基于多智能体DDQN的路由与用户关联联合优化

肖 飞
西北师范大学

摘要


随着用户对高速数据服务需求的不断攀升，毫米波技术凭借其丰富的带宽资源，成为5G及未来网络的关键
技术。尽管多跳毫米波接入与回传一体化网络（IABN）在提升频谱效率方面具有潜力，却也带来了网络干扰和管理
上的复杂性。本文研究了IABN中路由选择和用户关联的联合优化问题，该问题是一个混合整数非线性规划问题。鉴
于IABN环境的动态性，我们设计了一种基于多智能体双深度Q网络（MADDQN）的优化策略，利用并行处理和分
布式训练机制，动态调整决策，以增强网络的总吞吐量。实验结果验证了该策略在提升频谱利用率、用户服务质量
和链路传输效率方面的有效性。

关键词


格式要求；毫米波；IABN；路由选择；用户关联；深度强化学习；MADDQN

全文:

PDF


参考


[1]W. Hong, Z. Jiang and C. Yu et al.,“The Role

of Millimeter-Wave Technologies in 5G/6G Wireless

Communications”, IEEE J. Micro., vol. 1, no. 1, Jan.

2021,pp. 101-122.

[2]H. Singh, V. Kumar, K. Saxena, B. G. Bonev,R.

Prasad and V. M. Kapse, "Computational Intelligent

method for Cloud Layer Classification using Millimeter

Wave Technology for Designing of 6G Network," 2022

57th International Scientific Conference on Information,

Communication and Energy Systems and Technologies,

Ohrid, North Macedonia, 2022, pp. 1-3

[3]B. -S. Zhang, X. -W. Zhu and X. -L. Yang, "A

Sixth-Order SIW Wideband Filter for 5G Millimeter Wave

Application," 2022 International Conference on Microwave

and Millimeter Wave Technology (ICMMT), Harbin, China,

2022, pp. 1-3

[4]Z. Zha, L. Wang, C. Huang and C. Kai, "Quick

Matching for Interference Coordination in Ultra-Dense

Networks," in IEEE Wireless Communications Letters, vol. 9,

no. 1, pp. 47-50, Jan. 2020

[5]M. Polese et al.,“Integrated access and backhaul

in 5GmmWave networks:Potential and challenges,”IEEE

Commun. Mag., vol. 58, no. 3, pp. 62–68,Mar. 2020

[6]3rd Generation Partnership Project (3GPP),“Study

on Integrated Access and Backhaul,”3GPP, Sophia Antipolis

technology park, France, Tech.Rep. 38.874, 2018.

[7]C. Saha, M. Afshang, and H. S. Dhillon,“Bandwidth

partitioning and downlink analysis in millimeter wave

integrated access and backhaul for 5G,”IEEE Trans. Wireless

Commun., vol. 17, no. 12, pp. 8195–8210,Dec. 2018.

[8]R. S. Sutton and A. G. Barto, Reinforcement

Learning: An Introduction. Cambridge, MA, U.K.: MIT

Press, 2018.

[9]H. Ye, G. Y. Li, and B.-H. F. Juang,“Deep

reinforcement learning for resource allocation in V2V

communications, ”IEEE Trans. Veh. Technol., vol. 68, no. 4,

pp. 3163–3173, Apr. 2019.

[10]M. M. Sande, M. C. Hlophe and B. T.

Maharaj, "Instantaneous Load-Based User Association

in Multi-Hop IAB Networks using Reinforcement

Learning," GLOBECOM 2020 - 2020 IEEE Global

Communications Conference, Taipei, Taiwan, 2020, pp. 1-6


Refbacks

  • 当前没有refback。