Energy Enhancement of WSN with Deep Learning based SOM Scheduling Algorithm

Abstract

Energy efficiency is one of the primary requirements for designing a successful Wireless Sensor Network (WSN) model. The WSN systems are generally made with a group of nodes that are operated with a small size battery device. To improve the energy efficiency of such WSNs several methodologies like clustering approach, mobile node technique and optimal route planning designs were developed. Scheduling method is yet an efficient model that is widely used in WSN applications, that allows the nodes to be operated only for a certain prescribed time. The proposed work utilizes the Self Organizing Maps (SOM) approach for improving the performances of the scheduling algorithms to a certain limit. SOM is a kind of artificial neural network that analyzes the problem based on competitive learning rather than the backpropagation methods. The work compares the proposed algorithm with the traditional Ant Colony and Software Defined Network approaches, wherein the proposed approach has shown an improvement in terms of energy conservation and network lifetime.