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 introduces an energy-efficient, software-defined vehicular edgenetwork for the growing intelligent connected transportation system. A jointuser-centric virtual cell formation and resource allocation problem isinvestigated to bring eco-solutions at the edge. This joint problem aims tocombat against the power-hungry edge nodes while maintaining assuredreliability and data rate. More specifically, by prioritizing the downlinkcommunication of dynamic eco-routing, highly mobile autonomous vehicles areserved with multiple low-powered access points (APs) simultaneously forubiquitous connectivity and guaranteed reliability of the network. Theformulated optimization is exceptionally troublesome to solve within apolynomial time, due to its complicated combinatorial structure. Hence, adistributed multi-agent reinforcement learning (D-MARL) algorithm is proposedfor eco-vehicular edges, where multiple agents cooperatively learn to receivethe best reward. First, the algorithm segments the centralized action spaceinto multiple smaller groups. Based on the model-free distributed Q learner,each edge agent takes its actions from the respective group. Also, in eachlearning state, a software-defined controller chooses the global best actionfrom individual bests of the distributed agents. Numerical results validatethat our learning solution achieves near-optimal performances within a smallnumber of training episodes as compared with existing baselines.

Eco-Vehicular Edge Networks for Connected Transportation: A Distributed Multi-Agent Reinforcement Learning Approach