Differentiable Predictive Control for Large-Scale Urban Road Networks
This work addresses traffic congestion and emissions in large-scale urban networks, offering a more efficient control method, though it is incremental as it builds on existing physics-informed machine learning and control paradigms.
The paper tackles traffic network optimization to reduce CO2 emissions by introducing Differentiable Predictive Control (DPC) for large-scale urban road networks, achieving a 4 order of magnitude reduction in computation time and up to 37% improvement in traffic performance compared to existing MPC methods.
Transportation is a major contributor to CO2 emissions, making it essential to optimize traffic networks to reduce energy-related emissions. This paper presents a novel approach to traffic network control using Differentiable Predictive Control (DPC), a physics-informed machine learning methodology. We base our model on the Macroscopic Fundamental Diagram (MFD) and the Networked Macroscopic Fundamental Diagram (NMFD), offering a simplified representation of citywide traffic networks. Our approach ensures compliance with system constraints by construction. In empirical comparisons with existing state-of-the-art Model Predictive Control (MPC) methods, our approach demonstrates a 4 order of magnitude reduction in computation time and an up to 37% improvement in traffic performance. Furthermore, we assess the robustness of our controller to scenario shifts and find that it adapts well to changes in traffic patterns. This work proposes more efficient traffic control methods, particularly in large-scale urban networks, and aims to mitigate emissions and alleviate congestion in the future.