Resource allocation in sparse code multiple access‐based systems for cloud‐radio access network in 5G networks

Although the fifth-generation (5G) is not yet officially launched, researchers worldwide have turned to the sixth-generation (6G) communications system. The 3G has opened the gap to fourth-generation (4G). It will be the same for 5G, which will facilitate the path to 6G. The technology 5G provides a high-level infrastructure enabling various technologies such as autonomous cars, artificial intelligence, drone networking, mobile broadband communication, and, most importantly, the Internet of Things (IoT) and the concept of smart cities. We are, therefore, in the middle of the fourth industrial revolution (Industry 4.0). However, as new technologies gain traction, networks become increasingly complex and difficult to pin down to keep networks operating at the level prescribed by evolving services. The ultimate goal of 6G is to move from the concept of the Internet of intelligent things to the new idea of the intelligent Internet of intelligent things. This article shows the features and tools of 6G technology that will help meet these traffic needs. Besides, we highlight the main feature of the 6G, in terms of architecture and services, scheduled as recommended by the International Telecommunications Union (ITU) in its current technical specifications and discussions on the latest research in this area.

Section: Evolution From 5g To 6gmentioning

confidence: 99%

Toward 6G: Understanding network requirements and key performance indicators

Slalmi

Chaibi

Chehri

et al. 2020

“…Such centralized architecture opens the possibilities for dynamic resource allocation (RA), the objective function of which is commonly linked to total throughput, 3 transmission power, 4 and energy efficiency (EE) 5,6 . Also, in References 7‐9, the RA method is presented under different perspectives considering QoS and power constraints. These studies, however, pursue the short‐term reward without considering future states or consequences.…”

Section: Introductionmentioning

confidence: 99%

Resource allocation for joint energy and spectral efficiency in cloud radio access network based on deep reinforcement learning

Iqbal

Tham

Chang

2021

The rapid increase of user data traffic demand has promoted the telecommunication sector toward adopting a new generation, that is, fifth-generation (5G). Cloud radio access network (CRAN) has gained considerable attention to satisfy the high traffic demand in the 5G network via deployment and intelligent management of multiple remote radio units (RRHs). However, optimizing the instantaneous network performance may lead to myopic decision-making, such as excessive on/off switching of RRHs. This paper proposes a deep reinforcement learning (DRL) based framework, with the goal of maximizing the long-term tradeoff between energy efficiency (EE) and spectral efficiency (SE). To this end, we specifically formulate the joint optimization problem as a Markov decision process (MDP) subject to the constraints on per-RRH transmission power and user quality of service (QoS) demands. Meanwhile, considering the spatio-temporal channel state information (CSI), we adopt machine learning (ML) techniques to extract generalized features before feeding them into the input of DRL. Combining with RRH status and QoS requirements, the proposed algorithm can learn the near-optimal control strategy to turn on/off RRHs, followed by solving a power optimization problem. Simulation results reveal that the proposed method yields better performance as compared to myopic and DRL methods without considering CSI generalization.

“…Several studies have investigated different aspects of cloud radio access networks 8‐10 . While the advantages and employment of resource elasticity in 5G wireless networks have been studied in the literature, 7,11,12 no studies have been published so far regarding the cost implications in terms of the impact on the total cost of ownership (TCO) of elasticity in large‐scale 5G networks.…”

Section: Introductionmentioning

confidence: 99%

Cost assessment of elasticity for a 5G broadband network

Schneir

Bradford

Κωνσταντίνου

et al. 2021

In the highly competitive telecommunications market, operators need to consider techniques that might lead to a more cost-efficient use of the network resources. The recently proposed concept of resource elasticity focuses on the inherent cost reductions achieved by tailoring the resource utilization of network elements, such as radio and cloud elements, to the real network demand. However, no research has been conducted so far regarding the cost benefits that such schemes could bring to 5G networks, in terms of total cost of ownership. This article makes a novel contribution by analyzing the cost benefits of employing elasticity in a 5G network providing users with a broadband service in a hotspot area. The area exemplarily analyzed was the Port of Hamburg in Germany, which is a realistic scenario and which receives a considerable number of additional mobile users when a cruise ship arrives at the port. The results show that, for the different scenarios analyzed, the total radio access network cost reductions of using elasticity compared to a non-elastic network range from 2.5% to 4.4%. Considering the edge cloud site-related cost component alone, a 16.4% saving from elasticity was found. Further research is needed to understand the benefits of elasticity for other types of 5G use cases in different types of areas.