Novel hybrid energy efficient learning protocols for wsn iot networks

Abstract

The proliferations of small size and low cost wearable sensors have been aided by recent innovations in wireless communication. The main goal of this research is to use the latest efficient algorithms to reduce energy consumption and extend the life of communication networks. Industry 4.0 relies heavily on the Internet of Things (IoT) and wireless sensor networks (WSN). IoT and WSN are used in various control systems, including environmental monitoring, home automation, and chemical/biological attack detection. IoT devices and applications are used to process extracted data from WSN devices and transmit them to remote locations. In WSN for IoT, intelligent routing is an important phenomenon that is necessary to enhance the Quality of Service (QoS) in the network. Moreover, the energy required for communication in the IoT based sensor networks is an important challenge to avoid immense fast energy depletion and unfairness across the network leading to reduction in node performance and increase in delay with respect to packet delivery. Hence, there is an extreme need to check energy usage by the nodes in order to enhance the overall network performance through the application of intelligent Machine Learning (ML) Techniques for making effective routing decisions. Many approaches are already available in the literature on energy efficient routing for WSN. However, they must be enhanced to suite the WSN in IoT environment. This research work focus on the implementation of optimization techniques that enable wireless sensor networks - IoT with low-energy nodes to achieve more accurate connections than traditional routing algorithms. In contrast to state-of-the-art technology, this research work introduces Hybrid Energy Efficient Learning Protocols (HELP). The first work proposes the new protocol Hybrid Efficient Learning Protocol (HELP) using a hybrid multi-tier and intelligent energy efficient routing protocol which integrates the powerful Random Forest Learning Machines (RFML) for the selection of zone based Cluster heads along with the hybrid meta-heuristic algorithm for an efficient and optimal zonal routing protocol. In the second work, the powerful Reinforcement Learning Machine (RLM) for the selection of zone based Cluster heads along with hybrid Whale optimized swarm routing algorithms was investigated and found better results compared to the first approach. In the third work, the new protocol Hybrid Efficient Learning Protocol (HELP) with the powerful Extreme Learning Machines (ELM) has been used to hybrid Whale optimized swarm routing algorithms which is helpful to achieve the lossless data transmission and to prolong the network life time. newline