An Intelligent Machine Learning Framework for Performance Prediction in Mobile Ad Hoc Networks
##plugins.themes.bootstrap3.article.main##
Abstract
Mobile Ad Hoc Networks (MANETs) operate without fixed infrastructure and are affected by node mobility, dynamic topology, unstable links, limited energy, and traffic congestion. This research introduces a Machine Learning-Based Performance Prediction Framework (ML-PPF) to predict packet delivery ratio, throughput, end-to-end delay, packet loss, routing overhead, and energy consumption. The framework uses network parameters such as node density, mobility, residual energy, link stability, queue utilization, traffic load, and route length as input features. After preprocessing and feature selection, Random Forest, Support Vector Regression, XGBoost, and Artificial Neural Network models are trained and combined using a weighted ensemble approach. The proposed framework enables early detection of performance degradation and supports efficient routing, congestion control, load balancing, and energy management in MANETs.
##plugins.themes.bootstrap3.article.details##
References
[2]. O. J. Adaramola and J. R. Olasina, “Machine Learning-Driven Congestion Prediction in Mobile Ad-Hoc Networks Through Modelling Approaches,” International Journal of Scientific Research in Computer Science and Engineering, vol. 13, no. 2, pp. 30–38, Apr. 2025, doi: 10.26438/ijsrcse.v13i2.666.
[3]. O. Aruna, S. Sameerunnisa and R. Vedantham, “Routing in Mobile Ad Hoc Networks Using Machine Learning Techniques,” Journal of Wireless Mobile Networks, Ubiquitous Computing, and Dependable Applications, vol. 14, no. 4, pp. 84–95, Dec. 2023, doi: 10.58346/JOWUA.2023.I4.007.
[4]. D. Nayab, M. H. Zafar and M. Sher, “Adaptive Routing Strategies for Optimisation in MANETs Through Integration of Expanding Ring Search and Random Early Detection Using Machine Learning,” IET Networks, vol. 14, no. 1, Art. no. e70005, 2025, doi: 10.1049/ntw2.70005.
[5]. B. A. Vishwanathrao and P. A. Vikhar, “Reinforcement Machine Learning-Based Improved Protocol for Energy Efficiency on Mobile Ad-Hoc Networks,” International Journal of Intelligent Systems and Applications in Engineering, vol. 12, no. 8s, pp. 654–670, 2024.
[6]. Durr-e-Nayab, M. H. Zafar and A. Altalbe, “Prediction of Scenarios for Routing in MANETs Based on Expanding Ring Search and Random Early Detection Parameters Using Machine Learning Techniques,” IEEE Access, vol. 9, pp. 47033–47047, 2021, doi: 10.1109/ACCESS.2021.3067816.
[7]. Tekdogan, T. (2022). Analyzing the traffic of MANETs using graph neural networks. arXiv preprint arXiv:2212.08923. https://doi.org/10.48550/arXiv.2212.08923.
[8]. Suh, B., Akobir, I., Kim, J., Park, Y., & Kim, K.-I. (2025). A resilient routing protocol to reduce update cost by unsupervised learning and deep reinforcement learning in mobile ad hoc networks. Electronics, 14, 166. https://doi.org/10.3390/electronics14010166.
[9]. Alanazi, F., &Zareei, M. (2025). Multi-agent deep reinforcement learning for dynamic routing in MANETs using graph neural networks. IEEE Access, 13, 152469–152478. https://doi.org/10.1109/ACCESS.2025.3601994.
[10]. Li, J., Wang, M., Zhu, P., Wang, D., & You, X. (2021). Highly reliable fuzzy-logic-assisted AODV routing algorithm for mobile ad hoc networks. Sensors, 21, 5965. https://doi.org/10.3390/s21175965.