Answers are grounded in this paper and cite their sources.
Evaluates an IoV-driven traffic system to enhance flow and reduce congestion.
Due to rise in living standards, more people can now afford private vehicles, which effects with increased traffic demand. However, this population growth and increasing traffic volume are beyond the capacity of the current transportation system. Intelligent Transport Systems (ITS) are therefore required to increase the effectiveness of transportation networks, enabling quicker and more seamless travel while lowering traffic. An essential part of ITS is Smart Traffic Light Systems (TLS), which assist in modifying signal timings in response to actual traffic demand. This work develops an IoV-driven ITS for-congestion control and optimal traffic light Scheduling. The work mainly aims to control the traffic light signal, by which the congestion and traveling time could be lessened. Initially, the traffic data is simulated using SUMO set up. After setting up the traffic scenarios, the traffic data, containing varied parameters are provided as input to Residual Block integrated randomized Leaky ReLU with Mixed Pooling-based Improved LeNet (RBIRLRMP-ILNet) model for congestion prediction. After traffic congestion prediction, traffic light scheduling is performed optimally based on the prediction of congestion status for enhancing the traffic flow. For scheduling, a novel hybrid optimization model named Botox Optimization Integrated-Improved Hippopotamus Optimization Algorithm (BOI-IHOA) is developed that aids in adjusting the time for green traffic lights. By attaining this objective, congestion and traveling time is lessened and traffic flow is enhanced. This further aids in distance-based prioritizing of emergency vehicles that can be achieved using the optimized green light duration. From examination, the waiting time of vehicles using suggested BOI-IHOA received a less value of 45 s, when vehicle count is 50, while, extant algorithms achieved high waiting time.
No takes yet. Share an insight, caveat, or question.
Negi et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: