Machine Learning for Network Slicing Resource Management: A Comprehensive Survey

@article{Han2020MachineLF,
  title={Machine Learning for Network Slicing Resource Management: A Comprehensive Survey},
  author={B. Han and H. Schotten},
  journal={ArXiv},
  year={2020},
  volume={abs/2001.07974}
}
The emerging technology of multi-tenancy network slicing is considered as an essential feature of 5G cellular networks. It provides network slices as a new type of public cloud services, and therewith increases the service flexibility and enhances the network resource efficiency. Meanwhile, it raises new challenges of network resource management. A number of various methods have been proposed over the recent past years, in which machine learning and artificial intelligence techniques are widely… Expand
5G Network Slice - A URLLC Resource Allocation Perspective
TLDR
Challenges and open issues related to allocating enough resources to guarantee the desired QoS for specific services even when this virtual network fails remains forgotten by the literature. Expand
5G RAN Slicing: Dynamic Single Tenant Radio Resource Orchestration for eMBB Traffic within a Multi-Slice Scenario
Emerging 5G systems will need to seamlessly guarantee novel types of services in a multi-do-main ecosystem. New methodologies of network and infrastructure sharing facilitate the cooperation amongExpand
Leveraging Machine Learning for Industrial Wireless Communications
TLDR
Key open industrial challenges are identified and grouped into four use cases: wireless connectivity and edge-cloud integration, flexibility in network reconfiguration, dynamicity of heterogeneous network services, and mobility of robots and vehicles. Expand

References

SHOWING 1-10 OF 30 REFERENCES
Slice as an Evolutionary Service: Genetic Optimization for Inter-Slice Resource Management in 5G Networks
TLDR
The proposed method encodes slicing strategies into binary sequences to cope with the request-and-decision mechanism and supports heterogeneous slices while providing solid effectiveness, good robustness against non-stationary service scenarios, and high scalability. Expand
Radio access network resource slicing for flexible service execution
TLDR
This work formulate the problem of inter-slice resource partitioning and allocation, and propose an algorithm to efficiently tackle this problem, and provides simulation results that support the benefits of resource abstraction and the proposed algorithm. Expand
Admission and Congestion Control for 5G Network Slicing
TLDR
This paper proposes a novel approach of inter-slice control that well copes with existing pre-standardized 5G architectures and calls advanced solutions for slice admission and congestion control. Expand
STORNS: Stochastic Radio Access Network Slicing
TLDR
A new analytical framework, based on stochastic geometry theory, is proposed to model realistic RANs that leverage the business opportunities offered by network slicing, and mathematically prove the benefits of slicing radio access networks as compared to non-sliced infrastructures. Expand
A Profit-Maximizing Strategy of Network Resource Management for 5G Tenant Slices
TLDR
A stochastic model is built that describes the MNO's revenue and opportunity cost of accepting a contract, and a strategy that is analytically derived to maximize the expected profit at every decision is proposed. Expand
Deep Reinforcement Learning for Resource Management in Network Slicing
TLDR
This paper investigates the application of deep reinforcement learning in solving some typical resource management for network slicing scenarios, which include radio resource slicing and priority-based core network slicing, and demonstrates the advantage of DRL over several competing schemes through extensive simulations. Expand
DeepCog: Cognitive Network Management in Sliced 5G Networks with Deep Learning
TLDR
Comparative evaluations with real-world measurement data prove that DeepCog’s tight integration of machine learning into resource orchestration allows for substantial (50% or above) reduction of operating expenses with respect to resource allocation solutions based on state-of-the-art mobile traffic predictors. Expand
Slice as an Evolutionary Service : Genetic Optimization for Inter-Slice Resource Management in 5 G Networks
In the context of Fifth Generation (5G) mobile networks, the concept of “Slice as a Service” (SlaaS) promotes mobile network operators to flexibly share infrastructures with mobile service providersExpand
Slicing the Edge: Resource Allocation for RAN Network Slicing
TLDR
This letter designs two algorithms addressing these couplings between the RAN resource allocation for each slice and the coordination of the slices that share the same resources, which is formulated as a bi-convex problem. Expand
A Utility-Driven Multi-Queue Admission Control Solution for Network Slicing
TLDR
This paper aims to study the slicing admission control problem by means of a multi-queuing system for heterogeneous tenant requests, to derive its statistical behavior model, and to provide a utility-based admission control optimization. Expand
...
1
2
3
...