Traffic congestion in freeways poses significant challenges, impacting travel times and environmental sustainability. This paper proposes a novel approach to enhance ramp metering control using predictive traffic insights derived from physics-informed LSTM (Long Short-Term Memory) models. By integrating predictive capabilities with established control strategies like ALINEA, the method dynamically adjusts on-ramp flow rates based on anticipated traffic conditions. Real-world traffic data are used to evaluate the effectiveness of the approach, demonstrating improved performance compared to the adoption of conventional controllers.
AI-Based Predictive Ramp-Metering Control for Freeway Traffic Systems
Binjaku K.;Pasquale C.;Siri S.;Sacone S.
2024-01-01
Abstract
Traffic congestion in freeways poses significant challenges, impacting travel times and environmental sustainability. This paper proposes a novel approach to enhance ramp metering control using predictive traffic insights derived from physics-informed LSTM (Long Short-Term Memory) models. By integrating predictive capabilities with established control strategies like ALINEA, the method dynamically adjusts on-ramp flow rates based on anticipated traffic conditions. Real-world traffic data are used to evaluate the effectiveness of the approach, demonstrating improved performance compared to the adoption of conventional controllers.
File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
