Optimized Energy-Aware Routing for Internet of Things Enabled WSNS using Neuro-Fuzzy Clustering and Quantum Firefly Algorithm

Abstract

Researchers and industry professionals are highly interested in Wireless Sensor Networks (WSNs) due to their importance in utilizing low-cost, low-power microelements, such as radios, computers, and sensors, which are often integrated onto a single chip. Recently, the integration of the Internet of Things (IoT) with WSNs has been extensively explored. Effective routing techniques are crucial for optimizing power usage, ensuring Quality of Service (QoS), and maintaining network reliability in IoT-enabled WSNs. This paper presents an enhanced energy-aware navigation system that employs the Quantum Firefly Optimization (QFO) method and Neuro-Fuzzy Clustering for IoT-enabled WSNs. The Neuro-Fuzzy Clustering method extends the system's lifetime by automatically grouping sensor nodes into energy-efficient clusters. The QFO method is used to determine the optimal routing paths by considering factors such as energy consumption, QoS, and trust metrics. By incorporating these advanced methodologies, the proposed solution outperforms existing approaches in terms of energy efficiency, routing accuracy, and overall network stability. Simulation results demonstrate that this novel approach has the potential to significantly improve current routing protocols and expand the capabilities of IoT-enabled WSNs. Additionally, to enhance efficiency in mobile computing environments, the security of the intrusion detection system was strengthened through the use of deep learning techniques.