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

Deep Reinforcement Learning (DRL) is widely used to optimize the performanceof multi-UAV networks. However, the training of DRL relies on the frequentinteractions between the UAVs and the environment, which consumes lots ofenergy due to the flying and communication of UAVs in practical experiments.Inspired by the growing digital twin (DT) technology, which can simulate theperformance of algorithms in the digital space constructed by coping featuresof the physical space, the DT is introduced to reduce the costs of practicaltraining, e.g., energy and hardware purchases. Different from previousDT-assisted works with an assumption of perfect reflecting real physics byvirtual digital, we consider an imperfect DT model with deviations forassisting the training of multi-UAV networks. Remarkably, to trade off thetraining cost, DT construction cost, and the impact of deviations of DT ontraining, the natural and virtually generated UAV mixing deployment method isproposed. Two cascade neural networks (NN) are used to optimize the jointnumber of virtually generated UAVs, the DT construction cost, and theperformance of multi-UAV networks. These two NNs are trained by unsupervisedand reinforcement learning, both low-cost label-free training methods.Simulation results show the training cost can significantly decrease whileguaranteeing the training performance. This implies that an efficient decisioncan be made with imperfect DTs in multi-UAV networks.

Imperfect Digital Twin Assisted Low Cost Reinforcement Training for Multi-UAV Networks