PREDICTION OF ANOMALIES IN SOFTWARE-DEFINED NETWORKING
DOI:
https://doi.org/10.65164/788zsg39Keywords:
SDN, ICS, anomaly prediction, time-series analysis, machine learning, deep learning, network securityAbstract
The rapid adoption of Software-Defined Networking (SDN) and Industrial Control Systems (ICS) has significantly increased the need for advanced anomaly prediction mechanisms. Unlike traditional detection, anomaly prediction aims to identify malicious or abnormal behavior before it fully manifests, thereby enabling proactive defense. This paper investigates anomaly prediction in SDN environments with emphasis on ICS integration, anomaly characteristics, prediction methods, and datasets. Recent studies (2020–2026) demonstrate that machine learning and deep learning approaches can achieve prediction accuracy exceeding 97–99%, while reducing detection latency and improving network resilience. The paper highlights the importance of time-series modeling, hybrid AI techniques, and realistic datasets for effective anomaly prediction in modern programmable networks.
References
1.
Wang, Ziyi & Guan, Zhenyu & Liu, Xu & Li, Caixia & Sun, Xuan & Li, Jun. (2025). SDN Anomalous Traffic Detection Based on Temporal Convolutional Network. Applied Sciences. 15. 4317. 10.3390/app15084317.
2.
Koumar J. et al., “CESNET-TimeSeries24: Dataset for Network Traffic Anomaly Detection and Forecasting,” Scientific Data, 2025. Volume 12, number 1.
706
3.
A. Hirsi, L. Audah, A. Salh, N. M. Sahar, S. Ahmed and M. A. Alhartomi, "DDoS Anomaly Detection in Software-Defined Networks: An Evaluation of Machine Learning Techniques for Traffic Classification and Prediction," 2024 International Conference on Future Technologies for Smart Society (ICFTSS), Kuala Lumpur, Malaysia, 2024, pp. 100-105,
4.
Ataa, M. S., Sanad, E. E., & El-khoribi, R. A. (2024). Intrusion detection in software defined network using deep learning approaches. Scientific Reports, 14(1), 29159. https://doi.org/10.1038/s41598-024-79001-1
5.
Liao, Han & Murah, Mohd Zamri & Hasan, Mohammad Kamrul & Aman, Azana & Fang, Jin & Hu, Xuting & Khan, Atta ur Rehman. (2024). A Survey of Deep Learning Technologies for Intrusion Detection in Internet of Things. IEEE Access. PP. 1-1. 10.1109/ACCESS.2023.3349287.
6.
Pekar, Adrian & Jozsa, Richard. (2024). Evaluating ML-based anomaly detection across datasets of varied integrity: A case study. Computer Networks. 251. 110617. 10.1016/j.comnet.2024.110617.
7.
Fung, Clement & Zeng, Eric & Bauer, Lujo. (2024). Attributions for ML-based ICS Anomaly Detection: From Theory to Practice. 10.14722/ndss.2024.23216.
