Abstract

This study introduces an adaptive network optimization framework grounded in fuzzy logic and rule-based machine learning for cognitive radio systems. The primary objective is the concurrent minimization of interference, congestion, and bit error rate, coupled with enhancements in throughput and signal-to-noise ratio. A comprehensive set of rules, guided by linguistic variables for qualitative network aspects, is established alongside membership functions for quantitative analysis.The incorporation of machine learning into our approach enables adaptability to diverse network conditions, resulting in overall improved efficiency. The positive impact of machine learning is particularly evident in the reduction of congestion during specific timeframes. Specifically, on Saturday at hour 6, congestion decreases from the conventional 3.055 to 2.86. This notable improvement underscores the efficacy of machine learning in expediting the sensing mechanism of secondary users, facilitating the rapid identification of unused channels from primary users. The findings contribute to the advancement of cognitive radio systems, providing a robust and adaptable solution to address the intricate dynamics of modern wireless networks.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call