IntelliCrop: Advanced Security in RPL-Enabled IoT Networks Through Machine Learning

Smart irrigation systems have emerged as a novel technology due to the influence of the Internet of Things (IoT) on contemporary agriculture. T he Internet of Things (IoT) is vulnerable to significant security threats due to its reliance on the Routing Protocol for Low-Power and Lossy Networks (RPL). Network performance may deteriorate, data integrity may be jeopardized, and automatic irrigation systems may be interrupted by attacks like rank, Sybil, blackhole, and wormhole. This research presents an adaptive methodology named IntelliCrop, utilizing the XGBoost machine learning algorithm, which employs machine intelligence to enhance the security of RPL-based smart irrigation networks. IntelliCrop enables rapid categorization of network events, identification of errant or malicious users, and automated updates to routing tables, so ensuring optimal overall throughput throughout the process. Skymote devices, arbitrary topologies, and actual attack scenarios are employed to evaluate the system before to its implementation in IoT-based irrigation systems. In comparison to standard models like Random Forest and Decision Tree, our assessment results indicate that our model achieves superior accuracy (99.92%), perfect recall (100%), and a high F1-score (99.2%) on the test data. IntelliCrop enhances IoT-enabled irrigation networks through real-time threat assessment, adaptive delivery routing, and scalability, therefore safeguarding against routing threats and promoting dependable automated smart agricultural ecosystems.