ML-RPL: Machine Learning-Based Routing Protocol for Wireless Smart Grid Networks

This research explores the potential of Machine Learning (ML) to enhance wireless communication networks, specifically in context Wireless Smart Grid Networks (WSGNs). We integrated ML into well-established Routing Protocol for Low-Power and Lossy (RPL), resulting an advanced version called ML-RPL. novel protocol utilizes CatBoost, a Gradient Boosted Decision Trees (GBDT) algorithm, optimize routing decisions. The model, trained on dataset metrics, predicts probability successfully reaching destination node. Each node network uses model choose route with highest effectively delivering packets. Our performance evaluation, carried out realistic scenario under various traffic loads, reveals that ML-RPL significantly improves packet delivery ratio minimizes end-to-end delay, making it promising solution more efficient responsive WSGNs.