Abstract: Apparatus and methods are provided for AI-based compressed sensing for beam prediction. In one novel aspect, the UE obtains one or more sensing matrices with matrices training and performs weighted beam measurements. In one embodiment, the UE performs beam sweeping to generate one or more measurement matrices, obtains one or more sensing matrices by compressing the one or more measurement matrices with matrices training, and performs weighted beam measurements to generate one or more weighted beam measurement matrices. In one embodiment, the matrices training is performed by the UE or by the wireless network using an AI model. In one embodiment, the UE performs measurement matrix reconstruction based on the one or more weighted beam measurement matrices and the one or more sensing matrices. In one embodiment, the UE predicts an optimal beam based on the one or more predicted weighted beam measurement matrices.

Abstract: A method for realizing rate-splitting multi-access in a mobile cell-free massive MIMO system includes the following steps: splitting, by an access point, the data of each user into two parts with common message and private message, coding all the common message into one super message common message stream, coding each piece of the private message into a private message stream; coding, by the access point, the private message stream using an arbitrary linear pre-coding method, coding the super common message stream using an optimal pre-coding method, and sending the final coded super common message streams to user terminals after superimposing the final coded super common message stream on the private message streams; first decoding, by the user terminals, the super common message stream, removing the super common message stream using successive interference cancellation technology, and then decoding the private message streams.

Abstract: A method for realizing rate-splitting multi-access in a mobile cell-free massive MIMO system includes the following steps: splitting, by an access point, the data of each user into two parts with common message and private message, coding all the common message into one super message common message stream, coding each piece of the private message into a private message stream; coding, by the access point, the private message stream using an arbitrary linear pre-coding method, coding the super common message stream using an optimal pre-coding method, and sending the final coded super common message streams to user terminals after superimposing the final coded super common message stream on the private message streams; first decoding, by the user terminals, the super common message stream, removing the super common message stream using successive interference cancellation technology, and then decoding the private message streams.

Abstract: There is provided mechanisms for mitigating passive intermodulation in a first network node, wherein said PIM is caused by radio signals transmitted from at least an adjacent network node. The method is performed by a control device. The method comprises receiving at least an uplink radio signal and down-converting the received UL radio signal to a UL baseband signal. The method applies a cyclic redundancy check, CRC, to detected information bits of the received UL baseband signal, wherein in response to determining by the CRC that the UL baseband signal is detected correctly, directly output the detected information bits. The method comprises in response to determining by the CRC that the UL baseband signal is incorrectly detected, determining a residual signal of the received UL baseband signal applying a blind signal identification scheme on the residual signal of the UL baseband signal to obtain an estimate for a modeled PIM signal.

Abstract: There is provided mechanisms for mitigating passive intermodulation in a first network node, wherein said PIM is caused by radio signals transmitted from at least an adjacent network node. The method is performed by a control device. The method comprises receiving at least an uplink radio signal and down-converting the received UL radio signal to a UL baseband signal. The method applies a cyclic redundancy check, CRC, to detected information bits of the received UL baseband signal, wherein in response to determining by the CRC that the UL baseband signal is detected correctly, directly output the detected information bits. The method comprises in response to determining by the CRC that the UL baseband signal is incorrectly detected, determining a residual signal of the received UL baseband signal applying a blind signal identification scheme on the residual signal of the UL baseband signal to obtain an estimate for a modeled PIM signal.

Abstract: A Kernel-power-density based method for wireless channel multipath components (MPCs) clustering. Signals get to the receiver from a transmitter via multipath propagation. MIMO channels can be modeled as double-directional, which contains the information of power, delay, direction of departure (DOD) and direction of arrival (DOA) of MPCs. The MPCs tend to appear in clusters. All the parameters of MPCs can be estimated by using high-resolution algorithms, such as MUSIC, CLEAN, SAGE, and RiMAX. Considering a data snapshot for a certain time with several clusters, which include a number of MPCs, where each MPC is represented by its power, delay, DOD and DOA. This invention adopts a novel clustering framework by using a density based method, which can better identify the local density variations of MPCs and requires no prior knowledge about clusters. It can work for the cluster oriented channel processing technology in future wireless communication field.

Abstract: A Kernel-power-density based method for wireless channel multipath components (MPCs) clustering. Signals get to the receiver from a transmitter via multipath propagation. MIMO channels can be modeled as double-directional, which contains the information of power, delay, direction of departure (DOD) and direction of arrival (DOA) of MPCs. The MPCs tend to appear in clusters. All the parameters of MPCs can be estimated by using high-resolution algorithms, such as MUSIC, CLEAN, SAGE, and RiMAX. Considering a data snapshot for a certain time with several clusters, which include a number of MPCs, where each MPC is represented by its power, delay, DOD and DOA. This invention adopts a novel clustering framework by using a density based method, which can better identify the local density variations of MPCs and requires no prior knowledge about clusters. It can work for the cluster oriented channel processing technology in future wireless communication field.

Abstract: A power amplifying device with linear corrector utilizing the polynomial format to realize pre-distortion is disclosed. Its effective order estimation technique for polynomial based pre-distorter includes the following steps. Firstly, it receives the polynomial of the described pre-distorter and then, the polynomial is transformed into the matrix expression, obtaining the pre-distorter consisted of K pre-distortion functions, where K denotes the maximum order of the described polynomials. Secondly, singular value decomposition is performed for the pre-distortion matrix, obtaining singular value matrix. Thirdly, on the basis of the singular value matrix, effective rank of the pre-distortion matrix is obtained. Such effective rank of the pre-distortion matrix is determined as the effective order of the polynomial.