In the last few years, some research papers have proposed usage of UAVs organized in Flying Ad-Hoc Network (FANET) in remote areas with a poor or completely non-existent structured network to support novel application scenarios in which data generated by the end users must be processed on site with ultra-low latency. This way, a FANET can be seen as a provider of services and/or slices for extreme-edge 5G networks for delay-sensitive applications. However, keeping a FANET available and active is an ongoing challenge as the autonomy of UAVs is limited and strongly influenced by power consumption of both the engines and the computing element (CE) where the application functions are executed as virtual machines. In this paper, we present an optimization framework capable of increasing the overall duration of the FANET. To this purpose, we apply Reinforcement Learning (RL) based on Double Deep Q-learning (DDQN) to optimize the percentage of available CPU resources for Virtual Function virtualization, and Integer Linear Programming (ILP) to optimize VF placement inside the active UAVs of the FANET.

Galluccio, L., Grasso, C., Maier, G., Raftopoulos, R., Savi, M., Schembra, G., et al. (2022). Reinforcement Learning for Resource Planning in Drone-Based Softwarized Networks. In 2022 20th Mediterranean Communication and Computer Networking Conference, MedComNet 2022 (pp.200-207). IEEE [10.1109/MedComNet55087.2022.9810398].

Reinforcement Learning for Resource Planning in Drone-Based Softwarized Networks

Savi M.;
2022

Abstract

In the last few years, some research papers have proposed usage of UAVs organized in Flying Ad-Hoc Network (FANET) in remote areas with a poor or completely non-existent structured network to support novel application scenarios in which data generated by the end users must be processed on site with ultra-low latency. This way, a FANET can be seen as a provider of services and/or slices for extreme-edge 5G networks for delay-sensitive applications. However, keeping a FANET available and active is an ongoing challenge as the autonomy of UAVs is limited and strongly influenced by power consumption of both the engines and the computing element (CE) where the application functions are executed as virtual machines. In this paper, we present an optimization framework capable of increasing the overall duration of the FANET. To this purpose, we apply Reinforcement Learning (RL) based on Double Deep Q-learning (DDQN) to optimize the percentage of available CPU resources for Virtual Function virtualization, and Integer Linear Programming (ILP) to optimize VF placement inside the active UAVs of the FANET.
No
paper
Scientifica
FANET; NFV; Reinforcement Learning.; Resource Allocation; Virtual Function Placement
English
20th Mediterranean Communication and Computer Networking Conference, MedComNet 2022 - 1 June 2022 through 3 June 2022
978-1-6654-8729-0
https://ieeexplore.ieee.org/document/9810398
Galluccio, L., Grasso, C., Maier, G., Raftopoulos, R., Savi, M., Schembra, G., et al. (2022). Reinforcement Learning for Resource Planning in Drone-Based Softwarized Networks. In 2022 20th Mediterranean Communication and Computer Networking Conference, MedComNet 2022 (pp.200-207). IEEE [10.1109/MedComNet55087.2022.9810398].
Galluccio, L; Grasso, C; Maier, G; Raftopoulos, R; Savi, M; Schembra, G; Troia, S
File in questo prodotto:
File Dimensione Formato  
2022_MedComNet_FANET_Resource_Planning_RL.pdf

Solo gestori archivio

Descrizione: Proceedings - 20th Mediterranean Communication and Computer Networking Conference, MedComNet 2022 - 1 June 2022 through 3 June 2022
Tipologia di allegato: Publisher’s Version (Version of Record, VoR)
Dimensione 633.57 kB
Formato Adobe PDF
633.57 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/10281/389968
Citazioni
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
Social impact