AI-Integrated Swarm-Powered Self-Scheduling Routing for Heterogeneous Wireless Sensor Networks to Maximize Network Lifetime

Abstract

In Heterogeneous Wireless Sensor Networks (HWSNs), ensuring energy-efficient, adaptive, and intelligent data routing is a critical challenge due to the diversity of sensor capabilities, unpredictable traffic patterns, and dynamic environmental conditions. Traditional routing protocols often struggle with high energy consumption, unbalanced node utilization, and latency issues, leading to reduced network lifetime and communication inefficiency. To address these limitations, this research proposes an AI-Integrated Swarm-Powered Self-Scheduling Routing Framework designed to maximize the operational lifetime and enhance the adaptive communication capabilities of HWSNs. The proposed framework introduces a Prolong Traffic Behaviour Analyses Rate (PTBAR) mechanism, estimated through a K-Optimized Decision Tree, to predict and regulate traffic patterns dynamically. Subsequently, a Community Aware Node Selection Algorithm (CANSA) identifies optimal cluster heads by evaluating multiple parameters—energy level, support rate, response behaviour tolerance, and node activity status—ensuring efficient clustering and balanced energy utilization. For intelligent feature extraction and cluster optimization, a Deep Cluster Intensive Best-Fit Whale Optimization Algorithm (DCI-BFWOA) is applied to enhance data accuracy and minimize redundancy within cluster formation. The next phase employs an Energy-Tolerant Proactive Self-Scheduling Routing Protocol (ETPSSRP) to enable adaptive and cooperative communication among nodes, balancing energy consumption and minimizing delay across heterogeneous environments. Finally, a Time-Triggered Max-Priority Route Switchover Algorithm (TTMP-RSOA) ensures timely packet delivery and route stability by dynamically switching routes based on real-time priority and network conditions. Comprehensive simulation results demonstrate that the proposed system significantly improves network lifetime, packet delivery ratio (PDR), throughput, delay tolerance, and computational efficiency when compared with existing routing models. The integrated use of AI decision-making, swarm intelligence, and self-scheduling strategies establishes a resilient, energy-aware, and adaptive routing mechanism—marking a significant advancement in intelligent HWSN communication systems.