Hierarchical Reinforcement Learning Empowered Task Offloading in V2I Networks

TL;DR

This paper introduces a hierarchical deep reinforcement learning approach for task offloading in V2I networks, optimizing delay, energy, and cost by modeling tasks as DAGs and leveraging graph neural networks.

Contribution

It presents a novel hierarchical offloading scheme using DRL and graph neural networks to handle complex task dependencies in dynamic V2I networks.

Findings

Reduces system overhead effectively in simulations.

Handles hierarchical action spaces with mixed discrete and continuous actions.

Improves task processing efficiency in V2I scenarios.

Abstract

Edge computing plays an essential role in the vehicle-to-infrastructure (V2I) networks, where vehicles offload their intensive computation tasks to the road-side units for saving energy and reduce the latency. This paper designs the optimal task offloading policy to address the concerns involving processing delay, energy consumption and edge computing cost. Each computation task consisting of some interdependent sub-tasks is characterized as a directed acyclic graph (DAG). In such dynamic networks, a novel hierarchical Offloading scheme is proposed by leveraging deep reinforcement learning (DRL). The inter-dependencies among the DAGs of the computation tasks are extracted using a graph neural network with attention mechanism. A parameterized DRL algorithm is developed to deal with the hierarchical action space containing both discrete and continuous actions. Simulation results with a real-world car speed dataset demonstrate that the proposed scheme can effectively reduce the system overhead.