Generative Adversarial Networks with Quantum Optimization Model for Mobile Edge Computing in IoT Big Data

In present times, a massive quantity of big data has been generated by the Internet of Things (IoT) devices for a wide range of applications. The IoT devices generate an enormous data quantity that is troublesome for data processing and analytics functionalities, which is effortlessly managed by the cloud before the explosive development of the IoT. Specifically, the big IoT data analytics by mobile edge computing (MEC) becomes a hot research topic and needs comprehensive research works for intelligent decision making. This paper introduces a new generative adversarial network (GAN) with a quantum elephant herd optimization (QEHO) algorithm for MEC in IoT enabled big data environment called GAN-QEHO. The presented GAN-QEHO algorithm follows two-stage processes, namely feature selection (FS) and data classification. The QEHO algorithm is used to elect an optimal feature subset for the FS process. By the quantization of elephant individuals, the search scope of feature space can be enhanced, and an optimal tradeoff has been attained among exploration and exploitation. Then, the GAN model is employed for the classification process to identify different class labels. In order to validate the experimental results analysis of the GAN-QEHO algorithm, a series of simulations take place in terms of diverse aspects.