Parveen Bajaj ¹, A. K. Goel ², Harbhajan Singh ³

Affiliations
1 Department of Electronics and Communication Engineering, IKGPTU, Near Pushpa Gujral Science City, Ibban, Distt. Kapurthala, Kapurthala - 144603, Jalandhar, Punjab, IN
2 Department of Electronics and Communication Engineering, Maharaja Ranjit Singh State Technical University, Dabwali Road, Bathinda - 151001, Punjab, IN
3 Department of Electronics & Communication Engineering, SSIET, Saraswati Vihar, Mohali, Dera Bassi - 140507,Punjab, IN

Abstract

Objectives: This paper proposed a new method for performance enhancement of Optical Add or Drop Multiplexer (OADM) with the Dense Wavelength Division Multiplexing (DWDM) based on the artificial intelligence. Methods/Statistical Analysis: The FF-NN is trained and tested in the MATLAB platform from the parameters obtained from simulation. The NN is trained for 70 signals with different number of channels and with different data rates as well as it is tested with 30 signals. The classification of the signals to be added or dropped is determined by the FF-NN. The DWDM network is initially modeled with the OptiSystem software tool with different number of channels with different data rates and channel spacing. Findings: The parameters BER, OSNR, Jitter and Chromatic Dispersion have been calculated. The training and testing of the neural network is carried out on the MATLAB platform and based on this, the signal will add/drop or allow the signal to pass. The result shows that the proposed method achieves the accuracy of 97.28% on classifying the signals to be dropped from the fiber or passed through it without any interruption regarding its ability to make the transmission with minimum error. The performance of the proposed method is also analyzed in terms of Transmitted & Received Signal Power and compared with the conventional OADM system with multiple filters. Applications/Improvements: The proposed method offers a viable solution to increase the performance of OADM with the DWDM. The improvement includes the use of hybrid algorithms, to further increase the performance.

Keywords

Dense Wavelength Division Multiplexing, Feed Forward Artificial Neural Network, Fiber Bragg Grating, Optical Multiplexer, Performance Enhancement, Signal Power.

Full Text

   

Rohan Gupta ¹, Harbhajan Singh ², Gurpreet Singh ³

Affiliations
1 Department of Electronics and Communication Engineering, IKG Punjab Technical University Kapurthala–144603, Punjab, IN
2 Department of Electronics and Communication Engineering, SSIET, Derabassi – 140507, Punjab, IN
3 Department of Computer Science Engineering, GZSCCET, Bhatinda – 151001, Punjab, IN

Abstract

Objectives: To provide characteristics of several routing algorithms by discussing the benefits and limitations in relevance to various metrics namely number of packets send, Packets dropped, delivery ratio and throughput. Methods/Statistical analysis: Some well known network simulators are available like Ns2 (Network Simulator 2), Ns3 (Network Simulator 3), OPNET, OMNeT++, Net Sim, REAL, Q. In order to achieve the objectives we shall be using simulator with the name of “network simulator - NS (version 2.35)” for the practical work. It is well known simulator and is an open source. So one can easily modify and add the new code according to their requirements. Findings: Nodes can be created in wired and wireless media using NS-2.35. These nodes can be assigned properties according to their characteristics and need of traffic. Analysis of routing algorithms has been done for 10, 30 and 40 nodes. From analysis it has been demonstrated that no. of packets dropped in AODV, DSDV, DSR and Want Net are equal to zero. No. of packets send is maximum in Want Net as compared to other routing protocols with whom the comparison has been done like AODV, DSDV and DSR. Delivery ratio is 100% in all the routing protocols AODV, DSDV, DSR and Want Net which are taken in this research paper. Throughput that represents the number of packets which are sent effectively per unit time is maximum in WAntNet as compared to other routing protocols AODV, DSDV and DSR .We have done the simulations using NS 2.35 in order to prove the benefits of WAntNet over the routing protocols that are existing in the literature. Improved performance has been attained through the WAntNet. Application/Improvements: MANET is infrastructure less network which is helpful in allocating information using movable devices. The various applications include Military Sector, Commercial Sector, Data Networks, Emergency Services and Sensor Networks.

Keywords

Mobile Adhoc Network, Routing Protocol

Full Text