首页> 外国专利> MIMO-OFDM Adaptive transmission scheme determination apparatus based on MIMO-OFDM System using machine learning model and adaptive transmission method the same

MIMO-OFDM Adaptive transmission scheme determination apparatus based on MIMO-OFDM System using machine learning model and adaptive transmission method the same

机译:基于使用机器学习模型的MIMO-OFDM系统的MIMO-OFDM自适应传输方案确定装置及其自适应传输方法

摘要

The present invention relates to an apparatus for determining an adaptive transmission scheme using a machine learning model based on a MIMO-OFDM system, and an adaptive transmission method using the same. According to the present invention, the adaptive transmission method using a machine learning model based on a MIMO-OFDM system comprises the steps of: learning a machine learning model by using a plurality of learning data using feature information extracted from a channel state of a signal received in a receiving terminal having N antennas, as an input, and a label defining optimal transmission scheme information applied to each antenna of a transmitting terminal having N antennas corresponding to the channel state, as an output; estimating a channel state from a received signal of the receiving terminal, received in response to a transmission signal of the transmitting terminal, extracting the feature information from the channel state, and inputting the same to the learned machine learning model; and determining the optimal transmission scheme information applied to each antenna of the transmitting terminal on the basis of the label output from the machine learning model in response to the input feature information, and feeding back the same to the transmitting terminal. According to the present invention, different transmission schemes can be selected as an optimal transmission scheme in accordance with a channel state even in the same SNR, and a transmission rate of a system can be improved.
机译:本发明涉及一种用于基于MIMO-OFDM系统使用机器学习模型来确定自适应传输方案的设备,以及使用该设备的自适应传输方法。根据本发明,使用基于MIMO-OFDM系统的机器学习模型的自适应传输方法包括以下步骤:通过使用从信号的信道状态中提取的特征信息,通过使用多个学习数据来学习机器学习模型。在具有N个天线的接收终端中接收的输入作为输入,并且将定义最佳传输方案信息的标签作为输出,该标签被应用于具有与信道状态相对应的N个天线的发送终端的每个天线。从响应于发送终端的发送信号而接收的接收终端的接收信号中估计信道状态,从信道状态中提取特征信息,并将其输入到学习的机器学习模型中;响应于输入的特征信息,根据从机器学习模型输出的标签,确定应用于发送终端的每个天线的最优发送方案信息,并将其反馈给发送终端。根据本发明,即使在相同的SNR下,也可以根据信道状态选择不同的传输方案作为最佳传输方案,并且可以提高系统的传输速率。

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号