Intelligent Energy Optimization in Wireless Sensor Networks via Machine Learning Under 5G/6G Architectures

Abstract

The use of wireless sensor networks, or WSNs, is expanding for a number of purposes, such as environmental monitoring, healthcare delivery, and more. These networks are composed of tiny, sensor-equipped devices known as nodes that are able to wirelessly sense, analyze, and send data. Because of their short network lifetime and high energy consumption node, WSNs provide the most challenging problem when connected to the Internet of Things. Sensor data exchange, routing protocols, and energy limitations in sensor nodes are the fundamental ideas of WSNs. Random Forest Classifier and Marine Predators Algorithm-Based Energy Management in Wireless Sensor Networks utilizing 5G and 6G Networking Paradigms (RFC-MPA) has been created to extend network lifetime and ensure secure data transfer by identifying the optimal CH inside the network. RFC is used to select the cluster head. The fitness function considers cluster density, traffic rate, energy, collision, delay throughput, and distance from the capacity node. Three elements are considered in order to choose the best course of action: QoS, trust, and connectivity. To pick the optimal path with the least amount of latency, the Marine Predators Algorithm (MPA) has been utilized to enhance trust, connectivity, and quality of service (QoS) elements. A number of performance measures have been used to assess the effectiveness of the created method, which has been simulated using a MATLAB tool. The simulation results show that the proposed method achieves decreased packet drop of 93.15%, reduced latency of 56.78%, 23.56%, 33.89%, and 88.96%, and higher delivery ratios of 89.34%, 89.34%, 83.12%, and 88.96%.