Journal Menu
By: Harshit Choudhary and Ruchi Jain.
1, Student, Department of CSE-CYBER SECURITY Lakshmi Narain College Of Technology And Science, Bhopal, Madhya Pradesh, 462022,India
2,Assistant Professor, Department of Computer Science, Lakshmi Narain College of Technology & Science, Bhopal, Madhya Pradesh, 462022,India
The rapid growth of data traffic, fueled by emerging applications such as autonomous systems, augmented reality (AR), virtual reality (VR), and the Internet of Things (IoT), poses major challenges for modern communication networks. With the rollout of 5G and the continuous transition to 6G, sophisticated congestion control techniques are needed to satisfy the demanding requirements of massive machine-type communication (mMTC), ultra-reliable low-latency communication (URLLC), and improved mobile broadband (eMBB). Conventional congestion control strategies, originally designed for less dynamic environments, often fall short in addressing the complexity, heterogeneity, and variability of next-generation networks. The exponential rise in connected devices and data-driven services further amplifies the need for intelligent, adaptive solutions. The current study suggests a hybrid congestion control strategy that combines deep learning (DL) and machine learning (ML) approaches to address this issue. Specifically, the model combines the predictive capabilities of K- Nearest Neighbors (KNN) and Support Vector Machines (SVM) with the adaptability of neural networks to forecast congestion and optimize traffic flow. The framework was evaluated using publicly available network datasets, with key performance indicators such as latency, throughput, packet loss, and queue length serving as benchmarks. Findings reveal that the hybrid model outperforms standalone ML or DL approaches, offering higher accuracy, improved adaptability, and enhanced scalability. These results highlight the promise of hybrid AI-based systems in achieving real-time and efficient congestion management for the evolving landscape of 5G and future 6G networks.
Deep learning, KNN(k Nearest Neighbours), SVM(Support Vector Machine), Naïve Bayes
Citation:
Refrences:
- Khan S, Hussain A, Nazir S, Khan F, Oad A, Alshehri MD. Efficient and reliable hybrid deep learning-enabled model for congestion control in 5G/6G networks. Comput Commun. 2022 Jan 15;182:31-40.
- Alnawayseh SE, Al-Sit WT, Ghazal TM. Smart congestion control in 5G/6G networks using hybrid deep learning techniques. Complexity. 2022;2022(1):1781952.
- Logeshwaran J, Patel SK, Kumar OP, Al-Zahrani FA. Hybrid optimization for efficient 6G IoT traffic management and multi-routing strategy. Sci Rep. 2024 Dec 28;14(1):30915.
- Agrawal A, Pal AK. Adaptive hybrid genetic-ant colony optimization for dynamic self-healing and network performance optimization in 5G/6G networks. Procedia Comput Sci. 2025 Jan 1;252:404-13.
- Saoud B, Shayea I, Yahya AE, Shamsan ZA, Alhammadi A, Alawad MA, Alkhrijah Y. Artificial intelligence, Internet of Things and 6G methodologies in the context of Vehicular Ad-hoc Networks (VANETs): Survey. ICT Express. 2024 May;10(4):959-80.
- Chabira C, Shayea I, Nurzhaubayeva G, Aldasheva L, Yedilkhan D, Amanzholova S. AI-driven handover management and load balancing optimization in ultra-dense 5G/6G cellular networks. Technologies. 2025 Jul 1;13(7):276.
- Puspitasari AA, An TT, Alsharif MH, Lee BM. Emerging technologies for 6G communication networks: Machine learning approaches. Sensors. 2023 Sep 6;23(18):7709.
- Keer PK, Deepthi NL, Nijhawan G, Chahuan N, Albawi A, Palati M. Optimizing V2V communication in 5G/6G networks with enhanced deep cooperative Q-learning. In: 2025 International Conference on Next Generation Communication & Information Processing (INCIP); 2025 Jan 23. p. 304-9. IEEE.
- Zhang G. 6G enabled UAV traffic management models using deep learning algorithms. Wirel Netw. 2024 Nov;30(8):6709-19.
- Dangi R, Lalwani P. Optimizing network slicing in 6G networks through a hybrid deep learning strategy. J Supercomput. 2024 Sep;80(14):20400-20.