NFV Orchestration Platform for 5G over On-the-fly Provisioned Infrastructure

Salhab, Nazih; Rahim, Rana; Langar, Rami

doi:10.1109/infcomw.2019.8845141

Cited by 12 publications

(9 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…31,33 Despite the gains in terms of modularity and deployment, several issues still need further research like efficient monitoring and security. 34 Experimental works 30,35 instantiate core services in LTE networks like the Evolved Packet Core (EPC) using microservices and employ OpenAirInterface for the radio access network, being able to achieve end-to-end delay below 20 s.…”

Section: Microservices and Services In 5g Networkmentioning

confidence: 99%

Next generation of microservices for the 5G Service‐Based Architecture

et al. 2020

View full text Add to dashboard Cite

The architecture for 5G core includes a Service-Based Architecture for the diverse network functions (NFs), which relies on HTTP/2 for the SBI and TCP as the underlying transport protocol. The specifications of the HTTP family is moving towards more efficient and secure protocols, which are based on UDP to assure enhanced transport but using TLS to secure the communication channel. The next generation of microservices needs to be more secure, performant and easily manageable, where HTTP/3 and containers orchestration platforms (like Kubernetes) can provide significative contributions towards such goals. Different deployment approaches can be followed for services implemented in compliance to the 5G SBA. This paper contributes with the assessment of deployment models for services in 5G networks, where NFs are implemented following traditional architectures (all the functions in a VM) or as serverless architectures (with functions distributed in containers). The performance of microservices in Kubernetes is also evaluated. The evaluation conducted also considers the employment of different versions of HTTPs to empower the service-based interfaces of 5G services. Results demonstrate performance benefits of employing HTTP/3, based on QUIC protocol, in scenarios with networks characterised by losses or delay conditions. Despite such gain, deployment in 5G networks needs to carefully consider aspects related with connection tracking mechanisms to support high volumes of requests.

show abstract

Section: Microservices and Services In 5g Networkmentioning

confidence: 99%

Next generation of microservices for the 5G Service‐Based Architecture

et al. 2020

View full text Add to dashboard Cite

show abstract

“…ML based approaches are expected to be competitive in accuracy due to data abundance that is exploited in continuous training and re-training of models. In addition, differently from such related works, to prove the effectiveness of our proposal, we generated a realistic dataset using our 5G experimental prototype presented in [5,6].…”

Section: Related Workmentioning

confidence: 99%

“…Specifically, we use multiple predictor variables extracted from the traffic profile (such as, time, day-of-the-week, plannedevent existence, and other environmental factors) to predict an optimal value of bandwidth ratio. We use our 5G experimental prototype [5,6] based on OpenAirInterface™ (OAI) to generate a realistic dataset and benchmark the performance of several ML based approaches as well as two baselines solutions: static slicing and un-informed random slicing-decisions. Our contributions can be thus summarized as follows:…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Based Resource Orchestration for 5G Network Slices

Salhab

Rahim

Langar

et al. 2019

2019 IEEE Global Communications Conference (GLOBECOM)

Self Cite

View full text Add to dashboard Cite

5G will serve heterogeneous demands in terms of data-rate, reliability, latency, and efficiency. Mobile operators shall be able to serve all of these requirements using shared network infrastructure's resources. To this end, we propose in this paper a framework for resource orchestration for 5G network slices implementing four Quality of Service pillars. Starting from traffic classification, demands are marked so that they are best served by dedicated logical virtual networks called Network Slices (NSs). To optimally serve multiple NSs over the same physical network, we then implement a new dynamic slicing approach of network resources exploiting Machine Learning (ML). Indeed, as demands change dynamically, a mere recursive optimization leading to progressive convergence towards an optimum slice is not sufficient. Consequently, we need an initial well-informed slicing decision of physical resources from a total available resource pool. Moreover, we formalize both admission control and slice scheduler modules as Knapsack problems. Using our 5G experimental prototype based on OpenAirInterface (OAI), we generate a realistic dataset for evaluating ML based approaches as well as two baselines solutions (i.e. static slicing and uninformed random slicing-decisions). Simulation results show that using regression trees as an ML based approach for both classification and prediction, outperform other alternative solutions in terms of prediction accuracy and throughput.

show abstract

“…Providing a reliable communication technology represents a key challenge for 5G systems in both Core Network [2] and Radio Access Network (RAN) levels. In order to achieve reliability at the RAN level, a base station (eNodeB or gNodeB, in 4G and 5G terminology, respectively) should allocate a sufficient amount of radio resources per UE, and appropriately select the modulation and coding scheme (MCS) in order to meet the requirements of each considered application.…”

Section: Introductionmentioning

confidence: 99%

A Machine Learning Approach to Predict Channel Stability Using Channel Quality Index

Mahalaxmi¹

2022

IJSREM

View full text Add to dashboard Cite

Channel quality feedback is crucial for the operation of 4G and 5G radio networks, as it allows to control User Equipment (UE) connectivity, transmission scheduling, and the modulation and rate of the data transmitted over the wireless link. However, when such feedback is frequent and the number of UEs in a cell is large, the channel may be overloaded by signalling messages, resulting in lower throughput and data loss. Optimizing this signaling process thus represents a key challenge. In this paper, a focus on Channel Quality Indicator (CQI) reports that are periodically sent from a UE to the base station, and propose mechanisms to optimize the reporting process with the aim of reducing signaling overhead and avoiding the associated channel overloads, particularly when channel conditions are stable. To this end, we apply machine learning mechanisms to predict channel stability, which can be used to decide if the CQI of a UE is necessary to be reported, and in turn to control the reporting frequency. For this purpose,four machine learning models,namely Support Vector Machines (SVM),K-Nearest Neighbour (KNN),Random Forest and Neural Networks (ANN). Simulation results shows that both provide a high prediction accuracy, with ANN consistently outperforming, especially as CQI reporting frequency reduces. Keywords: ANN,KNN,SVM,Random Forest,CQI,5G,UE

show abstract

NFV Orchestration Platform for 5G over On-the-fly Provisioned Infrastructure

Cited by 12 publications

References 2 publications

Next generation of microservices for the 5G Service‐Based Architecture

Next generation of microservices for the 5G Service‐Based Architecture

Machine Learning Based Resource Orchestration for 5G Network Slices

A Machine Learning Approach to Predict Channel Stability Using Channel Quality Index

Contact Info

Product

Resources

About