Optimizing Node Localization in Wireless Sensor Networks Using Hybrid Red Fox Optimization-Genetic Algorithm

Wireless Sensor Networks (WSNs) are extensively utilised in a variety of domains, including disaster response, healthcare, and environmental monitoring. However, factors such as imprecise distance measurements, limited energy, and deployment conditions make sensor node localization a difficult problem to solve. Old localization approaches are motivated by high Mean Localization Error (MLE), inefficient convergence levels, and lowered computation capabilities. In this regard, an optimized genetic algorithm joined with particle swarm optimization and Hybrid Red Fox Optimization-Genetic Algorithm has been developed to facilitate improved node localization. The Hybrid RFO-GA represents an innovative fusion of Red Fox Optimization (RFO) and Genetic Algorithm (GA) methodologies. This approach leverages RFO's robust exploration capabilities while incorporating GA's refined evolutionary operators to achieve superior localization accuracy and computational efficiency. Comprehensive testing was conducted using Wireless Sensor Network simulations with 300 sensor nodes, anchor node configurations ranging from 10 to 100 units, and transmission ranges spanning 10 to 200 meters. These experimental results demonstrate significant performance improvements across all evaluated metrics. The Hybrid RFO-GA MLE improvement was 25.4%, local nodes increased by 17.8%, and computation efficiency was improved by 22.6% compared to GA and PSO. The results corroborate that Hybrid RFO-GA has better accuracy and efficiency of WSN localization. Future work is fucus on deep learning and its role in node localization for better wireless sensor networks.