An adaptive scaling mechanism for managing performance variations in network functions virtualization: A case study in an NFV-based EPC

Arteaga, Carlos Hernan Tobar; Rissoi, Fulvio; Rendón, Óscar Mauricio Caicedo

doi:10.23919/cnsm.2017.8255982

Cited by 30 publications

(22 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An alternative to static-threshold-based solutions is the usage of adaptive techniques, as proposed in [10]. In this work, the authors have proposed a mechanism that combines Q-Learning with Gaussian Processes-based system models, which allows to adapt to dynamic environments and improve the scaling policy before taking any action.…”

Section: B Related Workmentioning

confidence: 99%

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

et al. 2018

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: B Related Workmentioning

confidence: 99%

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

et al. 2018

View full text Add to dashboard Cite

show abstract

“…The DRP solutions can be broadly categorized into rulebased and model-based approaches [8]. The rule-based ap-proaches, such as those proposed in [9] and [10], are based on reinforcement learning, statistical machine learning, and fuzzy control. On the other hand, the model-based approaches are based on control theory and Queueing Theory (QT).…”

Section: Related Workmentioning

confidence: 99%

Closed-Form Expression for the Resources Dimensioning of Softwarized Network Services

Prados-Garzon

Taleb

Marai

et al. 2019

2019 IEEE Global Communications Conference (GLOBECOM)

View full text Add to dashboard Cite

Network Function Virtualization (NFV) ecosystem enables the automation of deployment and scaling of softwarized network services (SNSs), thus reducing their operational expenditures. This enables operators to handle workload fluctuations, to keep the desired performance, with great agility and reduced costs. However, to realize the automation of such management practices, it is needed to determine the amount of required resources to allocate the SNS so that its performance requirements are met. This problem is commonly referred to as resources dimensioning problem. In this paper, we address the derivation of a closed-form expression for the optimal resources dimensioning of an SNS in terms of cost or energy efficiency. The performance requirement considered for the SNS is a limit on its mean response time. The performance model considered for the SNS is practical and accurate. The usefulness of the derived closedform expression is successfully validated by means of simulation. The scenario considered for the validation is a video optimization chain located at the SGi-LAN of a mobile network.

show abstract

“…Other techniques of VNF scaling are adaptive techniques. In [7], the authors propose a mechanism that combines Q-Learning with Gaussian Processes-based system models, which allows to adapt to dynamic environments and improve the scaling policy before taking any action. Indeed, this proposal, as the authors assume, reacts better than static threshold.…”

Section: Related Workmentioning

confidence: 99%

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

Alawe¹,

Hadjadj‐Aoul²,

Ksentini³

et al. 2018

2018 IEEE Global Communications Conference (GLOBECOM)

View full text Add to dashboard Cite

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.

show abstract

An adaptive scaling mechanism for managing performance variations in network functions virtualization: A case study in an NFV-based EPC

Cited by 30 publications

References 19 publications

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

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

Closed-Form Expression for the Resources Dimensioning of Softwarized Network Services

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

Contact Info

Product

Resources

About