Abstract: Mobile Ad Hoc Networks (MANETs) are self-organizing, self-configuring, and infrastructure-less networks for performing multi-hop communication. The source mobile node can transmit the information to any other destination node, but it has limitations with energy consumption and battery lifetime. Since it appeals to a huge environment, there is a probability of obstacle present. Thus, the network requires finding the obstacles to evade performance degradation and also enhance the routing efficiency. To achieve this, an obstacle-aware efficient routing using a heuristic-based deep learning model is proposed in this paper. Firstly, the nodes in the MANET are employed for initiating the transmission. Further, it is needed to be predicted whether the node is malicious or not. Consequently, the prediction for link connection between the nodes is achieved by the Optimized Bi-directional Long-Short Term Memory (OBi-LSTM), where the hyperparameters are tuned by the Adaptive Horse Herd Optimization (AHHO) algorithm. Secondly, once the links are secured from the obstacle, it is undergone for routing purpose. Routing is generally used to transmit data or packets from one place to another. To attain better routing, various objective constraints like delay, distance, path availability, transmission power, and several interferences are used for deriving a multi-objective function, in which the optimal path is obtained through the AHHO algorithm. Finally, the simulation results of the proposed model ensure to yield efficient multipath routing by accurately identifying the intruder present in the network. Thus, the proposed model aims to reduce the objectives like delay, distance, and power consumption.
Keywords: Mobile ad hoc networks, obstacle-aware routing, link connectivity prediction, adaptive horse herd optimization algorithm, optimized bi-directional long-short term memory, optimal routing, multi-objective constraints
