Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{200954,
        author = {Mrs.T. Praveena and Thaiyiba Tanveer N and Ambika R and Dhivya Dharshini G},
        title = {Learning-Driven Cross-Layer Control for Wireless Traffic Video Surveillance Using Multi-Agent Systems},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {no},
        pages = {142-149},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=200954},
        abstract = {Wireless traffic video surveillance systems require efficient transmission of high-quality video data over bandwidthlimited and dynamic wireless networks. Traditional layered network architectures fail to adapt quickly to fluctuating network conditions. This project proposes a Learning-Driven Cross-Layer Control Mechanism using Multi-Agent Systems (MAS) to dynamically optimize network performance. Intelligent agents operate at different layers (application, MAC, and physical layers) and collaborate to adapt transmission rate, power control, routing, and video compression.
In this project, technologies such as Wireless Sensor Networks (WSN), Reinforcement Learning (e.g., Q-learning), NS-3/NS-2 network simulation tools, Python or MATLAB for implementation, and TensorFlow/PyTorch for machine learning modeling can be used. Traffic cameras act as video sources, while distributed software agents monitor network parameters like bandwidth, signal strength, congestion level, and packet loss. Based on real-time feedback, agents make intelligent decisions to dynamically adjust encoding bitrate, transmission power, and routing paths. The system can be implemented in a simulated wireless environment or deployed in a real-time intelligent transportation setup.
By incorporating machine learning techniques, the system learns traffic patterns and network conditions to improve Quality of Service (QoS), reduce packet loss, minimize delay, and enhance energyefficiency.},
        keywords = {.},
        month = {May},
        }