Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{188762,
        author = {Ayasha Avinash Chavan and Swati Padmakar Akhare and Manisha Bharatram Bannagare},
        title = {Energy-Efficient Routing in IoT Networks using Reinforcement Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {7},
        pages = {3526-3528},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=188762},
        abstract = {IoT networks suffer from rapid battery depletion, unstable link quality, and dynamic topologies that make traditional routing inefficient. Existing energy-aware routing protocols rely on static rules and cannot adapt to real-time variations in node energy, traffic load, or link reliability. This paper proposes an adaptive Reinforcement Learning-based routing framework that integrates multi-factor reward design, topology awareness, and predictive energy modeling to extend IoT network lifetime. The model evaluates residual energy, link quality, node stability, and estimated future consumption to select optimal routes. Experiments conducted in NS-3 demonstrate improved network lifetime, balanced energy consumption, and higher packet delivery ratio compared to LEACH, AODV-Energy, and basic RL models. The novelty lies in combining multi-factor reward shaping with dynamic learning, enabling IoT nodes to autonomously adapt routing policies under changing conditions.},
        keywords = {IoT Routing, Reinforcement Learning, Energy Efficiency, Multi-Agent RL, Network Lifetime Optimization.},
        month = {December},
        }