Intelligent Traffic Prediction and Anomaly Detection for UAV Networks Using Dynamic Predictive Queuing Model
DOI:
https://doi.org/10.31838/NJAP/08.01.15Keywords:
Anomaly Detection, Network Performance Monitoring, Networks, Traffic Behavior, Unmanned Aerial Vehicle.Abstract
Unmanned Aerial Vehicle (UAV) network is growing rapidly and requires an efficient and intelligent network-level mechanism to provide reliable communication and security in a dynamic network. In this work, a Dynamic Predictive Queuing Model (DPQM) cumulating on an Adaptive Statistical Anomaly Detector (ASAD) is proposed to accomplish prediction accuracy and strong anomaly detection in the UAV traffic flows. Normally, DPQM utilizes Non-linear Time-Series Regression (NTR) to estimate the key parameters, which include Inter-Arrival Time (IAT), Transmission Delay (TD) and Packet Count (PC), and give a predictive baseline that can adapt to non linear and bursteted network behavior. ASAD augments this with the outlier residual analysis, threshold adapting to the dynamics, and the identifications of anomalies in real-time with little false positives. The hybrid model allows the performance of anticipatory and adaptive monitoring, which provides a great deal of congestion, misconfigurations and possible cyber-attack resiliency. Expanse analysis attests that DPQM is far better than the conventional models such as Linear Regression (LR), ARIMA, and Non-linear Regression (NLR), as can be seen in various scales of networks. System is scalable when the size of nodes is expanded, so it is resilient to forecasting and communication delays are minimal. The synergy between predictive and anomaly detection contributes to the enhanced network performance in general and reliability of UAV traffic in particular, as well as delivering admissible alerts to administrators. The design of DPQM-ASAD model provides better flexibility, active anomaly detection, and response time as compared to existing methods and therefore offers cost-effective and scale-able solution in the monitoring of UAV networks. The contribution in this work is a novel (intelligent, self-learning mechanism) and the mechanism is used to progress reliable, secure, and low latency UAV communication under dynamic scenarios in the network.
References
1. Xiao, K., Zhao, J., He, Y., Li, C., & Cheng, W. (2019). Abnormal behavior detection scheme of UAV using recurrent neural networks. IEEE Access, 7, 110293-110305.
2. Cai, H., Song, Z., Xu, J., Xiong, Z., & Xie, Y. (2022). CUDM: a combined UAV detection model based on video abnormal behavior. Sensors, 22(23), 9469.
3. Cui, G., & Zhang, L. (2024). Improved faster region convolutional neural network algorithm for UAV target detection in complex environment. Results in Engineering, 23, 102487.
4. Basan, E., Basan, A., Nekrasov, A., Fidge, C., Abramov, E., &Basyuk, A. (2022). A data normalization technique for detecting cyber attacks on UAVs. Drones, 6(9), 245.
5. Ma, Z., & Chen, J. (2022). Adaptive path planning method for UAVs in complex environments. International Journal of Applied Earth Observation and Geoinformation, 115, 103133.
6. Agnew, D., Del Aguila, A., & McNair, J. (2024). Enhanced network metric prediction for machine learning-based cyber security of a software-defined UAV relay network. IEEE Access, 12, 54202-54219.
7. Mehmood, A. (2021). Lightanomalynet: a lightweight framework for efficient abnormal behavior detection. Sensors, 21(24), 8501.
8. Mehmood, A. (2021). Abnormal behavior detection in uncrowded videos with two-stream 3D convolutional neural networks. Applied Sciences, 11(8), 3523.
9. Avola, D., Cinque, L., Di Mambro, A., Diko, A., Fagioli, A., Foresti, G. L., ... & Pannone, D. (2021). Low-altitude aerial video surveillance via one-class SVM anomaly detection from textural features in UAV images. Information, 13(1), 2.
10. Zhai, W., Liu, L., Ding, Y., Sun, S., & Gu, Y. (2023). ETD: an efficient time delay attack detection framework for UAV networks. IEEE transactions on information forensics and security, 18, 2913-2928.
11. Basan, E., Basan, A., Nekrasov, A., Fidge, C., Abramov, E., &Basyuk, A. (2022). A data normalization technique for detecting cyber attacks on UAVs. Drones, 6(9), 245.
12. Mallesh, A. (2025). Autonomous Security Response Architecture for Flight Path Anomaly Detection in Defense Drone Systems. Journal of Computer Science and Technology Studies, 7(8), 652-662.
13. Korium, M. S., Saber, M., Ahmed, A. M., Narayanan, A., & Nardelli, P. H. (2024). Image-based intrusion detection system for GPS spoofing cyberattacks in unmanned aerial vehicles. Ad Hoc Networks, 163, 103597.
14. Zhai, W., Liu, L., Ding, Y., Sun, S., & Gu, Y. (2023). ETD: an efficient time delay attack detection framework for UAV networks. IEEE transactions on information forensics and security, 18, 2913-2928.
15. Li, T., Hong, Z., Cai, Q., Yu, L., Wen, Z., & Yang, R. (2021). Bissiam: Bispectrumsiamese network based contrastive learning for uav anomaly detection. IEEE transactions on knowledge and data engineering, 35(12), 12109-12124.
16. Babu, J. R., Giri, T., Anusha, G., Reddy, R. G., & Shaik, A. (2023). Drone Network Incident Detection And Response. Material Science, 22(06).
17. Trinh, M. L., Nguyen, D. T., Dinh, L. Q., Nguyen, M. D., Setiadi, D. R. I. M., & Nguyen, M. T. (2025). Unmanned Aerial Vehicles (UAV) Networking Algorithms: Communication, Control, and AI-Based Approaches. Algorithms, 18(5), 244.
18. Hamad, A. H., Hussein, N. K., & Abdulghani, A. M. (2025). A Deep Learning Paradigm for Intrusion Detection in Unmanned Aerial Vehicle Networks Using Extended LSTM. International Journal of Intelligent Engineering & Systems, 18(4).
19. Aldossary, M., Alzamil, I., & Almutairi, J. (2025). Enhanced intrusion detection in drone networks: a cross-layer convolutional attention approach for drone-to-drone and drone-to-base station communications. Drones, 9(1), 46.
20. Rezaee, K., Zadeh, H. G., Chakraborty, C., Khosravi, M. R., & Jeon, G. (2022). Smart visual sensing for overcrowding in COVID-19 infected cities using modified deep transfer learning. IEEE Transactions on Industrial Informatics, 19(1), 813-820.
21. Haider, U., Shoukat, H., Ayub, M. Y., Tashfeen, M. T. A., Bhatia, T. K., & Khan, I. U. (2024). Cyber attack detection analysis using machine learning for IoT-based UAV network. In Cyber security for next-generation computing technologies (pp. 253-264). CRC Press.
22. Alghawli, A. S. (2022). Complex methods detect anomalies in real time based on time series analysis. Alexandria Engineering Journal, 61(1), 549-561.
23. Park, K. H., Park, E., & Kim, H. K. (2021). Unsupervised fault detection on unmanned aerial vehicles: Encoding and thresholding approach. Sensors, 21(6), 2208.
24. Baig, Z., Syed, N., & Mohammad, N. (2022). Securing the smart city airspace: Drone cyber attack detection through machine learning. Future Internet, 14(7), 205.
25. Ajayi, R., & Masunda, M. (2025). Integrating edge computing, data science and advanced cyber defense for autonomous threat mitigation. Int J Sci Res Arch, 15(2), 63-80.
26. Yang, L., Li, S., Li, C., & Zhu, C. (2024). Data-driven multivariate regression-based anomaly detection and recovery of unmanned aerial vehicle flight data. Journal of Computational Design and Engineering, 11(2), 176-193.
27. Chandran, I., & Vipin, K. (2024). Multi-UAV networks for disaster monitoring: challenges and opportunities from a network perspective. Drone Systems and Applications, 12, 1-28.
28. Feng, C., Fan, J., Liu, Z., Jin, G., & Chen, S. (2025). Unmanned Aerial Vehicle Anomaly Detection Based on Causality-Enhanced Graph Neural Networks. Drones, 9(6), 408.
29. Harrou, F., Bouyeddou, B., Dairi, A., & Sun, Y. (2024). Exploiting autoencoder-based anomaly detection to enhance cybersecurity in power grids. Future Internet, 16(6), 184.
30. Huang, J., Chen, Y., Wang, X., Ouyang, Z., & Du, N. (2025). Optimization scheme of collaborative intrusion detection system based on blockchain technology. Electronics, 14(2), 261.
