Resource Allocation Based on Radio Intelligence Controller for Open RAN Toward 6G DOI Creative Commons
Qingtian Wang, Yang Liu, Yanchao Wang

и другие.

IEEE Access, Год журнала: 2023, Номер 11, С. 97909 - 97919

Опубликована: Янв. 1, 2023

In recent years, the open and standardized interfaces for radio access networks (Open RAN), promoted by standard organization O-RAN alliance, demonstrate potential to apply artificial intelligence in 6G networks. Among O-RAN, newly introduced controller (RIC), including near-real-time RIC non-real-time RIC, provides intelligent control of network. However, existing research on only focuses implementation progress, while ignoring resource allocation between near-RT non-RT which is essential ultra-low latency this paper, we propose a reinforcement learning-based scheme that minimizes service optimizing requests allocated processed RIC.Specifically, aim at improving request acceptance minimum average latency, our policy, Double DQN decide whether are or then allocate finish requests. Firstly, define formulate problem Markov decision process framework. Then an based Deep Q network technique (Double DQN), with two variations cache without cache) handling different types. Extensive simulations effectiveness proposed method offering maximum reward. Additionally, conduct experiments analyze updating cached AI models results show performance always optimal compared other algorithms terms accepted number

Язык: Английский

Newton-Raphson-based optimizer: A new population-based metaheuristic algorithm for continuous optimization problems DOI

R. Sowmya,

M. Premkumar, Pradeep Jangir

и другие.

Engineering Applications of Artificial Intelligence, Год журнала: 2023, Номер 128, С. 107532 - 107532

Опубликована: Дек. 12, 2023

Язык: Английский

Процитировано

124
Artificial Intelligence in 6G Wireless Networks: Opportunities, Applications, and Challenges DOI Open Access
Abdulraqeb Alhammadi, Ibraheem Shayea, Ayman A. El‐Saleh

и другие.

International Journal of Intelligent Systems, Год журнала: 2024, Номер 2024, С. 1 - 27

Опубликована: Март 25, 2024

Wireless technologies are growing unprecedentedly with the advent and increasing popularity of wireless services worldwide. With advancement in technology, profound techniques can potentially improve performance networks. Besides, artificial intelligence (AI) enables systems to make intelligent decisions, automation, data analysis, insights, predictive capabilities, learning, adaptation. A sophisticated AI will be required for next-generation networks automate information delivery between smart applications simultaneously. technologies, such as machines deep learning techniques, have attained tremendous success many recent years. Hances, researchers academia industry turned their attention advanced development AI-enabled This paper comprehensively surveys different various applications. Moreover, we present that exploit power enable desired evolution challenges unsolved research this area, which represent future trends networks, discussed detail. We provide several suggestions solutions help more handle complicated problems. In summary, deeply understand up-to-the-minute network designs based on identify interesting issues pursued a fast way.

Язык: Английский

Процитировано

20
IoT‐5G and B5G/6G resource allocation and network slicing orchestration using learning algorithms DOI Creative Commons
Ado Adamou Abba Ari,

Faustin Samafou,

Arouna Ndam Njoya

и другие.

IET Networks, Год журнала: 2025, Номер 14(1)

Опубликована: Янв. 1, 2025

Abstract The advent of 5G networks has precipitated an unparalleled surge in demand for mobile communication services, propelled by the sophisticated wireless technologies. An increasing number countries are moving from fourth generation (4G) to fifth (5G) networks, creating a new expectation services that dynamic, transparent, and differentiated. It is anticipated these will be adapted multitude use cases become standard practice. diversity increasingly complex network infrastructures present significant challenges, particularly management resources orchestration services. Network Slicing emerging as promising approach address it facilitates efficient Resource Allocation (RA) supports self‐service capabilities. However, effective segmentation implementation requires development robust algorithms guarantee optimal RA. In this regard, artificial intelligence machine learning (ML) have demonstrated their utility analysis large datasets facilitation intelligent decision‐making processes. certain ML methodologies limited ability adapt evolving environments characteristic beyond (B5G/6G). This paper examines specific challenges associated with evolution B5G/6G particular focus on solutions RA dynamic slicing requirements. Moreover, article presents potential avenues further research domain objective enhancing efficiency next‐generation through adoption innovative technological solutions.

Язык: Английский

Процитировано

1
Applications of Machine Learning in Resource Management for RAN-Slicing in 5G and Beyond Networks: A Survey DOI Creative Commons
Yaser Azimi, Saleh Yousefi, Hashem Kalbkhani

и другие.

IEEE Access, Год журнала: 2022, Номер 10, С. 106581 - 106612

Опубликована: Янв. 1, 2022

One of the key foundations 5 th Generation (5G) and beyond 5G (B5G) networks is network slicing, in which partitioned into several separated logical networks, taking account requirements diverse applications. In this context, resource management great importance to instantiate operate slices meet their performance functional requirements. Resource Radio Access Networks (RANs) associated with a range challenges due dynamics specific each application while ensuring isolation. paper, we present survey on state-of-the-art works that employ Machine Learning (ML) techniques RAN slicing. We begin by reviewing challenges, then review existing papers comprehensive manner, classify based used ML algorithm, addressed type allocated resources. evaluate maturity current methods state number open some solutions address these management.

Язык: Английский

Процитировано

30
Machine Learning in Network Slicing—A Survey DOI Creative Commons
Hnin Pann Phyu, Diala Naboulsi, Razvan Stanica

и другие.

IEEE Access, Год журнала: 2023, Номер 11, С. 39123 - 39153

Опубликована: Янв. 1, 2023

5G and beyond networks are expected to support a wide range of services, with highly diverse requirements. Yet, the traditional "one-size-fits-all" network architecture lacks flexibility accommodate these services. In this respect, slicing has been introduced as promising paradigm for networks, supporting not only mobile but also vertical industries very heterogeneous Along its benefits, practical implementation brings lot challenges. Thanks recent advances in machine learning (ML), some challenges have addressed. particular, application ML approaches is enabling autonomous management resources paradigm. Accordingly, paper presents comprehensive survey on contributions slicing, identifying major categories sub-categories literature. Lessons learned presented open research discussed, together potential solutions.

Язык: Английский

Процитировано

21
Data-driven hospitals staff and resources allocation using agent-based simulation and deep reinforcement learning DOI
Teddy Lazebnik

Engineering Applications of Artificial Intelligence, Год журнала: 2023, Номер 126, С. 106783 - 106783

Опубликована: Июль 24, 2023

Язык: Английский

Процитировано

20
Technology trends and challenges in SDN and service assurance for end-to-end network slicing DOI Creative Commons
Kibeom Park,

Sangmo Sung,

Hokeun Kim

и другие.

Computer Networks, Год журнала: 2023, Номер 234, С. 109908 - 109908

Опубликована: Июль 6, 2023

Network slicing is a core technology to enable new services and solutions in 5G upcoming 6G communications. However, many issues arise when applying network at commercial scale, as this requires end-to-end management automation of the network. also various state-of-the-art technologies based on collaboration across international standards organizations open-source communities. This paper reviews summarizes recent technological trends challenges related Software-Defined Networking (SDN) service assurance for slicing. First, we focus essential use cases associated with slicing, followed by survey standard projects how they have evolved. Then, overview an architecture considering Open Radio Access (O-RAN) standard. For (RAN) zero managing RAN xHaul integrated policy. transport discuss SDN requirements traffic isolation, unified QoS policy, engineering. We cover SLA using protocol-independent active monitoring passive monitoring. In later part paper, summarize technical considerations including RAN-integrated architecture, converged enterprise multi-connectivity, edge data center architectures programmable plane, security. Overall, design proposals resolve these facilitate scale.

Язык: Английский

Процитировано

18
Network Slicing Based Learning Techniques for IoV in 5G and Beyond Networks DOI
Wafa Hamdi, Chahrazed Ksouri, Hasan Bulut

и другие.

IEEE Communications Surveys & Tutorials, Год журнала: 2024, Номер 26(3), С. 1989 - 2047

Опубликована: Янв. 1, 2024

The effects of transport development on people's lives are diverse, ranging from economy to tourism, health care, etc. Great progress has been made in this area, which led the emergence Internet Vehicles (IoV) concept. main objective concept is offer a safer and more comfortable travel experience through making available vast array applications, by relying range communication technologies including fifth-generation mobile networks. proposed applications have personalized Quality Service (QoS) requirements, raise new challenging issues for management allocation resources. Currently, interest doubled with start discussion sixth-generation In context, Network Slicing (NS) was presented as one key 5G architecture address these challenges. article, we try bring together NS implications field show impact development. We begin reviewing state art IoV terms architecture, types, life cycle, enabling technologies, network parts, evolution within cellular Then, discuss benefits brought use such dynamic environment, along technical Moreover, provide comprehensive review deploying various aspects Learning Techniques Vehicles. Afterwards, present utilization different application scenarios domains; terrestrial, aerial, marine. addition, Vehicle-to-Everything (V2X) datasets well existing implementation tools; besides presenting concise summary Slicing-related projects that an IoV. Finally, order promote deployment IoV, some directions future research work. believe survey will be useful researchers academia industry. First, acquire holistic vision regarding IoV-based realization identify challenges hindering it. Second, understand progression powered fields (terrestrial, marine). determine opportunities using Machine (MLT), propose their own solutions foster NS-IoV integration.

Язык: Английский

Процитировано

7
A comprehensive review on internet of things task offloading in multi-access edge computing DOI Creative Commons

Wang Dayong,

Kamalrulnizam Bin Abu Bakar,

Babangida Isyaku

и другие.

Heliyon, Год журнала: 2024, Номер 10(9), С. e29916 - e29916

Опубликована: Апрель 22, 2024

With the rapid development of Internet Things (IoT) technology, Terminal Devices (TDs) are more inclined to offload computing tasks higher-performance servers, thereby solving problems insufficient capacity and battery consumption TD. The emergence Multi-access Edge Computing (MEC) technology provides new opportunities for IoT task offloading. It allows TDs access networks through multiple communication technologies supports mobility terminal devices. Review studies on offloading MEC have been extensive, but none them focus in MEC. To fill this gap, paper a comprehensive in-depth understanding algorithms mechanisms network. For each paper, main solved by mechanism, technical classification, evaluation methods, supported parameters extracted analyzed. Furthermore, shortcomings current research future trends discussed. This review will help potential researchers quickly understand panorama approaches find appropriate paths.

Язык: Английский

Процитировано

6
An In-Depth Survey on Virtualization Technologies in 6G Integrated Terrestrial and Non-Terrestrial Networks DOI Creative Commons
Sahar Ammar, Chun Pong Lau, Basem Shihada

и другие.

IEEE Open Journal of the Communications Society, Год журнала: 2024, Номер 5, С. 3690 - 3734

Опубликована: Янв. 1, 2024

6G networks are envisioned to deliver a large diversity of applications and meet stringent quality service (QoS) requirements.Hence, integrated terrestrial non-terrestrial (TN-NTNs) anticipated be key enabling technologies.However, the TN-NTNs integration faces number challenges that could addressed through network virtualization technologies such as Software-Defined Networking (SDN), Network Function Virtualization (NFV) slicing.In this survey, we provide comprehensive review on adaptation these networking paradigms in networks.We begin with brief overview NTNs techniques.Then, highlight integral role Artificial Intelligence improving by summarizing major research areas where AI models applied.Building foundation, survey identifies main issues arising from SDN, NFV, slicing TN-NTNs, proposes taxonomy offering thorough relevant contributions.The is built four-level classification indicating for each study level integration, used technology, problem, type proposed solution, which can based conventional or AI-enabled methods.Moreover, present summary simulation tools commonly testing validation networks.Finally, discuss open give insights future directions advancement era.

Язык: Английский

Процитировано

6