Abstract: The coexistence of ultra-reliable low-latency communication (URLLC) and enhanced mobile broadband (eMBB) services in 5G-based industrial wireless networks (IWNs) poses significant resource slicing challenges due to their inherent performance requirement conflicts. To address this challenge, this paper proposes a puncturing method that uses a model-aided deep reinforcement learning (DRL) algorithm for URLLC over eMBB services in uplink 5G networks. First, a puncturing-based optimization problem is formulated to maximize the eMBB accumulated rate under strict URLLC latency and reliability constraints. Next, we design a random repetition coding-based contention (RRCC) scheme for sporadic URLLC traffic and derive its analytical reliability model. To jointly optimize the scheduling parameters of URLLC and eMBB, a DRL solution based on the reliability model is developed, which is capable of dynamically adapting to changing environments. The accelerated convergence of the model-aided DRL algorithm is demonstrated using simulations, and the superiority in resource efficiency of the proposed method over existing approaches is validated.

面向5G工业无线网络的URLLC与eMBB混合业务上行链路穿刺传输：一种模型辅助深度强化学习方法

[1]3GPP, 2018. NR; Physical Layer Procedures for Data. Release 15. Technical Report No. 3GPP TS 38.214 v15.1.0. https://www.3gpp.org [Accessed on Mar. 16, 2025].

[2]Abreu R, Jacobsen T, Pedersen K, et al., 2019. System level analysis of eMBB and grant-free URLLC multiplexing in uplink. IEEE 89^th Vehicular Technology Conf, p.1-5.

[3]Alsenwi M, Tran NH, Bennis M, et al., 2021. Intelligent resource slicing for eMBB and URLLC coexistence in 5G and beyond: a deep reinforcement learning based approach. IEEE Trans Wirel Commun, 20(7):4585-4600.

[4]Ding JF, Zheng M, 2022. Resource allocation and retransmission scheme for URLLC in industrial wireless networks with mixed traffic. IEEE 20^th Int Conf on Industrial Informatics, p.630-635.

[5]Ding JF, Zheng M, Wang YT, et al., 2024. A probabilistic repetition coding-based access method for sporadic traffic. IEEE Trans Veh Technol, 73(9):14080-14085.

[6]Elayoubi SE, Brown P, Deghel M, et al., 2019. Radio resource allocation and retransmission schemes for URLLC over 5G networks. IEEE J Sel Areas Commun, 37(4):896-904.

[7]Feng L, Zi YQ, Li WJ, et al., 2020. Dynamic resource allocation with RAN slicing and scheduling for URLLC and eMBB hybrid services. IEEE Access, 8:34538-34551.

[8]Filali A, Mlika Z, Cherkaoui S, et al., 2022. Dynamic SDN-based radio access network slicing with deep reinforcement learning for URLLC and eMBB services. IEEE Trans Netw Sci Eng, 9(4):2174-2187.

[9]Han XH, Xiao K, Liu RQ, et al., 2022. Dynamic resource allocation schemes for eMBB and URLLC services in 5G wireless networks. Intell Converged Netw, 3(2):145-160.

[10]Huang Y, Li SR, Li CZ, et al., 2020. A deep-reinforcement-learning-based approach to dynamic eMBB/URLLC multiplexing in 5G NR. IEEE Int Things J, 7(7):6439-6456.

[11]Ji H, Park S, Yeo J, et al., 2018. Ultra-reliable and low-latency communications in 5G downlink: physical layer aspects. IEEE Wirel Commun, 25(3):124-130.

[12]Jiang XT, Liang K, Chu XL, et al., 2023. Multiplexing eMBB and URLLC in wireless powered communication networks: a deep reinforcement learning-based approach. IEEE Wirel Commun Lett, 12(10):1716-1720.

[13]Kassab R, Simeone O, Popovski P, 2018. Coexistence of URLLC and eMBB services in the C-RAN uplink: an information-theoretic study. IEEE Global Communications Conf, p.1-6.

[14]Khodakhah F, Stefanovic C, Mahmood A, et al., 2023. NOMA or puncturing for uplink eMBB-URLLC coexistence from an AOI perspective? IEEE Global Communications Conf, p.4301-4306.

[15]Lee K, Kim S, Kim J, et al., 2018. DRaMa: device-specific repetition-aided multiple access for ultra-reliable and low-latency communication. IEEE Int Conf on Communications, p.1-6.

[16]Li J, Zhang X, 2020. Deep reinforcement learning-based joint scheduling of eMBB and URLLC in 5G networks. IEEE Wirel Commun Lett, 9(9):1543-1546.

[17]Liu YW, Clerckx B, Popovski P, 2024. Network slicing for eMBB, URLLC, and MMTC: an uplink rate-splitting multiple access approach. IEEE Trans Wirel Commun, 23(3):2140-2152.

[18]Ma Z, Xiao M, Xiao Y, et al., 2019. High-reliability and low-latency wireless communication for Internet of Things: challenges, fundamentals, and enabling technologies. IEEE Int Things J, 6(5):7946-7970.

[19]Nomeir MW, Gadallah Y, Seddik KG, 2021. Uplink scheduling for mixed grant-based eMBB and grant-free URLLC traffic in 5G networks. 17^th Int Conf on Wireless and Mobile Computing, Networking and Communications, p.187-192.

[20]Nomeir MW, Gadallah Y, Seddik KG, 2023. Machine learning-based uplink scheduling approaches for mixed traffic in cellular systems. IEEE Access, 11:10238-10253.

[21]Popovski P, Trillingsgaard KF, Simeone O, et al., 2018. 5G wireless network slicing for eMBB, URLLC, and MMTC: a communication-theoretic view. IEEE Access, 6:55765-55779.

[22]Sardar AA, Rao AS, Alpcan T, et al., 2024. Network resource allocation for Industry 4.0 with delay and safety constraints. IEEE Trans Cogn Commun Netw, 10(1):223-237.

[23]Setayesh M, Bahrami S, Wong VWS, 2022. Resource slicing for eMBB and URLLC services in radio access network using hierarchical deep learning. IEEE Trans Wirel Commun, 21(11):8950-8966.

[24]Singh B, Tirkkonen O, Li ZX, et al., 2018. Contention-based access for ultra-reliable low latency uplink transmissions. IEEE Wirel Commun Lett, 7(2):182-185.

[25]Song QJ, She CY, Zheng FC, 2022. Optimization of repetition scheme for URLLC with diverse reliability requirements. IEEE 95^th Vehicular Technology Conf, p.1-5.

[26]Tian KX, Wang YT, Pan DT, et al., 2024. DRL-based dynamic resource configuration and optimization for B5G network slicing. IEEE Access, 12:120864-120876.

[27]van Hasselt H, Guez A, Silver D, 2016. Deep reinforcement learning with double Q-learning. Proc 30^th AAAI Conf on Artificial Intelligence, p.2094-2100.

[28]Xiao K, Liu X, Han XH, et al., 2020. Flexible multiplexing mechanism for coexistence of URLLC and eMBB services in 5G networks. ITU Kaleidoscope: Industry-Driven Digital Transformation, p.1-9.

[29]Yuan JT, Yu GD, Yin R, et al., 2020. Group-based data transmission protocol for small-sized URLLC services. IEEE Wirel Commun Lett, 9(9):1432-1436.

[30]Zaki-Hindi A, Elayoubi SE, Chahed T, 2020. URLLC and eMBB coexistence in unlicensed spectrum: a preemptive approach. Int Wireless Communications and Mobile Computing, p.229-234.

[31]Zhao LL, Ma SD, Chen WZ, et al., 2023. Semi-probabilistic repetition schemes for sporadic URLLC traffic in multiuser massive MIMO systems. IEEE Trans Commun, 71(4):2104-2120.

[32]Zhou Y, Feng ZY, Song ZQ, et al., 2025. Integrated sensing, communication, and control driven multi-AGV closed-loop control. IEEE Trans Veh Technol, 74(7):10853-10868.