SA & SUMO output

Abstract

This dataset contains the simulation outputs and supporting results generated by a two-phase framework applied to the Electric Vehicle Routing Problem with Time Windows (EVRPTW). The methodology combines a Simulated Annealing (SA) metaheuristic for route optimization with a SUMO (Simulation of Urban MObility) traffic simulator for real-world validation of the generated routes. ** SA Optimization Results routes.csv : Optimal vehicle routes generated by the SA algorithm: vehicle ID, sequence of visited customers, and capacity usage battery_summary.csv: Battery metrics per vehicle: initial/final battery level, total energy consumed (kWh), estimated distance (km), and number of charging stops sa_cost_with_penalty.png :Cost evolution including the penalty phase sa_cost_no_penalty.png: Cost evolution after penalty resolution sa_unserved_clients.png: Number of unserved clients over iterations sa_cumul_energy.png: Cumulative energy consumption per vehicle (SA) sa_cumul_distance.png: Estimated cumulative distance per vehicle (SA) sa_fleet_summary.png: Bar chart summarizing total energy and distance per vehicle (SA) ** SUMO Traffic Simulation Results delivery_records.csv : Detailed delivery log: client ID, time window (start/end), actual arrival time, delay (minutes), and on-time/late status plot_battery.png: Battery state of charge per vehicle over simulation time plot_distance.png : Cumulative distance per vehicle over simulation time plot_energy.png : Cumulative energy consumption per vehicle over simulation time plot_gantt_tw.png :Gantt chart of delivery time windows vs. actual arrivals plot_cumulative_deliveries. png : Cumulative client deliveries over time plot_client_distribution.png : Pie chart of client distribution per vehicle **Scripts AffichagDesRésultats.py : SA results visualization and export script ExportResultOnCsv.py: SUMO simulation CSV export script These files support the findings reported in the associated manuscript submitted to Sustainability (MDPI).