Energy‐Efficient Communication Using Auto‐Associative Polynomial Convolutional Neural Network in WSN

Abstract

Listen

Translate article

ABSTRACTSeveral changes have been implemented over the years to provide better resource management and service delivery for artificial wireless sensor networks (WSNs) that rely on the Internet of Things (IoT). Here, 5G networks offer high data rates with ultra‐low latency and robust reliability, which is essential for managing the substantial data volumes generated by IoT devices in 5G WSNs. IoT needs an optimal communication network to transmit data among different devices. The whole network is categorized as heterogeneous clusters in clustering. The cluster head (CH) selection achieves proficient data communication to the sink node through the chosen CH. In this manuscript, an energy‐efficient communication using auto‐associative polynomial convolutional neural network in 5G WSN (EEC‐HAPCNN) is proposed for improved data transmission through the selected route. Initially, clustering is done by parallel adaptive canopy k‐means clustering (PaC‐k‐M) algorithm. Then, Tasmanian devil optimization algorithm (TDOA) selects the CH required for facilitating the high capacity and low latency features of 5G. The data are given to sink node through the selected CH utilizing hierarchical auto‐associative polynomial convolutional neural network (HAPCNN) for efficient routing in 5G wireless communication network. The proposed EEC‐HAPCNN method is implemented in NS‐3 (network simulator 3). The proposed approach is examined using performance metrics like throughput, energy consumption, network lifetime, and number of nodes alive. The proposed EEC‐HAPCNN method provides 17.45%, 17.63%, and 18.43% lesser energy consumption and 17.64%, 17.64%, 18.54%, and 19.33% greater network life time compared with existing DBN‐MRFO‐5G‐WSN, IDCNN‐t‐DSBO, DACP‐WSN‐ANN, EEO‐IWSN‐ML, and EECA‐ML‐WSN techniques.