scholarly journals Performance Model for Video Service in 5G Networks

2020 ◽  
Vol 12 (6) ◽  
pp. 99
Author(s):  
Jiao Wang ◽  
Jay Weitzen ◽  
Oguz Bayat ◽  
Volkan Sevindik ◽  
Mingzhe Li
Keyword(s):  
Machine Learning ◽  
Bandwidth Allocation ◽  
Access Network ◽  
Service Level Agreement ◽  
Service Level ◽  
Performance Model ◽  
Radio Resource ◽  
Network Slicing ◽  
Optimal Bandwidth Allocation ◽  
Management Approaches

Network slicing allows operators to sell customized slices to various tenants at different prices. To provide better-performing and cost-efficient services, network slicing is looking to intelligent resource management approaches to be aligned to users’ activities per slice. In this article, we propose a radio access network (RAN) slicing design methodology for quality of service (QoS) provisioning, for differentiated services in a 5G network. A performance model is constructed for each service using machine learning (ML)-based approaches, optimized using interference coordination approaches, and used to facilitate service level agreement (SLA) mapping to the radio resource. The optimal bandwidth allocation is dynamically adjusted based on instantaneous network load conditions. We investigate the application of machine learning in solving the radio resource slicing problem and demonstrate the advantage of machine learning through extensive simulations. A case study is presented to demonstrate the effectiveness of the proposed radio resource slicing approach.

scholarly journals Performance Model for Factory Automation in 5G Networks

2021 ◽  
Author(s):  
jiao wang ◽  
Jay Weitzen ◽  
Oguz Bayat ◽  
Volkan Sevindik ◽  
Mingzhe Li
Keyword(s):  
Mobile Networks ◽  
Data Exchange ◽  
Network Performance ◽  
Access Network ◽  
Service Level Agreement ◽  
Service Level ◽  
Performance Model ◽  
Factory Automation ◽  
Public Network ◽  
Radio Access

Abstract The fifth generation (5G) of mobile networks is emerging as a key enabler of modern factory automation (FA) applications that ensure timely and reliable data exchange between network components. Network slicing (NS), which shares an underlying infrastructure with different applications and ensures application isolation, is the key 5G technology to support the diverse quality of service requirements of modern FA applications. In this article, an end-to-end NS solution is proposed for FA applications in a 5G network. Regression approaches are used to construct a performance model for each slice to map the service level agreement to the network attributes. Interference coordination approaches for switched beam systems are proposed to optimize radio access network performance models. A case study of a non-public network is used to show the proposed NS approach.

scholarly journals Machine learning-assisted cross-slice radio resource optimization: Implementation framework and algorithmic solution

2020 ◽  
Vol 1 (1) ◽  
pp. 103-120
Author(s):  
Ramon Agusti ◽  
Irene Vila ◽  
Oriol Sallent ◽  
Jordi Perez-Romero ◽  
Ramon Ferrus
Keyword(s):  
Machine Learning ◽  
Service Level ◽  
Resource Optimization ◽  
Central Feature ◽  
Radio Resource ◽  
Network Resources ◽  
Implementation Framework ◽  
Network Slicing ◽  
Spatio Temporal ◽  
And Performance

Network slicing is a central feature in 5G and beyond systems to allow operators to customize their networks for different applications and customers. With network slicing, different logical networks, i.e. network slices, with specific functional and performance requirements can be created over the same physical network. A key challenge associated with the exploitation of the network slicing feature is how to efficiently allocate underlying network resources, especially radio resources, to cope with the spatio-temporal traffic variability while ensuring that network slices can be provisioned and assured within the boundaries of Service Level Agreements / Service Level Specifications (SLAs/SLSs) with customers. In this field, the use of artificial intelligence, and, specifically, Machine Learning (ML) techniques, has arisen as a promising approach to cater for the complexity of resource allocation optimization among network slices. This paper tackles the description of a feasible implementation framework for deploying ML-assisted solutions for cross-slice radio resource optimization that builds upon the work conducted by 3GPP and O-RAN Alliance. On this basis, the paper also describes and evaluates an ML-assisted solution that uses a Multi-Agent Reinforcement Learning (MARL) approach based on the Deep Q-Network (DQN) technique and fits within the presented implementation framework.

scholarly journals A Survey on Machine Learning and Deep Learning based Quality of Service aware Protocols for Software Defined Networks

2021 ◽  
Author(s):  
Hiren Kumar Deva Sarma
Keyword(s):  
Machine Learning ◽  
Quality Of Service ◽  
Deep Learning ◽  
Service Level Agreement ◽  
Service Level ◽  
Future Research ◽  
Traffic Classification ◽  
Software Defined Networks ◽  
Research Issues

<p>Quality of Service (QoS) is one of the most important parameters to be considered in computer networking and communication. The traditional network incorporates various quality QoS frameworks to enhance the quality of services. Due to the distributed nature of the traditional networks, providing quality of service, based on service level agreement (SLA) is a complex task for the network designers and administrators. With the advent of software defined networks (SDN), the task of ensuring QoS is expected to become feasible. Since SDN has logically centralized architecture, it may be able to provide QoS, which was otherwise extremely difficult in traditional network architectures. Emergence and popularity of machine learning (ML) and deep learning (DL) have opened up even more possibilities in the line of QoS assurance. In this article, the focus has been mainly on machine learning and deep learning based QoS aware protocols that have been developed so far for SDN. The functional areas of SDN namely traffic classification, QoS aware routing, queuing, and scheduling are considered in this survey. The article presents a systematic and comprehensive study on different ML and DL based approaches designed to improve overall QoS in SDN. Different research issues & challenges, and future research directions in the area of QoS in SDN are outlined. <b></b></p>

Optical Access Comes of Age in a Packet-Delivery World

2010 ◽  
pp. 25-42
Author(s):  
William Yue ◽  
Brian Hunck
Keyword(s):  
Optical Fibers ◽  
Access Network ◽  
Service Level Agreement ◽  
Service Level ◽  
Access Networks ◽  
Synchronous Digital Hierarchy ◽  
Optical Access ◽  
The North ◽  
Provider Network ◽  
Last Mile

The access network is the last loop, or last mile, in the provider network between the central office (CO) or point of presence (PoP) and the customer premises. Competitive pressure to provide high-bandwidth services (such as video) to consumers, and Ethernet transport to enterprises, is forcing service providers to rebuild their access networks. More optical fibers are being added in the last mile to meet these new bandwidth demands since legacy access networks have not been sufficient to support bandwidth-intensive applications. This chapter reviews the multiple definitions of “optical access” and the migration from direct copper loops to a variety of optical architectures, including Synchronous Optical Networking (SONET), Synchronous Digital Hierarchy (SDH), Fiber to the x (FTTx), Ethernet and wavelength delivery. Key business drivers such as carrier competition, bandwidth needs, and the reliability and service level agreement issues of optical technology are covered. The chapter concludes by considering the near future of optical access product trends and key optical deployment options in applications such as cellular backhaul. The data presented in this chapter is mainly based on our recent deployment experience in the North American optical access market segment.

Machine Learning Approach to Task Scheduling in Cloud Computing

2020 ◽  
Vol 17 (9) ◽  
pp. 4213-4218
Author(s):  
H. S. Madhusudhan ◽  
T. Satish Kumar ◽  
G. Mahesh
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Genetic Algorithm ◽  
Cloud Computing ◽  
Task Scheduling ◽  
Research Work ◽  
Service Level Agreement ◽  
Service Level ◽  
Machine Learning Approach ◽  
Artificial Neural Network Ann

Cloud computing provides on demand service on internet using network of remote servers. The pivotal role for any cloud environment would be to schedule tasks and the virtual machine scheduling have key role in maintaining Quality of Service (QOS) and Service Level Agreement (SLA). Task scheduling is the process of scheduling task (user requests) to certain resources and it is an NP-complete problem. The primary objectives of scheduling algorithms are to minimize makespan and improve resource utilization. In this research work an attempt is made to implement Artificial Neural Network (ANN), which is a methodology in machine learning technique and it is applied to implement task scheduling. It is observed that neural network trained with genetic algorithm will outperforms default genetic algorithm by an average efficiency of 25.56%.

Sign in / Sign up

Export Citation Format

Share Document