Machine learning-optimized relay selection method for mitigating interference in next generation communication networks

In an effective Wireless Network (WN), low latency and reliability are essential to provide adequate infrastructure for better communication. Cooperative Communication is one efficient way to achieve these wireless network goals. In this research, the machine learning-based Decode and Forward (DF) coding was developed in conjunction with the network coding algorithm to improve cooperative communication and system functionality that select relays which will not cause interference in a wireless network. Here, the Interference-Thwarting Relay Selection (ITRS) technique is intended to aid reliable communication while reducing self-interference. It is possible to monitor and measure suitable relays in the communication process with the help of a machine learning system. Thus, the proposed Interference-Thwarting Relay Selection technique is implemented with the parameters like Bit Error Rate (BER) as 10 −6 , Signal to Noise Ratio (SNR) as 36 dB, Symbol Error Rate (SER) as 10 −8 and throughput with the power allocation factors. The simulated Machine Learning-Optimized Relay Selection Method (ML-ORSM) results achieve the improved optimal power allocation with symbol error rate.