Leveraging Machine-Learning for D2D Communications in 5G/Beyond 5G Networks

Device-to-device (D2D) communication is a promising paradigm for the fifth generation (5G) and beyond 5G (B5G) networks. Although D2D provides several benefits, including limited interference, energy efficiency, reduced delay, network overhead, it faces lot of technical challenges such as architecture, neighbor discovery, etc. The complexity configuring links managing their especially when using millimeter-wave (mmWave), inspire researchers to leverage different machine-learning (ML) techniques address these problems towards boosting performance In this paper, comprehensive survey about recent research activities on networks will be explored with putting more emphasis utilizing mmWave ML methods. After exploring existing directions accompanied conventional solutions, we show how can applied enhance over ways. Then, still open in applications investigated essential needs. A case study applying multi-armed bandit (MAB) an efficient online tool discovery selection (NDS) presented. This put high potency solutions non-ML based methods highly improving average throughput NDS.