IRS-aided cognitive radio short-packet communications over Nakagami-m fading channels: BLER analysis and deep learning evaluation

This study investigates intelligent reflecting surface (IRS)-assisted cognitiveradio (CR) short-packet communication (SPC) networks. In the secondarynetwork, a base station communicates with a user with support from an IRS ina Nakagami-m fading environment. We aimed to evaluate the block error rate(BLER) performance of the secondary network under a limited interferencetemperature for scenarios with the presence and absence of a direct basestation-user link. To this end, we employed two approaches: (i) conventionalmathematical analysis and (ii) data-driven performance evaluation. For theformer, closed-form expressions of the average BLER and asymptotic averageBLER of the secondary user were derived analytically. For the latter, a deepneural network (DNN) model was constructed to evaluate BLER as a regres-sion problem. A Monte Carlo simulation approach was adopted to verify theaccuracy of the derived analytical BLER and DNN-based BLER performanceevaluations. We determined that coherently utilizing both direct and IRS-reflecting links can significantly enhance the BLER performance of IRS-aidedCR SPC networks.