Heterogeneous Mean Field Game Framework for LEO Satellite-Assisted V2X Networks
This addresses a scalability bottleneck for coordinating mixed fleets of vehicles in next-generation V2X networks, providing a theoretical foundation for type-granularity selection.
The paper tackles the problem of determining the optimal number of agent types (K) for coordinating large fleets of vehicles in V2X networks using heterogeneous mean field games, proving that the error-minimizing type count scales as K*(N)=Θ(N^(1/3)) and showing that only about 28 types suffice for 10^5 vehicles. Experiments demonstrate 2.3× faster convergence, 29.5% lower delay, and 60% higher throughput compared to baselines.
Coordinating mixed fleets of $10^4$ to $10^5$ vehicles, passenger cars, freight trucks, and autonomous vehicles, under stringent delay constraints is a central scalability bottleneck in next-generation V2X networks. Heterogeneous mean field games (HMFG) offer a principled coordination framework, yet a fundamental design question lacks theoretical guidance: how many agent types $K$ should be used for a fleet of size $N$? The core challenge is a two-sided trade-off that existing theory does not resolve: increasing $K$ reduces type-discretization error but simultaneously starves each class of the samples needed for reliable mean-field approximation. We resolve this trade-off by deriving an explicit $\varepsilon$-Nash error decomposition driven by a Wasserstein-based heterogeneity measure, and prove that the unique error-minimizing type count satisfies $K^*(N)=Î(N^{1/3})$ in the canonical one-dimensional queue setting. We further establish a heterogeneity-aware convergence condition for G-prox PDHG and extend the framework to temporal-graph LEO satellite backhaul dynamics with provable robustness guarantees. A perhaps surprising consequence is that even for $N=10^5$ vehicles, only about 28 type classes suffice, cube-root compression rather than per-vehicle modeling, so type-granularity selection is largely a set-once design decision. Experiments validate the scaling law, achieve $2.3\times$ faster PDHG convergence at $K=5$, and deliver up to $29.5\%$ lower delay and $60\%$ higher throughput compared with homogeneous baselines.