Summary
Vehicles often need to quickly process complex tasks, and they do this by sending parts of those tasks to nearby servers. However, these tasks depend on each other and need to be very reliable, while learning the best way to manage this offloading must work across different areas and keep the data safe. The paper’s authors designed a system called CRAFT that uses advanced learning methods to optimize how tasks are split and sent to edge servers while ensuring reliability and security. They tested their method in a realistic city network and showed it improves performance by reducing costs and keeping most tasks completed successfully, with only a small security cost.
What this means in practice
- •For vehicular network engineers: Improve the reliability and cost-efficiency of task offloading policies for connected vehicles using secure federated reinforcement learning.
- •For edge computing platform providers: Deploy secure federated learning for adaptive resource allocation that handles dependent tasks in multi-region vehicular networks.
Abstract
Vehicular Edge Computing (VEC) reduces latency for computation-intensive vehicular applications by offloading tasks to roadside edge servers. Real vehicular workloads, however, consist of dependent subtasks with stringent reliability needs, while the cross-region collaborative learning used to adapt offloading policies must stay robust to heterogeneous data and secure over open wireless channels. We propose CRAFT, a Constrained Reinforcement-based Adaptive Federated Task Offloading framework that casts Directed Acyclic Graph (DAG)-structured offloading and resource allocation as a Constrained Markov Decision Process. CRAFT couples centralized-critic policy learning with Lagrangian relaxation to explicitly regulate the long-term task-completion constraint, and uses two-tier federated aggregation with proximal regularization to jointly mitigate non-Independent and Identically Distributed (non-IID) drift and stabilize constraint adaptation. Confidentiality and integrity for federated parameter exchange are provided by post-quantum homomorphic encryption and lattice-based signatures with modest amortized overhead. On a Virtual Machine-based testbed over a realistic Melbourne Central Business District network with real computation kernels, CRAFT cuts weighted cost by up to 42% over state-of-the-art baselines, maintains a completion rate of around 96%, and adds 6.4% security overhead.