dataset · Zenodo (CERN European Organization for Nuclear Research)
This deposit provides simulation benchmark data evaluating five different decision-making policies for electric vehicle charging-station assignment. The evaluated policies comprise random selection, an adaptive heuristic, standard Q-learning, Deep Q-Networks, and Double Deep Q-Networks. Testing was conducted using the SUMO traffic simulator mapped onto real-world road network layouts from Rabat and Tangier in Morocco. The dataset includes raw seed-level comma-separated values, structured summaries, and campaign manifests with cryptographic hashes to ensure data integrity across multiple experimental runs and scenarios. This release serves as an audit record covering comparative diagnostic trials between trained, untrained, and heuristic algorithms, although simulation event logs and the trained model weights themselves remain separate from this specific data package.
Managing electric vehicle charging demand is critical for modern transport grids. By comparing advanced artificial intelligence methods directly against simpler heuristic rules on real city road networks, such benchmarks help engineers and planners evaluate whether complex reinforcement learning algorithms provide reliable advantages over conventional operational approaches.
The data supports research into automated fleet management and smart charging systems for urban transport networks. Intended users include software developers, traffic planners, and energy network operators assessing assignment algorithms. Because the deposit comprises early-stage simulation data without accompanying trained model weights or event logs, direct operational applications remain at a preliminary research stage.
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.22181433
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.
