A survey of deep reinforcement learning application in 5G and beyond network slicing and virtualization

Ssengonzi, Charles; Kogeda, Okuthe P.; Olwal, Thomas O.

doi:10.1016/j.array.2022.100142

“…The actor network updates its parameters according to the deterministic policy gradient. The target Q value is calculated using the actor target network and the critic target network as follows: (11) where θ v ′ and θ µ ′ denote the parameters of the critic target network and the actor target network, respectively. Q-learning in DDPG is performed by minimizing the following mean square error function:…”

Section: ) Deep Deterministic Policy Gradient (Ddpg)mentioning

confidence: 99%

Federated Learning for RAN Slicing in Beyond 5G Networks

Abouaomar¹,

Taïk²,

Filali³

et al. 2022

Preprint

View full text Add to dashboard Cite

Radio access network (RAN) slicing allows the division of the network into several logical networks tailored to different and varying service requirements in a sustainable way. It is thereby considered a key enabler of 5G and next generation networks. However, determining optimal strategies for RAN slicing remains a challenging issue. Using machine learning algorithms to address such a difficult problem is promising. However, due to the large differences imposed by RAN deployments and the disparity of their required services it is difficult to utilize the same slicing model across all the covered areas. Moreover, the data collected by each mobile virtual network operator (MVNO) in different areas is mostly limited and rarely shared among operators. Federated learning presents new opportunities for MVNOs to benefit from distributed training. In this paper, we propose a federated deep reinforcement learning (FDRL) approach to train bandwidth allocation models among MVNOs based on their interactions with their users. We evaluate the proposed approach through extensive simulations to show the importance of such collaboration in building efficient network slicing models.

show abstract

“…However, forecasting related problems are not covered by their study. Furthermore, the authors in [19] survey a similar topic: the feasibility of DRL frameworks in the 5G network slicing paradigm. However, these studies dedicate little to no discussion about other ML techniques, like the role of supervised and unsupervised learning in the traffic forecasting function, or to multi-armed bandit techniques which have been widely used in the network slicing resource management regime.…”

Section: A Scope Of the Surveymentioning

confidence: 99%

Machine Learning in Network Slicing - A Survey

Phyu¹,

Naboulsi²,

Stanica³

2022

Preprint

View full text Add to dashboard Cite

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 the flexibility to accommodate these services. In this respect, network slicing has been introduced as a promising paradigm for 5G and beyond networks, supporting not only traditional mobile services, but also vertical industries services, with very heterogeneous requirements. Along with its benefits, the practical implementation of network slicing brings a lot of challenges. Thanks to the recent advances on Machine Learning (ML), some of these challenges have been addressed. In particular, the application of ML approaches is enabling the autonomous management of resources, in the network slicing paradigm. Accordingly, this paper presents a comprehensive survey on contributions on ML in network slicing, identifying major categories and sub-categories in the literature. Key takeaways are also presented and open research challenges are discussed, together with potential solutions.

show abstract

“…A few of them review network slicing architectures and principles [3], [13], [14], while others focus on the algorithmic aspects of network slicing [15], [17] and its common mathematical modeling [16]. Two recent surveys focused on very specific applications of deep reinforcement learning (DRL) in a network slicing context [18], [19].…”

Section: A Scope Of the Surveymentioning

confidence: 99%

“…They analyze the key attributes and functions of the most common models and propose unified network slicing models for efficient end-to-end (E2E) network slicing management. Furthermore, the authors of [14] discuss the potential and integration of multi-access edge computing (MEC) and cloud [3] 5G network slicing architectures [13] Network slice creation models and slicing templates proposed by SDOs [14] 5G network slicing development and its integration with the MEC and the cloud [15] Optimization frameworks for network slicing [16] Mathematical modelling encompassing game theory models, prediction models, failure recovery models in resource allocation methods [17] Algorithmic issues for admission control and resource allocation aspects in network slicing, including RL methods [18] Admission control, resource allocation and resource orchestration aspects in network slicing with DRL approaches [19] DRL-based contributions in network slicing Our Survey ML-based algorithmic approaches in network slicing technologies in network slicing. However, algorithmic aspects of resource management perspectives in network slicing have not been studied in these surveys.…”

Section: A Scope Of the Surveymentioning

confidence: 99%

Machine Learning in Network Slicing - A Survey

Phyu¹,

Naboulsi²,

Stanica³

2022

Preprint

0

View full text Add to dashboard Cite

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 the flexibility to accommodate these services. In this respect, network slicing has been introduced as a promising paradigm for 5G and beyond networks, supporting not only traditional mobile services, but also vertical industries services, with very heterogeneous requirements. Along with its benefits, the practical implementation of network slicing brings a lot of challenges. Thanks to the recent advances on Machine Learning (ML), some of these challenges have been addressed. In particular, the application of ML approaches is enabling the autonomous management of resources, in the network slicing paradigm. Accordingly, this paper presents a comprehensive survey on contributions on ML in network slicing, identifying major categories and sub-categories in the literature. Key takeaways are also presented and open research challenges are discussed, together with potential solutions.

show abstract

A survey of deep reinforcement learning application in 5G and beyond network slicing and virtualization

Cited by 42 publications

References 87 publications

Federated Learning for RAN Slicing in Beyond 5G Networks

Federated Learning for RAN Slicing in Beyond 5G Networks

Machine Learning in Network Slicing - A Survey

Machine Learning in Network Slicing - A Survey

Contact Info

Product

Resources

About