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

This paper investigates the problem of age of information (AoI) aware radioresource management for a platooning system. Multiple autonomous platoonsexploit the cellular wireless vehicle-to-everything (C-V2X) communicationtechnology to disseminate the cooperative awareness messages (CAMs) to theirfollowers while ensuring timely delivery of safety-critical messages to theRoad-Side Unit (RSU). Due to the challenges of dynamic channel conditions,centralized resource management schemes that require global information areinefficient and lead to large signaling overheads. Hence, we exploit adistributed resource allocation framework based on multi-agent reinforcementlearning (MARL), where each platoon leader (PL) acts as an agent and interactswith the environment to learn its optimal policy. Existing MARL algorithmsconsider a holistic reward function for the group's collective success, whichoften ends up with unsatisfactory results and cannot guarantee an optimalpolicy for each agent. Consequently, motivated by the existing literature inRL, we propose a novel MARL framework that trains two critics with thefollowing goals: A global critic which estimates the global expected reward andmotivates the agents toward a cooperating behavior and an exclusive localcritic for each agent that estimates the local individual reward. Furthermore,based on the tasks each agent has to accomplish, the individual reward of eachagent is decomposed into multiple sub-reward functions where task-wise valuefunctions are learned separately. Numerical results indicate our proposedalgorithm's effectiveness compared with the conventional RL methods applied inthis area.

AoI-Aware Resource Allocation for Platoon-Based C-V2X Networks via Multi-Agent Multi-Task Reinforcement Learning