RETRACTED: Multi‐objective metaheuristic optimization‐based clustering with network slicing technique for <scp>Internet of Things</scp>‐enabled wireless sensor networks in <scp>5G</scp> systems
B. Gracelin Sheena, N. Snehalatha
Abstract
Abstract Presently, 5G communication networks have become successful in achieving maximum data rage, and different Internet of Things (IoT) and wireless sensor networks (WSN) have been employed for data collection in 5G networks. Since IoT‐enabled WSN are considered as the major supporting technology for 5G networks, energy efficiency and network slicing remain challenging issues. This study designs a novel multi‐objective improved seagull optimization‐based clustering with network slicing (MOISGO‐CNS) technique for IoT‐enabled WSN in 5G Systems. The goal of the MOISGO‐CNS technique is to construct clusters to accomplish energy efficiency and perform network slicing to balance load in 5G systems. The MOISGO‐CNS technique encompasses two major stages namely ISGO‐based clustering and IGSO with bidirectional long short‐term memory (BiLSTM) based network slicing. The IGSO‐based clustering technique derives a fitness function involving three parameters namely two‐hop connectivity ratio (2‐HCR), remaining energy, and link quality. Besides, the network slicing process includes the design of ISGO algorithm to optimally select the hyperparameters and attain maximum slicing classification performance. A wide range of experiments was carried out and the obtained results demonstrate the supremacy of the MOISGO‐CNS technique over the recent approaches. From experimental results the proposed model attained 95.261% of accuracy, 7.89 ms of End‐to‐End Delay, 14.80% of Packet Loss Ratio, and 85.20% of Packet Delivery Ratio.