Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Aug 6;25(15):4838.
doi: 10.3390/s25154838.

GAPO: A Graph Attention-Based Reinforcement Learning Algorithm for Congestion-Aware Task Offloading in Multi-Hop Vehicular Edge Computing

Hongwei Zhao  1 , Xuyan Li  1 , Chengrui Li  1 , Lu Yao  1
Affiliations

GAPO: A Graph Attention-Based Reinforcement Learning Algorithm for Congestion-Aware Task Offloading in Multi-Hop Vehicular Edge Computing

Hongwei Zhao et al. Sensors (Basel). .

Abstract

Efficient task offloading for delay-sensitive applications, such as autonomous driving, presents a significant challenge in multi-hop Vehicular Edge Computing (VEC) networks, primarily due to high vehicle mobility, dynamic network topologies, and complex end-to-end congestion problems. To address these issues, this paper proposes a graph attention-based reinforcement learning algorithm, named GAPO. The algorithm models the dynamic VEC network as an attributed graph and utilizes a graph neural network (GNN) to learn a network state representation that captures the global topological structure and node contextual information. Building on this foundation, an attention-based Actor-Critic framework makes joint offloading decisions by intelligently selecting the optimal destination and collaboratively determining the ratios for offloading and resource allocation. A multi-objective reward function, designed to minimize task latency and to alleviate link congestion, guides the entire learning process. Comprehensive simulation experiments and ablation studies show that, compared to traditional heuristic algorithms and standard deep reinforcement learning methods, GAPO significantly reduces average task completion latency and substantially decreases backbone link congestion. In conclusion, by deeply integrating the state-aware capabilities of GNNs with the decision-making abilities of DRL, GAPO provides an efficient, adaptive, and congestion-aware solution to the resource management problems in dynamic VEC environments.

Keywords: V2X communication; attention; deep reinforcement learning; edge computing; graph neural network; multi-hop networks; task offloading.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Multi-hop Vehicular Edge Computing Network.
Figure 2
Figure 2
The GAPO Algorithm Framework.
Figure 3
Figure 3
GNN Network and Embeddings.
Figure 4
Figure 4
Attention-based Actor–Critic Policy Network.
Figure 5
Figure 5
Impact of Vehicle Count on Performance.
Figure 6
Figure 6
Impact of RSU Computational Capacity on Performance.
Figure 7
Figure 7
Impact of Task Arrival Interval on Performance.
Figure 8
Figure 8
Impact of Task Type Heterogeneity on Performance.
Figure 9
Figure 9
Impact of RSU Computational Resource Heterogeneity on Performance.
Figure 10
Figure 10
Ablation Model Training Metrics. (a) Policy Entropy. (b) Actor Network Policy Loss. (c) Total Loss. (d) Critic Network Policy Loss.
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Zhang J., Letaief K.B. Mobile Edge Intelligence and Computing for the Internet of Vehicles. Proc. IEEE. 2019;108:246–261. doi: 10.1109/JPROC.2019.2947490. - DOI
    1. Mach P., Becvar Z. Mobile Edge Computing: A Survey on Architecture and Computation Offloading. IEEE Commun. Surv. Tutor. 2017;19:1628–1656. doi: 10.1109/COMST.2017.2682318. - DOI
    1. Mao Y., You C., Zhang J., Huang K., Letaief K.B. A Survey on Mobile Edge Computing: The Communication Perspective. IEEE Commun. Surv. Tutor. 2017;19:2322–2358. doi: 10.1109/COMST.2017.2745201. - DOI
    1. Filali A., Abouaomar A., Cherkaoui S., Kobbane A., Guizani M. Multi-Access Edge Computing: A Survey. IEEE Access. 2020;8:197017–197046. doi: 10.1109/ACCESS.2020.3034136. - DOI
    1. Dai Y., Xu D., Maharjan S., Zhang Y. Joint Load Balancing and Offloading in Vehicular Edge Computing and Networks. IEEE Internet Things J. 2018;6:4377–4387. doi: 10.1109/JIOT.2018.2876298. - DOI

LinkOut - more resources