arXiv AI By Mertcan Daysalilar, Fuat Uyguroglu, Gabriel Nicolosi, Adam Meyers

SynthCharge: An Electric Vehicle Routing Instance Generator with Feasibility Screening to Enable Learning-Based Optimization and Benchmarking

Read the original on arXiv AI →

SynthCharge is a parametric generator that creates diverse, feasibility‑screened instances of the electric vehicle routing problem with time windows (EVRPTW). It produces instances ranging from 5 to 100 customers (up to 500 in theory) with adaptive energy capacity scaling and range‑aware charging station placement, filtering out unsolvable cases via a fast feasibility screening process. This dynamic benchmarking infrastructure enables systematic evaluation of learning‑based routing and data‑driven approaches.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.