Heterogeneous Tasks Offloading in Vehicular Edge Computing: A Federated Meta Deep Reinforcement Learning Approach

TL;DR

This paper introduces FedMAGS, a federated meta deep reinforcement learning framework utilizing GAT-Seq2Seq for efficient, privacy-preserving heterogeneous task offloading in vehicular edge computing systems.

Contribution

It presents a novel federated meta-learning approach with GAT-Seq2Seq modeling for fast, scalable, and privacy-aware task offloading in VEC with complex DAG workloads.

Findings

FedMAGS converges faster than existing methods.

Achieves lower delay and better scalability.

Preserves privacy with reduced communication overhead.

Abstract

Vehicular edge computing (VEC) enables latency-sensitive vehicular applications by offloading computation-intensive tasks to nearby edge servers. However, real-world vehicular workloads are typically modeled as heterogeneous directed acyclic graph (DAG) tasks with complex dependency structures, making joint offloading and resource allocation highly challenging. Moreover, distributed MEC deployment raises privacy concerns when collaboratively training learning-based policies. In this paper, we propose a Federated Meta Deep Reinforcement Learning framework with GAT-Seq2Seq modeling (FedMAGS) for heterogeneous task offloading in VEC systems. The proposed approach leverages Graph Attention Networks to capture DAG dependencies, a Seq2Seq-based policy to generate structured offloading decisions, and federated meta-learning to enable fast adaptation across distributed MEC servers without sharing raw data. Extensive simulations demonstrate that FedMAGS achieves faster convergence, lower execution delay, and better scalability compared with state-of-the-art baselines. In addition, the federated design preserves data privacy while reducing communication overhead, making the framework well suited for dynamic and large-scale VEC environments.