Deep learning based Self-Sustained Personal Network

Abstract

Most of the research on personal networking and deep learning have been conducted separately. Crossovers between the two fields have just emerged. This article provides a quick introduction to the fundamentals of deep learning, as well as the most recent advancements in the field. Other methodologies and platforms for deploying deep learning on personal network systems are also discussed and compared. Self-Sustained Personal Network (SSPN) is utilized for a wide range of networking functions, including computation, text analytics, and many more. Using deep learning approaches, this study demonstrates how to individualize personal networking activities in order to get the greatest performance in complicated settings with more efficient ones. Other features of deep learning modeling, such as supervised or unsupervised task learning skills with Generative Adversarial Networks (GAN), Convolutional Neural Network (CNN) and deep reinforcement learning, which aims to explain the capabilities of deep learning approaches to operate in an automated and intelligent way are described. Moreover, this research aims to provide the conceptual roadmap between network researchers to real-time networking practitioners who implement deep learning approaches in personal networks. As a result of the implementing deep learning algorithms into real time network installation, new and powerful tools have emerged. This research study develops an efficient learning protocol by predicting future traffic in the personal network using a time series forecast of past traffic. Furthermore, while the algorithm is run, the future personal network numbers are generated randomly. A deep learning method is used in the different algorithms to reduce the normalized mean square error. The correlation function and error histograms are shown in the results and discussion section. By examining the overlap between these modern trend algorithms for self- sustained personal networks, this research study tries to bridge the gap between the deep learning and computer networks.