Detail publikačního výsledku

Optimizing Flying Base Station Connectivity by RAN Slicing and Reinforcement Learning

MELGAREJO, D.; POKORNÝ, J.; ŠEDA, P.; NARAYANAN, A.; NARDELLI, P.; RASTI, M.; HOŠEK, J.; ŠEDA, M.; RODRÍGUEZ, D.; KOUCHERYAVY, Y.; FRAIDENRAICH, G.

Originální název

Optimizing Flying Base Station Connectivity by RAN Slicing and Reinforcement Learning

Anglický název

Optimizing Flying Base Station Connectivity by RAN Slicing and Reinforcement Learning

Druh

Článek WoS

Originální abstrakt

The application of flying base stations (FBS) in wireless communication is becoming a key enabler to improve cellular wireless connectivity. Following this tendency, this research work aims to enhance the spectral efficiency of FBSs using the radio access network (RAN) slicing framework; this optimization considers that FBSs’ location was already defined previously. This framework splits the physical radio resources into three RAN slices. These RAN slices schedule resources by optimizing individual slice spectral efficiency by using a deep reinforcement learning approach. The simulation indicates that the proposed framework generally outperforms the spectral efficiency of the network that only considers the heuristic predefined FBS location, although the gains are not always significant in some specific cases. Finally, spectral efficiency is analyzed for each RAN slice resource and evaluated in terms of service-level agreement (SLA) to indicate the performance of the framework.

Anglický abstrakt

The application of flying base stations (FBS) in wireless communication is becoming a key enabler to improve cellular wireless connectivity. Following this tendency, this research work aims to enhance the spectral efficiency of FBSs using the radio access network (RAN) slicing framework; this optimization considers that FBSs’ location was already defined previously. This framework splits the physical radio resources into three RAN slices. These RAN slices schedule resources by optimizing individual slice spectral efficiency by using a deep reinforcement learning approach. The simulation indicates that the proposed framework generally outperforms the spectral efficiency of the network that only considers the heuristic predefined FBS location, although the gains are not always significant in some specific cases. Finally, spectral efficiency is analyzed for each RAN slice resource and evaluated in terms of service-level agreement (SLA) to indicate the performance of the framework.

Klíčová slova

Flying Base Stations, UAVs, Location Optimization, Wireless Communication, Deep-reinforcement Learning

Klíčová slova v angličtině

Flying Base Stations, UAVs, Location Optimization, Wireless Communication, Deep-reinforcement Learning

Autoři

MELGAREJO, D.; POKORNÝ, J.; ŠEDA, P.; NARAYANAN, A.; NARDELLI, P.; RASTI, M.; HOŠEK, J.; ŠEDA, M.; RODRÍGUEZ, D.; KOUCHERYAVY, Y.; FRAIDENRAICH, G.

Rok RIV

2022

Vydáno

17.05.2022

Nakladatel

IEEE

ISSN

2169-3536

Periodikum

IEEE Access

Svazek

10

Číslo

1

Stát

Spojené státy americké

Strany od

53746

Strany do

53760

Strany počet

15

URL

https://ieeexplore.ieee.org/document/9775679

Plný text v Digitální knihovně

http://hdl.handle.net/11012/208143

BibTex

@article{BUT177853,
  author="Dick Carrillo {Melgarejo} and Jiří {Pokorný} and Pavel {Šeda} and Arun {Narayanan} and Pedro Henrique Juliano {Nardelli} and Mehdi {Rasti} and Jiří {Hošek} and Miloš {Šeda} and Demóstenes Zegarra {Rodríguez} and Yevgeni {Koucheryavy} and Gustavo {Fraidenraich}",
  title="Optimizing Flying Base Station Connectivity by RAN Slicing and Reinforcement Learning",
  journal="IEEE Access",
  year="2022",
  volume="10",
  number="1",
  pages="53746--53760",
  doi="10.1109/ACCESS.2022.3175487",
  issn="2169-3536",
  url="https://ieeexplore.ieee.org/document/9775679"
}

Dokumenty

Optimizing_Flying_Base_Station_Connectivity_by_RAN_Slicing_and_Reinforcement_Learning