Enhanced machine learning scheme for energy efficient resource allocation in 5G heterogeneous cloud radio access networks

AlQerm, Ismail; Shihada, Basem

doi:10.1109/pimrc.2017.8292227

Cited by 35 publications

(21 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, further research is required on the energy efficiency issue at resource utilization and allocation, power in C-RAN, and computational complexity. An H-CRAN resource allocation scheme is proposed based using machine learning to improve energy efficiency and QoS interference for the H-CRAN downlink [68]. The proposed scheme works by learning information online, and the allocation is performed on the assigned controller.…”

Section: Edge Network 1) Cranmentioning

confidence: 99%

Towards Energy Efficient 5G Networks Using Machine Learning: Taxonomy, Research Challenges, and Future Research Directions

et al. 2020

View full text Add to dashboard Cite

As the world pushes toward the use of greener technology and minimizes energy waste, energy efficiency in the wireless network has become more critical than ever. The next-generation networks, such as 5G, are being designed to improve energy efficiency and thus constitute a critical aspect of research and network design. The 5G network is expected to deliver a wide range of services that includes enhanced mobile broadband, massive machine-type communication and ultra-reliability, and low latency. To realize such a diverse set of requirement, 5G network has evolved as a multi-layer network that uses various technological advances to offer an extensive range of wireless services. Several technologies, such as software-defined networking, network function virtualization, edge computing, cloud computing, and small cells, are being integrated into the 5G networks to fulfill the need for diverse requirements. Such a complex network design is going to result in increased power consumption; therefore, energy efficiency becomes of utmost importance. To assist in the task of achieving energy efficiency in the network machine learning technique could play a significant role and hence gained significant interest from the research community. In this paper, we review the state-of-art application of machine learning techniques in the 5G network to enable energy efficiency at the access, edge, and core network. Based on the review, we present a taxonomy of machine learning applications in 5G networks for improving energy efficiency. We discuss several issues that can be solved using machine learning regarding energy efficiency in 5G networks. Finally, we discuss various challenges that need to be addressed to realize the full potential of machine learning to improve energy efficiency in the 5G networks. The survey presents a broad range of ideas related to machine learning in 5G that addresses the issue of energy efficiency in virtualization, resource optimization, power allocation, and incorporating enabling technologies of 5G can enhance energy efficiency.

show abstract

Section: Edge Network 1) Cranmentioning

confidence: 99%

Towards Energy Efficient 5G Networks Using Machine Learning: Taxonomy, Research Challenges, and Future Research Directions

et al. 2020

View full text Add to dashboard Cite

show abstract

“…other inter-cell interference solution applied in H-CRAN, like [200,201], propose an allocation of resource blocks (RBs) with considering the user's priority and power scheme in H-CRAN based on online learning in order to minimize the inter-cell interference between macro BSs and RRHs and improve energy-efficiency spectral efficiency and data rate. Comparing with standard online learning, the proposed online learning algorithm increases the convergence speed.…”

Section: Machine Learning Approaches Applied To H-cran Interference Cmentioning

confidence: 99%

A survey of 5G network systems: challenges and machine learning approaches

Mâaloul

Fourati

2020

Int. J. Mach. Learn. & Cyber.

115

View full text Add to dashboard Cite

5G cellular networks are expected to be the key infrastructure to deliver the emerging services. These services bring new requirements and challenges that obstruct the desired goal of forthcoming networks. Mobile operators are rethinking their network design to provide more flexible, dynamic, cost-effective and intelligent solutions. This paper starts with describing the background of the 5G wireless networks then we give a deep insight into a set of 5G challenges and research opportunities for machine learning (ML) techniques to manage these challenges. The first part of the paper is devoted to overview the fifth-generation of cellular networks, explaining its requirements as well as its key technologies, their challenges and its forthcoming architecture. The second part is devoted to present a basic overview of ML techniques that are nowadays applied to cellular networks. The last part discusses the most important related works which propose ML solutions in order to overcome 5G challenges.

show abstract

“…Due to the tremendous traffic generated by mobile users, the future mobile network deployment is going to be extremely complex. The spectrum utilization in the densely populated network is a challenging task and, if machine learning is used as an optimization tool to optimize the C‐RAN, the resource allocation scheme will be enabled to downlink H‐CRAN . H‐CRAN aims the reduction of an interference problem to maximize the energy efficiency and to guarantee the QoS between RRH and all User Equipment (UE) present in the network.…”

Section: Related Workmentioning

confidence: 99%

An optimal multitier resource allocation of cloud RAN in 5G using machine learning

Bashir

Arul

Basheer

et al. 2019

Trans Emerging Tel Tech

View full text Add to dashboard Cite

The networks are evolving drastically since last few years in order to meet user requirements. For example, the 5G is offering most of the available spectrum under one umbrella. In this work, we will address the resource allocation problem in fifth-generation (5G) networks, to be exact in the Cloud Radio Access Networks (C-RANs). The radio access network mechanisms involve multiple network topologies that are isolated based on the spectrum bands and it should be enhanced with numerous access technology in the deployment of 5G network. The C-RAN is one of the optimal technique to combine all the available spectral bands. However, existing C-RAN mechanisms lacks the intelligence perspective on choosing the spectral bands. Thus, C-RAN mechanism requires an advanced tool to identify network topology to allocate the network resources for substantial traffic volumes. Therefore, there is a need to propose a framework that handles spectral resources based on user requirements and network behavior. In this work, we introduced a new C-RAN architecture modified as multitier Heterogeneous Cloud Radio Access Networks in a 5G environment. This architecture handles spectral resources efficiently. Based on the simulation analysis, the proposed multitier H-CRAN architecture with improved control unit in network management perspective enables augmented granularity, end-to-end optimization, and guaranteed quality of service by 15 percentages over the existing system.Trans Emerging Tel Tech. 2019;30:e3627.wileyonlinelibrary.com/journal/ett spectrum like WiFi. 2 The advanced antennas with multiple input and multiple output technologies can be adopted in the evolving 5G to provide higher data rate. 3,4 The colossal requirements of future 5G networks cannot be accomplished by the existing radio access networks (RANs), wherein the base band units (BBUs) and radio units are consolidated. 2 Meanwhile, the cloud-enabled services in 5G ecosystem cater heterogeneous communication framework utilizing advanced virtualization techniques. The network virtualization stimulates multiservice and multitenancy for efficient network operations and service provisions, which, in turn, offers new-fangled service-oriented and edge-cloud 5G architectures with enhanced Quality of Experience (QoE). 5 Thus, the current RAN architectures need to be further extended with various virtualization techniques to develop Cloud RAN (C-RAN). Cloud RANs abutments the correlation of Access Points (APs) to the pool of BBU via a troop of transport links in the Control Unit (CU), 6 which conquers the limitations in the traditional RAN. 7 However, C-RAN requires an intelligent technique to recognize the topology of the network in the mobility stage and to locate the resources, as the vast traffic volume created by the sampled radio signals are directly transported to the CU. 8 The next-generation networks are expected to learn consistently based on the varied user behavior and spectral stability that depends on both the user's environment and network behavior. 9 Thereby, sea...

show abstract

Enhanced machine learning scheme for energy efficient resource allocation in 5G heterogeneous cloud radio access networks

Cited by 35 publications

References 10 publications

Towards Energy Efficient 5G Networks Using Machine Learning: Taxonomy, Research Challenges, and Future Research Directions

Towards Energy Efficient 5G Networks Using Machine Learning: Taxonomy, Research Challenges, and Future Research Directions

A survey of 5G network systems: challenges and machine learning approaches

An optimal multitier resource allocation of cloud RAN in 5G using machine learning

Contact Info

Product

Resources

About