@Article{cmc.2023.035735,
AUTHOR = {Kaleem Arshid, Jianbiao Zhang, Muhammad Yaqub, Mohammad Daud Awan, Habiba Ijaz, Imran Shabir Chuhan},
TITLE = {A New Strategy for Dynamic Channel Allocation in CR-WMN Based on RCA},
JOURNAL = {Computers, Materials \& Continua},
VOLUME = {76},
YEAR = {2023},
NUMBER = {3},
PAGES = {2631--2647},
URL = {http://www.techscience.com/cmc/v76n3/54320},
ISSN = {1546-2226},
ABSTRACT = {Channel assignment has emerged as an essential study subject in Cognitive Radio-based Wireless Mesh Networks
(CR-WMN). In an era of alarming increase in Multi-Radio Multi-Channel (MRMC) network expansion interference is decreased and network throughput is significantly increased when non-overlapping or partially overlapping
channels are correctly integrated. Because of its ad hoc behavior, dynamic channel assignment outperforms
static channel assignment. Interference reduces network throughput in the CR-WMN. As a result, there is an
extensive research gap for an algorithm that dynamically distributes channels while accounting for all types of
interference. This work presents a method for dynamic channel allocations using unsupervised Machine Learning
(ML) that considers both coordinated and uncoordinated interference. Unsupervised machine learning uses
coordinated and non-coordinated interference for dynamic channel allocation. To determine the applicability of the
proposed strategy in reducing channel interference while increasing WMN throughput, a comparison analysis was
performed. When the simulation results of our proposed algorithm are compared to those of the Routing Channel
Assignment (RCA) algorithm, the throughput of our proposed algorithm has increased by 34% compared to both
coordinated and non-coordinated interferences.},
DOI = {10.32604/cmc.2023.035735}
}