Intelligence Model based Routing with Channel Assignment in Multichannel Mobile Ad-Hoc Networks

Multiple wireless channels in MANET promise to enhance QoS, and their well-coordinated use can lead to major operational enhancements. For coordination & synchronization across numerous channels, existing approaches for developing multi-channels in mobile ad hoc networks (MANETs) employ a control channel-based technique. Offering QoS via resource reservation, routing, mobility management, & access/admission control has become the most important problems recently in MANETs. Nevertheless, due to obvious interference caused by mobility, several existing solutions fail to offer good QoS. This paper intends to introduce a novel routing and channel assignment in multichannel MANET. Here, the optimal routing is performed via selecting the cluster head under the certain constraints like Delay, distance, QoS, RSSI, and security. For this, (Chaotic Functions influenced spider monkey optimization) CFISMO algorithm is used. The assignment of channels as the scheduling policy is introduced through senders while it has packets to transmit. In this work, the channel assignment will be initiated via machine learning model that predicts the availability of the channels, which is based on the paths (channels) generated under the selected cluster head. Here, Optimized Neural Network (NN) will be used. Thus, the final output shows the paths (channel) to be assigned for data transmission. At the end, the performance of the adopted routing approach is evaluated over other traditional schemes based on various metrics like distance, PDR, delay, energy, alive nodes, QoS, security, and trust, respectively.