Abstract: The rapid development of communications industry has spawned more new services and applications. The sixth-generation wireless communication system (6G) network is faced with more stringent and diverse requirements. While ensuring performance requirements, such as high data rate and low latency, the problem of high energy consumption in the fifth-generation wireless communication system (5G) network has also become one of the problems to be solved in 6G. The wide-area coverage signaling cell technology conforms to the future development trend of radio access networks, and has the advantages of reducing network energy consumption and improving resource utilization. In wide-area coverage signaling cells, on-demand multi-dimensional resource allocation is an important technical means to ensure the ultimate performance requirements of users, and its effect will affect the efficiency of network resource utilization. This paper constructs a user-centric dynamic allocation model of wireless resources, and proposes a deep Q-network based dynamic resource allocation algorithm. The algorithm can realize dynamic and flexible admission control and multi-dimensional resource allocation in wide-area coverage signaling cells according to the data rate and latency demands of users. According to the simulation results, the proposed algorithm can effectively improve the average user experience on a long time scale, and ensure network users a high data rate and low energy consumption.

基于DQN的广域覆盖信令小区以用户为中心的动态多维资源分配

[1]Gang J, Friderikos V, 2019. Inter-tenant resource sharing and power allocation in 5G virtual networks. IEEE Trans Veh Technol, 68(8):7931-7943.

[2]Ji CY, Bi MH, Zhou Z, et al., 2021. Online bandwidth resources allocation algorithm for multi-tenancy PON based on deep reinforcement learning. Opt Commun Technol, 45(9):36-39 (in Chinese).

[3]Kalil M, Al-Dweik A, Sharkh MFA, et al., 2017. A framework for joint wireless network virtualization and cloud radio access networks for next generation wireless networks. IEEE Access, 5(1):20814-20827.

[4]Lin MT, Zhao YP, 2020. Artificial intelligence-empowered resource management for future wireless communications: a survey. China Commun, 17(3):58-77.

[5]Liu GY, Deng J, Zheng QB, et al., 2022a. Native intelligence for 6G mobile network: technical challenges, architecture and key features. J China Univ Posts Telecommun, 29(1):27-40.

[6]Liu GY, Li N, Deng J, et al., 2022b. The SOLIDS 6G mobile network architecture: driving forces, features, and functional topology. Engineering, 8(1):42-59.

[7]Luo Y, Shi ZP, Zhou X, et al., 2014. Dynamic resource allocations based on Q-learning for D2D communication in cellular networks. 11^th Int Computer Conf on Wavelet Active Media Technology and Information Processing, p.385-388.

[8]Lü YP, Jia XD, Lu Y, et al., 2021. A deep Q-learning based resource allocation algorithm in indoor wireless networks. Comput Eng Sci, 43(7):1250-1255 (in Chinese).

[9]Ren YJ, Sun YH, Peng MG, 2021. Deep reinforcement learning based computation offloading in fog enabled Industrial Internet of Things. IEEE Trans Ind Inform, 17(7):4978-4987.

[10]Xu H, Tong Z, Shen H, et al., 2021. Dynamic communication and computation resource allocation algorithm for end-to-end slicing in mobile networks. 3^rd Int Conf on Artificial Intelligence for Communications and Networks, p.251-267.

[11]Zhang TK, Wang XF, Yang LW, et al., 2021. A SFC deployment and computation resource allocation joint algorithm in mobile networks. J Beijing Univ Posts Telecommun, 44(1):7-13 (in Chinese).

[12]Zhao QY, Grace D, Vilhar A, et al., 2015. Using K-means clustering with transfer and Q learning for spectrum, load and energy optimization in opportunistic mobile broadband networks. Int Symp on Wireless Communication Systems, p.116-120.