Age Prediction for Energy-Aware Communication in WSN Using Hybrid Optimization-Enabled Deep Belief Network

Abstract

To perceive the data utilizing sensor nodes, wireless sensor network (WSN) consists of several nodes connected to a wireless channel. However, the sink node, also known as a base station (BS), provides power to the WSN and acts as an access node for a number of the network’s sensor devices. Weather monitoring, field surveillance, and the collection of meteorological data are just a few of the various uses for WSN. The energy of each node directly affects how long a wireless network will last. So, to increase the lifespan of WSN, effective routing is required. Using the suggested Taylor sea lion optimization-based deep belief network (TSLnO-based DBN), the ultimate purpose of this research is to build a method for energy-aware communication in WSN. In the setup stage, cluster head (CH) is chosen using a hybrid optimization technique called ant lion whale optimization (ALWO), which is created by fusing the whale optimization algorithm (WOA) and ant lion optimizer (ALO). It is important to note that CH’s selection criteria are solely based on fitness factors such as energy and distance. The second phase, known as the steady state step, is when the updating of energy and trust takes place. In the prediction phase, the network classifier is trained using a newly created optimization method called TSLnO, and the age of neighbor nodes is predicted by estimating the energy of neighbors using DBN. By combining the Taylor Series and the sea lion optimization (SLnO) method, the proposed TSLnO is produced. The communication/route discovery phase, which occurs in the fourth phase, is where the path through nearby nodes is chosen. The maintenance phase of the route is the fifth phase.