Adapting to Dynamic LEO-B5G Systems : Meta-Critic Learning Based Efficient Resource Scheduling
Yuan, Y., Lei, L., Vu, T. X., Chang, Z., Chatzinotas, S., & Sun, S. (2022). Adapting to Dynamic LEO-B5G Systems : Meta-Critic Learning Based Efficient Resource Scheduling. IEEE Transactions on Wireless Communications, 21(11), 9582-9595. https://doi.org/10.1109/TWC.2022.3178171
Published inIEEE Transactions on Wireless Communications
Lei, Lei |
DisciplineSecure Communications Engineering and Signal ProcessingTietotekniikkaOhjelmisto- ja tietoliikennetekniikkaSecure Communications Engineering and Signal ProcessingMathematical Information TechnologySoftware and Communications Engineering
© Authors, 2022
Low earth orbit (LEO) satellite-assisted communications have been considered as one of the key elements in beyond 5G systems to provide wide coverage and cost-efficient data services. Such dynamic space-terrestrial topologies impose an exponential increase in the degrees of freedom in network management. In this paper, we address two practical issues for an over-loaded LEO-terrestrial system. The first challenge is how to efficiently schedule resources to serve a massive number of connected users, such that more data and users can be delivered/served. The second challenge is how to make the algorithmic solution more resilient in adapting to dynamic wireless environments. We first propose an iterative suboptimal algorithm to provide an offline benchmark. To adapt to unforeseen variations, we propose an enhanced meta-critic learning algorithm (EMCL), where a hybrid neural network for parameterization and the Wolpertinger policy for action mapping are designed in EMCL. The results demonstrate EMCL’s effectiveness and fast-response capabilities in over-loaded systems and in adapting to dynamic environments compare to previous actor-critic and meta-learning methods. ...
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
ISSN Search the Publication Forum1536-1276
Publication in research information system
MetadataShow full item record
Additional information about fundingThe work has been supported by the ERC project AGNOSTIC (742648), by the FNR CORE projects ROSETTA (C17/IS/11632107), FlexSAT (C19/IS/13696663), SmartSpace (C21/IS/16193290), and by the FNR bilateral project LARGOS (12173206).
Showing items with similar title or keywords.
Advanced voice and data solutions for evolution of cellular network system Chen, Tao (University of Jyväskylä, 2014)
Multi-Connectivity for User Throughput Enhancement in 5G Non-Terrestrial Networks Majamaa, Mikko; Martikainen, Henrik; Sormunen, Lauri; Puttonen, Jani (IEEE, 2022)To meet the increasing throughput and reliability demands, satellites may be used to complement the Fifth Gener-ation (5G) Terrestrial Networks (TNs). To increase the efficiency of the satellite communications involved, ...
Dual Connectivity in Non-Stand Alone Deployment mode of 5G in Manhattan Environment Sheik, Muhammad Usman; Asghar, Muhammad Zeeshan; Jäntti, Riku (IEEE, 2020)The main target of this paper is to analyze the performance of an outdoor user in a dense micro cellular Manhattan grid environment using a ray launching simulation tool. The radio propagation simulations are performed ...
Energy efficiency in wireless networks Alviola, Teemu (2013)Tämä pro gradu -työ on sekundääritutkimuksena tehty kirjallisuuskatsaus energiatehokkuuden tarkastelusta langattomissa verkoissa. Työssä tarkastellaan erilaisia mobiiliverkkojen energiansäästömahdollisuuksia. ...
Multipoint transmission scheme for HSDPA Puchko, Oleksandr (University of Jyväskylä, 2013)