INTELLIGENT MONITORING FOR DISTRIBUTED SYSTEMS: LEVERAGING MACHINE LEARNING TO DETECT AND ADAPT TO EVOLVING CYBER THREATS

Roman Karpiuk

Анотація


Ensuring the stability, performance, and security of distributed computer systems is a critically important task in modern cybersecurity. This paper explores how advanced monitoring systems leveraging machine learning can provide real-time anomaly detection and proactive adaptation. Key challenges include handling large data volumes, architectural complexity, and reducing false positives that burden cybersecurity analysts. The proposed approach integrates centralized data aggregation tools such as ELK and Splunk, machine learning models like Random Forest and DensityFunction for anomaly detection, and scalable microservices architectures deployed on elastic cloud platforms. Additional enhancements include regular model retraining, dynamic threshold adjustments, and automated alerting to improve the detection of evolving cyber threats

Повний текст:

PDF (English)

Посилання


Chen K., Huang C., He J. Fault detection, classification and location for transmission lines and distribution systems: a review on the methods. – High Voltage, 2016. – URL: https://doi.org/10.1049/hve.2016.0005. 4 Karpiuk R. 2. Verdier G., Ferreira A. Adaptive Mahalanobis Distance and k-Nearest Neighbor Rule for Fault Detection in Semiconductor Manufacturing. – IEEE Transactions on Semiconductor Manufacturing, 2010. – URL: https://doi.org/10.1109/TSM.2010.2096538. 3. Tian J., Morillo C., Azarian M.H., Pecht M. Motor Bearing Fault Detection Using Spectral Kurtosis-Based Feature Extraction Coupled With K-Nearest Neighbor Distance Analysis. – IEEE Transactions on Industrial Electronics, 2015. – URL: https://doi.org/10.1109/TIE.2015.2478397. 4. Safizadeh M.S., Latifi S.K. Using multi-sensor data fusion for vibration fault diagnosis of rolling element bearings by accelerometer and load cell. – Information Fusion, 2013. – URL: https://doi.org/10.1016/j.inffus.2013.10.002.




DOI: http://dx.doi.org/10.30970/vam.2024.33.12791

Посилання

  • Поки немає зовнішніх посилань.