Application of soft computing technique for optical add/drop multiplexer in terms of OSNR and optical noise power

The demand for transmission capacity is increasing day by day which forces the service providers to enhance their network performance for increasing data rates or number of wavelengths in Dense Wavelength Division Multiplexing systems. The most important element which decides the signal to be transmitted through the DWDM system is the Optical Add or Drop Multiplexer (OADM) which can drop or add the signal from or to the DWDM network based on the network requirements. In this paper a performance improved OADM is proposed with artificial intelligence. The work proposed contains three phases: Initially the DWDM network is modeled in the OptSystem which is an optical simulation network tool and the parameters such as Optical Signal to Noise Ratio(OSNR), Jitter, Chromatic Dispersion and Bit Error Rate(BER) and are obtained, which are used for training the Feed Forward Artificial Neural Network (FF-ANN) in second phase. Finally in the third phase, testing of the signal is carried out for classification of signals. MATLAB is used for training and testing of the FF-NN by interfacing the results from Optisystem and the classification accuracy of the proposed method is given. At last, the performance of the proposed method in terms of OSNR & Optical Noise Power is analyzed and compared with the existing methods.