Time Reduction for SLM OFDM PAPR Based on Adaptive Genetic Algorithm in 5G IoT Networks

In this paper, a new peak average power and time reduction (PAPTR) based on the adaptive genetic algorithm (AGA) strategy is used in order to improve both the time reduction and PAPR value reduction for the SLM OFDM and the conventional genetic algorithm (GA) SLM-OFDM. The simulation results demonstrate that the recommended AGA technique reduces PAPR by about 3.87 dB in comparison to SLM-OFDM. Comparing the suggested AGA SLM-OFDM to the traditional GA SLM-OFDM using the same settings, a significant learning time reduction of roughly 95.56% is achieved. The PAPR of the proposed AGA SLM-OFDM is enhanced by around 3.87 dB in comparison to traditional OFDM. Also, the PAPR of the proposed AGA SLM-OFDM is roughly 0.12 dB worse than that of the conventional GA SLM-OFDM.

Automated summary

This paper proposes a new peak average power and time reduction strategy based on the adaptive genetic algorithm (AGA) to improve the time reduction and PAPR value reduction for SLM OFDM. Simulation results show that the recommended AGA technique reduces PAPR by about 3.87 dB compared to SLM-OFDM, and achieves a significant learning time reduction of roughly 95.56% compared to traditional GA SLM-OFDM. The proposed AGA SLM-OFDM has an enhanced PAPR of around 3.87 dB compared to traditional OFDM, but is roughly 0.12 dB worse than the conventional GA SLM-OFDM.