Dynamic Scheduling for Vehicle-to-Vehicle Communications Enhanced Federated Learning

TL;DR

This paper introduces a V2V-enhanced dynamic scheduling algorithm for vehicular federated learning, improving training efficiency and accuracy by optimizing communication and energy constraints in mobile vehicular networks.

Contribution

It formulates a stochastic optimization model and proposes a novel V2V-based dynamic scheduling algorithm with theoretical performance bounds for vehicular federated learning.

Findings

Enhances CIFAR-10 image classification accuracy by 4.20%.

Reduces average displacement errors on trajectory prediction by 9.82%.

Provides a scalable, efficient solution for VFL in vehicular networks.

Abstract

Leveraging the computing and sensing capabilities of vehicles, vehicular federated learning (VFL) has been applied to edge training for connected vehicles. The dynamic and interconnected nature of vehicular networks presents unique opportunities to harness direct vehicle-to-vehicle (V2V) communications, enhancing VFL training efficiency. In this paper, we formulate a stochastic optimization problem to optimize the VFL training performance, considering the energy constraints and mobility of vehicles, and propose a V2V-enhanced dynamic scheduling (VEDS) algorithm to solve it. The model aggregation requirements of VFL and the limited transmission time due to mobility result in a stepwise objective function, which presents challenges in solving the problem. We thus propose a derivative-based drift-plus-penalty method to convert the long-term stochastic optimization problem to an online mixed integer nonlinear programming (MINLP) problem, and provide a theoretical analysis to bound the performance gap between the online solution and the offline optimal solution. Further analysis of the scheduling priority reduces the original problem into a set of convex optimization problems, which are efficiently solved using the interior-point method. Experimental results demonstrate that compared with the state-of-the-art benchmarks, the proposed algorithm enhances the image classification accuracy on the CIFAR-10 dataset by 4.20% and reduces the average displacement errors on the Argoverse trajectory prediction dataset by 9.82%.