RESUMEN
Ultra-reliable and low-latency communication (URLLC) is considered as one of the major use cases in 5G networks to support the emerging mission-critical applications. One of the possible tools to achieve URLLC is the device-to-device (D2D) network. Due to the physical proximity of communicating devices, D2D networks can significantly improve the latency and reliability performance of wireless communication. However, the resource management of D2D networks is usually a non-convex combinatorial problem that is difficult to solve. Traditional methods usually optimize the resource allocation in an iterative way, which leads to high computational complexity. In this paper, we investigate the resource allocation problem in the time-sensitive D2D network where the latency and reliability performance is modeled by the achievable rate in the short blocklength regime. We first design a game theory-based algorithm as the baseline. Then, we propose a deep learning (DL)-based resource management framework using deep neural network (DNN). The simulation results show that the proposed DL-based method achieves almost the same performance as the baseline algorithm, while it is more time-efficient due to the end-to-end structure.
RESUMEN
Device-to-device communications in underlay mode has emerged as a promising way to enhance spectrum efficiency in cellular networks. Recently, relay selection in D2D communications underlaying cellular networks is gaining more research interest. In this paper, we propose two relay selection schemes for D2D communications underlaying cellular networks, Midpoint Relay Selection using Social Trust and Battery Level (MRS-ST-BL) and Midpoint Relay Selection using Social Distance and Battery Level (MRS-SD-BL). These proposed schemes utilize battery power level information of devices together with social trust information of users in the network for relay selection. For performance evaluation, initially we show that the throughput of state-of-the-art schemes Hybrid Relay Selection (HRS) and our previously proposed schemes Midpoint Relay Selection using Social Trust (MRS-ST) and Midpoint Relay Selection Using Social Distance (MRS-SD) decrease, when relays have varying battery power. Then, we compare the performance of our proposed schemes against existing schemes including HRS, MRS-ST and MRS-SD. The performance comparison is done at various social trust scenarios and device densities. We show that our proposed schemes can significantly improve the throughput of D2D communications, particularly when relays have different battery power levels in weak social trust scenarios. Finally, we show that the performance of our proposed scheme MRS-ST-BL varies with the change in battery power threshold.