Radio Resource Allocation Method for Network Slicing using Deep Reinforcement Learning

Abiko, Yu; Saito, Takato; Ikeda, Daizo; Ohta, K.; Mizuno, Tadanori; Mineno, Hiroshi

doi:10.1109/icoin48656.2020.9016577

Cited by 16 publications

(21 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Abiko et al [28] and Yu et al [29] utilized a DRL network slicing architecture to accommodate diverse Quality-of-Service (QoS) requirements in 5th generation cellular networks, rationally allocating resources to minimize energy usage of the remote radio heads (RRHs). Since the state of the radio access network changes from moment to moment and automatic control of network slicing is necessary to respond to service requirements in real-time, [28] proposes using DRL to design state, action and reward to allocate resource block (RB). The agent estimates the optimal RB amount for the state using the information in the slice as the state and controls the RB allocation to satisfy the slice requirements as an action.…”

Section: A Drlmentioning

confidence: 99%

“…In current works of literature, DL has been compared to traditional resource optimization methods [31], [64] with great success and advantageous such as flexibility and computing speed. DL has also been used to allocation resources to satisfy diverse quality of service constraints [29], [28], [65] or to minimize system energy consumption [29], [30], [65]. QoS requirements are technical specifications of the system quality in areas like performance, scalability, serviceability, and availability.…”

Section: Resource Allocationmentioning

confidence: 99%

See 1 more Smart Citation

A Review of Deep Learning in 5G Research: Channel Coding, Massive MIMO, Multiple Access, Resource Allocation, and Network Security

Yao

2021

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

The current development of 5G technology is flourishing with widespread deployment across the world at a rapid pace. However, there is still a demand concerning 5G research for service and performance improvement. Research tasks include but are not limited to quality-of-service (QoS), energy efficiency, massive connectivity, reliable communications, and security. Due to the advancement of deep learning, numerous such research has utilized this technique. This paper provides a comprehensive review of 5G communications research using deep learning. Specifically, we address the issues of low-density parity-check (LDPC) coding, massive multiple-input multiple-output (MIMO), non-orthogonal multiple access (NOMA), resource allocation, and security.

show abstract

Section: A Drlmentioning

confidence: 99%

Section: Resource Allocationmentioning

confidence: 99%

A Review of Deep Learning in 5G Research: Channel Coding, Massive MIMO, Multiple Access, Resource Allocation, and Network Security

Yao

2021

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

show abstract

“…In other words, if the number of slices is different from the number of slices during training, RB allocation to slices is impossible. Therefore, RB allocation independent of the number of slices was proposed [25]- [27]. Sun et al [25] proposed a method in which one agent predicts the required number of RBs for one slice and reserves it in advance using the DQN.…”

Section: Related Workmentioning

confidence: 99%

“…In addition, because the number of slices in the evaluation is fixed to two, it is necessary to investigate the scalability of the method. In [26] and [27], a method was proposed that circumvents the reservation of the RB allocation used in [25] and allocates the required amount. Therefore, they showed improvement in RB utilization efficiency.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Flexible Resource Block Allocation to Multiple Slices for Radio Access Network Slicing Using Deep Reinforcement Learning

Abiko

Saito²,

Ikeda³

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

In the fifth-generation of mobile communications, network slicing is used to provide an optimal network for various services as a slice. In this paper, we propose a radio access network (RAN) slicing method that flexibly allocates RAN resources using deep reinforcement learning (DRL). In RANs, the number of slices controlled by a base station fluctuates in terms of user ingress and egress from the base station coverage area and service switching on the respective sets of user equipment. Therefore, when resource allocation depends on the number of slices, resources cannot be allocated when the number of slices changes. We consider a method that makes optimal-resource allocation independent of the number of slices. Resource allocation is optimized using DRL, which learns the best action for a state through trial and error. To achieve independence from the number of slices, we show a design for a model that manages resources on a one-slice-by-one-agent basis using ApeX , which is a DRL method. In ApeX , because agents can be employed in parallel, models that learn various environments can be generated through trial and error of multiple environments. In addition, we design a model that satisfies the slicing requirements without overallocating resources. Based on this design, it is possible to optimally allocate resources independently of the number of slices by changing the number of agents. In the evaluation, we test multiple scenarios and show that the mean satisfaction of the slice requirements is approximately 97%. INDEX TERMS Deep reinforcement learning, network slicing, RAN slicing, resource management.

show abstract

Intelligent Allocation Technologies for All-Scenario KDN Resources

Liao,

He,

Wang

et al. 2024

Wireless Networks

View full text Add to dashboard Cite

Radio Resource Allocation Method for Network Slicing using Deep Reinforcement Learning

Cited by 16 publications

References 13 publications

A Review of Deep Learning in 5G Research: Channel Coding, Massive MIMO, Multiple Access, Resource Allocation, and Network Security

A Review of Deep Learning in 5G Research: Channel Coding, Massive MIMO, Multiple Access, Resource Allocation, and Network Security

Flexible Resource Block Allocation to Multiple Slices for Radio Access Network Slicing Using Deep Reinforcement Learning

Intelligent Allocation Technologies for All-Scenario KDN Resources

Contact Info

Product

Resources

About