Random Forest Approach for Enhancing Resilience Against False Data Injection in Power Distribution Systems
International Journal of Innovative Science and Research Technology · 20.06.2026 · 683
DOI: 10.38124/ijisrt/26jun622 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Innovative Science and Research Technology, online erschienen am 20.06.2026. Verfasst von Sony Venugopal und 2 weiteren Autor:innen. Die Arbeit nennt 11 Literaturangaben.
Abstract (Originalsprache)
False Data Injection (FDI) attacks represent a critical cyber-security threat to modern smart grids, as they deliberately manipulate measurement data used for system monitoring and control while remaining difficult to detect using conventional techniques. This paper presents a machine learning-based framework for the detection and localization of FDI attacks in power distribution systems. An IEEE 5-Bus test system is modeled and simulated in the MATLAB/Simulink environment to generate voltage measurements under normal operating conditions. FDI attack scenarios are created by selectively altering bus voltage data to emulate compromised measurement states without disturbing the physical dynamics of the system. Voltage magnitude features extracted from the simulation data are used to train a Random Forest classifier for identifying abnormal operating conditions and localizing the attacked bus. Simulation results demonstrate that the proposed approach effectively detectsThe results highlight the potential of integrating power system simulation with datadriven machine learning techniques to enhance cyber-security and situational awareness in smart grid applications.
Zitieren
APA
Venugopal, S., S., Y., & V., S. M. (2026). Random Forest Approach for Enhancing Resilience Against False Data Injection in Power Distribution Systems. International Journal of Innovative Science and Research Technology, 683. https://doi.org/10.38124/ijisrt/26jun622
Vancouver
Venugopal S, S. Y, V. SM. Random Forest Approach for Enhancing Resilience Against False Data Injection in Power Distribution Systems. International Journal of Innovative Science and Research Technology. 2026:683. doi:10.38124/ijisrt/26jun622
BibTeX
@article{Venugopal2026,
author = {Venugopal, Sony and S., Yogini and V., Sameeksha M.},
title = {Random Forest Approach for Enhancing Resilience Against False Data Injection in Power Distribution Systems},
journal = {International Journal of Innovative Science and Research Technology},
year = {2026},
pages = {683},
doi = {10.38124/ijisrt/26jun622}
}
EUVIMED