Downloads: 1
Research Paper | Computer Science | Volume 15 Issue 3, March 2026 | Pages: 674 - 680 | India
Comparative Analysis of DRL Techniques for Energy-Aware Clustering in IoT-WSN
Abstract: The rapid expansion of Internet of Things (IoT)-based Wireless Sensor Networks (WSN) has introduced significant challenges in energy management, routing efficiency, scalability, and network reliability. Traditional optimization techniques often fail to adapt to the dynamic and resource-constrained nature of large-scale IoT environments. To address these limitations, recent advancements in Deep Reinforcement Learning have emerged as promising solutions for intelligent and energy-aware network optimization. This paper presents a unified comparative framework for evaluating multiple Deep Reinforcement Learning (DRL) algorithms in IoT-based WSN environments. The key performance metrics such as Energy Consumption, Packet Delivery Ratio, Latency, Throughput, and Network Lifetime are systematically evaluated. The results clearly demonstrate that federated DRL frameworks provide enhanced scalability, privacy preservation, and optimization capability, making them the most effective solution for IoT-based WSN environments.
Keywords: Wireless Sensor Networks, Deep Reinforcement Learning, Energy-Efficient Routing, Intelligent Clustering, Resource Optimization
How to Cite?: Dr. S. Rizwana, M. Sangeetha, "Comparative Analysis of DRL Techniques for Energy-Aware Clustering in IoT-WSN", Volume 15 Issue 3, March 2026, International Journal of Science and Research (IJSR), Pages: 674-680, https://www.ijsr.net/getabstract.php?paperid=SR26309100052, DOI: https://dx.dx.doi.org/10.21275/SR26309100052