English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

By offloading computation-intensive tasks of vehicles to roadside units(RSUs), mobile edge computing (MEC) in the Internet of Vehicles (IoV) canrelieve the onboard computation burden. However, existing model-based taskoffloading methods suffer from heavy computational complexity with the increaseof vehicles and data-driven methods lack interpretability. To address thesechallenges, in this paper, we propose a knowledge-driven multi-agentreinforcement learning (KMARL) approach to reduce the latency of taskoffloading in cybertwin-enabled IoV. Specifically, in the considered scenario,the cybertwin serves as a communication agent for each vehicle to exchangeinformation and make offloading decisions in the virtual space. To reduce thelatency of task offloading, a KMARL approach is proposed to select the optimaloffloading option for each vehicle, where graph neural networks are employed byleveraging domain knowledge concerning graph-structure communication topologyand permutation invariance into neural networks. Numerical results show thatour proposed KMARL yields higher rewards and demonstrates improved scalabilitycompared with other methods, benefitting from the integration of domainknowledge.

Knowledge-Driven Multi-Agent Reinforcement Learning for Computation Offloading in Cybertwin-Enabled Internet of Vehicles