Energy-efficient data routing using neuro-fuzzy based data routing mechanism for IoT-enabled WSNs

Abstract

Abstract This paper proposes a novel Neuro-fuzzy-based Data Routing (NFDR) mechanism for efficient data routing and dynamic cluster formation in Internet of Things (IoT) enabled Wireless Sensor Networks (WSNs). The NFDR mechanism incorporates optimal scalability factors computed from past and present network parameter values, acting as an additional buffer factor to sustain nodes within clusters, even with partial satisfaction of network parameter values. The neural network determines cluster formation requirements, while the objective function adjusts according to the updated fuzzy logic of identified cluster members. Super heads are initially selected, and cluster member size is adjusted to sustain maximum data transmission without affecting network parameter thresholds. Simulation results demonstrate that the NFDR mechanism enhances clustering range and cluster members while sustaining evaluation metrics such as 75% energy retention, 20% end-to-end delay reduction, and a 15% reduction in dead nodes, ultimately contributing to the development of efficient and robust IoT-enabled WSNs.

Keywords

• Dynamic environment adaptability
• Scalability feature
• IoT-enabled WSNs
• Neuro-fuzzy based data routing
• Maximum data transmission rate
• And network efficiency