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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

In this paper, the problem of data pre-storing and routing in dynamic,resource-constrained cube satellite networks is studied. In such a network,each cube satellite delivers requested data to user clusters under itscoverage. A group of ground gateways will route and pre-store certain data tothe satellites, such that the ground users can be directly served with thepre-stored data. This pre-storing and routing design problem is formulated as adecentralized Markov decision process (Dec-MDP) in which we seek to find theoptimal strategy that maximizes the pre-store hit rate, i.e., the fraction ofusers being directly served with the pre-stored data. To obtain the optimalstrategy, a distributed distribution-robust meta reinforcement learning(D2-RMRL) algorithm is proposed that consists of three key ingredients:value-decomposition for achieving the global optimum in distributed settingwith minimum communication overhead, meta learning to obtain the optimalinitial to reduce the training time under dynamic conditions, and pre-trainingto further speed up the meta training procedure. Simulation results show that,using the proposed value decomposition and meta training techniques, thesatellite networks can achieve a 31.8% improvement of the pre-store hits and a40.7% improvement of the convergence speed, compared to a baselinereinforcement learning algorithm. Moreover, the use of the proposedpre-training mechanism helps to shorten the meta-learning procedure by up to43.7%.

Distributed and Distribution-Robust Meta Reinforcement Learning (D2-RMRL) for Data Pre-storing and Routing in Cube Satellite Networks