SYSTEMS FOR AUTOMATIC DETECTION AND ANALYSIS OF FAILURES IN COMPUTER NETWORKS
Abstract
This article discusses automated network fault detection systems, their operating principles, algorithms, and modern methodologies. It analyzes system architectures, practical experiences related to fault prediction, and the ability to detect anomalies in advance. The study highlights that machine-learning-based approaches provide higher accuracy and efficiency compared to traditional methods. Additionally, the advantages, functional features, and the role of artificial intelligence and machine learning–driven automatic detection systems in optimizing network management processes are thoroughly examined.
Keywords
network fault, automatic detection, analysis system, artificial intelligence, machine learning, network monitoring, Autoencoder, Random Forest, K-Means.
References
- S.Russell, P.Norvig. Artificial Intelligence: A Modern Approach, 4th Edition. Pearson Education, 2021.
- I.Goodfellow, Y.Bengio, A.Courville. Deep Learning. MIT Press, 2016.
- Z.Darban, M.H.Hossain, A.Rahman. “Time-series anomaly detection using Autoencoder in network traffic.” Journal of Network and Computer Applications, Vol. 205, 2022.
- D.Vajda, P.Novák, L.Kovács. “Real-time network telemetry anomaly detection using deep Autoencoders.” IEEE Transactions on Network and Service Management, Vol. 21, No. 2, 2024.
- Sangaiah.A.K., “Random Forest for intelligent intrusion detection.” Journal of Information Security and Applications, Vol. 68, 2022.
- N.Trapani, R.D’Amico. “Fault detection in sensor networks using ensemble Random Forest approach.” Sensors, Vol. 23, No. 5, 2023.
- E.Toth, G.Horváth, B.Papp. “Using K-Means clustering for DDoS detection in large-scale networks.” Computer Networks, Vol. 221, 2023.
- M.Singh, A.Patel. “Hybrid Autoencoder and Random Forest approach for anomaly detection in KDD99 dataset.” International Journal of Computer Applications, Vol. 189, No. 4, 2023.
- Matyokubov O‘.K. “LTE tarmoqlarida xizmatdagi nosozliklarni aniqlash uchun mashinaviy o‘rganish modellaridan foydalanish.” O‘zbekiston Axborot Texnologiyalari Jurnali, №3, 2022.
- AbdullayevaN. “Korporativ tarmoqlarda trafikni avtomatik nazorat qilishda mashinaviy o‘rganishning o‘rni.” O‘zbekiston Kompyuter Ilmlari Jurnali, №2, 2023.
- H.Zhao, J.Chen, W.Li. “Deep learning for network anomaly detection: A comprehensive survey.” IEEE Communications Surveys & Tutorials, Vol. 23, No. 1, 2021.
- C.Li, X.Zhang, “Clustering-based approaches for intelligent intrusion detection.” Journal of Network Security, Vol. 45, No. 3, 2022.
- A.Kumar, R.Sharma, “Combining Autoencoder and K-Means for hybrid network fault detection.” International Journal of Computer Science and Information Security, Vol. 21, 2023.
- ISO/IEC 27001:2013, Information Security Management Standards, International Organization for Standardization, 2013.
- O.Yuldashev, N.Karimova. “Sun’iy intellekt asosida tarmoqdagi nosozliklarni avtomatik aniqlash tizimlarini yaratish imkoniyatlari.” TATU Ilmiy Axborotlari, №1, 2024.