GA-DRL: Graph Neural Network-Augmented Deep Reinforcement Learning for DAG Task Scheduling over Dynamic Vehicular Clouds

TL;DR

This paper introduces GA-DRL, a novel graph neural network-augmented deep reinforcement learning approach for efficient DAG task scheduling in dynamic vehicular clouds, improving completion times by leveraging advanced feature extraction and decision-making techniques.

Contribution

The paper proposes a new GA-DRL framework combining GAT and deep Q-networks for DAG scheduling over VCs, with novel neighborhood sampling for unseen topologies.

Findings

GA-DRL outperforms existing benchmarks in DAG task completion time.

The GAT effectively captures DAG features considering predecessors and successors.

The approach adapts well to dynamic vehicle heterogeneity and mobility.

Abstract

Vehicular clouds (VCs) are modern platforms for processing of computation-intensive tasks over vehicles. Such tasks are often represented as directed acyclic graphs (DAGs) consisting of interdependent vertices/subtasks and directed edges. In this paper, we propose a graph neural network-augmented deep reinforcement learning scheme (GA-DRL) for scheduling DAG tasks over dynamic VCs. In doing so, we first model the VC-assisted DAG task scheduling as a Markov decision process. We then adopt a multi-head graph attention network (GAT) to extract the features of DAG subtasks. Our developed GAT enables a two-way aggregation of the topological information in a DAG task by simultaneously considering predecessors and successors of each subtask. We further introduce non-uniform DAG neighborhood sampling through codifying the scheduling priority of different subtasks, which makes our developed GAT generalizable to completely unseen DAG task topologies. Finally, we augment GAT into a double deep Q-network learning module to conduct subtask-to-vehicle assignment according to the extracted features of subtasks, while considering the dynamics and heterogeneity of the vehicles in VCs. Through simulating various DAG tasks under real-world movement traces of vehicles, we demonstrate that GA-DRL outperforms existing benchmarks in terms of DAG task completion time.