Mobile traffic forecasting for maximizing 5G network slicing resource utilization

Sciancalepore, Vincenzo; Samdanis, Konstantinos; Costa‐Pérez, Xavier; Bega, Dario; Gramaglia, Marco; Banchs, Albert

doi:10.1109/infocom.2017.8057230

Cited by 250 publications

(161 citation statements)

References 15 publications

Supporting

Mentioning

160

Contrasting

Order By: Relevance

“…To deal with the dynamic of services, e.g., users' resource demands and their occupation time, the authors in [13] proposed a model to predict the future demand of slices, thereby maximizing the system resource utilization for the provider.…”

Section: A Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Optimal and Fast Real-Time Resource Slicing With Deep Dueling Neural Networks

Huynh

Hoang

Nguyen

et al. 2019

IEEE J. Select. Areas Commun.

123

View full text Add to dashboard Cite

Effective network slicing requires an infrastructure/network provider to deal with the uncertain demand and real-time dynamics of network resource requests. Another challenge is the combinatorial optimization of numerous resources, e.g., radio, computing, and storage. This article develops an optimal and fast real-time resource slicing framework that maximizes the long-term return of the network provider while taking into account the uncertainty of resource demand from tenants. Specifically, we first propose a novel system model which enables the network provider to effectively slice various types of resources to different classes of users under separate virtual slices. We then capture the real-time arrival of slice requests by a semi-Markov decision process. To obtain the optimal resource allocation policy under the dynamics of slicing requests, e.g., uncertain service time and resource demands, a Q-learning algorithm is often adopted in the literature. However, such an algorithm is notorious for its slow convergence, especially for problems with large state/action spaces. This makes Q-learning practically inapplicable to our case in which multiple resources are simultaneously optimized. To tackle it, we propose a novel network slicing approach with an advanced deep learning architecture, called deep dueling that attains the optimal average reward much faster than the conventional Q-learning algorithm. This property is especially desirable to cope with real-time resource requests and the dynamic demands of users. Extensive simulations show that the proposed framework yields up to 40% higher long-term average return while being few thousand times faster, compared with state of the art network slicing approaches. {Hoang.Dinh, Diep.Nguyen, and Eryk.Dutkiewicz}@uts.edu.au. and development. In order to enhance operators' products for vertical enterprises and provide service customization for emerging massive connections, as well as to give more control to enterprises and mobile virtual network operators, the concept of network slicing has been recently introduced to allow the independent usage of a part of network resources by a group of mobile terminals with special requirements.Network slicing was introduced by Next Generation Mobile Networks Alliance [2], and it has quickly received a lot of attention from both academia and industry. In general, network slicing is a novel virtualization paradigm that enables multiple logical networks, i.e., slices, to be created according to specific technical or commercial demands and simultaneously run on top of the physical network infrastructure. The core idea of the network slicing is using software-defined networking (SDN) and network functions virtualization (NFV) technologies for virtualizing the physical infrastructure and controlling network operations. In particular, SDN provides a separation between the network control and data planes, improving the flexibility of network function management and efficiency of data transfer. Meanwhile, NFV allows various network functio...

show abstract

Section: A Related Workmentioning

confidence: 99%

“…The proof of Theorem 1 is given in Appendix A. From (13) and (14), the computational complexity of uniformization method is derived as O(vt|S| 2 ), where |S| is the number of states of the system. Based on z and z s , we can determine the probabilities for events as follows.…”

Section: Continuous-timementioning

confidence: 99%

Optimal and Fast Real-Time Resource Slicing With Deep Dueling Neural Networks

Huynh

Hoang

Nguyen

et al. 2019

IEEE J. Select. Areas Commun.

123

View full text Add to dashboard Cite

show abstract

“…Sciancalepore et al [14] developed an admission control module for slice admission into a mobile network. Their model assumes that the bottleneck of the network is the physical resource (spectrum) which is to be shared among the network tenants.…”

Section: Related Workmentioning

confidence: 99%

Tenant-Aware Slice Admission Control Using Neural Networks-Based Policy Agent

Batista

Khan

Öhlen

et al. 2019

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

View full text Add to dashboard Cite

5G networks will provide the platform for deploying large number of tenant-associated management, control and end-user applications having different resource requirements at the infrastructure level. In this context, the 5G infrastructure provider must optimize the infrastructure resource utilization and increase its revenue by intelligently admitting network slices that bring the most revenue to the system. In addition, it must ensure that resources can be scaled dynamically for the deployed slices when there is a demand for them from the deployed slices. In this paper, we present a neural networks-driven policy agent for network slice admission that learns the characteristics of the slices deployed by the network tenants from their resource requirements profile and balances the costs and benefits of slice admission against resource management and orchestration costs. The policy agent learns to admit the most profitable slices in the network while ensuring their resource demands can be scaled elastically. We present the system model, the policy agent architecture and results from simulation study showing an increased revenue for infra-structure provider compared to other relevant slice admission strategies.

show abstract

“…However, early actions may turn out to be unnecessary (e.g., the traffic of a certain service did not grow as much as anticipated), or even wrong. To minimize such mishaps, several traffic prediction [13] techniques have been developed, typically leveraging machine learning techniques to accurately detect relevant trends.…”

Section: Challengesmentioning

confidence: 99%

Service Shifting: A Paradigm for Service Resilience in 5G

Malandrino¹,

Chiasserini²,

Landi

2019

IEEE Commun. Mag.

View full text Add to dashboard Cite

Many real-world services can be provided through multiple virtual network function (VNF) graphs, corresponding, e.g., to high-and low-complexity variants of the service itself. Based on this observation, we extend the concept of service scaling in network orchestration to service shifting, i.e., upgrading or downgrading the VNF graph to use among those implementing the same service. Service shifting can serve multiple goals, from reducing operational costs to reacting to infrastructure problems. Furthermore, it enhances the flexibility of service-level agreements between network operators and third party content providers ("verticals"). In this paper, we introduce and describe the service shifting concept, its benefits, and the associated challenges, with special reference to how service shifting can be integrated within real-world 5G architectures and implementations. We conclude that existing network orchestration frameworks can be easily extended to support service shifting, and its adoption has the potential to make 5G network slices easier for the operators to manage under high-load conditions, while still meeting the verticals' requirements.

show abstract

Mobile traffic forecasting for maximizing 5G network slicing resource utilization

Cited by 250 publications

References 15 publications

Optimal and Fast Real-Time Resource Slicing With Deep Dueling Neural Networks

Optimal and Fast Real-Time Resource Slicing With Deep Dueling Neural Networks

Tenant-Aware Slice Admission Control Using Neural Networks-Based Policy Agent

Service Shifting: A Paradigm for Service Resilience in 5G

Contact Info

Product

Resources

About