DCRNN predictive rerouting cuts average travel-time index by about 1.8% versus no-reroute in SUMO while accepting only 41 route changes
The study presents a framework combining diffusion convolutional recurrent neural network (DCRNN) traffic and charging-demand forecasts with a CAV rerouting policy, evaluated in SUMO under controlled disruptions at five CAV penetration levels from 5% to 45%; DCRNN achieves the lowest average travel-time index, highest average speed, and lowest aggregate CO2 emissions among active routing methods, reduces average TTI by about 1.8% versus the no-reroute reference, and accepts only 41 route changes across all penetration levels versus 146 for K-shortest-path and 153 for V2X.