Machine Learning Technique for Mobility and Signal Strength-Based Route Selection in MANET

A mobile ad hoc network is a collection of movable nodes that are capable of facilitating a route that requires a source node and transmitting the data using multipoint communication. The node uses energy for operation, but its lifespan is limited, necessitating the implementation of techniques to extend its communication lifetime. Many studies have proposed energy and mobility-based communication to increase the lifetime using various methods, but a better technique is still needed. In this paper, we integrate the AODV with machine learning (ML) technique, which gathers data from all nodes regarding their energy and mobility values. This data is then used to predict a more efficient route from the source to the destination node. The combination of machine learning with AODV routing minimizes the route failure ratio and increases the network life time. In the proposed section, we elucidate how the machine learning utilizes input parameters such as energy, mobility, and signal strength to select the optimal route. The results section looks at how well the proposed machine learning system works with the min-max battery cost routing (MMBCR) and receiving signal strength routing protocol (RSS-RP). We find that the proposed system does a better job in terms of throughput, energy use, residual energy, PDR, delay, and overhead. It concludes that the proposed ML-AODV increases the lifetime of the MANET network.