UPGRID

The project aims to develop an advanced Machine Learning (ML)-based Intrusion Detection System (IDS) to safeguard power grids in India against cyber-attacks. Given the increasing vulnerability of modern power grids due to the integration of Computing and Communication (CC) devices, the project will focus on devising unsupervised learning models capable of detecting anomalies across various communication protocols. By leveraging state-of-the-art techniques like isolation forest, One-Class Support Vector Machine (OCSVM), and auto-encoders, the project seeks to enhance the specificity and sensitivity of the detection system. The research involves extensive data analysis using open datasets and synthetic data generation from power grid simulators. The developed models will be evaluated using standard metrics and deployed over GPU-accelerated computing platforms for real-time monitoring. Ultimately, the project’s goal is to create a robust and adaptive solution that can effectively detect and prevent cyber threats in the Indian power grid, making it more resilient to dynamic and sophisticated attacks.