Traffic Flow Optimization at Toll Plaza Using Pro‐Active Deep Learning Strategies

Abstract

Global urbanization and increasing traffic volume have intensified traffic congestion on transportation infrastructure. This highlights the critical need to implement more intelligent and proactive transportation infrastructure solutions. Transportation infrastructure on freeway such as toll plazas are crucial for traffic flow and revenue, yet they often face congestion challenges, leading to longer queues, increased travel times, and environmental issues. To combat toll plazas congestion and optimize traffic management, this study proposes a proactive traffic control strategy using advanced technologies. The approach involves deep learning convolutional neural network models (YOLOv7-DeepSORT) for vehicle counting and long short-term memory model for short-term arrival rate prediction. When projected arrival rates exceed a threshold, the strategy proactively activates Variable Speed Limits (VSL) and Ramp Metering (RM) strategies during peak hours. Validated through a case study at Ravi Toll Plaza using PTV VISSIM, the proposed method reduces queue length by 57% and vehicle delays by 47%, while cutting fuel consumption and pollutant emissions by 28.4% and 34%, respectively. Additionally, an implementation framework alongside the proposed strategy, this study aims to bridge the gap between theory and practice, making it easier for toll plaza operators and transportation authorities to adopt and benefit from the advanced traffic management techniques. Ultimately, this study underscores the importance of integrated and proactive traffic control strategies in enhancing traffic management, minimizing congestion, and fostering a more sustainable transportation system. Intelligent Transportation System, Variable Speed Limits, Ramp Metering and Deep Learning, YOLOV7-Deep-SORT and LSTM