Towards Intelligent RAN Slicing for B5G: Opportunities and Challenges

Mazied, EmadElDin A; Liu, Lingjia; Midkiff, Scott F.

doi:10.48550/arxiv.2103.00227

Cited by 5 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For this reason, the focus of this paper is the map of data flow types to specific 5QI slices and its evaluation in a real 5G network with network slicing techniques at the RAN level. It should be noted that the solution presented in this paper is also in line with the core challenges described in [33].…”

Section: Sstsupporting

confidence: 56%

Traffic Classification for Network Slicing in Mobile Networks

et al. 2022

View full text Add to dashboard Cite

Network slicing is a promising technique used in the smart delivery of traffic and can satisfy the requirements of specific applications or systems based on the features of the 5G network. To this end, an appropriate slice needs to be selected for each data flow to efficiently transmit data for different applications and heterogeneous requirements. To apply the slicing paradigm at the radio segment of a cellular network, this paper presents two approaches for dynamically classifying the traffic types of individual flows and transmitting them through a specific slice with an associated 5G quality-of-service identifier (5QI). Finally, using a 5G standalone (SA) experimental network solution, we apply the radio resource sharing configuration to prioritize traffic that is dispatched through the most suitable slice. The results demonstrate that the use of network slicing allows for higher efficiency and reliability for the most critical data in terms of packet loss or jitter.

show abstract

Section: Sstsupporting

confidence: 56%

Traffic Classification for Network Slicing in Mobile Networks

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Some of these works focus on radio access network (RAN) slicing. Article [11] has addressed the opportunities and challenges of RAN slicing using ML-based techniques. An ensemble learning method-based SAC for adaptive RAN is proposed in [12].…”

Section: Related Workmentioning

confidence: 99%

Approximate Q-learning-based (AQL) network slicing in mobile edge-cloud for delay-sensitive services

Khani,

Jamali,

Sohrabi

2023

J Supercomput

View full text Add to dashboard Cite

Network slicing (NS) technology promises to provide a variety of services based on diverse latencysensitive over shared infrastructure in Mobile Edge-Cloud (MEC) by creating customized slices for each application. However, to process users' dynamic slice requests, the infrastructure provider (InP) must be the online slice acceptance check and scaled if required. Based on a business model, network revenue is dependent on the acceptance of slices and the provision of infrastructure for them. If an InP does not provide more resources for an active slice, the network is penalized and its revenues are degraded. A proper solution to the aforementioned problem is to use reinforcement learning methods. But most of these methods have challenges in continuous spaces. This work presents a reinforcement learning-based method called approximate Q-learning (AQL) to intelligently slice acceptance control (SAC) to maximize utility in MEC for latency-sensitive services. The core idea of AQL is based on Q-learning, so we have developed some of its functions to adapt to a large area of spaces and actions. We have evaluated the performance of AQL in terms of coverage, cumulative rewards, resource utilization, and revenue. The results show the proposed approach has an acceptable performance.

show abstract

“…So the publications concentrate on slicing radio access networks (RANs). The advantages and disadvantages of RAN slicing using MLbased algorithms have been discussed in article [11]. In [12], a SAC based on the ensemble learning approach for adaptive RAN is presented.…”

Section: Related Workmentioning

confidence: 99%

Approximate Q-Learning-based (AQL) Network Slicing in Mobile Edge-Cloud environments for Delay-sensitive Services Using Markov Decision Process

Bharanidharan¹,

Malathi²,

Sathya³

et al. 2023

Preprint

View full text Add to dashboard Cite

Network slicing in mobile edge-cloud environments has gained significant attention due to its ability to provide customized network services tailored to the specific requirements of different applications. However, ensuring efficient resource allocation and meeting the tough delay requirements of delay-sensitive services remain major challenges in network slicing. In this paper, we propose an Approximate Q-Learning-based (AQL) approach for network slicing in mobile edge-cloud systems, specifically targeting delay-sensitive services. The AQL approach utilizes Q-Learning, a reinforcement learning technique, to optimize resource allocation and decision-making in network slicing. By formulating the resource allocation problem as a Markov Decision Process (MDP), the proposed AQL model learns to make intelligent decisions on resource allocation to minimize delays and maximize resource utilization. The model takes into account various factors such as network congestion, service priority, and available resources to dynamically adapt the network slice configuration. To evaluate the performance of the AQL approach, we conducted extensive simulations comparing it with traditional resource allocation methods. The results demonstrate that the AQL-based network slicing approach effectively reduces delay and improves resource utilization, outperforming conventional methods. The approach also demonstrates its adaptability to dynamic network conditions and varying service requirements. Furthermore, we investigate the impact of different factors on the AQL model's performance, such as the number of network slices, resource availability, and service priority. Our analysis provides valuable insights into the optimal configuration and operation of network slicing for delay-sensitive services. Overall, this paper contributes to the field of network slicing in mobile edge-cloud systems by introducing an AQL-based approach that efficiently addresses the resource allocation challenges for delay-sensitive services. The proposed approach offers a flexible and intelligent solution that can be applied in real-world scenarios, enabling network operators to provide reliable and high-performance network services for a variety of delay-sensitive applications.

show abstract

Towards Intelligent RAN Slicing for B5G: Opportunities and Challenges

Cited by 5 publications

References 12 publications

Traffic Classification for Network Slicing in Mobile Networks

Traffic Classification for Network Slicing in Mobile Networks

Approximate Q-learning-based (AQL) network slicing in mobile edge-cloud for delay-sensitive services

Approximate Q-Learning-based (AQL) Network Slicing in Mobile Edge-Cloud environments for Delay-sensitive Services Using Markov Decision Process

Contact Info

Product

Resources

About