首页|Researchers from Yazd University Detail New Studies and Findings in the Area of Networks (Recurrent Neural Network and Federated Learning Based Channel Estimation Approach In Mmwave Massive Mimo Systems)
Researchers from Yazd University Detail New Studies and Findings in the Area of Networks (Recurrent Neural Network and Federated Learning Based Channel Estimation Approach In Mmwave Massive Mimo Systems)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Network Daily News - A new studyon Networks is now available. According to news reporting out of Yazd, Iran, by NewsRx editors, researchstated, “So far, various data-driven approaches have been presented to obtain channel state information(CSI) in millimeter wave multiple-input-multiple-output wireless networks. In almost all previous works,training and testing channels were assumed to have the same distribution, which may not be the case inpractice.”Our news journalists obtained a quote from the research from Yazd University, “In this article, weaddress this challenge by proposing a learning framework that is a combination of a recurrent neural network(RNN) model and a deep neural network (DNN) for estimating CSI in a dynamic wireless communicationenvironment. Furthermore, we use federated learning to train the learning-based channel estimation model.More specifically, we introduce a two-stage downlink pilot transmission procedure, where in the initial stage,long frame length downlink pilot signals are used to train the introduced RNN-DNN model. Followingthat, users will receive shorter-frame-length pilot signals that can be used for CSI estimation. To speed upthe training procedure of the proposed network, we first generate a pre-trained model and then modify itaccording to the collected data samples. Simulation results demonstrate that, when the channel distributionis unavailable, the proposed approach performs significantly better than the most recent channel estimationalgorithms in terms of estimation performance and computational complexity.”
NETL
NSTL
