Performance Analysis of Deep Learning Based Autoencoders for Single Carrier and OFDM Systems

Abstract

The autoencoder (AE) is utilized to model an entire system of Single Carrier (SC) Communication and Orthogonal Frequency Division Multiplexing (OFDM). In this model, Deep Neural Networks (DNNs) represent the transmitter and receiver for encoding, modulation, demodulation, and decoding. The effectiveness of this approach is demonstrated by its ability to outperform traditional communication systems in real-world scenarios that involve channel and interference effects, as measured by the Block Error Rate (BLER). AI-enabled wireless systems can overcome limitations of traditional communication systems by learning from wireless spectrum data and optimizing performance for new wireless applications. This paper explores the use of autoencoder-based deep learning to improve the performance of an End-to-End communication system for Single Carrier and OFDM. The architecture effectively addresses channel impairments and improves overall performance. The simulation results suggest that even when the autoencoder's channel layer is affected by impairments, autoencoders still outperform traditional communication systems in terms of BLER performance.