Cyber security and 5G-assisted industrial internet of things using novel artificial adaption based evolutionary algorithm

The Industrial Internet of Things (IIoT) evolved quickly at the start of the twenty-first century. Various services, such as quality of service (QoS) for smart cyber security management from the industrial domain, are complicated for us. It is challenging to select the optimal malicious nodes by taking into account QoS criteria, including information communication, and network coverage regions. Numerous constrained evolutionary optimization strategies are known to address these problems. This study proposes a broader definition of differential evolution (DE) that uses a quick adaptation strategy and an optimization-based design. It combines DE with a unique mutation approach to broaden the range of viable answers. This research also suggests a novel fitness function for energy harvesting in IoT-based applications. Both on the IIoT-service architecture and in IIoT-based applications, the suggested method is assessed. The outcomes are then contrasted using state-of-the-art algorithms. It is discovered that the proposed approach produces better results in terms of cyber security of QoS, fitness cost, and detection of IIoT nodes from the IIoT service network.