Improved buffalo optimized deep feed forward neural learning based multipath routing for energy efficient data aggregation in WSN

Abstract

Wireless sensor networks comprised inadequate computational power and memory for application developers.Data aggregation is the method of gathering the useful information. Data aggregation is the new process for reducing the energy consumption. In WSN, data aggregation is an efficient method with limited resources. Many classification methods were introduced for performing data aggregation in WSN. But, the energy consumption and delay was not reduced by existing techniques. In order to address these problems, an Improved Buffalo Optimized Route Selective Deep Feed Forward Neural Learning (IBORSDFFNL) Model is introduced. The main objective of the IBORSDFFNL Model is to construct multiple paths for efficient data aggregation in WSN. IBORSDFFNL Model carried out route path discovery process and optimal route path selection process. The multiple route paths are constructed from distributed sensor nodes. Among the constructed route paths, an optimal route path is chosen by using improved buffalo optimization for performing efficient data aggregation in WSN. After selecting efficient optimal route path, data aggregation process is carried out with minimal delay and higher packet delivery ratio. Experiments are carried out to determine the performance in terms of end-to-end delay, energy consumption and packet delivery ratio.Simulation results show that the proposed model attained lesser energy consumption and end-to-end delay for data aggregation and increases the packet delivery ratio in WSNs.