A redundancy system for data transport in a Distributed Antenna System (DAS) includes a plurality of Digital Access Units (DAUs). Each of the plurality of DAUs is fed by a plurality of data streams and is operable to transport digital signals between others of the plurality of DAUs. The redundancy system also includes a plurality of Digital Distribution Units (DDUs). Each of the plurality of DDUs is in communication with each of the plurality of DAUs using cross connection communication paths. The redundancy system further includes a plurality of Digital Remote Units (DRUs). Each of the plurality of DRUs is in communication with each of the plurality of DDUs using cross connection communications paths.

A redundancy system for data transport in a Distributed Antenna System (DAS) includes a plurality of Digital Access Units (DAUs). Each of the plurality of DAUs is fed by a plurality of data streams and is operable to transport digital signals between others of the plurality of DAUs. The redundancy system also includes a plurality of Digital Distribution Units (DDUs). Each of the plurality of DDUs is in communication with each of the plurality of DAUs using cross connection communication paths. The redundancy system further includes a plurality of Digital Remote Units (DRUs). Each of the plurality of DRUs is in communication with each of the plurality of DDUs using cross connection communications paths.

An apparatus for determining unknown radio frequencies is described. The apparatus modulates a first optical signal from tunable optical source with RF signal that includes unknown center frequency value to generate modulated optical signal. The apparatus combines modulated optical signal with second optical signal to generate combined modulated optical signal. The apparatus receives output electrical signal from photodetector in response to receiving combined modulated optical signal at photodetector, splits output electrical signal into first output electrical signal and second output electrical signal, and filter first output electrical signal by applying first optical bandpass filter centered to generate first filtered RF signal. The apparatus tunes tunable optical source to first beat frequency value to determine unknown frequency value of RF signal.

An apparatus for determining unknown radio frequencies is described. The apparatus modulates a first optical signal from tunable optical source with RF signal that includes unknown center frequency value to generate modulated optical signal. The apparatus combines modulated optical signal with second optical signal to generate combined modulated optical signal. The apparatus receives output electrical signal from photodetector in response to receiving combined modulated optical signal at photodetector, splits output electrical signal into first output electrical signal and second output electrical signal, and filter first output electrical signal by applying first optical bandpass filter centered to generate first filtered RF signal. The apparatus tunes tunable optical source to first beat frequency value to determine unknown frequency value of RF signal.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learned identification of radio frequency (RF) signals. One of the methods includes: determining an RF signal configured to be transmitted through an RF band of a communication medium; determining first classification information that is associated with the RF signal, and that includes a representation of a characteristic of the RF signal or a characteristic of an environment in which the RF signal is communicated; using at least one machine-learning network to process the RF signal and generate second classification information as a prediction of the first classification information; calculating a measure of distance between (i) the second classification information that was generated by the at least one machine-learning network, and (ii) the first classification information associated with the RF signal; and updating the at least one machine-learning network based on the measure of distance.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learned identification of radio frequency (RF) signals. One of the methods includes: determining an RF signal configured to be transmitted through an RF band of a communication medium; determining first classification information that is associated with the RF signal, and that includes a representation of a characteristic of the RF signal or a characteristic of an environment in which the RF signal is communicated; using at least one machine-learning network to process the RF signal and generate second classification information as a prediction of the first classification information; calculating a measure of distance between (i) the second classification information that was generated by the at least one machine-learning network, and (ii) the first classification information associated with the RF signal; and updating the at least one machine-learning network based on the measure of distance.

An operating method of a power estimation apparatus comprising a fixed antenna and a mobile antenna may comprise: a first operation of obtaining N measurement values by receiving a signal from signal sources using the fixed antenna and the mobile antenna that moves at a speed v from a first point to an Nth point; a second operation of generating a two-dimensional (2D) data collection set comprising N×M measurement values, by repeating the first operation M times; applying an approximation singular value decomposition (SVD) algorithm to the 2D data collection set; and obtaining information of the signal sources based on an application result of the approximation SVD algorithm, wherein N and M are natural numbers.

An operating method of a power estimation apparatus comprising a fixed antenna and a mobile antenna may comprise: a first operation of obtaining N measurement values by receiving a signal from signal sources using the fixed antenna and the mobile antenna that moves at a speed v from a first point to an Nth point; a second operation of generating a two-dimensional (2D) data collection set comprising N×M measurement values, by repeating the first operation M times; applying an approximation singular value decomposition (SVD) algorithm to the 2D data collection set; and obtaining information of the signal sources based on an application result of the approximation SVD algorithm, wherein N and M are natural numbers.

This application provides a data transmission method and apparatus. The method includes: receiving, by a terminal device, a first reference signal sent by a network device; measuring, by the terminal device, a downlink channel based on the first reference signal, to obtain a channel status of the downlink channel; determining, by the terminal device, a target mode from a plurality of modes based on the channel status of the downlink channel, where information that is used to feed back channel state information (CSI) and that is sent by the terminal device in different modes of the plurality of modes is different; and sending, by the terminal device, indication information to the network device, where the indication information is used to indicate the target mode. The data transmission method and apparatus in the embodiments of this application are conducive to improve flexibility of feeding back CSI.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learned compact representations of radio frequency (RF) signals. One of the methods includes: determining a first RF signal to be compressed; using an encoder machine-learning network to process the first RF signal and generate a compressed signal; calculating a measure of compression in the compressed signal; using a decoder machine-learning network to process the compressed signal and generate a second RF signal that represents a reconstruction of the first RF signal; calculating a measure of distance between the second RF signal and the first RF signal; and updating at least one of the encoder machine-learning network or the decoder machine-learning network based on (i) the measure of distance between the second RF signal and the first RF signal, and (ii) the measure of compression in the compressed signal.