SynthCharge: An Electric Vehicle Routing Instance Generator with Feasibility Screening to Enable Learning-Based Optimization and Benchmarking
This provides a dynamic benchmarking infrastructure for researchers in learning-based optimization and routing, though it is incremental as it builds on existing EVRPTW frameworks.
The authors tackled the lack of dynamic and verifiably feasible benchmark datasets for the electric vehicle routing problem with time windows (EVRPTW), which restricts reproducible evaluation of learning-based models, by introducing SynthCharge, a parametric generator that produces diverse, feasibility-screened instances for up to 500 customers, with experiments focusing on 5 to 100 customers.
The electric vehicle routing problem with time windows (EVRPTW) extends the classical VRPTW by introducing battery capacity constraints and charging station decisions. Existing benchmark datasets are often static and lack verifiable feasibility, which restricts reproducible evaluation of learning-based routing models. We introduce SynthCharge, a parametric generator that produces diverse, feasibility-screened EVRPTW instances across varying spatiotemporal configurations and scalable customer counts. While SynthCharge can currently generate large-scale instances of up to 500 customers, we focus our experiments on sizes ranging from 5 to 100 customers. Unlike static benchmark suites, SynthCharge integrates instance geometry with adaptive energy capacity scaling and range-aware charging station placement. To guarantee structural validity, the generator systematically filters out unsolvable instances through a fast feasibility screening process. Ultimately, SynthCharge provides the dynamic benchmarking infrastructure needed to systematically evaluate the robustness of emerging neural routing and data-driven approaches.