Quantifying Distribution Shift in Traffic Signal Control with Histogram-Based GEH Distance
This addresses the problem of distribution shift in traffic signal control for traffic engineers and researchers, offering a policy-independent and interpretable framework for benchmarking and monitoring, though it is incremental as it builds on existing GEH statistics.
The paper tackles the problem of performance degradation in traffic signal control algorithms due to distribution shift by introducing a method to quantify shift using demand histograms and a GEH-based distance function. Results show that larger distances correspond to increased travel time and reduced throughput, with strong explanatory power for learning-based control, predicting degradation better than previous techniques.
Traffic signal control algorithms are vulnerable to distribution shift, where performance degrades under traffic conditions that differ from those seen during design or training. This paper introduces a principled approach to quantify distribution shift by representing traffic scenarios as demand histograms and comparing them with a GEH-based distance function. The method is policy-independent, interpretable, and leverages a widely used traffic engineering statistic. We validate the approach on 20 simulated scenarios using both a NEMA actuated controller and a reinforcement learning controller (FRAP++). Results show that larger scenario distances consistently correspond to increased travel time and reduced throughput, with particularly strong explanatory power for learning-based control. Overall, this method can predict performance degradation under distribution shift better than previously published techniques. These findings highlight the utility of the proposed framework for benchmarking, training regime design, and monitoring in adaptive traffic signal control.