Integrated Analysis of Real-Time Traffic Data with M/G/1 Queuing Model in IoT-Enabled Traffic Management

Real-time traffic data from the system was analysed by the M/G/1 queuing model in an IoT-linked traffic monitoring framework. Because of a growing number of vehicles in India and other densely populated countries, the usual traffic control methods are not enough to tackle congestion. The research is aimed at studying the traffic movement along a 500-meter highway in the city with the help of special equipment. In two months, data were gathered with the help of sensors and cameras connected to a cloud platform. Because the M/G/1 model supports unpredictable service times, it was used to analyse how traffic moves into and out of the system. Certain factors like traffic intensity, waiting time, and queue length were identified to analyse the congestion pattern, mainly during busy hours. Experts looked at how the queuing system worked and examined how long it took cars to wait by using performance indicators λ, μ, σ, and waiting time in queue (Wq). The graph proved that the traffic in the right lane was a lot denser than that in the left, which suggests a need for adjusting lane setup. It was also discovered that longer wait times during busy hours showed that adaptive traffic control worked. The results prove that queuing theory helps with anticipating traffic congestion and finding solutions to reduce it using modern traffic systems. The suggested IoT + M/G/1 queuing model-based traffic monitoring technique achieves an overall accuracy of 96.5% in actual-time traffic analysis of patterns.