H∞-dCNN: Enhancing the SNR using Deep Learning Algorithm in Wireless Communication System

In Wireless communication systems, the deep learning-based convolution neural networks (dCNN) are performed to gain a better improvement of quality of services (QoS) with higher signal-to-noise ratio (SNR). Multiple-input and multiple-output systems are presented for real-time evaluation from various technologies, which has served the purpose of services in improving the communication performance of the physical layer of the wireless network. By increasing the communication throughput by focusing on resource allocation, the overall efficiency was not up to the market due to the network’s dynamic behavior. This article proposes the system in two different stages to express the analytical solution for decreasing the bit error rate (BER). The first is to employ the Hybrid Infinity (H∞) through the channel for better robustness in wireless network computing. Next is to optimize bit error rate (BER) with carrier detection as well as other criteria for improving service quality by analyzing the network behavior using deep learning algorithm. The deep convolution neural network with Hybrid Infinity (H∞—dCNN) is implemented and evaluates the low BER values with high SNR for the performance of QoS. Thus, H∞—dCNN is proved and outperform the simulated results with better characteristics by using the MATLAB software. Hence, the mathematical expression for the proposed system is noticed that a significant improvement is obtained in terms of BER lesser than 0.6e−4. It is observed the SNR lesser than 18 dB, which is comparatively best than the baseline method.