| Title | Machine Learning-Based Cybersecurity Framework for Smart Grid Protection |
| Research Area | Smart Grid Security |
| Abstract | Smart grids integrate advanced communication networks, automation systems, and distributed energy resources to enhance efficiency, reliability, and sustainability of power systems. However, the increasing digitalization of power infrastructure has also expanded the attack surface for cyber threats such as false data injection, denial-of-service attacks, malware infiltration, and unauthorized access. Traditional rule-based security mechanisms are insufficient to counter sophisticated and evolving cyberattacks targeting smart grids. This paper presents a machine learning-based cybersecurity framework designed to detect and mitigate cyber threats in smart grid environments. The proposed approach leverages supervised and unsupervised learning algorithms to identify anomalies in grid communication and operational data. Experimental analysis demonstrates that machine learning-based detection improves threat identification accuracy by more than 20% compared to conventional methods, while significantly reducing false alarms. The study highlights the role of intelligent security systems in ensuring resilient and secure smart grid operations. |
| Keywords | Smart Grid Security, Cybersecurity, Machine Learning, Intrusion Detection, Power Systems, Anomaly Detection |
| Paper Status | Published |
| Volume | 1 |
| Issue | 6 |
| Published On | 06/11/2025 |
| Published File |
IJSRTD_4870.pdf
|