Multifunctional Model for Traffic Flow Prediction Congestion Control in Highway Systems

Highway transportation systems are facing challenges such as congestion due to urban development and increasing number of vehicles. This study presents a model using Long Short-Term Memory (LSTM) networks and Graph Neural Networks (GNN) to improve real-time traffic prediction and alleviate traffic congestion. The model combines LSTM networks and GNN for traffic prediction and applies multi-agent reinforcement learning (MARL) for route planning and traffic control. The study used traffic history, weather, and road network data and conducted experiments on TensorFlow, PyTorch, and SUMO platforms. The model achieved 91.8% prediction accuracy, 21.5% reduction in traffic delays and 27.0% reduction in congestion. It also reduced emergency response time by 2.3 seconds. The results of the study show that the model helps create smarter and safer transportation systems. Highway transportation systems are facing challenges such as congestion due to urban development and increasing number of vehicles. This study presents a model using Long Short-Term Memory (LSTM) networks and Graph Neural Networks (GNN) to improve real-time traffic prediction and alleviate traffic congestion. The model combines LSTM networks and GNN for traffic prediction and applies multi-agent reinforcement learning (MARL) for route planning and traffic control. The study used traffic history, weather, and road network data and conducted experiments on TensorFlow, PyTorch, and SUMO platforms. The model achieved 91.8% prediction accuracy, 21.5% reduction in traffic delays and 27.0% reduction in congestion. It also reduced emergency response time by 2.3 seconds. The results of the study show that the model helps create smarter and safer transportation systems.