Utilizing the Internet of Things and Big Data for Traffic Management: The Role of Physical Network Systems and Collaborative Signal Light Control

In investigating the use of big data and the Internet of Things (IoT) for traffic control, this study emphasizes the value of physical network systems and cooperative signal light control. This paper proposes a novel giant armadillo optimized model predictive controller (GAO-MPC) method for dynamically controlling the phases and cycles of traffic lights in a remote intersection. The GAO strategy is applied to enhance the parameters of the MPC. The goal of the effort is to create an enhanced, adaptable technology that could be acquired off-the-shelf, eschewing intricate and costly computational techniques that would make it more difficult to use in real-world situations. An IEEE 802.15.4-based WSN (Wireless Sensor Network) during actual traffic surveillance is combined into several MPCs, one for every stage, that operate simultaneously to create the suggested traffic light adaptive management system. Every MPC controls the turning motion of automobiles and continually alters the traffic light’s phase and green period. The suggested system integrates the pros associated with employing simultaneous MPCs enhanced effectiveness, tolerance for faults, and assistance for phase-specific management with the advantages of the WSN, including ease of installation and management, inexpensiveness, and adaptability. The GAO-MPC approach improves traffic flow, decreases vehicle paths, and adjusts dynamically to different traffic situations, making it superior to conventional fuzzy logic controller (FLC) and programmable logic controller (PLC) systems. The suggested technique outperforms the current alternatives in published research and opens the door for increased adoption because it drastically cuts down on car queues.