A Flexible Hybrid Resource Allocation Model for Enhanced Efficiency using AI in Wireless Sensor Networks
Purushotham Endla, R. Mohandas, Achinta Saikia, C. Lakshmi, Ganesh Karthikeyan V, Tejashree Tejpal Moharekar · 2025
Wireless Sensor Networks (WSNs) have become a cornerstone technology in various fields, including environmental monitoring, industrial automation, and healthcare. This paper presents a novel hybrid resource allocation model designed to enhance efficiency in Wireless Sensor Networks (WSNs) using advanced Artificial Intelligence (AI) techniques. The proposed model integrates static and dynamic resource allocation strategies with machine learning and reinforcement learning to optimize key network resources such as energy, bandwidth, and processing power. Comprehensive evaluations demonstrate that the proposed model outperforms nine existing models across multiple metrics, including energy efficiency, network lifetime, throughput, delay, latency, and accuracy of resource allocation. The proposed model achieved an energy efficiency of 0.98 J/bit, extended network lifetime to 620 days, and maintained a high throughput of 620 Kbps. Notably, the model demonstrated the lowest delay (90 ms) and latency (180 ms) while achieving the highest resource allocation accuracy of 97.8%. These results highlight the model’s capability to dynamically adjust resource allocation in response to real-time network conditions, ensuring optimal performance and resource utilization. The proposed model’s success in efficiently managing WSN resources marks a significant advancement in the field, offering a robust solution for various WSN applications requiring high efficiency and reliability.