Predicting and Classifying Ofdm Modulated Signals for 6G Wireless Network

Since many countries have adopted the fifth generation (5 G) mobile communication systems, and many users have subscribed to this new system, there is a growing interest in the subsequent sixth generation (6 G). This paper gives a systemic overview of 6 G and helps to understand the future research prospect after 5 G. In more detail, it focuses on the application of Orthogonal Frequency-Division Multiplexing (OFDM) in 6 G networks. Therefore, by discussing OFDM principles, the current applications, and future possibilities, or this research seeks to explain how it might be useful in 6G. Hence by trying to model and simulate OFDM and comparing the performance with different QAM schemes it demonstrates that OFDM offers high data throughput, spectral efficiency, low delay and distortion immunity. Also, the use of Long Short Term Memory (LSTM), Gated Recurrent Unit (GRU), and Transform models for predictive analysis of OFDM signal improves the 6 G networks applications. Further, we have used Discrete Wavelet Transform (DWT) to extract features of different Quadrature Amplitude Modulation (QAM) schemes and classify them using random forest classifier. The insights and further research opportunities provided should help to enhance the OFDM characteristics and enable its application for advanced wireless communication technologies that are expected to define the prospects of the 6 G network. Testing of OFDM in 6 G networks delivered throughput as high as 2012.77 Gbps, spectral efficiencies up to 16380 bps/s/Hz, and 80 ms latency at all QAM modulations.