Outage Performance of Multihop Networks Using Reconfigurable Intelligent Surface by Deep Learning Methods

In this paper, we analyze the performance of reconfigurable intelligent surface (RIS)-assisted multihop networks in terms of outage probability (OP) and average symbol error rate (ASER) over Rayleigh fading channels to enhance network coverage and improve system reliability. Specifically, the destination node receives data through RISs on a per-hop basis. We derive closed-form expressions for the OP and ASER under Rayleigh fading conditions and provide upper bounds to provide further analytical insights. In addition, based on numerical results, we develop a deep learning model to estimate system performance. The results demonstrate excellent agreement, confirming the accuracy of both the analytical approach and the deep learning model.