• A model-aided deep reinforcement learning algorithm is proposed to jointly optimize puncturing and scheduling for URLLC/eMBB coexistence in uplink 5G industrial wireless networks.
• A random repetition coding-based contention (RRCC) scheme is designed for sporadic URLLC traffic, with an analytical reliability model that enables robust decision-making.
• The model-aided DRL approach accelerates convergence and adapts dynamically to changing network conditions, balancing strict URLLC latency/reliability with eMBB throughput.
• Simulations demonstrate superior resource efficiency of the proposed method over existing approaches, confirming its practical value for 5G industrial automation.