Abstract :

This Project Presents An Adaptive Hierarchical Framework For The Detection And Localization Of Cyberattacks In Active Distribution Systems Within Modern Smart Grids. With The Increasing Integration Of Distributed Energy Resources And Advanced Communication Technologies, Power Systems Have Become More Vulnerable To Sophisticated Cyber Threats Such As False Data Injection, Signal Manipulation, And Unauthorized Access. To Address These Challenges, The Proposed System Utilizes High-resolution Electrical Waveform Data, Including Voltage And Current Signals, To Identify Abnormal Patterns Caused By Cyber Intrusions. The Framework Combines Signal Processing Techniques With Machine Learning And Deep Learning Algorithms To Enhance Detection Accuracy And System Adaptability. Initially, The Distribution Network Is Partitioned Into Smaller Clusters Using Spectral Clustering, Enabling Efficient Monitoring And Reducing Computational Complexity. A Coarse-level Anomaly Detection Stage Identifies Suspicious Regions, Followed By A Fine-level Localization Process That Accurately Determines The Exact Point Of Attack Using Waveform-based Feature Analysis And Impact Scoring Mechanisms. The System Incorporates Incremental Learning To Adapt To Evolving Cyber-attack Patterns Without Requiring Complete Retraining, Making It Suitable For Real-time Applications. Experimental Results Demonstrate That The Proposed Approach Achieves High Detection Accuracy, Low False Alarm Rates, And Precise Localization Performance Compared To Traditional Methods. Overall, This Work Provides A Scalable, Efficient, And Robust Solution For Enhancing The Cybersecurity, Reliability, And Resilience Of Modern Power Distribution Networks.

Published:

24-4-2026

Issue:

Vol. 26 No. 4 (2026)

Page Nos:

2909 - 2916

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite