Enhancing Energy Efficiency in IoT Wireless Sensor Networks: AI-Driven Clustering and Routing Protocols

Abstract

The Internet of Things (IoT) is now a disruptive technology that gives electronic devices the capacity for communication and cooperation in multiple fields. This research aims to enhance the efficiency of WSNs by including IoT and sophisticated energy-saving methods. The study is based on the “Modern Cluster Supervisor-Based Cluster Head (MCSBCH)” selection algorithm and Token Broker- Based Routing (TBBR), which applies Reinforcement Learning (RL) to improve energy management, clustering, and routing. The simulation results show that the RL-enhanced MCSBCH protocol has a packet delivery ratio of 66%, which outperforms ABR and 3LHHBTD protocols with PDRs of 42% and 22% respectively. The application of RL makes a significant improvement in the energy consumption as well, and saves energy for 25% more in MCSBCH + RL and prolongs network lifetime till 90%, while MCSBCH only consumes 50% of energy and has 55% network lifetime. It is shown that the proposed algorithms provide significant gains in network performance, energy consumption, and scalability, which are well-suited for many wireless applications such as disaster monitoring, health monitoring, and smart cities. In the future, integration of AI with developing technologies such as edge computing and blockchain may be investigated for improved scalability, security, and energy efficiency in WSNs with the IoT.