Researchers Develop GA-PTS + CNN Technique for Mitigating PAPR in FBMC Systems

Strategic Insights -

Investigators from New Horizon College of Engineering in Bengaluru, India, have published a new report on a promising technique for next-generation wireless systems. The Filter Bank Multicarrier (FBMC) system is a candidate for wireless systems due to its superior spectral efficiency and resilience to synchronization errors. However, its high Peak-to-Average Power Ratio (PAPR) remains a challenge affecting power efficiency and nonlinear distortion performance.

The researchers propose a GA-assisted partial transmit sequence with a convolutional neural network (GA-PTS + CNN) technique to mitigate PAPR in FBMC systems. The method optimally selects phase factors using a Genetic Algorithm (GA) while leveraging a CNN for adaptive learning, accelerating convergence, and improving system robustness. The proposed approach was validated through numerical simulations under Rayleigh and Rician fading channels and compared with conventional PAPR reduction techniques, including Clipping and Filtering (C&F), Selective Mapping (SLM), Partial Transmit Sequence (PTS), and Particle Swarm Optimization (PSO)-aided PTS.

Key Takeaways:

  • The GA-PTS + CNN technique effectively reduces PAPR in FBMC systems by 2-3 dB in Rayleigh fading and 1.5-3 dB in Rician fading.
  • The proposed approach demonstrates a significant improvement in Bit Error Rate (BER) analysis, revealing an SNR gain of 2.5-6.5 dB at BER = 10-4 with 256-QAM in Rayleigh fading and 3-5 dB gain in Rician fading.
  • The technique also shows a consistent improvement in BER for 64-QAM, with a gain of 4-10 dB.
  • The GA-PTS + CNN technique is a practical and robust solution for future wireless networks, including 5G and beyond.
  • Researcher Arun Kumar stated, "The proposed method optimally selects phase factors using a Genetic Algorithm while leveraging a CNN for adaptive learning, accelerating convergence, and improving system robustness."
  • The study was published in Ain Shams Engineering Journal, Vol. 16, No. 7, 2025, with Article ID 103434.

Statistics:

  • PAPR reduction in Rayleigh fading: 2-3 dB
  • PAPR reduction in Rician fading: 1.5-3 dB
  • SNR gain at BER = 10-4 with 256-QAM in Rayleigh fading: 2.5-6.5 dB
  • SNR gain at BER = 10-4 with 256-QAM in Rician fading: 3-5 dB
  • Gain in BER for 64-QAM: 4-10 dB

Sources:

  • Ain Shams Engineering Journal, Vol. 16, No. 7, 2025, with Article ID 103434 (https://doi-org.sdpl.idm.oclc.org/10.1016/j.asej.2025.103434)
  • NewsRx. Researchers from New Horizon College of Engineering Discuss Research in Engineering (Genetic algorithm-based PTS with CNN for PAPR and BER reduction in FBMC systems under fading channels). Life Science Weekly. July 8, 2025; p 5720.