Enhanced Comparative Analysis of Network Anomaly Detection and Prediction in IoT Using Vector Autoregressive Models

다국어 초록 (Multilingual Abstract)

This research conducts a comparative analysis of Vector Autoregressive (VAR) models for network anomaly detection and prediction, focusing on two specific VAR versions. It empirically assesses their effectiveness in detecting and forecasting anomalies, finding that the VAR-Filtered moving-average-AR model excels in single-node anomaly detection, while the VAR-Adaptive Learning model is more effective for detecting anomalies across multiple nodes. The study explores the reasons behind the performance differences of these models and compares VARs with other methods like Markov Chain Monte Carlo and Artificial Neural Networks, using datasets based on real-world and fictional network scenarios. It evaluates the trade-offs between these techniques and provides insights into their advantages, disadvantages, and potential improvements for network anomaly detection.

참고문헌 (Reference)

1 Bae, J., "Pni:industrial anomaly detection using position and neighborhood information" 6373-6383, 2023

2 He, Q., "Multivariate time-series anomaly detection via temporal convolutional and graph attention networks" 1-10, 2023

3 Wang, Y., "Intrusion detection for high-speed railways based on unsupervised anomaly detection models" 53 (53): 8453-8466, 2023

4 Pan, D., "From Traffic Analysis to Real-Time Management: A Hazard-Based Modeling for Incident Durations Extracted Through Traffic Detector Data Anomaly Detection" 2023

5 Dwivedi, D., "DynamoPMU: A Physics Informed Anomaly Detection, Clustering and Prediction Method using Non-linear Dynamics on μPMU Measurements" 2023

6 Liu, H., "Anomaly detection of high-frequency sensing data in transportation infrastructure monitoring system based on fine-tuned model" 2023

7 Saha, S., "Analyzing the Impact of Outlier Data Points on Multi-Step Internet Traffic Prediction using Deep Sequence Models" 2023

8 Copiaco, A., "An innovative deep anomaly detection of building energy consumption using energy time-series images" 119 : 105775-, 2023

9 Xu, Z., "A hybrid data-driven framework for satellite telemetry data anomaly detection" 205 : 281-294, 2023

10 Qiao, Y., "A Multi-head Attention Self-supervised Representation Model for Industrial Sensors Anomaly Detection" 2023