Efficient RSOA modelling using polar complex-valued neural networks

This work presents an effective solution to reduce the computational complexity order of behavioral model generation for reflective semiconductor optical amplifier (RSOA). The proposed model is based on a complex valued (CV) neural network (CVNN) structure, using polar CV basis functions architecture. The CV model parameters are extracted by means of nonlinear complex-domain Levenberg–Marquardt algorithm, from recorded experimental 20 Msymbol/s 64-quadrature amplitude modulation (QAM) input–output data. The evaluation results of polar CVNN model prove to be more adequate to accurately describe the nonlinear dynamic magnitude and phase distortions of RSOA, compared to double-input double-output real-valued neural network (RVNN) rectangular structure. Additionally, significant reduction of the computational cost is achieved in comparison to the RVNN approach.