Journal
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
Volume 70, Issue 10, Pages 10792-10803Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TVT.2021.3103416
Keywords
Resource management; Real-time systems; 5G mobile communication; Reinforcement learning; Heuristic algorithms; Ultra reliable low latency communication; Quality of service; 5G; network slicing; multi-agent reinforcement learning; graph attention network; resource management
Categories
Funding
- National Key R&D Program of China [2020YFB1804804]
- National Natural Science Foundation of China [61731002, 62071425]
- Zhejiang Key Research and Development Plan [2019C01002, 2019C03131]
- Huawei Cooperation Project
- Zhejiang Lab [2019LC0AB01]
- Zhejiang Provincial Natural Science Foundation of China [LY20F010016]
Ask authors/readers for more resources
This paper proposes a multi-agent reinforcement learning (MARL) algorithm for designing real-time slice resource management strategies in multi-base station networks. By applying graph attention network (GAT) to enhance the cooperation between base stations and integrating GAT into deep reinforcement learning, an intelligent real-time resource management strategy is designed.
Network slicing (NS) management devotes to providing various services to meet distinct requirements over the same physical communication infrastructure and allocating resources on demands. Considering a dense cellular network scenario that contains several NS over multiple base stations (BSs), it remains challenging to design a proper real-time inter-slice resource management strategy, so as to cope with frequent BS handover and satisfy the fluctuations of distinct service requirements. In this paper, we propose to formulate this challenge as a multi-agent reinforcement learning (MARL) problem in which each BS represents an agent. Then, we leverage graph attention network (GAT) to strengthen the temporal and spatial cooperation between agents. Furthermore, we incorporate GAT into deep reinforcement learning (DRL) and correspondingly design an intelligent real-time inter-slice resource management strategy. More specially, we testify the universal effectiveness of GAT for advancing DRL in the multi-agent system, 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). Finally, we verify the superiority of the GAT-based MARL algorithms through extensive simulations.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available