hence the NFVO. The latter takes decisions to scale-in or -out using predefined thresholds.…”

Section: Prediction-based Scalabilitymentioning

confidence: 99%

“…The AMF should be over sized (scale-out), if the number of attach requests is high, and down sized (scale-in) if the number of such requests is low. In [4], we proposed a mechanism to scale the AMF using a threshold-based algorithm, which was derived using control theory. The proposed mechanism uses a threshold (the number of attach requests received by the AMF) to take the decision to scale-out or -in.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Improving Traffic Forecasting for 5G Core Network Scalability: A Machine Learning Approach

et al. 2018

Self Cite

View full text Add to dashboard Cite

5G is expected to provide network connectivity to not only classical devices (i.e. tablets, smartphones, etc) but also to the Internet Of Things (IOT), which will drastically increase the traffic load carried over the network. 5G will mainly rely on Network Function Virtualization (NFV) and Software Defined Network (SDN) to build flexible and on-demand instances of functional networking entities, via Virtual Network Functions (VNF). Indeed, 3GPP is devising a new architecture for the core network, which replaces point to point interfaces used in 3G and 4G, by a producer/consumer-based communication among 5G core network functions, facilitating deployment over a virtual infrastructure. One big advantage of using VNF, is the possibility of dynamically scaling, depending on traffic load (i.e. instantiate new resources to VNF when the traffic load increases, and reduce the number of resources when the traffic load decreases). In this paper, we propose a novel mechanism to scale 5G core network resources by anticipating traffic load changes through forecasting via Machine Learning (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: (i) Recurrent Neural Network (RNN), more specifically Long Short Term Memory Cell (LSTM); and (ii) Deep Neural Network (DNN). Simulation results showed 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.

show abstract

Section: A Scalability Issue Of the Amfmentioning

confidence: 80%

Section: B Related Workmentioning

confidence: 99%

Section: Prediction-based Scalabilitymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Improving Traffic Forecasting for 5G Core Network Scalability: A Machine Learning Approach

et al. 2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…The idea behind this technique is simple: a scale in process is launched whenever the actual load goes below a fixed "scale in" threshold and a scale up process is launched when the actual load bypass a fixed "scale up" threshold. In [6], we proposed such a solution to manage the congestion that the AMF may undergo with the massive access of IoT devices. Besides, these kind of techniques are widely deployed in many commercial solutions and open-source cloud solutions [7] [8].…”

Section: Related Workmentioning

confidence: 99%

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

Alawe

Hadjadj‐Aoul

Ksentinit

et al. 2018

2018 IEEE Conference on Standards for Communications and Networking (CSCN)

Self Cite

View full text Add to dashboard Cite

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 proposed a novel solution to generalize neural networks while accelerating the learning process by using K-mean 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 predicting the upcoming network load for dynamic and proactive resource provisioning. The proposed solution allow obtaining very good predictions of the traffic evolution while reducing by 50% the time needed for the learning phase.

show abstract