"High-Altitude Mountainous Highway Scenario for Integrated Aerial-Ground Vehicular Networks (IAGVN)"

"This dataset provides high-fidelity, spatiotemporal simulation traces designed to evaluate resource allocation, client scheduling, and network association algorithms for Vehicular Federated Learning (VFL) within a Space-Air-Ground Integrated Network (SAGIN). Specifically tailored for high-altitude freight transportation scenarios, the dataset incorporates heavy-duty vehicle mobility (based on the Intelligent Driver Model), sparse Roadside Unit (RSU) deployments, and multi-tier satellite constellations (LEO, MEO, GEO). It explicitly captures the harsh dynamic channel conditions of mountainous environments\u2014including line-of-sight blockages and severe shadow fading\u2014as well as the extreme device heterogeneity in terms of CPU computation power, energy budgets, and communication latency.This dataset also provides a comprehensive, time-series simulation of a large-scale vehicular network operating in a high-altitude mountainous highway environment. It captures the dynamic interplay between a fleet of freight vehicles, sparse ground-based Roadside Units (RSUs), and a multi-layered satellite constellation (LEO, MEO, GEO), modeling critical aspects of communication and computation for next-generation integrated aerial-ground networks."