Comprehensive Learning Particle Swarm Optimization based TSK structure identification and its application in OFDM receiver for nonlinear channel equalization

This paper presents a first order Takagi-Sugeno-Kang (TSK) type fuzzy equalizer to mitigate nonlinear power amplifier distortion effects from the received signal in orthogonal frequency division multiplexing (OFDM) systems. Here we propose a Comprehensive Learning Particle Swarm Optimizer (CLPSO) based structure identification of the TSK equalizer. CLPSO uses a new learning strategy that achieves the goal to accelerate the convergence of the classical particle swarm optimization (PSO) to the global optimal values. Unlike gradient based techniques CLPSO has the capability to escape from the traps of local optima while obtaining the values of nonlinear premise parameters of TSK equalizer. In this work, proposed equalization technique reduces the adverse nonlinear distortion effects at receiver in a Rayleigh faded OFDM communication system and a significant improvement in bit error rate (BER) performance is achieved. Computer Simulations show improved bit error rate (BER) and mean square error (MSE) performances of this novel PSO based TSK equalization in OFDM receiver compared to the latest power amplifier nonlinearity cancellation (PANC) technique.