Channel assignment has emerged as an essential study subject in Cognitive Radio-basedWireless Mesh Networks(CR-WMN).In an era of alarming increase in Multi-Radio Multi-Channel(MRMC)network expansion interference is de...Channel assignment has emerged as an essential study subject in Cognitive Radio-basedWireless 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 unsupervisedMachine 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 increasingWMNthroughput,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.展开更多
基金funded by the National Natural Science Foundation of China(61971014),Zhang Jianbiao.
文摘Channel assignment has emerged as an essential study subject in Cognitive Radio-basedWireless 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 unsupervisedMachine 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 increasingWMNthroughput,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.
