Efficient toll processing is critical for mitigating traffic congestion and enhancing transportation network efficiency at toll stations. This study explores the Neelamangala Toll Plaza on India’s National Highway 48, employing artificial intelligence (AI) to optimize toll operations. The research integrates a Supervised Learning (SL) time series model for traffic prediction and a Reinforcement Learning (RL) framework based on a Markov Decision Process (MDP), coupled with a randomized algorithm for equitable task distribution. These AI-driven models dynamically adapt to real-time traffic conditions, preventing peak-hour system overload. Key performance metrics—Average Processing Time (APT), Queue Length Reduction (QLR), and Throughput (TP) were used to evaluate the system. Research also demonstrates the model’s superior performance in handling high traffic volumes and reducing congestion. The study underscores the potential of integrating AI and randomized algorithms in modern toll management, offering a scalable and adaptive solution for sustainable transportation infrastructure.
Adaptive AI-Driven Toll Management: Enhancing Traffic Flow and Sustainability Through Real-Time Prediction, Allocation, and Task Optimization
2025
Aufsatz (Zeitschrift)
Elektronische Ressource
Unbekannt
Metadata by DOAJ is licensed under CC BY-SA 1.0
Real time toll optimization based on predicted traffic conditions
DSpace@MIT | 2016
|Traffic Prediction for Real Time Traffic Management
British Library Conference Proceedings | 1995
|Real-Time Traffic Flow Optimization
Tema Archiv | 1971
|Adaptive, real-time traffic control management
Kraftfahrwesen | 2000
|