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{183951,
        author = {S MAHABOOB SUBHAHAN and Dr R Rajasekhar},
        title = {ML-Optimized RPL: Advanced Routing Protocol for Wireless Smart Grid},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {3},
        pages = {4169-4176},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=183951},
        abstract = {The Routing Protocol for Low Power and Lossy Networks (RPL) has become the de facto standard for routing in resource-constrained wireless networks, such as those found in smart grid and IoT environments. However, traditional RPL suffers from static decision-making, limited adaptability to dynamic conditions, and suboptimal parent selection strategies. This paper proposes ML-RPL, a machine learning-enhanced routing protocol that integrates a Naive Bayes classifier into RPL’s parent selection mechanism. Unlike conventional approaches that rely on fixed metrics like ETX or hop count, ML-RPL leverages real-time network features— including RSSI, MAC losses, throughput, queue utilization, and node density—to estimate the probability of successful packet delivery through each neighbor. The routing decision is made by selecting the parent with the highest predicted reliability while maintaining compatibility with standard RPL control messages. A Python-based simulation environment was developed to evaluate the proposed approach across networks with 50, 100, and 200 nodes. Results demonstrate that ML-RPL outperforms standard RPL and RPL+ in terms of Packet Delivery Ratio (PDR) and end-to-end delay, especially under high-traffic and high-density conditions. The findings highlight ML-RPL’s potential to enable intelligent, adaptive, and efficient routing in low-power wireless networks.},
        keywords = {Machine Learning, RPL, Wireless Sensor Networks, Low Power and Lossy Networks, Naive Bayes, Smart Grid Communication, Routing Protocols, Packet Delivery Ratio, End-to-End Delay, Network Optimization},
        month = {September},
        }