Home // AICT 2022, The Eighteenth Advanced International Conference on Telecommunications // View article

A Machine Learning Approach for Resource Allocation in Wireless Industrial Environments

Authors:
Idayat O. Sanusi
Karim M. Nasr

Keywords: 5G and beyond networks; Radio Resource Management; Distributed Algorithms; Device-to-Device Communication; Reinforcement Learning.

Abstract:
In this paper, we present a machine learning technique for channel selection in a Device to Device (D2D)-enabled cellular network targeting a wireless industrial environment. The presented Base Station Assisted (BSA) reinforcement learning technique uses a distributed local Q-table for the agents (users), to prevent global information gathering within the cellular network. A stateless Q-learning approach is adopted to reduce the complexity of learning and the dimension of the Q-table. After the training of the D2D agents, the Q-tables of the D2D users are uploaded to the base station for resource allocation to be implemented centrally. Simulations results show that the presented technique provides a Radio Resource Management (RRM) solution with a good Quality of Service (QoS) performance compared to other conventional approaches.

Pages: 18 to 23

Copyright: Copyright (c) IARIA, 2022

Publication date: June 26, 2022

Published in: conference

ISSN: 2308-4030

ISBN: 978-1-61208-956-0

Location: Porto, Portugal

Dates: from June 26, 2022 to June 30, 2022