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

Unmanned Aerial Vehicles (UAVs) promise to become an intrinsic part of nextgeneration communications, as they can be deployed to provide wirelessconnectivity to ground users to supplement existing terrestrial networks. Themajority of the existing research into the use of UAV access points forcellular coverage considers rotary-wing UAV designs (i.e. quadcopters).However, we expect fixed-wing UAVs to be more appropriate for connectivitypurposes in scenarios where long flight times are necessary (such as for ruralcoverage), as fixed-wing UAVs rely on a more energy-efficient form of flightwhen compared to the rotary-wing design. As fixed-wing UAVs are typicallyincapable of hovering in place, their deployment optimisation involvesoptimising their individual flight trajectories in a way that allows them todeliver high quality service to the ground users in an energy-efficient manner.In this paper, we propose a multi-agent deep reinforcement learning approach tooptimise the energy efficiency of fixed-wing UAV cellular access points whilestill allowing them to deliver high-quality service to users on the ground. Inour decentralized approach, each UAV is equipped with a Dueling Deep Q-Network(DDQN) agent which can adjust the 3D trajectory of the UAV over a series oftimesteps. By coordinating with their neighbours, the UAVs adjust theirindividual flight trajectories in a manner that optimises the total systemenergy efficiency. We benchmark the performance of our approach against aseries of heuristic trajectory planning strategies, and demonstrate that ourmethod can improve the system energy efficiency by as much as 70%.

Multi-Agent Deep Reinforcement Learning For Optimising Energy Efficiency of Fixed-Wing UAV Cellular Access Points