dataset · Zenodo (CERN European Organization for Nuclear Research)
This dataset provides raw benchmark records and verification files evaluating five algorithmic approaches for electric vehicle charging-station assignment. The evaluated methods include random selection, an adaptive heuristic, Q-learning, Deep Q-Networks, and Double Deep Q-Networks. Operational performance was simulated across real road networks representing Rabat and Tangier in Morocco using the SUMO traffic simulation platform. The repository contains seed-level experimental data, cryptographic provenance manifests, and diagnostic records comparing trained and untrained policies across three specific scenarios, alongside a legacy benchmark spanning 210 runs. Structured summary files supporting comparative analysis tables are also provided to ensure experimental verification. While simulation event logs and trained model weights are excluded from this initial release, the collection supplies the necessary empirical outputs to audit single-agent reinforcement learning against conventional heuristic rules under realistic urban conditions.
Efficient charging allocation is vital for managing electric vehicle growth and preventing traffic bottlenecks. Providing transparent, seed-level simulation data helps researchers and infrastructure developers rigorously verify whether complex machine learning methods genuinely outperform simpler heuristic rules when directing vehicles to charging stations across real urban networks.
The benchmark data could assist electric vehicle fleet operators and smart-city software developers evaluating automated charging assignment algorithms. As a preliminary, data-only deposit drawn from simulated traffic environments, the findings reflect early-stage research that requires implementation into live dispatch systems and physical trial validation before commercial deployment.
AI-generated from the published abstract. Always read the original work before citing.
Data for "Auditing Single-Agent Reinforcement Learning for EV Charging Assignment: A Protocol-Amended Comparison of Trained, Untrained, and Heuristic Policies" Raw seed-level data and campaign manifests for a benchmark of five agents (Random, Adaptive Heuristic, Q-Learning, DQN, Double DQN) on EV charging-station assignment, simulated on real Rabat and Tangier (Morocco) road networks in SUMO. Includes: campaign manifests with SHA-256 provenance, raw per-seed CSVs for the confirmatory trained/untrained diagnostic (three scenarios) and the legacy 210-run benchmark, and the JSON summaries behind the manuscript's result tables. Integrity verifiable via the included SHA-256 manifest. Preliminary, data-only deposit. Simulation event logs and trained model weights are not included in this version; available from the corresponding author on request.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.5281/zenodo.22181434
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
