Abstract
The stringent requirements of ultra-reliable low-latency communication (URLLC) contribute to an enhanced service experience for user equipments (UEs). However, it also poses a challenge to the design of security strategies when UEs require multiple businesses while the communication resources are constrained. This letter focuses on the security and reliability of URLLC for uplink transmission in cell-free massive multiple-input multiple-output (CF-mMIMO) systems. We define a new metric, secure and reliable probability (SRP), to characterize the trade-off between secure and reliable services in the system. Furthermore, we propose a power control approach based on self-supervised learning, which adjusts the user's power allocation strategy to meet maximum security or maximum reliability requirements of different UEs and improve the performance of the whole system. Finally, extensive simulation results validate the effectiveness of the proposed approach.