An efficient impulsive noise cancellation scheme for power-line communication systems using ANFIS and chaotic interleaver

Impulsive noise is one of the main disturbances that damage the data transmission over power-line communication (PLC) systems. This paper presents an adaptive noise cancellation approach based on the adaptive neuro-fuzzy inference system (ANFIS) and a chaotic interleaver, namely ANC-CI-ANFIS scheme for impulsive noise estimation and suppression from the OFDM PLC channel. The ANFIS is based on a hybrid learning algorithm to identify parameters of Sugeno-type fuzzy inference system. Accordingly, fuzzy membership function parameters are trained using a combination of both least-square and back propagation gradient descent algorithms to emulate a given training data set. Furthermore, transmitted data are managed with a chaotic interleaver to secure data transmission and give more robustness against impulsive bursts. Simulation results are carried out on an OFDM PLC transmission chain compatible with the HomePlug AV standard under different impulsive noise scenarios. The results demonstrated the scheme's ability to detect and remove the impulsive noise from the PLC channel while keeping a high security level by using the chaotic interleaver. The major advantage of this system is its ease of implementation and faster convergence rate.