Energy-Efficient Data Aggregation and Cluster-Based Routing in Wireless Sensor Networks Using Tasmanian Fully Recurrent Deep Learning Network with Pelican Variable Marine Predators Algorithm

Abstract

One of the major significant problems in the existing techniques in Wireless Sensor Networks (WSNs) is Energy Efficiency (EE) because sensor nodes are battery-powered devices. The energy-efficient data transmission and routing to the sink are critical challenges because WSNs have inherent resource limitations. On the other hand, the clustering process is a crucial strategy that can rapidly increase network lifetime. As a result, WSNs require an energy-efficient routing strategy with optimum route election. These issues are overcome by using Tasmanian Fully Recurrent Deep Learning Network with Pelican Variable Marine Predators Algorithm for Data Aggregation and Cluster-Based Routing in WSN (TFR-DLN-PMPOA-WSN) which is proposed to expand the network lifetime. Initially, Tasmanian Fully Recurrent Deep Learning Network (TFR-DLN) is proposed to elect the Optimal Cluster Head (OCH). After OCH selection, the three parameters, trust, connectivity, and QoS, are optimized for secure routing with the help of the Pelican Variable Marine Predators Optimization Algorithm (PMPOA). Finally, the proposed method finds the minimum distance among the nodes and selects the best routing to increase energy efficiency. The proposed approach will be activated in MATLAB. The efficacy of the TFR-DLN- PMPOA-WSN approach is assessed in terms of several performances. It achieves higher throughput, higher packet delivery ratio, higher detection rate, lower delay, lower energy utilization, and higher network lifespan than the existing methods.