An Intelligent Channel Assignment Approach for Minimum Interference in Wireless Mesh Networks Using Learning Automata and Genetic Algorithms

Multi-radio multi-channel WMNs are innovative technical kind of WMNs, i.e., the nodes with multi radios and numerous channels for communication. In wireless mesh routers of WMNs, multiple network interfaces caused due to multiple channels typically increases the network throughput, i.e., in multi-channel WMN, whenever two neighboring nodes transfer information using the similar channel, they might interfere with one another and eventually decreases the throughput. Thus, there is a need for an effective approach to reduce network interference and significantly enhance throughput. This paper primarily concentrates on issues of multicasts channel assignment in WMNs to diminish the interference in the network. The adaptive decision-making strategy of learning automata and strong searching capability of the genetic algorithm is employed in this approach. The methodology combined multicast tree construction and channel assignment, to evade that channel assignment could not function well with the specific multicast tree. In this paper, the initial multicast tree construction by learning automata and the optimal channel assignment is performed by genetic algorithm. The experiment outcomes for the suggested methodology is carried out using NS2 and performance efficiency is matched with LAMR, LCA, and GA based multicast channel assignment approach and suggested higher performance using packet delivery ratio, an end to end delay, throughput and total cost.