Optimizing Network Performance through Advanced Machine Learning-Based Traffic Management
Abstract
With the explosion of network traffic, network performance becomes more important. In the process of achieving high-efficiency and ultra-reliable connections, this paper explores the more sophisticated ML/AI based traffic management solution. Here we propose a general framework which combines various ML models to optimize the network performance in terms of traffic prediction, anomaly detection and resource allocation. Our results indicate the proposed system is able to achieve significant improvements in essential performance metrics of latency, throughput, and packet loss rates when evaluated with a real-time network traffic dataset. The performance results of ML-Model 4 outclassed the other models, exhibiting high precision, recall, and accuracy while minimizing resource allocation overhead, resulting in reduced CPU usage and network I/O, as well as the system's ability to adapt its behavior to accommodate fluctuating network conditions using a more efficient strategy that enhances performance and scalability when compared with the traditional approach. This research conducts a deep understanding of these models, their implementation and their effect on network performance, suggesting the power of machine learning in changing the way we manage network traffic.
References
D. Parra-Ovalle, C. Miralles-Guasch, and O. Marquet, "Pedestrian Street Behavior Mapping Using Unmanned Aerial Vehicles: A Case Study in Santiago de Chile," PLoS ONE, vol. 18, p. e0282024, 2023.
Y. Ma, J. Zhang, and X. Yang, "Effects of Audio-Visual Environmental Factors on Emotion Perception of Campus Walking Spaces in Northeastern China," Sustainability, vol. 15, p. 15105, 2023.
M. Zhu, R. Teng, C. Wang, Y. Wang, J. He, and F. Yu, "Key Environmental Factors Affecting Perceptions of Security of Night-Time Walking in Neighborhood Streets: A Discussion Based on Fear Heat Maps," J. Transp. Health, vol. 32, p. 101636, 2023.
A. Stanitsa, S. H. Hallett, and S. Jude, "Investigating Pedestrian Behavior in Urban Environments: A Wi-Fi Tracking and Machine Learning Approach," Multimodal Transp., vol. 2, p. 100049, 2023.
J. Peng et al., "Prediction and Optimization of the Flexural Behavior of Corroded Concrete Beams Using Adaptive Neuro Fuzzy Inference System," Structures, vol. 43, pp. 200–208, 2022.
T. G. Wakjira, A. Abushanab, U. Ebead, and W. Alnahhal, "FAI: Fast, Accurate, and Intelligent Approach and Prediction Tool for Flexural Capacity of FRP-RC Beams Based on Super-Learner Machine Learning Model," Mater. Today Commun., vol. 33, p. 104461, 2022.
G. T. Truong, K. K. Choi, and C. S. Kim, "Implementation of Boosting Algorithms for Prediction of Punching Shear Strength of RC Column Footings," Structures, vol. 46, pp. 521–538, 2022.
T. G. Wakjira, A. Rahmzadeh, M. S. Alam, and R. Tremblay, "Explainable Machine Learning Based Efficient Prediction Tool for Lateral Cyclic Response of Post-Tensioned Base Rocking Steel Bridge Piers," Structures, vol. 44, pp. 947–964, 2022.
A. A. Kutty, T. G. Wakjira, M. Kucukvar, G. M. Abdella, and N. C. Onat, "Urban Resilience and Livability Performance of European Smart Cities: A Novel Machine Learning Approach," J. Clean. Prod., vol. 378, p. 134203, 2022.
P. Kourehpaz and C. Molina Hutt, "Machine Learning for Enhanced Regional Seismic Risk Assessments," J. Struct. Eng., vol. 148, p. 04022126, 2022.
R. Solhmirzaei, H. Salehi, V. Kodur, and M. Z. Naser, "Machine Learning Framework for Predicting Failure Mode and Shear Capacity of Ultra High-Performance Concrete Beams," Eng. Struct., vol. 224, p. 111221, 2020.
B. Cai, G. Pan, and F. Fu, "Prediction of the Postfire Flexural Capacity of RC Beam Using GA-BPNN Machine Learning," J. Perform. Constr. Facil., vol. 34, p. 04020105, 2020.
W. Cao, A. Wang, D. Yu, S. Liu, and W. Hou, "Establishment and Implementation of an Asphalt Pavement Recycling Decision System Based on the Analytic Hierarchy Process," Resour. Conserv. Recycl., vol. 149, pp. 738–749, 2019.
L. Xiang, M. Cai, C. Ren, and E. Ng, "Modeling Pedestrian Emotion in High-Density Cities Using Visual Exposure and Machine Learning: Tracking Real-Time Physiology and Psychology in Hong Kong," Build. Environ., vol. 205, p. 108273, 2021.
E. Murgano, R. Caponetto, G. Pappalardo, S. D. Cafiso, and A. Severino, "A Novel Acceleration Signal Processing Procedure for Cycling Safety Assessment," Sensors, vol. 21, p. 4183, 2021.
F. Young, R. Mason, R. E. Morris, S. Stuart, and A. Godfrey, "IoT-Enabled Gait Assessment: The Next Step for Habitual Monitoring," Sensors, vol. 23, p. 4100, 2023.
S. Miah, E. Milonidis, I. Kaparias, and N. Karcanias, "An Innovative Multi-Sensor Fusion Algorithm to Enhance Positioning Accuracy of an Instrumented Bicycle," IEEE Trans. Intell. Transp. Syst., vol. 21, pp. 1145–1153, 2020.
Y. Feng, D. Duives, W. Daamen, and S. Hoogendoorn, "Data Collection Methods for Studying Pedestrian Behavior: A Systematic Review," Build. Environ., vol. 187, p. 107329, 2021.
T. Nishio and M. Niitsuma, "Environmental Map Building to Describe Walking Dynamics for Determination of Spatial Feature of Walking Activity," in Proc. IEEE 28th Int. Symp. Ind. Electron. (ISIE), Vancouver, BC, Canada, 2019, pp. 12–14.
T. Wan, W. Lu, and P. Sun, "Constructing the Quality Measurement Model of Street Space and Its Application in the Old Town in Wuhan," Front. Public Health, vol. 10, p. 816317, 2022.
C. Aqeel Luaibi and A. Hasan Hussein, "Enhancing the Performance Assessment of Network-Based and Machine Learning for Module Availability Estimation," Int. J. Syst. Syst. Eng., vol. 14, no. 1, pp. 1–22, 2024.
P. Kourehpaz and C. Molina Hutt, "Machine Learning for Enhanced Regional Seismic Risk Assessments," J. Struct. Eng., vol. 148, p. 04022126, 2022.
C. A. Luaibi and A. H. Hussein, "Enhancing the Performance Assessment of Network-Based and Machine Learning for Module Availability Estimation," Int. J. Syst. Syst. Eng., vol. 14, no. 1, pp. 1–22, 2024.
R. Solhmirzaei, H. Salehi, V. Kodur, and M. Z. Naser, "Machine Learning Framework for Predicting Failure Mode and Shear Capacity of Ultra High-Performance Concrete Beams," Eng. Struct., vol. 224, p. 111221, 2020.
