An Analysis on the Implementation of Deep Learning in Wireless Networks

The emerging modern wireless communication networks and systems such as mobile networks and Internet of Things (IoT) results in generating big data and enabling heterogeneous data transfer, which results in high amount of data traffic. Wireless Networks are broadly classified into local and wide area networks. Currently, managing the wide area networks to perform large-scale monitoring and data analytics faces several challenges in terms of real-time data processing and network analysis. Moreover, due to the emerging challenges in network interpretability and monitoring, the networking pattern of wireless networks, especially mobile networks have become more complex. Motivated by the recent success of applying Deep Learning in may real-time applications, this study explores the application of Deep Learning (DL) in different network layers and deep learning generated interpretations that assist the network operators to design and deploy the DL based networking systems. Further, this study discusses about the simulation tools that are currently used to simulate the Deep Learning (DL) based Wireless Networks. From the findings, we have finally listed out some of the unsolved challenges faced while integrating deep learning model in wireless networks.