A novel fractional rat hawk optimization–enabled routing with deep learning–based energy prediction in wireless sensor networks

Summary Wireless sensor networks (WSNs) contain different sensors, which collect various data in the monitoring area. In general, one of the significant resources in WSNs is energy, which prolongs the network's lifetime. The energy‐efficient routing algorithms reduce energy consumption and enhance the survival cycle of WSNs. Thus, this work developed the optimization‐based WSN routing and deep learning (DL)–enabled energy prediction scheme for efficient routing in WSNs. Initially, the WSN simulation is carried out, and then, the node with minimum energy consumption is chosen as the cluster head (CH). Here, the proposed rat hawk optimization (RHO) algorithm is established for finding the best CH, and the RHO is the integration of rat swarm optimization (RSO) and fire hawk optimization (FHO). Furthermore, the routing is accomplished by the developed fractional rat hawk optimization (FRHO) using the fitness function includes delay, distance, link lifetime, and predicted energy of a network for predicting the finest route. Here, the fractional calculus (FC) is incorporated with the RHO to form the FRHO. The energy prediction is achieved by deep recurrent neural network (DRNN). The energy, delay, and throughput evaluation metrics are considered for revealing the efficiency of the proposed system, and the proposed system achieves the best results of 0.246 J, 0.190 s, and 67.13 Mbps, respectively.