A BP Neural Network Based Punctured Scheduling Scheme Within Mini-slots for Joint URLLC and eMBB Traffic

To satisfy the strict latency requirement of Ultra Reliable Low Latency Communications (URLLC) traffic, it is usually scheduled on resources occupied by enhanced Mobile Broadband (eMBB) transmissions at the expense of a highly degraded eMBB spectral efficiency (SE). In this paper, we propose a back propagation neural network (BPNN) based punctured scheduling scheme to address the URLLC placement problem on eMBB traffic within mini-slots. In the proposed scheme, we first design a three-layer BPNN to predict decoding probability of eMBB users with different puncturing situation, then scheduler will select the eMBB user with the least potential throughput loss to puncture. Simulation results demonstrate that the proposed scheme can efficiently reduce the loss of throughput and improve the reliability of eMBB users.