期刊名称：International Journal of Wireless & Mobile Networks
印刷版ISSN：0975-4679
电子版ISSN：0975-3834
出版年度：2018
卷号：10
期号：4
出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：Providing seamless mobility and a uniform user experience, independent of location, is an importantchallenge for 5G wireless networks. The combination of Coordinated Multipoint (CoMP) networks andVirtual- Cells (VCs) are expected to play an important role in achieving high throughput independent of themobile’s location by mitigating inter-cell interference and enhancing the cell-edge user throughput. UserspecificVCs will distinguish the physical cell from a broader area where the user can roam without theneed for handoff, and may communicate with any Base Station (BS) in the VC area. However, this requiresrapid decision making for the formation of VCs. In this paper, a novel algorithm based on a form ofRecurrent Neural Networks (RNNs) called Gated Recurrent Units (GRUs) is used for predicting thetriggering condition for forming VCs via enabling Coordinated Multipoint (CoMP) transmission.Simulation results, show that based on the sequences of Received Signal Strength (RSS) values of differentmobile nodes used for training the RNN, the future RSS values from the closest three BSs can be accuratelypredicted using GRU, which is then used for making proactive decisions on enabling CoMP transmissionand forming VCs.
