Artificial Intelligence for Network Congestion Control: A Review of Learning-Based Transport Protocols and Adaptive Traffic Management
Abstract
Network congestion remains a fundamental challenge in communication systems because excessive traffic can cause packet loss, increased latency, reduced throughput, and degraded application performance. Conventional congestion-control mechanisms generally rely on manually designed algorithms and predefined feedback mechanisms, which may not adapt effectively to rapidly changing network conditions. Artificial Intelligence (AI) provides an alternative paradigm in which congestion-control policies can be learned from network observations. This review examines machine learning and reinforcement learning approaches for intelligent congestion control across wired, wireless, data-center, and heterogeneous networks. Existing techniques are categorized according to their learning algorithms, network observations, control actions, reward functions, and performance objectives. The paper compares AI-based approaches with traditional congestion-control mechanisms using metrics such as throughput, latency, packet loss, fairness, and convergence speed. Challenges related to training stability, generalization across network environments, fairness, safety, and deployment overhead are discussed. Emerging opportunities involving deep reinforcement learning, graph neural networks, multi-agent learning, and programmable networks are identified for developing adaptive and autonomous congestion-control mechanisms.
References
Anand, A. (2025). Self-Healing Network Infrastructure using AI-based Intent Recognition. Available at SSRN 5726222.
Dang, S., Amin, O., Shihada, B., & Alouini, M.-S. (2020). What should 6G be? Nature Electronics, 3, 20–29. https://doi.org/10.1038/s41928-019-0355-6
Akyildiz, I. F., Kak, A., & Nie, S. (2020). Internet of Things (IoT): 5G and 6G vision, architecture, and applications. Microprocessors and Microsystems, 77, 103237. https://doi.org/10.1016/j.micpro.2020.103237
Shafin, R., Chen, L., Matinmikko-Blue, M., & Saad, W. (2020). Artificial intelligence-enabled cellular networks: A survey. IEEE Communications Surveys & Tutorials, 22(1), 795–819.
Sirohi, D., Kumar, N., Rana, P. S., Tanwar, S., Iqbal, R., & Hijjii, M. (2023). Federated learning for 6G-enabled secure communication systems: A comprehensive survey. Artificial Intelligence Review, 56, 1–93. https://doi.org/10.1007/s10462-023-10417-3
Niknam, S., Dhillon, H. S., & Reed, J. H. (2020). Federated learning for wireless communications: Motivation, opportunities and challenges. IEEE Communications Magazine, 58(6), 46–51.
Lim, W. Y. B., Luong, N. C., Hoang, D. T., Jiao, Y., Liang, Y.-C., Yang, Q., Niyato, D., & Miao, C. (2020). Federated learning in mobile edge networks: A comprehensive survey. IEEE Communications Surveys & Tutorials, 22(3), 2031–2063.
Nguyen, D. C., Ding, M., Pathirana, P. N., Seneviratne, A., Li, J., Niyato, D., & Poor, H. V. (2022). Federated learning for Internet of Things: A comprehensive survey. IEEE Communications Surveys & Tutorials, 23(3), 1622–1658.
Rahmani, S., Baghbani, A., Bouguila, N., & Patterson, Z. (2023). Graph neural networks for intelligent transportation systems: A survey. IEEE Transactions on Intelligent Transportation Systems, 24(8), 8846–8885. https://doi.org/10.1109/TITS.2023.3257759
Ouyang, Y., Zhao, Z., & others. (2025). AI-enabled routing in next generation networks: A survey. Alexandria Engineering Journal, 120, 449–474. https://doi.org/10.1016/j.aej.2025.01.095
Tang, F., Mao, B., Kawamoto, Y., & Kato, N. (2021). Survey on machine learning for intelligent end-to-end communication toward 6G: From network access, routing to traffic control and streaming adaption. IEEE Communications Surveys & Tutorials, 23(3), 1578–1598. https://doi.org/10.1109/COMST.2021.3073009
Rahmani, M., Norouzi, S., Chen, J., Ahmadi, H., Braun, T., Chowdhury, K., & Burr, A. G. (2026). Hybrid GNN-centric architectures for AI-native 6G wireless networks: A comprehensive survey. IEEE Communications Surveys & Tutorials, 28, 5678–5712. https://doi.org/10.1109/COMST.2026.3681198
Anand, A., SR, L., & Charith, P. (2026, February). Role-Aware Contrastive Graph Neural Network for Social Network Analysis in Twitter Bot Detection. In 2026 3rd International Conference on Integrated Intelligence and Communication Systems (ICIICS) (pp. 1-6). IEEE.
