# Deep Reinforcement Learning for Resource Management in Network Slicing

@article{Li2018DeepRL,
title={Deep Reinforcement Learning for Resource Management in Network Slicing},
author={Rongpeng Li and Z. Zhao and Qi Sun and I C. and C. Yang and X. Chen and Minjian Zhao and Honggang Zhang},
journal={IEEE Access},
year={2018},
volume={6},
pages={74429-74441}
}
Network slicing is born as an emerging business to operators by allowing them to sell the customized slices to various tenants at different prices. [...] Key Result Finally, we also discuss the possible challenges to apply DRL in network slicing from a general perspective.Expand
110 Citations

#### Figures, Tables, and Topics from this paper

Two-Tier Resource Allocation in Dynamic Network Slicing Paradigm with Deep Reinforcement Learning
• Computer Science
• 2019 IEEE Global Communications Conference (GLOBECOM)
• 2019
Simulation results demonstrate that the proposed paradigm can achieve better throughput and QoE in comparison with the traditional network slicing paradigms. Expand
A Constrained Reinforcement Learning Based Approach for Network Slicing
• Computer Science
• 2020 IEEE 28th International Conference on Network Protocols (ICNP)
• 2020
This work formulate the resource allocation problem as a Constrained Markov Decision Process (CMDP) and solve it using constrained reinforcement learning algorithms to deal with cumulative and instantaneous constraints. Expand
Radio Resource Allocation Method for Network Slicing using Deep Reinforcement Learning
• Computer Science
• 2020 International Conference on Information Networking (ICOIN)
• 2020
This paper proposes a method to allocate radio resources that satisfy the service requirements regardless of the number of slices using deep reinforcement learning and flexibly controls multiple slices by observing the state of one slice and calling a model that controls one slice multiple times. Expand
GAN-Powered Deep Distributional Reinforcement Learning for Resource Management in Network Slicing
• Computer Science, Mathematics
• IEEE Journal on Selected Areas in Communications
• 2020
This paper considers a scenario that contains several slices in a radio access network with base stations that share the same physical resources (e.g., bandwidth or slots), and proposes generative adversarial network-powered deep distributional Q network (GAN-DDQN) to learn the action-value distribution driven by minimizing the discrepancy between the estimated action- Value distribution and the target action- value distribution. Expand
Applying Model-Free Reinforcement Learning Algorithm in Network Slicing for 5G
• Computer Science
• 2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT)
• 2019
This paper will appropriately address to develop a policy-gradient based model-free RL approach to achieve optimal policy for NS with current values and action variables and accomplish optimal solutions for security improvement and detecting malicious nodes within the NS for 5G. Expand
Graph Attention Network-based Multi-agent Reinforcement Learning for Slicing Resource Management in Dense Cellular Network
• Yan Shao, Rongpeng Li, Bing Hu, Yingxiao Wu, Zhifeng Zhao
• Computer Science
• ArXiv
• 2021
The universal effectiveness of GAT for advancing DRL in the multi-agent system is testified, by applying GAT on the top of both the value-based method deep Q-network (DQN) and a combination of policy-based and value- based method advantage actor-critic (A2C). Expand
Flexible Resource Block Allocation to Multiple Slices for Radio Access Network Slicing Using Deep Reinforcement Learning
• Computer Science
• IEEE Access
• 2020
This paper proposes a radio access network (RAN) slicing method that flexibly allocates RAN resources using deep reinforcement learning (DRL), and shows a design for a model that manages resources on a one-slice-by-one-agent basis using Ape-X, which is a DRL method. Expand
The LSTM-Based Advantage Actor-Critic Learning for Resource Management in Network Slicing With User Mobility
• Computer Science
• IEEE Communications Letters
• 2020
This letter considers a scenario that contains several slices in a radio access network with base stations that share the same physical resources (e.g., bandwidth or slots), and incorporates the long short-term memory (LSTM) into A2C, and puts forward an LSTM-A2C algorithm to track the user mobility and improve the system utility. Expand
Slice Management in Radio Access Network via Deep Reinforcement Learning
• Computer Science
• 2020 IEEE 91st Vehicular Technology Conference (VTC2020-Spring)
• 2020
A hybrid method of Jacobian-matrix approximation with RL approach has been devised and shown to be a practical and efficient solution to steer the radio resource management (RRM) of the radio access network. Expand
GAN-Based Deep Distributional Reinforcement Learning for Resource Management in Network Slicing
• Computer Science
• 2019 IEEE Global Communications Conference (GLOBECOM)
• 2019
This paper proposes generative adversarial network based deep distributional Q network (GAN- DDQN) to learn the distribution of state-action values and estimates the distributions by approximating a full quantile function, which can make the training error more controllable. Expand

#### References

SHOWING 1-10 OF 25 REFERENCES
Slice as an Evolutionary Service: Genetic Optimization for Inter-Slice Resource Management in 5G Networks
• Computer Science
• IEEE Access
• 2018
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
Optimising 5G infrastructure markets: The business of network slicing
• Computer Science
• IEEE INFOCOM 2017 - IEEE Conference on Computer Communications
• 2017
This paper designs an algorithm for the admission and allocation of network slices requests that maximises the infrastructure provider's revenue and ensures that the service guarantees provided to tenants are satisfied and designs an adaptive algorithm that achieves close to optimal performance. Expand
A deep reinforcement learning based framework for power-efficient resource allocation in cloud RANs
• Zhiyuan Xu, Jing Wang
• Computer Science
• 2017 IEEE International Conference on Communications (ICC)
• 2017
A novel DRL-based framework for power-efficient resource allocation in cloud RANs is presented, which can achieve significant power savings while meeting user demands, and it can well handle highly dynamic cases. Expand
The Algorithmic Aspects of Network Slicing
This article focuses on the algorithmic challenges that emerge in efficient network slicing, necessitating novel techniques from the communities of operation research, networking, and computer science. Expand
Network Slicing for Service-Oriented Networks Under Resource Constraints
• Computer Science
• IEEE Journal on Selected Areas in Communications
• 2017
The network slicing problem is formulated as a mixed binary linear program and its strong NP-hardness is established, and efficient penalty successive upper bound minimization and PSUM-R(ounding) algorithms are proposed and two heuristic algorithms to solve the problem are proposed. Expand
Integrated Networking, Caching, and Computing for Connected Vehicles: A Deep Reinforcement Learning Approach
• Computer Science
• IEEE Transactions on Vehicular Technology
• 2018
This paper proposes an integrated framework that can enable dynamic orchestration of networking, caching, and computing resources to improve the performance of next generation vehicular networks and formulate the resource allocation strategy in this framework as a joint optimization problem. Expand
Deep Reinforcement Learning for Distributed Dynamic Power Allocation in Wireless Networks
• Computer Science
• ArXiv
• 2018
This work indicates that deep reinforcement learning based radio resource management can be very fast and deliver highly competitive performance, especially in practical scenarios where the system model is inaccurate and CSI delay is non-negligible. Expand
QoS-Aware and Reliable Traffic Steering for Service Function Chaining in Mobile Networks
• Computer Science
• IEEE Journal on Selected Areas in Communications
• 2017
This paper defines and forms the traffic steering problem for service function chaining in mobile networks, which turns out to be $\mathcal {NP}$ -hard, and develops a fast approximation scheme for the problem, and evaluates its performance via extensive simulation experiments. Expand
DeepNap: Data-Driven Base Station Sleeping Operations Through Deep Reinforcement Learning
• Computer Science
• IEEE Internet of Things Journal
• 2018
Experiments show that both the end-to-end and the model-assisted version of DeepNap outperform table-based ${Q}$ -learning algorithm and the nonstationarity enhancements improve the stability of vanilla DQN. Expand
Network Slicing for 5G: Challenges and Opportunities
• Xin Li, +4 authors R. Jain
• Computer Science
• IEEE Internet Computing
• 2017
The authors discuss this technology’s background and propose a framework for network slicing for 5G, and discuss remaining challenges and future research directions. Expand