🤖 AI Summary
This study investigates why improved traffic prediction fails to enhance signal control performance, focusing on the "value gap" between prediction and decision-making. We propose a hierarchical diagnostic framework and a practical auditing protocol, leveraging real-world data from Xuancheng within a closed-loop controller setting. By integrating conformal intervals, dependence-aware scenario generation, causal prediction, and exhaustive joint action search, we systematically evaluate how prediction accuracy, uncertainty quantification, and interface alignment affect control outcomes. Our findings reveal a counterintuitive phenomenon wherein reduced prediction errors paradoxically increase queue lengths. Furthermore, this work establishes the critical roles of temporal observability, action identifiability, and objective alignment, offering a precise diagnostic methodology for identifying cross-stage failures in prediction-driven traffic control systems.
📝 Abstract
Improved traffic forecasts do not necessarily yield better signal-control decisions. We investigate this gap through a layered diagnostic study using 29 days of reconstructed demand from Xuancheng, China, with seven dates reserved for testing. The framework evaluates point forecasts, conformal intervals, dependence-aware scenarios, and matched closed-loop controllers. Entry-level and movement-level forecasts reduce mean absolute error by 4.03% and 3.92%, respectively, relative to historical means. A nominal 90% conformal interval achieves 90.72% marginal coverage but only 75.66% on an ex-post high-demand subset. Interface audits identify decision-time leakage and reveal that only two of nine controlled intersections offer multiple effective actions. We correct the temporal interface and compare causal forecasts with a five-second event oracle using exhaustive joint-action search. A synthetic positive control demonstrates that future information can reduce the internal rollout cost by 61.5%. On the frozen test dates, however, causal forecasts and the event oracle increase queue vehicle?seconds by 6.09% and 3.39% relative to the matched no-future rollout, while the oracle reduces spillback exposure by 3.78%; paired-day bootstrap intervals cross zero. These findings indicate that forecast value depends on temporal observability, action identifiability, dynamics consistency, and objective alignment. The proposed protocol provides a practical way to diagnose where predictive improvements fail to translate into operational benefits.