FGOGNN: An Energy-Efficient and Intelligent Cluster-Based Routing Protocol for Wireless Sensor Networks
TL;DR
A novel cluster-based routing protocol that integrates a Fungal Growth Optimizer for adaptive cluster head (CH) selection and a Graph Neural Network for inter-cluster routing, which demonstrates FGOGNN’s potential for deployment in real-time WSN applications, where energy efficiency and dynamic adaptability are paramount.
Abstract
Energy-efficient and robust routing remains a critical problem in wireless sensor networks (WSNs), where limited energy resources and dynamic topologies hinder performance. To address this challenge, a novel cluster-based routing protocol FGOGNN is proposed in this paper, which integrates a Fungal Growth Optimizer (FGO) for adaptive cluster head (CH) selection and a Graph Neural Network (GNN) for inter-cluster routing. The FGO simulates fungal growth processes, ensuring balanced and energy-efficient CH selection while preventing premature convergence. In the routing phase, the GNN dynamically adapts routing paths by leveraging node energy, connectivity, and directional edge features, offering low computational overhead while maintaining accuracy. Extensive simulations show that FGOGNN outperforms existing routing protocols, extending network lifetime by up to 75% and improving throughput by 38%, with a reduction in end-to-end delay. These results demonstrate FGOGNN’s potential for deployment in real-time WSN applications, where energy efficiency and dynamic adaptability are paramount.