Blockchain-Empowered Resource Allocation in Multi-UAV-Enabled 5G-RAN: A Multi-Agent Deep Reinforcement Learning Approach

Abegaz Mohammed Seid, Aiman Erbad*, Hayla Nahom Abishu, Abdullatif Albaseer, Mohamed Abdallah, Mohsen Guizani

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

17 Citations (Scopus)

Abstract

In 5G and B5G networks, real-time and secure resource allocation with the common telecom infrastructure is challenging. This problem may be more severe when mobile users are growing and connectivity is interrupted by natural disasters or other emergencies. To address the resource allocation problem, the network slicing technique has been applied to assign virtualized resources to multiple network slices, guaranteeing the 5G-RAN quality of service. Moreover, to tackle connectivity interruptions during emergencies, UAVs have been deployed as airborne base stations, providing various services to ground networks. However, this increases the complexity of resource allocation in the shared infrastructure of 5G-RAN. Therefore, this paper proposes a dynamic resource allocation framework that synergies blockchain and multi-agent deep reinforcement learning for multi-UAV-enabled 5G-RAN to allocate resources to smart mobile user equipment (SMUE) with optimal costs. The blockchain ensures the security of virtual resource transactions between SMUEs, infrastructure providers (InPs), and virtual network operators (VNOs). We formulate a virtualized resource allocation problem as a hierarchical Stackelberg game containing InPs, VNOs, and SMUEs, and then transform it into a stochastic game model. Then, we adopt a Multi-agent Deep Deterministic Policy Gradient (MADDPG) algorithm to solve the formulated problem and obtain the optimal resource allocation policies that maximize the utility function. The simulation results show that the MADDPG method outperforms the state-of-the-art methods in terms of utility optimization and quality of service satisfaction.

Original languageEnglish
Pages (from-to)991-1011
Number of pages21
JournalIEEE Transactions on Cognitive Communications and Networking
Volume9
Issue number4
DOIs
Publication statusPublished - 1 Aug 2023

Keywords

  • 5G-RAN
  • Blockchain
  • Stackelberg game
  • multi-agent DRL
  • network slicing
  • virtualization

Fingerprint

Dive into the research topics of 'Blockchain-Empowered Resource Allocation in Multi-UAV-Enabled 5G-RAN: A Multi-Agent Deep Reinforcement Learning Approach'. Together they form a unique fingerprint.

Cite this