LSTM-Based Traffic Flow Prediction for Congestion Avoidance in Wireless IoT Networks
Keywords:
LSTM, Traffic Flow Prediction, Wireless IoT Networks, Congestion Avoidance, Deep Learning, QoS, Time-Series Forecasting, Adaptive Routing, Network Performance OptimizationAbstract
Wireless Internet of Things (IoT) networks are increasingly deployed in smart cities, healthcare, industrial automation, and intelligent transportation systems, where efficient traffic management is critical for maintaining Quality of Service (QoS). However, dynamic node behavior, limited bandwidth, and unpredictable traffic patterns often lead to network congestion, packet loss, and increased latency. To address these challenges, this paper proposes an LSTM-based Traffic Flow Prediction model for congestion avoidance in wireless IoT networks. Long Short-Term Memory (LSTM), a variant of Recurrent Neural Networks (RNN), is well-suited for modeling time-series data and capturing long-term dependencies in traffic patterns.
The proposed system collects historical network parameters such as packet arrival rate, queue length, transmission delay, and throughput to train the LSTM model. The trained model predicts future traffic load and identifies potential congestion points in advance. Based on the predicted congestion level, adaptive routing and load-balancing strategies are applied to reroute traffic through less congested paths. Simulation results demonstrate that the proposed approach significantly improves Packet Delivery Ratio (PDR), reduces end-to-end delay, and enhances overall network throughput compared to traditional routing protocols without predictive mechanisms.
References
S. Jagan, G. K. Jadhav, C. Priya, P. Adhikary, U. M. Bhatt and V. Jayasri, "Reinforcement Learning-Based Autonomous Collision Prediction and Avoidance System for Vehicles," 2023 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES), Chennai, India, 2023, pp. 1-5
Candela, E., Doustaly, O., Parada, L., Feng, F., Demiris, Y. and Angeloudis, P., 2023 Risk-aware controller for autonomous vehicles using model-based collision prediction and reinforcement learning. Artificial Intelligence, 320, p. 103923.
Ouahouah, S., Bagaa, M., Prados-Garzon, J. and Taleb, T., 2021 Deep-reinforcement-learning-based collision avoidance in uav environment. IEEE Internet of Things Journal, 9 ( 6 ), pp. 4015 - 4030.
Li, J., Yao, L., Xu, X., Cheng, B. and Ren, J., 2020 Deep reinforcement learning for pedestrian collision avoidance and human-machine cooperative driving. Information Sciences, 532, pp. 110 - 124.
S. Mishra, P. V. Krishna, and V. Saritha, “A learning automata-based congestion avoidance scheme for wireless sensor networks,” IEEE Trans. Mobile Comput., vol. 15, no. 3, pp. 563–576, Mar. 2016.
N. Pantazis, S. Nikolidakis, and D. Vergados, “Energy-efficient routing protocols in wireless sensor networks: A survey,” IEEE Commun. Surveys Tuts., vol. 15, no. 2, pp. 551–591, 2014.
D. K. Panda and K. K. R. Dash, “A survey on congestion control protocols in WSNs,” IEEE Access, vol. 7, pp. 124396–124417, Sept. 2019.
Z. Cui, K. Henrickson, R. Ke, Z. Pu, and Y. Wang, “Traffic Graph Convolutional Recurrent Neural Network for network-scale traffic learning and forecasting,” arXiv preprint, 2018.
Ihab N. Najm et al., “Machine learning prediction approach to enhance congestion control in 5G IoT environment,” Electronics, vol. 8, no. 6, 2019.
L. Leo Prasanth and E. Uma, “A computationally intelligent framework for traffic engineering and congestion management in software-defined network (SDN),” EURASIP J. Wireless Commun. Netw., vol. 2024, Art. no. 63, 2024.
I. Ahmed Najm, A. K. Hamoud, J. Lloret, and I. Bosch, “Machine learning prediction approach to enhance congestion control in 5G IoT environment,” Electronics, vol. 8, no. 6, 2019.
B. M. Kuboye, T. O. Aratunde, and G. A. Ayomide, “Users’ evaluation of traffic congestion in LTE networks using deep learning techniques,” Int. J. Computer Applications, vol. 183, no. 44, pp. 9–13, Dec. 2021.
Y. Yuan, M. Abdel-Aty, J. Gong, and Q. Cai, “Real-time crash risk prediction using long short-term memory recurrent neural network,” IEEE Trans. Intelligent Transportation Systems, vol. 19, no. 2, pp. 431–441, Feb. 2018.
S. Mishra, P. V. Krishna, and V. Saritha, “A learning automata-based congestion avoidance scheme for wireless sensor networks,” IEEE Trans. Mobile Comput., vol. 15, no. 3, pp. 563–576, Mar. 2016.
Downloads
How to Cite
Issue
Section
License
Copyright (c) 2025 International Journal of Engineering Science & Humanities
This work is licensed under a Creative Commons Attribution 4.0 International License.
