Methods, apparatus and systems for efficient information processing and compression using adaptive basis matrices and sparse representation
Sparsity-based models with subspace projection and dimension reduction techniques address interoperability and adaptation challenges in wireless communication systems, achieving efficient CSI compression and reduced computational demands.
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- HUAWEI TECH CO LTD
- Filing Date
- 2025-03-06
- Publication Date
- 2026-07-30
AI Technical Summary
The deployment of two-side AI/ML models in wireless communication systems faces challenges such as multi-vendor model interoperability and adaptation to dynamic environments, primarily due to the black-box nature of these models, which hinders effective data compression and computational efficiency.
The use of sparsity-based models incorporating subspace projection and dimension reduction techniques for channel state information (CSI) compression, utilizing basis functions and reduced-dimension codebook dictionaries to efficiently manage high-dimensional data while minimizing computational demands.
This approach allows for effective data compression that retains essential features, reduces computational complexity, and enhances model transmission efficiency in wireless communication systems.
Smart Images

Figure CN2025080983_30072026_PF_FP_ABST
Abstract
Description
METHODS, APPARATUS AND SYSTEMS FOR EFFICIENT INFORMATION PROCESSING AND COMPRESSION USING ADAPTIVE BASIS MATRICES AND SPARSE REPRESENTATIONCROSS-REFERENCE TO RELATED APPLICATION
[0001] The present application is related to, and claims priority to, United States provisional patent application Serial No. 63 / 748, 292 filed on January 22, 2025, the entire contents of which are hereby incorporated by reference.TECHNICAL FIELD
[0002] The present disclosure relates generally to wireless communications, and in particular to methods, apparatus and systems for efficient processing and compression of information, such as channel state information.BACKGROUND
[0003] With the maturity of fifth-generation (5G) wireless communication technologies and the development of sixth-generation (6G) , wireless communication systems are advancing toward higher speeds, larger capacities, lower latency, and greater intelligence. Artificial intelligence (AI) and machine learning (ML) have become essential technologies to achieve these goals. They are widely applied in various aspects, including channel state information (CSI) feedback, beamforming, resource allocation, and mobility management, improving overall network performance, spectral efficiency, and user experience.
[0004] In deploying AI / ML models, a two-side model is a common approach in wireless communications. The "two-side model" refers to AI / ML models deployed separately at both the transmission end (e.g., user equipment) and the receiving end (e.g., base stations) of a wireless communication system. For example, in CSI feedback and compression, the AI / ML model (encoder) at the transmission end is responsible for compressing high-dimensional CSI data into low-dimensional code words, while the AI / ML model (decoder) at the receiving end decompresses these low-dimensional code words back into high-dimensional CSI data.
[0005] Vendors frequently recommend two-side AI / ML models in the form of black boxes. This means that the internal structure, algorithms, and parameters of these AI / ML models are invisible to other vendors or devices. This black-box approach arises due to several reasons: · Intellectual Property Protection: The development of AI / ML models requires substantial research and development (R&D) investments. Vendors often consider these models as core intellectual property and typically prefer not to disclose their internal workings to prevent technology leakage and competitor imitation. · Trade Secrets: The performance of AI / ML models often depends on the quality and quantity of training datasets, which are typically proprietary to the vendor. Such datasets are often regarded as trade secrets and are not publicly disclosed. · Security and Reliability: Revealing the internal details of AI models may increase the risk of adversarial attacks or tampering. For instance, malicious actors could exploit model vulnerabilities to conduct adversarial attacks or modify model parameters for nefarious purposes.
[0006] Despite its advantages, the application of the two-side model in wireless communication systems faces several significant challenges, the most pressing of which may be multi-vendor AI / ML model interoperability and adaptation of AI / ML models to dynamic environments.SUMMARY
[0007] Aspects of the present disclosure relate to a novel approach for deploying sparsity-based models specifically designed for wireless communications. The present disclosure describes example implementations with a focus on channel state information (CSI) compression as a representative communication task, demonstrating how these models can efficiently manage high-dimensional data. Aspects of the present disclosure leverage the linear property of sparse approximation while incorporating dimension reduction techniques to address computational complexity and potentially minimize model transmission costs.
[0008] To that end, aspect of the present disclosure utilize subspace projection and sparse approximation techniques that allow for effective data compression while retaining the essential features of the channel data. By reducing the data dimensionality, the disclosed methods may allow the sparse representation to remain efficient for downstream processing, with significantly reduced computational demands for tasks such as channel feedback and beamforming.
[0009] According to a first aspect, there is provided a method that includes transmitting encoder information for sparsity-based compression of information at a user device. The encoder information may include: a basis function operable as a dimension reduction function to reduce a dimension of the information at the user device; and a reduced-dimension codebook dictionary function that has reduced dimensions relative to a higher-dimension codebook dictionary function.
[0010] In some implementations of the first aspect, the method further includes receiving a connection request, wherein transmitting the encoder information includes transmitting the encoder information responsive to receiving the connection request.
[0011] In some implementations of the first aspect, the connection request is indicative of at least one of: whether the sparsity-based compression can be performed; whether the basis function is requested; or whether the reduced-dimension codebook dictionary function is requested.
[0012] In some implementations of the first aspect, the connection request is received via radio resource control (RRC) signaling.
[0013] In some implementations of the first aspect, the method further includes: receiving compressed information, the compressed information including a sparse representation of the information; and decompressing the sparse representation of the information to recover uncompressed information using the higher-dimension codebook dictionary function.
[0014] In some implementations of the first aspect, the information to be compressed includes channel state information (CSI) .
[0015] In some implementations of the first aspect, the method further includes: transmitting a CSI reference signal (CSI-RS) . In such implementations, receiving the compressed information may include receiving compressed CSI that includes a sparse representation of the CSI. In such implementations, decompressing the sparse representation of the information to recover uncompressed information using the higher-dimension codebook dictionary function may include decompressing the sparse representation of the CSI to recover a reconstruction of the CSI using the higher-dimension codebook dictionary function.
[0016] In some implementations of the first aspect, the method further includes: receiving an uplink resources request; and transmitting uplink resources allocation information indicating uplink resources allocated for uplink transmission. In such implementations, receiving the compressed CSI may include receiving the compressed CSI over the allocated uplink resources.
[0017] In some implementations of the first aspect, the method further includes: transmitting a CSI-RS; and receiving a signal indicative of a compression failure indicating a compression failure of the CSI.
[0018] In some implementations of the first aspect, the method further includes, after receiving the signal indicative of the compression failure, at least one of: transmitting a new CSI-RS across different resource elements; increasing the resource allocation for CSI estimation; or initiating a codebook dictionary update process for the higher-dimension codebook dictionary function.
[0019] In some implementations of the first aspect, the basis function and the reduced-dimension codebook dictionary function are derived from the higher-dimension codebook dictionary function.
[0020] In some implementations of the first aspect: the basis function includes a basis matrix; the higher-dimension codebook dictionary function includes a higher-dimension codebook dictionary matrix; and the reduced-dimension codebook dictionary function includes a reduced-dimension codebook dictionary matrix that has reduced dimensions relative to the higher-dimension codebook dictionary matrix.
[0021] In some implementations of the first aspect, the method further includes transmitting dimension information indicative of:dimensions of the basis matrix; and dimensions of the reduced-dimension codebook dictionary matrix.
[0022] In some implementations of the first aspect, transmitting the dimension information includes broadcasting the dimension information in one or more system information blocks (SIBs) .
[0023] In some implementations of the first aspect, the higher-dimension codebook dictionary matrix defines a reduced-dimension subspace projection of an information space of the information to be compressed.
[0024] In some implementations of the first aspect, the method further includes determining the basis matrix and the reduced-dimension codebook dictionary matrix through matrix decomposition of the higher-dimension codebook dictionary matrix.
[0025] In some implementations of the first aspect, the matrix decomposition is such that rows of the basis matrix form an orthonormal basis for a column space of the higher-dimension codebook dictionary matrix.
[0026] In some implementations of the first aspect, the matrix decomposition includes singular value decomposition (SVD) or QR decomposition.
[0027] In some implementations of the first aspect, the information to be compressed includes CSI. In such implementations, the higher-dimension codebook dictionary matrix may define a reduced-dimension subspace projection of the channel space.
[0028] In some implementations of the first aspect, the matrix decomposition includes SVD according to: Ψ=USV*, and Ψ′=SV*, where: Ψ is the higher-dimension code book dictionary matrix; U is the basis matrix, wherein U is a unitary matrix, where n is the channel dimension, and r is the rank of Ψ; S is a diagonal matrix; V is a unitary matrix, wherein V* is the Hermitian transpose of V; and Ψ′is the reduced-dimension codebook dictionary matrix.
[0029] In some implementations of the first aspect, the matrix decomposition includes QR decomposition according to: Ψ=QR, and Ψ′=R, where: Ψ is the higher-dimension code book dictionary matrix; Q is the basis matrix, wherein Q is an orthogonal matrix; R is an upper triangular matrix; and Ψ′is the reduced-dimension codebook dictionary matrix.
[0030] In some implementations of the first aspect, the method further includes: transmitting a CSI-RS; receiving, by the network device from the user device, compressed CSI, the compressed CSI including a sparse vector representation of the CSI; and decompressing the sparse representation of the CSI to recover a reconstruction of the CSI according to: where: is the CSI reconstruction; Ψ is the higher-dimension code book dictionary matrix; and s* is the sparse vector representation of the CSI.
[0031] In some implementations of the first aspect, transmitting the CSI-RS includes: dynamically selecting a subset of resource elements from a set of resource elements; and transmitting the CSI-RS using the selected subset of resource elements.
[0032] In some implementations of the first aspect, columns of the basis matrix corresponding to resource elements not used for transmitting the CSI-RS are zeroed.
[0033] In some implementations of the first aspect, the set of resource elements includes a set of transmit antennas and a set of frequency bands. In such implementations, dynamically selecting a partial subset of resource elements may include: dynamically selecting a partial subset of transmit antennas from the set of transmit antennas; and dynamically selecting a partial subset of frequency bands from the set of frequency bands. In such implementations, transmitting the CSI-RS using the selected subset of resource elements may include transmitting the CSI-RS by the selected subset of transmit antennas in the selected subset of frequency bands.
[0034] In some implementations of the first aspect, the method further includes transmitting signaling indicative of the selected subset of resource elements.
[0035] In some implementations of the first aspect, the signaling indicative of the selected subset of resource elements includes download control information (DCI) or higher layer signaling.
[0036] In some implementations of the first aspect, transmitting the CSI-RS includes transmitting the CSI-RS using a pre-selected subset of resource elements. In such implementations, transmitting the encoder information may include transmitting, for the basis matrix, only the columns of the basis matrix that correspond to the pre-selected subset of resource elements, and columns of the basis matrix corresponding to resource elements other than the pre-selected subset of resource elements may be zeroed.
[0037] In some implementations of the first aspect, transmitting the CSI-RS includes: dynamically selecting a subset of resource elements from a set of resource elements; and transmitting the CSI-RS using the selected subset of resource elements. In such implementations, transmitting the encoder information may include transmitting, for the basis matrix, only columns of the basis matrix that correspond to the dynamically-selected subset of resource elements, and columns of the basis matrix corresponding to resource elements other than the dynamically-selected subset of resource elements may be zeroed.
[0038] In some implementations of the first aspect, transmitting the encoder information includes transmitting, for the basis matrix, only columns of the basis matrix that: i) correspond to the dynamically-selected subset of resource elements; and ii) have been changed since a preceding CSI-RS transmission.
[0039] In some implementations of the first aspect, the basis matrix and the reduced-dimension codebook dictionary matrix included in the encoder information transmitted to the user device are one pair of a plurality of pairs of such matrices, each pair of such matrices being associated with a different geographic region. In such implementations, transmitting the encoder information to the user device may include transmitting, by the network device to the user device, the basis matrix and the reduced-dimension codebook dictionary matrix associated with a specific geographic region in which the user device is located when the user device connects to the network device.
[0040] In some implementations of the first aspect, the plurality of pairs of such matrices includes at least two pairs of such matrices in which each pair of the at least two pairs of such matrices is determined based on matrix decomposition of a respective subset of columns of a common higher-dimension codebook dictionary matrix. In such implementations, each respective subset of columns of the common higher-dimension codebook dictionary matrix, and the respective pair of matrices determined based on matrix decomposition thereof, may be associated with a different geographic region.
[0041] In some implementations of the first aspect, the at least two pairs of such matrices includes: a first pair of such matrices determined based on matrix decomposition of a first subset of columns of the common higher-dimension codebook dictionary matrix, the first subset of columns being associated with a first geographic region; and a second pair of such matrices determined based on matrix decomposition of a second subset of columns of the common higher-dimension codebook dictionary matrix, the second subset of columns being associated with a second geographic region. In such implementations, the first subset of columns may partially overlap with the second subset of columns.
[0042] In some implementations of the first aspect, the method further includes: monitoring one or more environmental indicators for one or more trigger conditions; and in response to detecting an occurrence of at least one of the one or more trigger conditions, transmitting update information for the encoder, the update information for the encoder including update information for the basis matrix based on the at least one detected trigger condition.
[0043] In some implementations of the first aspect, the update information for the encoder further includes update information for the reduced-dimension codebook dictionary matrix.
[0044] In some implementations of the first aspect, transmitting the update information for the encoder includes transmitting an update notification message, the update notification message including: information indicating a reason for the update; information indicating whether the update is a full update or a differential update; and the update information for the encoder.
[0045] In some implementations of the first aspect, the method further includes monitoring for an update acknowledgement message to confirm whether the update information for the encoder has been successfully applied.
[0046] In some implementations of the first aspect, the method further includes receiving a capability report, the capability report including processing capability information indicative of a processing capability. In such implementations, transmitting the encoder information may include transmitting, for the basis matrix, a reduced basis matrix based on the processing capability, the reduced basis matrix including a subset of columns of the basis matrix.
[0047] In some implementations of the first aspect, transmitting the reduced basis matrix includes transmitting reduced basis matrix information, the reduced basis matrix information including: type information indicating a type of the reduced basis matrix; and size information indicating a size of the reduced basis matrix.
[0048] In some implementations of the first aspect, the method further includes monitoring for a reduced basis acknowledgement message to confirm whether the reduced basis matrix for the encoder has been successfully applied.
[0049] In some implementations of the first aspect, the method further includes: receiving a request for a larger basis matrix; and transmitting update information for the reduced basis matrix based on the request, the update information for the reduced basis matrix including additional columns of the basis matrix to expand the reduced basis matrix.
[0050] In some implementations of the first aspect, each network layer of a plurality of network layers of a communication network has a respective codebook dictionary according to a hierarchical codebook structure, each respective codebook dictionary having associated therewith a unique identifier.
[0051] In some implementations of the first aspect, the basis matrix and the reduced-dimension codebook dictionary matrix indicated in the encoder information are based on matrix decomposition of the respective codebook dictionary matrix of the network layer in which a user device operates.
[0052] In some implementations of the first aspect, the method further includes, in response to the user device transitioning from a current network layer of the plurality of network layers to a target network layer of the plurality of network layers, transmitting inter-layer transition information. In such implementations, the inter-layer transition information may include: current layer codebook dictionary information indicating the unique identifier associated with the respective codebook dictionary of the current network layer from which the user device is transitioning; and / or target layer codebook dictionary information indicating the unique identifier associated with the respective codebook dictionary of the target network layer to which the user device is transitioning.
[0053] In some implementations of the first aspect, the method further includes, in response to the user device entering the target network layer, transmitting codebook dictionary synchronization information. For example, the codebook dictionary synchronization information may indicate differences between the respective codebook dictionary of the current network layer the user device has transitioned from and the respective codebook dictionary of the target network layer the user device has transitioned to.
[0054] In some implementations of the first aspect, the method further includes monitoring for a dictionary synchronization acknowledgement message to confirm whether the user device has successfully transitioned to the respective codebook dictionary of the target network layer.
[0055] According to a second aspect, there is provided a method that includes receiving encoder information for sparsity-based compression of information at a user device. The encoder information may include: a basis function operable as a dimension reduction function to reduce a dimension of the information at the user device; and a reduced-dimension codebook dictionary function that has reduced dimensions relative to a higher-dimension codebook dictionary function.
[0056] In some implementations of the second aspect, the method further includes transmitting a connection request, wherein receiving the encoder information from the network device includes receiving the encoder information from the network device after transmitting the connection request.
[0057] In some implementations of the second aspect, the connection request may be indicative of at least one of: whether the sparsity-based compression can be performed; whether the basis function is requested; or whether the reduced-dimension codebook dictionary function is requested.
[0058] In some implementations of the second aspect, the connection request may be transmitted via radio resource control (RRC) signaling.
[0059] In some implementations of the second aspect, the method further includes: using the basis function and the reduced-dimension codebook dictionary function to compress information at the user device; and transmitting the compressed information, the compressed information including a sparse representation of the information.
[0060] In some implementations of the second aspect, the compressed information includes compressed channel state information (CSI) .
[0061] In some implementations of the second aspect, the method further includes: receiving, a CSI reference signal (CSI-RS) ; utilizing the received CSI-RS to estimate CSI; and using the basis matrix and the reduced-dimension codebook dictionary function to compress the CSI, the compressed CSI including a sparse representation of the CSI.
[0062] In some implementations of the second aspect, using the basis matrix and the reduced-dimension codebook dictionary function to compress the CSI includes: using the basis function to project the CSI into a reduced dimension subspace to obtain a reduced-dimension representation of the CSI; and performing sparse approximation using the reduced-dimension codebook dictionary function and the reduced-dimension representation of the CSI to solve for the sparse representation of the CSI.
[0063] In some implementations of the second aspect, transmitting the compressed information includes transmitting the compressed CSI.
[0064] In some implementations of the second aspect, the method further includes: assessing the quality of channel estimation and compression based on statistics of the compressed CSI; in response to determining the quality of channel estimation and compression is acceptable, transmitting an uplink resources request; and receiving uplink resources allocation information indicating uplink resources allocated to the user device for uplink transmission. In such implementations, transmitting the compressed CSI may include transmitting the compressed CSI over the allocated uplink resources.
[0065] In some implementations of the second aspect, the method further includes: assessing the quality of channel estimation and compression based on statistics of the compressed CSI; and in response to determining the quality of channel estimation or compression is not acceptable, transmitting a signal indicative of a compression failure indicating a compression failure of the CSI.
[0066] In some implementations of the second aspect, the method further includes, after transmitting the signal indicative of the compression failure, at least one of: receiving a new CSI-RS across different resource elements; receiving information indicating an increase in the resource allocation for CSI estimation; or receiving updated encoder information based on an update to the higher-dimension codebook dictionary function.
[0067] In some implementations of the second aspect, the basis function and the reduced-dimension codebook dictionary function are derived from the higher-dimension codebook dictionary function.
[0068] In some implementations of the second aspect: the basis function includes a basis matrix; the higher-dimension codebook dictionary function includes a higher-dimension codebook dictionary matrix; and the reduced-dimension codebook dictionary function includes a reduced-dimension codebook dictionary matrix that has reduced dimensions relative to the higher-dimension codebook dictionary matrix.
[0069] In some implementations of the second aspect, the method further includes receiving dimension information indicative of:dimensions of the basis matrix; and dimensions of the reduced-dimension codebook dictionary matrix.
[0070] In some implementations of the second aspect, receiving the dimension information includes receiving the dimension information in one or more system information blocks (SIBs) .
[0071] In some implementations of the second aspect, the higher-dimension codebook dictionary matrix defines a reduced-dimension subspace projection of the channel space.
[0072] In some implementations of the second aspect, the basis matrix and the reduced-dimension codebook dictionary matrix are determined through matrix decomposition of the higher-dimension codebook dictionary matrix such that rows of the basis matrix form an orthonormal basis for a column space of the higher-dimension codebook dictionary matrix.
[0073] In some implementations of the second aspect, the matrix decomposition includes singular value decomposition (SVD) or QR decomposition.
[0074] In some implementations of the second aspect, the matrix decomposition includes SVD according to: Ψ=USV*, and Ψ′=SV*, where: Ψ is the higher-dimension code book dictionary matrix; U is the basis matrix, wherein U is a unitary matrix, where n is the channel dimension, and r is the rank of Ψ; S is a diagonal matrix; V is a unitary matrix, wherein V* is the Hermitian transpose of V; and Ψ′is the reduced-dimension codebook dictionary matrix.
[0075] In such implementations, using the basis matrix to project the CSI into a reduced dimension subspace to obtain a reduced-dimension representation of the CSI may include using the matrix U to project h into the subspace of Ψ to obtaining a reduced-dimension representation of the CSI according to: h′= U*h, where: h is the CSI; and h′is the reduced-dimension representation of the CSI.
[0076] In such implementations, performing sparse approximation using the reduced-dimension codebook dictionary matrix and the reduced-dimension representation of the CSI to solve for the sparse representation of the CSI may include performing sparse approximation by solving an optimization problem according to: where: s* is the optimal sparse vector representation of the CSI; and α is a sparsity-inducing parameter.
[0077] In some implementations of the second aspect, the matrix decomposition includes QR decomposition according to: Ψ=QR, and Ψ′=R, where: Ψ is the higher-dimension code book dictionary matrix; Q is the basis matrix, wherein Q is an orthogonal matrix; R is an upper triangular matrix; and Ψ′is the reduced-dimension codebook dictionary matrix.
[0078] In such implementations, using the basis matrix to project the CSI into a reduced dimension subspace to obtain a reduced-dimension representation of the CSI may include using the matrix U to project h into the subspace of Ψ to obtaining a reduced-dimension representation of the CSI according to: h′= Q*h, where: h is the CSI; and h′is the reduced-dimension representation of the CSI.
[0079] In such implementations, performing sparse approximation using the reduced-dimension codebook dictionary matrix and the reduced-dimension representation of the CSI to solve for the sparse representation of the CSI may include performing sparse approximation by solving an optimization problem according to: where: s* is the optimal sparse vector representation of the CSI; and αα is a sparsity-inducing parameter.
[0080] In some implementations of the second aspect, receiving the CSI-RS includes: receiving the CSI-RS using a subset of resource elements from a set of resource elements.
[0081] In some implementations of the second aspect, columns of the basis matrix corresponding to resource elements not used for transmitting the CSI-RS are zeroed.
[0082] In some implementations of the second aspect, the set of resource elements includes a set of transmit antennas and a set of frequency bands. In such implementations, receiving the CSI-RS using the selected subset of resource elements may include receiving the CSI-RS transmitted by a partial subset of transmit antennas from the set of transmit antennas in a partial subset of frequency bands dynamically selected, by the network device, from the set of frequency bands.
[0083] In some implementations of the second aspect, the method further includes receiving signaling indicative of the subset of resource elements.
[0084] In some implementations of the second aspect, the signaling indicative of the subset of resource elements includes downlink control information (DCI) or higher layer signaling.
[0085] In some implementations of the second aspect, receiving the CSI-RS includes receiving the CSI-RS transmitted using a pre-selected subset of resource elements. In such implementations, receiving the encoder information from the network device may include receiving, for the basis matrix, only the columns of the basis matrix that correspond to the pre-selected subset of resource elements; and zero-padding columns of the basis matrix corresponding to resource elements other than the pre-selected subset of resource elements.
[0086] In some implementations of the second aspect, receiving the CSI-RS includes receiving the CSI-RS transmitted using a subset of resource elements from a set of resource elements. In such implementations, receiving the encoder information from the network device may include: receiving, for the basis matrix, only columns of the basis matrix that correspond to the subset of resource elements; and zero-padding columns of the basis matrix corresponding to resource elements other than the subset of resource elements.
[0087] In some implementations of the second aspect, receiving the encoder information from the network device includes receiving, for the basis matrix, only columns of the basis matrix that: i) correspond to the dynamically-selected subset of resource elements; and ii) have been changed since a preceding CSI-RS transmission.
[0088] In some implementations of the second aspect, the basis matrix and the reduced-dimension codebook dictionary matrix included in the encoder information received from the network device are one pair of a plurality of pairs of such matrices, each pair of such matrices being associated with a different geographic region. In such implementations, receiving the encoder information may include receiving, by the user device from the network device, the basis matrix and the reduced-dimension codebook dictionary matrix associated with a specific geographic region in which the user device is located when the user device connects to the network device.
[0089] In some implementations of the second aspect, the plurality of pairs of such matrices includes at least two pairs of such matrices in which each pair of the at least two pairs of such matrices is determined based on matrix decomposition of a respective subset of columns of a common higher-dimension codebook dictionary matrix. In such implementations, each respective subset of columns of the common higher-dimension codebook dictionary matrix, and the respective pair of matrices determined based on matrix decomposition thereof, may be associated with a different geographic region.
[0090] In some implementations of the second aspect, the at least two pairs of such matrices includes: a first pair of such matrices determined based on matrix decomposition of a first subset of columns of the common higher-dimension codebook dictionary matrix, the first subset of columns being associated with a first geographic region; and a second pair of such matrices determined based on matrix decomposition of a second subset of columns of the common higher-dimension codebook dictionary matrix, the second subset of columns being associated with a second geographic region. In such implementations, the first subset of columns may partially overlap with the second subset of columns.
[0091] In some implementations of the second aspect, the method further includes receiving update information for the encoder. For example, the update information for the encoder may include update information for the basis matrix based on at least one trigger condition detected by the network device based on one or more environmental indicators.
[0092] In some implementations of the second aspect, the update information for the encoder further includes update information for the reduced-dimension codebook dictionary matrix.
[0093] In some implementations of the second aspect, receiving the update information for the encoder includes receiving an update notification message, the update notification message including: information indicating a reason for the update; information indicating whether the update is a full update or a differential update; and the update information for the encoder.
[0094] In some implementations of the second aspect, the method further includes: applying the update information for the encoder; and transmitting an update acknowledgement message to confirm the user device has successfully applied the update information for the encoder.
[0095] In some implementations of the second aspect, the method further includes: transmitting a capability report, the capability report including processing capability information indicative of a processing capability. In such implementations, receiving the encoder information may include receiving, for the basis matrix, a reduced basis matrix based on the processing capability. For example, the reduced basis matrix may include a subset of columns of the basis matrix.
[0096] In some implementations of the second aspect, receiving the reduced basis matrix includes receiving reduced basis matrix information, the reduced basis matrix information including: type information indicating a type of the reduced basis matrix; and size information indicating a size of the reduced basis matrix.
[0097] In some implementations of the second aspect, the method further includes transmitting a reduced basis acknowledgement message to confirm the user device has successfully received the reduced basis matrix and is ready to apply the reduced basis matrix.
[0098] In some implementations of the second aspect, the method further includes: transmitting a request for a larger basis matrix; and receiving update information for the reduced basis matrix based on the request. For example, the update information for the reduced basis matrix may include additional columns of the basis matrix to expand the reduced basis matrix.
[0099] In some implementations of the second aspect, each network layer of a plurality of network layers of a communication network has a respective codebook dictionary according to a hierarchical codebook structure, each respective codebook dictionary having associated therewith a unique identifier.
[0100] In some implementations of the second aspect, the basis matrix and the reduced-dimension codebook dictionary matrix indicated in the encoder information received by the user device from the network device are based on matrix decomposition of the respective codebook dictionary matrix of the network layer in which the user device operates.
[0101] In some implementations of the second aspect, the method further includes, in response to transitioning from a current network layer of the plurality of network layers to a target network layer of the plurality of network layers, receiving inter-layer transition information. For example, the inter-layer transition information may include: current layer codebook dictionary information indicating the unique identifier associated with the respective codebook dictionary of the current network layer from which the transitioning is performed; and / or target layer codebook dictionary information indicating the unique identifier associated with the respective codebook dictionary of the target network layer to which the transitioning is performed.
[0102] In some implementations of the second aspect, the method further includes, in response to entering the target network layer, receiving codebook dictionary synchronization information. For example, the codebook dictionary synchronization information may indicate differences between the respective codebook dictionary of the current network layer and the respective codebook dictionary of the target network layer.
[0103] In some implementations of the second aspect, the method further includes transmitting a dictionary synchronization acknowledgement message to confirm the respective codebook dictionary of the target network layer has been successfully transitioned to.
[0104] According to a third aspect, a communication apparatus is described. The communication apparatus has a function of implementing the first aspect. For example, the communication apparatus includes a corresponding module, unit, or means for performing operations in the first aspect. The module, unit, or means may be specifically implemented by using software, may be implemented by using hardware, or may be implemented by using software in combination with hardware.
[0105] According to a fourth aspect, a communication apparatus is described. The communication apparatus has a function of implementing the second aspect. For example, the communication apparatus includes a corresponding module, unit, or means for performing operations in the second aspect. The module, unit, or means may be specifically implemented by using software, may be implemented by using hardware, or may be implemented by using software in combination with hardware.
[0106] According to a fifth aspect, another communication apparatus is described. The communication apparatus includes a memory and one or more processors. The memory is configured to store a part or all of a necessary computer program or instructions for implementing a function in the first aspect. The one or more processors may execute the computer program or the instructions, and when the computer program or the instructions is / are executed, the communication apparatus is enabled to implement the method in any possible design or implementation of the first aspect.
[0107] According to a sixth aspect, another communication apparatus is described. The communication apparatus includes a memory and one or more processors. The memory is configured to store a part or all of a necessary computer program or instructions for implementing a function in the second aspect. The one or more processors may execute the computer program or the instructions, and when the computer program or the instructions is / are executed, the communication apparatus is enabled to implement the method in any possible design or implementation of the second aspect.
[0108] In some implementations, the communication apparatus may further include an interface circuit, and the processor is configured to communicate with another apparatus or component through the interface circuit.
[0109] In some implementations, the communication apparatus may further include the memory.
[0110] The communication apparatus may be a terminal, a module in a terminal, or a chip responsible for a communication function in a terminal, for example, a modem chip (also referred to as a baseband chip) or an SoC chip or an SIP chip that includes a modem module.
[0111] According to a seventh aspect, a communication system is described. The communication system includes a processor and a computer-readable medium having stored thereon, computer executable isntructions that, when exectued, cause the system to perform the methods as any one of the possible designs of the first aspect or second aspect.
[0112] According to an eighth aspect, a computer-readable storage medium is described. The computer-readable storage medium stores computer-readable instructions, and when a computer reads and executes the computer-readable instructions, the computer is enabled to perform the method in any one of the possible designs of the first aspect or second aspect.
[0113] According to a ninth aspect, this application provides a computer program product. When a computer reads and executes the computer program product, the computer is enabled to perform the method in any one of the possible designs of the first aspect or second aspect.
[0114] According to a tenth aspect, this application provides a system including at least one of an apparatus at a UE of the present application, or an apparatus at a network device of the present application.
[0115] According to an eleventh aspect, this application provides a method performed by a system including at least one of an apparatus at a UE of the present application, and an apparatus at a network device of the present application.
[0116] In another aspect, this application provides a communication system, where the communication system includes a first node configured to perform the methods according to the first aspect disclosed herein and a second node configured to perform the methods according to the second aspect disclosed herein.
[0117] In another aspect, there is provided a communication system including a network device and a user device. The network device may be configured to transmit, to the user device, encoder information for sparsity-based compression of information at the user device. The encoder information may include: a basis matrix operable as a dimension reduction matrix to reduce a dimension of channel state information (CSI) at the user device; and a reduced-dimension codebook dictionary matrix that has reduced dimensions relative to a higher-dimension codebook dictionary matrix. The network device may also be configured to transmit a CSI reference signal (CSI-RS) to the user device. The user device may be configured to receive the encoder information and the CSI-RS, and utilize the CSI-RS to estimate CSI. The user device may also be configured to use the basis matrix to project the CSI into a reduced dimension subspace to obtain a reduced-dimension representation of the CSI, and perform sparse approximation using the reduced-dimension codebook dictionary matrix and the reduced-dimension representation of the CSI to solve for a sparse representation of the CSI. The user device may also be configured to transmit the sparse representation of the CSI to the network device.
[0118] This application encompasses various implementations, including not only method implementations, but also other implementations such as apparatus implementations and implementations related to non-transitory computer readable storage media. implementations may incorporate, individually or in combinations, the features disclosed herein.BRIEF DESCRIPTION OF THE DRAWINGS
[0119] For a more complete understanding of the present implementations, and the advantages thereof, reference is now made, by way of example, to the following descriptions taken in conjunction with the accompanying drawings, in which:
[0120] FIG. 1 is a schematic diagram of a communication system in which the present disclosure may occur.
[0121] FIG. 2 is another schematic diagram of a communication system in which the present disclosure may occur.
[0122] FIG. 3 is a block diagram illustrating units or modules in a device in which the present disclosure may occur.
[0123] FIG. 4 is a block diagram illustrating units or modules in a device in which the present disclosure may occur.
[0124] FIG. 5 is a block diagram illustrating units or modules in a device in which the present disclosure may occur.
[0125] FIG. 6 illustrates an example procedure for radio resource control (RRC) connection and initial model sharing in a communication network, according to some implementations of the present disclosure.
[0126] FIG. 7 illustrates an example procedure for CSI estimation and compression at a user device in a communication network, according to some implementations of the present disclosure.
[0127] FIG. 8 illustrates an example procedure for CSI reporting in a communication network, according to some implementations of the present disclosure.
[0128] FIG. 9 illustrates an example procedure for basis matrix update messaging and acknowledgement in a communication network, according to some implementations of the present disclosure.
[0129] FIG. 10 illustrates an example procedure for basis matrix customization and transmission in a communication network, according to some implementations of the present disclosure.
[0130] FIG. 11 illustrates an example procedure for on-demand basis matrix expansion in a communication network, according to some implementations of the present disclosure.
[0131] FIG. 12 illustrates an example procedure for layered dictionary codebook management in a communication network, according to some implementations of the present disclosure.
[0132] FIG. 13 illustrates a method performed by the two apparatuses, according to some implementations of the present disclosure.DETAILED DESCRIPTION
[0133] For illustrative purposes, specific example implementations will now be explained in greater detail below in conjunction with the figures.
[0134] The implementations and examples set forth herein represent information sufficient to practice the claimed subject matter and illustrate ways of practicing such subject matter. Upon reading the following description in light of the accompanying figures, those of skill in the art will understand the concepts of the claimed subject matter and will recognize applications of these concepts not particularly addressed herein. It should be understood that these concepts and applications fall within the scope of the disclosure and the accompanying claims.
[0135] Moreover, it will be appreciated that any module, component, or device disclosed herein that executes instructions may include or otherwise have access to a non-transitory computer / processor readable storage medium or media for storage of information, such as computer / processor readable instructions, data structures, program modules, and / or other data. A non-exhaustive list of examples of non-transitory computer / processor readable storage media includes magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, optical disks such as compact disc read-only memory (CD-ROM) , digital video discs or digital versatile discs (i.e. DVDs) , Blu-ray DiscTM, or other optical storage, volatile and non-volatile, removable and non-removable media implemented in any method or technology, random-access memory (RAM) , read-only memory (ROM) , electrically erasable programmable read-only memory (EEPROM) , flash memory or other memory technology. Any such non-transitory computer / processor storage media may be part of a device or accessible or connectable thereto. Computer / processor readable / executable instructions to implement an application or module described herein may be stored or otherwise held by such non-transitory computer / processor readable storage media.
[0136] In the present disclosure, the term “codebook dictionary” may refer to a structured set of basis vectors or codewords used to represent channel state information (CSI) in a compressed form, facilitating efficient data transmission and storage in wireless communication systems.
[0137] In the present disclosure, the term “sparse representation” may refer to a mathematical representation where data is expressed as a combination of a few non-zero coefficients, often based on a codebook dictionary, to reduce dimensionality and computational complexity.
[0138] In the present disclosure, the term “model-of-data” may refer to astatistical or structural model derived from the sparse representation of channel data, capturing essential patterns, distributions, and characteristics for efficient data handling in downstream AI tasks.
[0139] In the present disclosure, the term “compression failure signal” may refer to a message sent by the user equipment (UE) indicating that the sparse representation of CSI data does not meet quality or sparsity requirements for tasks such as beamforming or resource allocation.
[0140] In the present disclosure, the term “subspace equivalence” may refer to the concept of processing high-dimensional data within a lower-dimensional subspace, maintaining equivalent information content while reducing computational overhead and storage requirements.
[0141] In the present disclosure, the term “two-side model” may refer to a model architecture where AI / ML processing components are deployed at both the User Equipment (transmission) and Base Station (receiving) ends, enabling efficient bi-directional data compression and decompression.
[0142] In the present disclosure, the term “differential transmission” may refer to a method where only changes or updates to a dataset, model, or matrix (e.g., codebook dictionary) are transmitted, reducing data transmission overhead by avoiding repetitive information.
[0143] In the present disclosure, the term “sparsity-based CSI compression” may refer to a technique to compress channel state information (CSI) by exploiting the sparsity characteristics of the data in certain domains, reducing transmission and processing burdens.
[0144] In the present disclosure, the term “sparse sampling” may refer to Selecting only essential resource elements for channel estimation or data processing, which may involve zeroing out certain components to reduce data volume while retaining essential information.
[0145] In the present disclosure, the term “projection matrix” may refer to A matrix used to map high-dimensional data onto a lower-dimensional subspace, commonly used in SVD or QR-based dimension reduction methods to simplify computations. 3GPP Channel Data
[0146] The data referred to in some of the implementations described herein is specific to 3rd Generation Partnership Project (3GPP) , and in some cases is particularly focused on channel-related data. This data can originate as raw channel estimation results or undergo various transformations, such as from time domain to frequency domain or to delay or spatial domains. Regardless of the transformation, this data remains closely associated with the channel. Some key characteristics of this 3GPP-related data include: · Large Data Volume: 3GPP channel data is vast, encompassing real-time communication statuses between user equipment (UE) and base stations (BS) . It includes parameters like frequency, bandwidth, delay, fading, and power, generating large-scale, continuously evolving data streams. ● Spatiotemporal Correlation: Data collected from nearby locations often shows high spatial correlation. Additionally, channel data, especially affected by user movement, exhibits temporal correlations due to the dynamic nature of wireless channels. ● Noise and Interference: Channel data commonly contains noise and interference, which needs to be managed during processing. ● Normalization for Data Consistency: After preprocessing and normalization, 3GPP-related data achieves more consistency compared to non-3GPP data, like images, audio, or video. This consistency stems from the data being sourced from terminal devices and network equipment. ● Single Source: The primary sources of 3GPP data are user equipment and network devices, typically from measurement results of these devices. ● Sparsity: In specific transform domains (e.g., the delay or angle domain) , channel data often exhibits sparsity, with most values being zero or near zero. This sparsity allows for efficient compression, reducing storage and transmission burdens.
[0147] These characteristics arise from the propagation properties of wireless channels, which are described by Maxwell’s equations-a set of partial differential equations (PDEs) . Solutions to PDE solutions are typically smooth and regular, meaning CSI changes follow predictable physical laws rather than random variations. Consequently, channel data can be effectively compressed by transforming high-dimensional data into lower-dimensional representations, such as codewords or feature vectors, thus reducing storage, transmission, and processing costs. ● Environmental Dependency: Channel data is heavily influenced by device location, movement, and the surrounding environment. For instance, in urban environments, channels are more complex due to multipath effects, whereas in open areas, they are simpler. This implies that different environments require distinct codebook dictionaries or AI / ML models for effective data processing. · Low Diversity: Compared to non-3GPP data, such as images or text, 3GPPchannel data exhibits lower diversity. After normalization, the data structure becomes more uniform, making it ideal for constructing codebook dictionaries, which help AI models to adapt more accurately to specific channel environments.
[0148] The following table summarizes some key differences between 3GPP channel data and general AI big model training data, such as images or text:
[0149] These differences highlight the unique characteristics of 3GPP channel data and explain why traditional AI model training and deployment methods typically cannot be directly applied to wireless communication systems.
[0150] The models discussed in relation to various aspects of the present disclosure may apply to a range of downstream tasks in wireless communication systems, including CSI feedback, channel prediction, beamforming, and resource allocation. These tasks may be performed by different vendors, each utilizing models of varying sizes, structures, and training methodologies. While vendors may use the same datasets, they may deploy their models tailored to specific operational needs and capabilities.
[0151] Figures 1, 2, 3, 4, and 5 provide context for a network and devices that may be in the network and that may implement aspects of the present disclosure.
[0152] FIG. 1 is a schematic illustration of an example communication system according to an implementation of the present disclosure, there is shown a communication system 100 that includes a radio access network (RAN) 120, one or more communication electronic devices (EDs) 10a, 110b, 110c, 110d, 110e, 110f, 110g, 110h, 110i, 110j (collectively referred to as 110) , a core network 130, a public switched telephone network (PSTN) 140, the Internet 150, and other networks 160 . The RAN 120 may include, but is not limited to, a future generation RAN, or a legacy RAN such as, but not limited to, 5th generation (5G) , 4th generation (4G) , 3rd generation (3G) or 2nd generation (2G) radio access network. The RAN 120 may be, for example, an evolved universal mobile telecommunications system (UMTS) terrestrial radio access network (E-UTRAN) , a NextGen RAN (NG RAN) , or some other type of RAN. Examples of RAN 120 based on the evolution of telecommunications standards include, but is not limited to, GSM (Global System for Mobile Communications) and code division multiple access (CDMA) for 2G, universal mobile telecommunications system (UMTS) based on wideband code division multiple access (WCDMA) and CDMA2000 for 3G, long-term evolution (LTE) and WiMAX (Worldwide Interoperability for Microwave Access) for 4G, and new radio (NR) for 5G. In some implementations, The RAN 120 may use any radio access technology (RAT) in the wireless interface between the one or more EDs 110 and the RAN 120. In some implementations, the term “radio access” may refer to the future generation air interface standards which may include both terrestrial networks (TNs) and non-terrestrial networks (NTNs) . These networks will be described in greater detail below in conjunction with various implementations. The one or more communication EDs 110 (also referred to as “user equipment” ) are configured to connect (e.g., communicatively couple) with each other or to one or more network nodes 170a, 170b (collectively referred to as 170) in the RAN 120. The core network (CN) 130 is a part of the communication system 100 and consists of network nodes (e.g., 170a, 170b) which provide support for the network features and telecommunication services. In some implementations, the CN 130 may be dependent on the RAT used in the communication system 100. In other implementations, the CN 130 may be access-agnostic, i.e., the CN 130 may be independent of the RAT used in the communication system 100. There are different types of CN 130, for different 3GPP system generations. For example, the CN 130 is the evolved packet core (EPC) in 4G, also known as the evolved packet system (EPS) . In another example, the CN 130 is the 5G Core (5GC) which was developed as part of the 5G System (5GS) . The CN 130 also enables integration of different 3GPP and non-3GPP access types. In some implementations and referring to Figure 1, the CN 130 also provides the interface towards external networks that may include the PSTN 140, the Internet 150, and other networks 160 in the communication system 100.
[0153] In general, the communication system 100 facilitates interaction between multiple wireless or wired elements. The communication system 100 may transmit different types of content, such as voice, data, video, and / or text, through different transmission methods such as, but not limited to, broadcast, multicast, groupcast, and unicast. Additionally, the communication system 100 operates by allocating and / or sharing resources, such as carrier spectrum bandwidth, among its constituent elements.
[0154] The communication system 100 may provide a wide range of communication services and applications including, but not limited to, Enhanced Mobile Broadband (eMBB) services, ultra-reliable low-latency communication (URLLC) services, Massive Machine Type Communication (mMTC) services, integrated sensing and communication (ISAC) , immersive communication, Ultra-massive Machine-Type Communication (uMTC) , hyper reliable and low-latency communication, ubiquitous connectivity, integrated AI and communication, and other services that can be provided by a future generation communication system. The communication system 100 may provide other services and applications such as, but not limited to, earth monitoring, remote sensing, passive sensing and positioning, navigation and tracking, autonomous delivery and mobility and the like.
[0155] The communication system 100 may include a terrestrial communication system (or network) and / or a non-terrestrial communication system (or network) . The communication system 100 may provide a high degree of availability and robustness through a joint operation of the terrestrial communication system and the non-terrestrial communication system. For example, integrating a non-terrestrial communication system (or components thereof) into a terrestrial communication system can result in a heterogeneous network comprising multiple layers. The heterogeneous network may achieve better overall performance through efficient multi-link joint operation, more flexible functionality sharing, and faster physical layer link switching between terrestrial networks and non-terrestrial networks. The terrestrial communication system and the non-terrestrial communication system could be considered as sub-systems of the communication system 100.
[0156] FIG. 2 illustrates another example communication system 100 according to an implementation of the present disclosure, there is shown the communication system 100 includes EDs 110a, 110b, 110c, 110d (collectively referred to as ED 110) , RANs 120a, 120b, one or more CNs 130, a PSTN 140, the Internet 150, and other networks 160. Additionally, the communication system 100 may also include a non-terrestrial network (NTN) 120c. The RANs 120a and120b may include network nodes 170a and 170b respectively. Examples of network nodes 170a, 170b include base stations, which can be generally referred to as terrestrial network (TN) devices or terrestrial transmit and receive points (T-TRPs) 170a and 170b (collectively referred to as 170) . In this context, the terms "TRP" and "base station" are used interchangeably unless otherwise specified. For simplicity, present disclosure primarily refers to network nodes as base stations; however, unless explicitly stated otherwise, references to TRP are considered non-limiting and interchangeable. The T-TRPs 170a, 170b may be base stations mounted on a building or tower. In one implementation, the NTN 120c includes a RAN node such as a base station 172, which may be generally referred to as an NTN device, a non-terrestrial node, a non-terrestrial network device, a non-terrestrial base station, or a non-terrestrial transmit and receive point (NT-TRP) 172.
[0157] In some implementations, the NT-TRP 172 is not attached to the ground, for example, as in the case of an airborne base station. An airborne base station may be implemented using communication equipment supported or carried by a flying device. For example, a flying device may include, but is not limited to, an airborne platform (such as a blimp or an airship) , balloon, drone (such as quadcopter) , and other types of aerial vehicles. In some implementations, an airborne base station may be supported or carried by an unmanned aerial system (UAS) or an unmanned aerial vehicle (UAV) , such as a drone. An airborne base station may be a moveable or mobile base station that can be flexibly deployed in different locations to meet network demand. A satellite base station is another example of a non-terrestrial base station. A satellite base station may be implemented using communication equipment supported or carried by a satellite. A satellite base station may also be referred to as an orbiting base station. High altitude platforms are yet another example of non-terrestrial base stations, including international mobile telecommunication base stations.
[0158] As referred to herein, and unless specified otherwise, a “TRP” may also refer to a T-TRP or an NT-TRP, a “T-TRP” may also refer to a “TN TRP” , and an “NT-TRP” may also refer to an “NTN TRP” . The NTN 120c may be considered a RAN, sharing operational aspects with RANs 120a, 120b. The NTN 120c may include at least one NTN device and at least one corresponding terrestrial network device. The at least one NTN device may function as a transport layer device and the at least one corresponding terrestrial network device may function as a RAN node, communicating with the ED 110 via the NTN device. Additionally, there may be an NTN gateway on the ground (referred to as a terrestrial network device) that also functions as a transport layer device facilitating communication with both the NTN device and the RAN node. The RAN node may communicate with the ED 110 via the NTN device and the NTN gateway. In some implementations, the NTN gateway and the RAN node may be located within the same device.
[0159] A base station 170 (also referred to as a TRP as stated above) is a network element within a radio access network responsible for radio transmission and reception in one or more cells to or from the ED (such as auser equipment) . In different implementations, the base station 170 may also be known as a base transceiver station (BTS) , a radio base station, a network node, a network device, a device on the network side, a transmit / receive node, a Node B, an evolved NodeB (eNodeB or eNB) , a Home eNodeB, a next Generation NodeB (gNB) , a transmission point (TP) , a site controller, an access point (AP) , a wireless router, a relay station, a terrestrial node, a terrestrial network device, a terrestrial base station, a non-terrestrial node, a non-terrestrial network device, a non-terrestrial base station, and a positioning node, among other possibilities. The base station 170 may be a macro base station (BS) , a pico BS, a relay node, a donor node, or combinations thereof. When the base station 170 performs (or is configured to perform) a method described herein, it may be interpreted as the base station itself, one or more modules (or units) in the base station, a circuit or chip, or a combination thereof, performing the method. For example, the circuit or chip may include a modem chip, also referred to as a baseband chip, a system on chip (SoC) including a modem core, system in package (SIP) ) , and the like, and may be responsible for one or more communication functions within the base station.
[0160] The EDs 110a-110d and TRPs 170a-170b, 172 are examples of communication equipment configured to implement some or all of the operations and / or implementations described herein. The T-TRP 170a forms part of the RAN 120a, which may include other TRPs, and / or other devices. Also, the TRP 170b forms part of the RAN 120b, which may include other TRPs, and / or devices. Each TRP 170a, 170b may transmit and / or receive wireless signals within a particular geographic region or area, sometimes referred to as a “cell” or a “coverage area” . The TRPs 170a-170b may be responsible for allocating and / or configuring resources and transmission and / or reception in a set of cell (s) . A cell is a radio network object that can be uniquely identified by a cell identification that is broadcasted over a geographical region or area from base stations associated with the cell. A cell can work in either FDD or TDD mode. A cell may be further divided into cell sectors, and a base station 170a-170b may, for example, employ one or more transceivers to provide services to one or more sectors. Some implementations, may include pico or femto cells if supported by the radio access technology. In some implementations, one or more transceivers could be used for each cell, such as with multiple-input multiple-output (MIMO) technology. The number of RANs 120a-120b shown is merely an example. Any number of RANs may be contemplated when designing the communication system 100.
[0161] A base station may be a single element, as shown in the figures, or multiple elements distributed throughout the corresponding RAN, or otherwise configured. In some implementations, a plurality of RAN nodes coordinate to assist the ED 110 in implementing radio access, and different RAN nodes separately implement and handle different functions of the base station. For example, the RAN node may be a central unit (CU) , a distributed unit (DU) , a CU-control plane (CP) , a CU-user plane (UP) , or a radio unit (RU) etc. The CU and the DU may be separately deployed, or included within the same element (i.e., a baseband unit (BBU) ) . The RU may be included in a radio frequency device or a radio frequency unit (i.e., a remote radio unit (RRU) , an active antenna unit (AAU) , or a remote radio head (RRH) ) . In different systems, the CU (or the CU-CP and the CU-UP) , the DU, or the RU may be known by different names, but their functions are understood by person skilled in the art. For example, in an open radio access network (ORAN) system, a CU may be referred to as an open CU (O-CU) , a DU may be referred to as an open DU (O-DU) , and a CU-CP may be referred to as an open CU-CP (O-CU-CP) . The CU-UP may also be referred to as an open CU-UP (O-CU-UP) , and the RU may also be referred to as an open RU (O-RU) . Any one of the CU (or the CU-CP, the CU-UP) , the DU, and the RU may be implemented using a software module, a hardware module, or a combination of a software module and a hardware module.
[0162] Furthermore, communication between different devices / apparatuses in various implementations of present disclosure may refer to direct communication (that is, without the need of forwarding by another device / apparatus) , or may refer to communication (s) between different devices / apparatuses via another device / apparatus (that is, requiring forwarding by another device / apparatus) . Alternatively, such communication (s) may involve one functional unit inside a device / apparatus using another functional unit within the device / apparatus to communicate with another device / apparatus. In other words, phrases such as "sending (or transmitting) information to... (an ED or a base station) " in present disclosure may be understood as a destination endpoint of the information being an ED or a base station, including, sending / transmitting information directly or indirectly to an ED or a base station. Similarly, phrases like "receiving information from... (an ED or a base station) " may be understood as a source endpoint of the information being an ED or a base station, including directly or indirectly receiving information from an ED or a base station. Between the source endpoint that sends the information and the destination endpoint, necessary processing such as, but not limited to, format conversion, digital-to-analog conversion, amplification, and filtering may be performed on the information. However, the destination endpoint may understand valid information from the source endpoint. A similar understanding applies to other descriptions in present disclosure without reiterating details already described. In the present disclosure, the terms "send" and "transmit" may be used interchangeably in different implementations of present disclosure.
[0163] The ED 110 is used to connect people, objects, machines, and other entities. The ED 110 may be widely used in various scenarios including, but not limited to, cellular communications, device-to-device (D2D) , vehicle to everything (V2X) , peer-to-peer (P2P) , machine-to-machine (M2M) , MTC, internet of things (IoT) , virtual reality (VR) , augmented reality (AR) , mixed reality (MR) , metaverse, digital twin, industrial control, self-driving, remote medical, smart grid, smart furniture, smart office, smart wearable, smart transportation, smart city, drones, robots, remote sensing, passive sensing, positioning, navigation and tracking, and autonomous delivery and mobility.
[0164] Each ED 110 represents any suitable end user device for wireless operation and may include such devices (or may be referred to as, but not limited to) a user equipment (UE) or a user device or a terminal device, a wireless transmit / receive unit (WTRU) , a mobile station, a fixed or mobile subscriber unit, a cellular telephone, a station (STA) , an MTC device, a personal digital assistant (PDA) , a smartphone, a laptop, a computer, a tablet, a wireless sensor, a consumer electronics device, a smart book, a vehicle, a car, a truck, a bus, a train, or an IoT device, wearable devices (such as a watch, a pair of glasses, head mounted equipment, etc. ) , an industrial device, or an apparatus (such as a module, modem, or chip) in the forgoing devices, among other possibilities. Future generation EDs 110 may be referred to by other terms. When an ED 110 performs (or is configured to perform) a method described herein, it may be interpreted as the ED itself, one or more modules (or units) in the ED, a circuit or chip, or a combination thereof, performing the method. For example, the circuit or chip may include a modem chip, also referred to as a baseband chip, a system on chip (SoC) including a modem core, or system in package (SIP) ) , and the like, and may be responsible for one or more communication functions in the ED.
[0165] Each ED 110 connected to TRPs 170a-170b, and / or TRPs 172 can be dynamically or semi-statically turned-on (i.e., established, activated, or enabled) , turned-off (i.e., released, deactivated, or disabled) and / or configured in response to one of more of: connection availability and connection necessity.
[0166] Any ED 110 may be alternatively or additionally configured to interface, access, or communicate with any of the TRPs 170a, 170b and 172, the Internet 150, the CN 130, the PSTN 140, the other networks 160, or any combination thereof. In some examples, the ED 110a may communicate an uplink (UL) and / or downlink (DL) transmission over a terrestrial air interface 190a with station-TRP 170a. In some examples, the EDs 110a, 110b, 110c, and 110d may also communicate directly with one another via one or more sidelink (SL) air interfaces 190b. In some examples, the EDs 110a, 110d may communicate using an UL and / or DL transmission over a non-terrestrial air interface 190c with NT-TRP 172.
[0167] An air interface (such as, for example, 190a, 190b, 190c) generally includes a number of components and associated parameters that collectively specify how a transmission is to be sent and / or received over a wireless communications link between two or more communicating devices such as EDs and base station (s) . For example, an air interface may include one or more components defining the waveform (s) , frame structure (s) , multiple access scheme (s) , protocol (s) , coding scheme (s) and / or modulation scheme (s) for conveying information (such as, data) over a wireless communications link. The air interfaces 190a and 190b may use similar communication technology, that may include any suitable radio access technology.
[0168] The non-terrestrial air interface 190c can enable communication between the EDs 110a, 110d and one or more NT-TRPs 172 via a wireless link or simply a link. For some examples, the link is a dedicated connection for unicast transmission, a connection for broadcast transmission, or a connection between a group of EDs 110 and one or more NT-TRPs 172 for multicast transmission.
[0169] The TRPs 170a-170b, 172 may communicate with one another over one or more air interfaces 190e, 190f using wireless communication links (such as radio frequency (RF) , microwave, infrared (IR) , etc. ) or wired communication links. The air interfaces 190e, 190f may utilize any suitable radio access technology, and may be substantially similar to the air interfaces 190a, 190c over which the EDs 110a-110d communicate with one or more of the TRP 170a-170b, 172 or they may be substantially different. For example, the communication system 100 may implement one or more channel access methods, such as time division multiple access (TDMA) , frequency division multiple access (FDMA) , code division multiple access (CDMA) , Single Carrier Frequency Division Multiple Access (SC-FDMA) , Low Density Signature Multicarrier Code Division Multiple Access (LDS-MC-CDMA) , non-orthogonal multiple access (NOMA) , pattern division multiple access (PDMA) , lattice partition multiple access (LPMA) , resource spread multiple access (RSMA) , and sparse code multiple access (SCMA) .
[0170] The RANs 120a and 120b are in communication with the CN 130 to provide the EDs 110a 110b, and 110c with various services such as voice, data, multimedia, and other services. The RANs 120a and 120b and / or the CN 130 may be in direct or indirect communication with one or more other RANs (not shown) , which may or may not be directly served by the CN 130, and may employ different radio access technologies from RAN 120a and / or RAN 120b. The CN 130 may also serve as a gateway access between (i) the RANs 120a and 120b and / or the EDs 110a 110b, and 110c, and (ii) other networks (such as the PSTN 140, the Internet 150, and the other networks 160) . In addition, some or all of the EDs 110a 110b, and 110c may include functionality for communicating with different wireless networks over different wireless links using different wireless technologies and / or protocols. For example, the EDs 110a 110b, and 110c communicate using different cellular communications protocols, such as, but not limited to, a Global System for Mobile Communications (GSM) protocol, a code-division multiple access (CDMA) network protocol, a Push-to-Talk (PTT) protocol, a PTT over Cellular (POC) protocol, a universal mobile telecommunications system (UMTS) protocol, a 3GPP long term evolution (LTE) protocol, a fifth generation (5G) protocol, a new radio (NR) protocol, and the like. Instead of wireless communication (or in addition thereto) , the EDs 110a 110b, and 110c may communicate using wired communication channels to a service provider or switch (not shown) , and / or to the Internet 150. The PSTN 140 may include circuit switched telephone networks for providing plain old telephone service (POTS) . The Internet 150 may include a network of computers and subnets (intranets) or both, and incorporate protocols, such as internet protocol (IP) , transmission control protocol (TCP) , user datagram protocol (UDP) . EDs 110a 110b, and 110c may be multimode devices capable of operation according to multiple radio access technologies, and may incorporate one or multiple transceivers necessary to support such.
[0171] In addition, the communication system 100 may comprise a sensing agent (not shown) to manage the sensed data from ED 110 and / or any one of TRPs 170a, 170b, 172. In one implementation, the sensing agent may be part of any one of TRPs 170a, 170b, 172. In another implementation, the sensing agent is a separate node that can communicate with the CN 130 and / or the RAN 120 (such as any one of TRPs 170a, 170b, 172) .
[0172] FIG. 3 is a schematic illustration showing an apparatus 310 wirelessly communicating with another apparatus 320 within a communication system (e.g., the communication system 100) according to an implementation of the present disclosure. The apparatus 310 may be an electronic device (such as ED 110) . The apparatus 320 may be a network node (e.g., the network node 170) such as T-TRP 170 or an NT-TRP 172. Although only one apparatus 310, and one apparatus 320 are shown in the figure, the number of apparatus 310 and / or number of apparatus 320 can vary, potentially including one or more of each. For example, a single ED 110 may be served by a single T-TRP 170 (or a single NT-TRP 172) , or by multiple T-TRPs 170 (or multiple NT-TRPs 172) . Similarly, a single ED 110 may be served by one or more T-TRPs 170 and one or more NT-TRPs 172. Similarly, a single T-TRP 170 (or a single NT-TRP 172) may serve one or more EDs 110.
[0173] The apparatus 310 may include one or more processors 210. For clarity and to avoid overcrowding the illustration, only a single processor 210 is illustrated. The apparatus 310 may further include a transmitter 201 and a receiver 203 coupled to one or more antennas 204. For clarity, only a singleantenna 204 is illustrated. One, some, or all of the antennas 204 may alternatively be panels. In some implementations, the transmitter 201 and the receiver 203 are separate from each other. In other implementations, the transmitter 201 and the receiver 203 may be integrated into a single unit, for example, as a transceiver. The transceiver is configured to modulate data or other content for transmission by the one or more antennas 204 or a network interface controller (NIC) . The transceiver may also be configured to demodulate data or other content received by the one or more antennas 204. A transceiver may include any suitable structure for generating signals for wireless or wired transmission and / or for processing signals received through wireless or wired communication. Each antenna 204 includes any suitable structure for transmitting and / or receiving wireless or wired signals. The apparatus 310 may include a memory 208. In some implementations, the apparatus 310 may include multiple memories 208. Only a single transmitter 201, receiver 203, processor 210, memory 208, and antenna 204 is illustrated for simplicity, but the apparatus 310 may include one or more other components. In some implementations of the present disclosure, the transceiver (or transmitter 201 and / or receiver 203) may be viewed as an interface circuit.
[0174] The memory 208 is configured to store instructions used to perform operations described herein. The memory 208 may also be configured to store data that is used, generated, or collected by the apparatus 310. For example, the memory 208 can store software instructions or modules configured to implement some or all of the functionalities and / or operations described herein and that which are executed by the one or more processors 210.
[0175] The apparatus 310 may further include one or more input / output devices (not shown) or interfaces. The input / output devices or interfaces facilitate interaction with a user or other devices in the network. Each input / output device or interface includes suitable components for faciltating transmission of information to a user and reception of information from a user, and for various network interface communications. Such components may include, but are not limited to, a speaker, microphone, keypad, keyboard, display, touch screen, and the like.
[0176] The processor 210 may be configured to perform (or control the apparatus 310 to perform) operations (or methods) described herein as being performed by the apparatus 310. For example, the processor 210 performs or controls the apparatus 310 to perform the operations of: a) receiving one or more transport blocks (TBs) , b) using a resource for decoding at least one of the received TBs, c) releasing the resource for decoding another of the received TBs, and / or d) receiving configuration information configuring a resource. Specifically, the operations may include tasks related to: preparing a transmission for UL transmission to the apparatus 320, processing DL transmissions received from the apparatus 320, and handling SL transmission to and from another apparatus 310. Processing operations related to preparing a transmission for UL transmission may include operations such as, but not limited to, encoding, modulating, transmit beamforming, and generating symbols for transmission. Processing operations related to processing DL transmissions may include operations such as, but not limited to, receive beamforming, demodulating and decoding received symbols. Processing operations related to processing SL transmissions may include operations such as, but not limited to, transmit / receive beamforming, modulating / demodulating and encoding / decoding symbols. Depending upon the implementation, a DL transmission may be received by the receiver 203, possibly using receive beamforming, and the processor 210 may extract signaling from the DL transmission (such as by detecting and / or decoding the signaling) . An example of signaling may be a reference signal transmitted by the apparatus 320. In some implementations, the processor 210 implements the transmit beamforming and / or the receive beamforming based on the indication of beam direction, such as beam angle information (BAI) , received from the apparatus 320. In some implementations, the processor 210 may be configured to perform operations relating to network access (such as initial access) and / or downlink synchronization, which includes operations for detecting a synchronization sequence, decoding and obtaining the system information, and the like. In some implementations, the processor 210 may perform channel estimation, such as using a reference signal received from the apparatus 320.
[0177] Although not illustrated, in some implementations, the processor 210 may either be a part of the transmitter 201 or a part of the receiver 203 or a part of both the transmitter 201 and the receiver 203. Although not illustrated, in some implementations, the memory 208 may be a part of the processor 210.
[0178] The processor 210, along with the processing components of the transmitter 201 and the receiver 203 may each be implemented by one or more processors that may the same or different. These processors are configured to execute instructions stored in a memory (such as in the memory 208) .
[0179] The apparatus 320 includes one or more processors 260 (only one processor 260 is illustrated ) . The apparatus 320 may further include one or more transmitters 252 and one or more receivers 254 coupled to one or more antennas 256. Only a single antenna 256 is illustrated to avoid clutter in the illustration. One, some, or all of the antennas 256 may alternatively be panels. In some implementations, the transmitter 252 and the receiver 254 are separate from each other. In other implementations, the transmitter 252 and the receiver 254 may be integrated into a single unit such as, for example, as a transceiver. The apparatus 320 may further include a memory 258. In some implementations, the apparatus 320 may include multiple memories 258. The apparatus 320 may further include a scheduler 253. Only a single transmitter 252, receiver 254, processor 260, memory 258, antenna 256 and scheduler 253 are illustrated for simplicity, however the apparatus 320 may include one or more other components. In the present disclosure, in some implementations, the transceiver (or transmitter 252 and / or receiver254) may be viewed as an interface circuit.
[0180] In some implementations, various components of the apparatus 320 may be distributed. For example, some of the modules of the apparatus 320 may be located remotely from the equipment housing the antennas 256 for the apparatus 320 (and therefore also can be viewed as one or more nodes) . These modules, which can be considered as one or more nodes, may be coupled to the equipment that houses the antennas 256 over a communication link (not shown) , sometimes referred to as front haul, such as the common public radio interface (CPRI) . Therefore, in some implementations, the term apparatus 320 may also refer to network-side nodes that perform processing operations such as, but not limited to, determining the location of the apparatus 310, resource allocation (scheduling) , message generation, and encoding / decoding, and that which are not necessarily part of the equipment that houses the antennas 256 of the apparatus 320. The nodes may also be coupled to other apparatuses 320. In some implementations, the apparatus 320 may actually be a plurality of nodes that are operating together to serve the apparatus 310, such as through the use of coordinated multipoint transmissions, or through the use of ORAN system as described above in the disclosure.
[0181] The processor 260 is configured to perform operations including those related to: preparing a transmission for DL transmission to the apparatus 310, processing an UL transmission received from the apparatus 310, preparing a transmission for backhaul transmission to another apparatus 320, and processing a transmission received over backhaul from another apparatus 320. Processing operations related to preparing a transmission for DL or backhaul transmission may include operations such as, but not limited to, encoding, modulating, precoding (such as MIMO precoding) , transmit beamforming, and generating symbols for transmission. Processing operations related to processing received transmissions in the UL or over backhaul may include operations such as, but not limited to, receive beamforming, demodulating received symbols, and decoding received symbols. The processor 260 may also be configured to perform operations relating to network access (such as initial access) and / or DL synchronization, such as generating the content of synchronization signal blocks (SSBs) , generating the system information, and the like. In some implementations, the processor 260 is further configured to generate an indication of beam direction, such as BAI, which may be scheduled for transmission by the scheduler 253 which will be described below. In some implementations, the processor 260 implements the transmit beamforming and / or receive beamforming based on beam direction information (such as BAI) received from another apparatus 320. The processor 260 is configured to perform other network side processing operations described herein, such as, but not limited to, determining the location of the apparatus 310, determining where to deploy another apparatus 320, and the like. In some implementations, the processor 260 may generate signaling data, to configure one or more parameters of the apparatus 310 and / or one or more parameters of another apparatus 320. Any signaling data generated by the processor 260 is sent by the transmitter 252. In some implementations, the apparatus 320 implements physical layer processing. In some implementations, the apparatus 320 may perform higher layer functions such as those at the medium access control (MAC) or radio link control (RLC) layers in addition to physical layer processing. In the apparatus 320, the scheduler 253 may be coupled to the processor 260 or integrated within the processor 260. In some implementations, the scheduler 253 may be integrated within the apparatus 320 or may be operated separately from the apparatus 320. The scheduler 253 may schedule UL, DL, SL, and / or backhaul transmissions, including issuing scheduling grants and / or configuring scheduling-free (such as “configured grant” ) resources.
[0182] The apparatus 320 may further include a memory 258 that is configured to store instructions for performing the operations described herein. The memory 258 may also store data that is used, generated, or collected by the apparatus 320. For example, the memory 258 can store software instructions or modules configured to implement some or all of the functionalities and / or implementations described herein and that which are executed by the processor 260.
[0183] Although not illustrated, the processor 260 may be implemented as part of the transmitter 252 and / or a part of the receiver 254. Although not illustrated, in some implementations, the processor 260 may implement the scheduler 253 andthe memory 258 may be implemeted as part of the processor 260.
[0184] The processor 260, the scheduler 253, the processing components of the transmitter 252, and the processing components of the receiver 254 may each be implemented by the same or different processors that are configured to execute instructions stored in a memory, such as in the memory 258.
[0185] The apparatus 320 and / or the apparatus 310 may include other components, not shown or described herein for the sake of clarity.
[0186] Note that the term “signaling” , as used herein, may alternatively be referred to as control signaling, control message, control information, or message for simplicity. Signaling between a base station (such as the TRP 170a. 170b, 172) and a UE or sensing device (such as ED 110) , or signaling between a different UE or sensing device (such as between ED 110a and ED 110b) may be carried in physical layer signaling (also called as dynamic signaling) , which is transmitted in a physical layer control channel. For DL, the physical layer signaling may be known as downlink control information (DCI) which is transmitted in a physical downlink control channel (PDCCH) . For UL, the physical layer signaling may be known as uplink control information (UCI) which is transmitted in a physical uplink control channel (PUCCH) . For SL, signaling between different UEs or sensing devices (such as between ED 110a and ED 110b) may be known as SL control information (SCI) which is transmitted in a physical sidelink control channel (PSCCH) . Signaling may be carried in a higher layer (such as higher than physical layer) signaling, which is transmitted in a physical layer data channel, such as in a physical downlink shared channel (PDSCH) for downlink signaling, in a physical uplink shared channel (PUSCH) for uplink signaling, and in a physical sidelink shared channel (PSSCH) for SL signaling. Higher layer signaling may also be called static signaling, or semi-static signaling. The higher layer signaling may include radio resource control (RRC) protocol signaling or media access control -control element (MAC-CE) signaling. Signaling may be included in a combination of physical layer signaling and higher layer signaling.
[0187] It should be noted that in the present disclosure, “information” , when different from “message” , may be carried within a single message, or may be carried in multiple separate messages.
[0188] FIG. 4 illustrates an example apparatus 410 according to an implementation of the present disclosure. The apparatus 410 may be a communication device or an apparatus implemented in a communication device such as the ED 110 or the TRPs 170a, 170b, 172. For example, the apparatus 410 implemented in an ED may be an integrated circuit, which in some instances may be referred to as a chip, a modem, a modem chip, a baseband chip, or a baseband processor. In some implementations, one or more integrated circuits can be packaged into a system-on-chip, a system-in-package, or a multi-chip module. The apparatus 410 can include one or more integrated circuits and other discrete components. In some implementations, the apparatus 410 may be a module within the ED 110, or within the apparatus 310. In some implementations, the apparatus 410 may be a module within one of the TRPs 170a, 170b, 172, or the apparatus 320.
[0189] In an example, the apparatus 410 may include one or more processors 411, and an interface circuit 412. The apparatus 410 may further include a memory 413. The one or more processors 411 are configured to process signals and execute one or more communication protocols. The memory 413 is configured to store at least a part of corresponding computer program instructions and / or data. In an example, the one or more processors 411 execute the computer program instructions stored in the memory 413 to implement related operations (for example, inputting, outputting, receiving, and transmitting) in the method embodiments disclosed herein. In some implementations, the memory 413 being configured to store the corresponding computer program instructions and / or data may mean that the memory 413 is configured to store all of the corresponding computer program instructions and / or data for execution by the one or more processors 411. In some implementations, the memory 413 being configured to store the corresponding computer program instructions and / or data may mean that the memory 413 is configured to store a part of the corresponding computer program instructions and / or data. For example, the part of the corresponding computer program instructions and / or data may include computer program instructions and / or data that need to be currently executed by the one or more processors 411. Thus, the memory 413 may store different parts of computer program instructions and / or data for a plurality times for the one or more processors 411 to perform related operations in the method embodiments disclosed herein. As a communication interface, the interface circuit 412 is configured to implement communication with another component. For example, the interface circuit 412 may communicate a signal with another apparatus or system, such as a radio frequency processing apparatus or another processor. The signal may include or carry information intended as a payload, such as user data, control information, etc. The signal may also include or carry information useful to a receiver, but not necessarily as a payload, such as a pilot signal or reference signal. Communicating the signal may include transmitting the signal to another component or device. Communicating the signal may additionally or alternatively include receiving the signal from another component or device. Transmitting the signal may include outputting the signal to a component or device that is directly or indirectly coupled to the interface circuit 412. Receiving the signal may include inputting or obtaining the signal from a component or device that is directly or indirectly coupled to the interface circuit 412. Optionally, to reduce a load of the one or more processors, a baseband signal processing circuit 414 may be also disposed to implement processing of at least a part of baseband signals, including signal demodulation, modulation, encoding, decoding, or the like.
[0190] The apparatus 410 may be the processor 210 (or 260) within the apparatus 310 (or 320) , in some scenarios, or may be included witin the processor 210 (or 260) within the apparatus 310 (or 320) in some scenarios. The apparatus 410 may be a baseband chip or may include a baseband chip. In some implementations, the apparatus 410 may be independently packaged into a chip. In some implementations, the apparatus 310 (or 320) includes different types of chips. The apparatus 410 may be packaged into a processor chip (for example, an SoC chip or an SIP chip) with the different types of chips. In some implementations, the apparatus 410 may be packaged into a chip with some or all of circuits of a radio frequency processing system that may further be included in the apparatus 310 (or 320) .
[0191] FIG. 5 illustrates example apparatus 510 according to an implementation of the present disclosure. The apparatus 510 may include corresponding modules or units configured to implement methods and / or implementations described herein. In some implementations, the apparatus 510 includes a processing unit 512 and a communication unit 513. Optionally, the apparatus 510 may further include a storage unit 511 configured to store apparatus program code (or instructions) and / or data.
[0192] The apparatus 510 may be an ED side apparatus, for example, an ED or a module in an ED, or a circuit or a chip responsible for a communication function in an ED. In some implementations, apparatus 510 may be the apparatus 310. The processing unit 512 may be the processor 210. The communication unit 513 may comprise a receiving unit and / or a transmitting unit. The receiving unit and / or the transmitting unit may be the transmitter 201 and / or the receiver 203 respectively. The storage unit 511 may be the memory 208.
[0193] The apparatus 510 may be a base station side apparatus, for example, a base station or a module in a base station, or a circuit or a chip responsible for a communication function in a base station. In some implementations, apparatus 510 may be apparatus 320. The processing unit 512 may be the processor 260 (the scheduler 253 may also be included) . The communication unit 513 may comprise a receiving unit and / or a transmitting unit. The receiving unit and / or the transmitting unit may be the transmitter 252 and / or the receiver 254 respectively. The storage unit 511 may be the memory 258.
[0194] In some implementations, when the apparatus 510 is an ED 110 or a module in an ED 110, a function of the apparatus 510 may be implemented by one or more processors. Specifically, the processor may include a modem chip, or a system on chip (SoC) chip or an SIP chip that includes a modem core. A function of the communication unit 513 may be implemented by a transceiver circuit.
[0195] In some implementations, when the apparatus 510 is a circuit or a chip that is responsible for a communication function in an ED 110, -such as a modem chip, a system on chip (SoC) chip or an SIP chip that includes a modem core -a function of the processing unit 512 may be implemented by a circuit system within the chip which includes one or more processors. A function of the communication unit 513 may be implemented by an interface circuit or a data transceiver circuit on the chip.
[0196] It may be understood that the units in the apparatus 510 may be logical or functional. Each function may correspond to one functional unit, or two or more functions may be integrated into a single functional unit. In actual implementation, all or some of the units may be integrated into a single physical entity, or may be distributed across different physical entities. In addition, the functional units may be implemented in the form of hardware, software, or a combination of hardware and software. Whether a function is implemented in the form of hardware or software depends on particular applications and design constraint conditions of the technical solutions. A person skilled in the art may use different methods to implement the described functions for specific applications, but it should not be considered that the implementation goes beyond the scope of present disclosure.
[0197] In an example, a functional unit in any one of the apparatuses may be configured as one or more integrated circuits for implementing the methods disclosed herein, for example, as one or more application-specific integrated circuits (application-specific integrated circuits, ASICs) , one or more central processing units (CPUs) , one or more microprocessors or microprocessor units (MPUs) , one or more microcontrollers or microcontroller units (MCUs) , one or more digital signal processors (DSPs) , one or more field programmable gate arrays (FPGAs) , or a combination of these.
[0198] In an example, the storage unit 511 may include a random access memory, a flash memory, a read-only memory, a programmable read-only memory, an electrically erasable programmable memory, and / or a register.
[0199] A processor may be referred to as a processor system, an application processor, a baseband processor, a processor circuit, or a processor core. The processor may include one or a combination of one or more central processing units (CPUs) , one or more digital signal processors (DSPs) , one or more microprocessors (microprocessor units, MPUs) , one or more microcontrollers (microcontroller units, MCUs) , one or more graphics processing units (GPUs) , one or more field programmable gate arrays (FPGAs) , one or more artificial intelligence processors (AI processors) , or one or more neural network processing units (NPUs) .
[0200] Memory or a storage unit may include one or more of the following storage media: a random access memory (RAM) , a static random access memory (static RAM, SRAM) , a dynamic random access memory (dynamic RAM, DRAM) , a phase-change memory (PCM) , a resistive random access memory (resistive RAM, ReRAM) , a magnetoresistive random access memory (magnetoresistive RAM, MRAM) , a ferroelectric random access memory (ferroelectric RAM, FRAM) , a cache, a register, a read-only memory (ROM) , a flash memory (flash memory) , an erasable programmable read-only memory (erasable programmable ROM, EPROM) , a hard disk, and the like. In an example, computer program instructions used to execute embodiments may be stored in a non-volatile memory, for example, at least a part of a memory or storage unit (for example, one or more of a ROM, a flash memory, an EPROM, or a hard disk) . When a terminal runs, a part or all of corresponding computer program instructions may be loaded to a memory that has a higher transmission speed with the processor, for example, at least a part of a memory or a storage unit (for example, one or more of a RAM, an SRAM, a DRAM, a PCM, a RERAM, an MRAM, a FRAM, a cache, or a register) , so that the processor executes the computer program instructions to perform the steps in the method embodiments disclosed herein. LASSO
[0201] Least absolute shrinkage and selection operator (LASSO) is a method used for sparse representation . Specifically, given a dictionary Ψ and a data sample h, LASSO identifies a sparse representation of h within the column space of Ψ, or, mathematically, it solves the following optimization problem: where ||·||L is the L-norm of a vector. LASSO’s optimization balances a least-squares error term with a sparsity-inducing term α||s||1, controlled by the parameter α. This approach finds the sparsest representation of h that best approximates it within the dictionary space.
[0202] Various implementations exist for solving this optimization problem, including techniques such as matching pursuit, iterative soft-thresholding, and other efficient algorithms for sparse approximation. Subspace Representation
[0203] One approach to processing the vast 6G MIMO channel space is by mapping it to an equivalent subspace, rather than directly handling the original space. This approach involves the following steps: · Projection into the Subspace: A subspace projection of the channel space is determined using various methods, aiming to compress the data into an equivalent reduced-dimensional subspace. For instance, a linear projection can be learned through principal component analysis (PCA) . · Projection back to the Original Dimension: A projection from the subspace back to the original high-dimensional channel space is established. Like the subspace projection, this mapping can also be achieved through a linear projection learned via PCA. · Equivalent Subspace Processing: Once the data is mapped to the equivalent subspace, the scale of data processing is significantly reduced, e.g., decreasing from tens of millions to a few thousand or even smaller scales. This may not only improve processing efficiency but may also lower the computational complexity required.
[0204] Mathematically, the equivalent subspace ensures that any transformation performed in the subspace can be equivalently applied in the original high-dimensional space, allowing efficient yet accurate representation and processing of channel data.
[0205] Prior solutions in wireless communications have introduced methods for constructing and deploying sparsity-based models to manage high-dimensional channel data. One common approach is to use the Least Absolute Shrinkage and Selection Operator (LASSO) algorithm, which projects channel data into a sparse domain by finding a sparse representation in the dictionary matrix (Ψ) . This approach allows for data compression, cleaning, and efficient transmission by retaining only the most critical features, thereby reducing overall data dimensionality.
[0206] While these sparsity-based techniques have proven effective for data storage and transmission, they often rely on a large dictionary matrix (Ψ) whose dimensionality is directly related to the full size of the channel data. As a result, running LASSO within this high-dimensional space presents significant computational challenges, especially in real-time applications. The vast size of the dictionary matrix introduces high latency and computational complexity, making it difficult to achieve timely and efficient processing for large-scale datasets typical in next-generation networks.
[0207] Although sparsity-based models have reduced the resource demands associated with high-dimensional data, they come with limitations that hinder their efficiency, particularly in dynamic and high-mobility wireless environments: ● Excessive Computational Burden Due to High-Dimensional Dictionary Matrix (Ψ) : The primary limitation in the prior art is the reliance on a large dictionary matrix Ψ with dimensions corresponding to the full size of the channel data. Performing LASSO on this matrix in its original high-dimensional space is computationally intensive and often results in substantial delays. This high complexity arises from the need to calculate sparse representations across a vast number of basis vectors, which is neither scalable nor practical for real-time processing in 6G and beyond. ● High Latency in Sparse Approximation: Because of the dimensionality of Ψ, the time required to compute the sparse representation using LASSO or similar algorithms is significantly prolonged. This latency issue is particularly detrimental in environments where channel data needs to be processed quickly, such as in high-speed user scenarios or in networks with rapidly fluctuating channel conditions. ● Substantial Estimation Overhead for Full Channel Data: Existing solutions often require estimating the full channel data across all antennas and frequency bins, which contributes to resource exhaustion and estimation overhead. This process is not only time-consuming but also resource-intensive, straining the network's capacity to handle multiple simultaneous connections and high data throughput demands. · Limited Flexibility in Dynamic Environments: The current models are less adaptable in dynamic or high-mobility environments, where channel characteristics vary rapidly. Without efficient dimensionality reduction, the models are forced to process and estimate channel data at its full scale, making it challenging to maintain performance when conditions change frequently.
[0208] These limitations underscore the need for innovative solutions that can reduce the dimensionality of the dictionary matrix Ψ prior to performing sparse approximation. By addressing the size of Ψ directly, aspects of the present disclosure may decrease the computational complexity and latency associated with running LASSO in the original high-dimensional space, thereby enabling more efficient and timely processing of channel data in dynamic wireless environments.
[0209] Some aspects of the present disclosure may address one or more of the following technical problems within the domain of wireless communication systems, particularly those deploying channel state information (CSI) compression and sparse representation methods: 1. High Dimensionality of Channel Data One of the primary challenges in wireless communications, especially in 6G and beyond, is the high dimensionality of channel data generated by multi-antenna (MIMO) systems. Processing, storing, and transmitting this high-dimensional data can strain system resources and reduce network efficiency. Some aspects of the present disclosure may address this by implementing dimension reduction techniques, such as SVD and QR decomposition, which allow for effective data compression without loss of essential information. 2. Efficient Sparse Representation with Reduced Computational Complexity Traditional sparse representation techniques, such as LASSO, often involve high computational complexity when applied to large channel datasets, leading to latency and inefficiency. Some aspects of the present disclosure may streamline the sparse representation process by introducing projection matrices (from SVD or QR decompositions) that transform data into lower-dimensional subspaces before applying LASSO, significantly reducing computational overhead. 3. Dynamic Update and Maintenance of Codebook Dictionaries in Real-Time Environments In dynamic wireless environments, channel conditions fluctuate, which requires continuous updates to the codebook dictionary to maintain an accurate representation of the channel data. Some aspects of the present disclosure may address the challenge of real-time dictionary updates, enabling codebook dictionaries to be efficiently adjusted and disseminated across network nodes without causing excessive overhead or latency. 4. Interoperability Between user equipment (UE) and Base Stations with Varying Computational Capabilities Different user equipment (UE) may have varying computational capabilities, making it challenging to standardize compression methods across devices. Some aspects of the present disclosure may resolve this problem by providing UEs with the option to selectively request updated dictionaries and projection matrices from the base station, allowing UEs to use compressed CSI data effectively, even if computational power is limited. 5. Reduction of Bandwidth Requirements for CSI Feedback Continuous CSI feedback from UE to base stations can consume significant bandwidth. Some aspects of the present disclosure may reduce the need for high-bandwidth feedback by enabling UEs to transmit compressed and sparsified CSI data, allowing the network to allocate bandwidth more efficiently while maintaining channel accuracy. 6. Efficient CSI Recovery and Resource Allocation at the Base Station The base station must decode sparse CSI data from UEs with high accuracy to optimize resource allocation, beamforming, and channel prediction. Some aspects of the present disclosure may include mechanisms for efficient CSI recovery at the base station, leveraging sparse representations to ensure accurate reconstruction of channel conditions while using minimal processing resources.
[0210] By addressing one or more of these technical problems, some aspects of the present disclosure may enhance system performance, reduce latency, and optimize data handling within high-demand wireless communication environments.
[0211] Aspects of the present disclosure relate to a novel approach for deploying sparsity-based models specifically designed for wireless communications. The present disclosure describes example implementations with a focus on channel state information (CSI) compression as a representative communication task, demonstrating how these models can efficiently manage high-dimensional data. Aspects of the present disclosure leverage the linear property of sparse approximation while incorporating dimension reduction techniques to address computational complexity and potentially minimize model transmission costs.
[0212] To achieve this, aspects of the present disclosure may utilize subspace projection and sparse approximation techniques that allow for effective data compression while retaining the essential features of the channel data. By reducing the data dimensionality, the disclosed methods may allow the sparse representation to remain efficient for downstream processing, with significantly reduced computational demands for tasks such as channel feedback and beamforming.
[0213] It is noted that several terms used in the present disclosure have equivalents that will be understood by a person of skill in the art. For example, a skilled person will understand that the terms “compress” and “compressed” may be considered to be equivalent to “encode” and “encoded” , respectively. Similarly, a skilled person will understand that the term “decompress” and “uncompressed” may be considered to be equivalent to “decode” and “decoded” , respectively. Moreover, a skilled person will understand that the term “recover” may be considered to be equivalent to “reconstruct” . Subspace Equivalence
[0214] In a sparse approximation framework, the objective is to represent a data sample h as a vector in the subspace of Ψ, that is, h=Ψs, where Ψ is the codebook dictionary matrix, and s is the sparse coefficient vector. To facilitate efficient processing, one can pre-multiply both sides of the equation by a carefully chosen matrix A, preserving the equality. From solving the optimization problem: to
[0215] If A is chosen to be a unitary matrix such that AHA=I, the transformation preserves the solution equivalence. One of the key innovations of the present disclosure, however, is selecting A so that it also serves as a dimension reduction matrix, thereby reducing the dimension of h.
[0216] To achieve this, in some embodiments of the present disclosure A may be chosen such that its rows form an orthonormal basis for the column space of Ψ. This ensures that AΨ spans the same column space as Ψ, enabling the sparse approximation to operate within a compressed subspace. In this way, the dimensionality of Ψ is effectively reduced, enabling low-complexity computations and transmission in uplink that maintain equivalency with the original high-dimensional problem.
[0217] This choice of matrix A reduces the computational burden without sacrificing accuracy, allowing transformations in the subspace to be equivalently reflected in the original space at a significantly lower computational cost. Sparse Sampling
[0218] An additional component of some embodiments of the present disclosure is the use of sparse sampling to minimize resource usage when estimating h. This approach involves zeroing out specific columns of A, thereby eliminating the need to estimate the elements of h associated with these columns. Unlike the subspace equivalence transformation, this selective sampling approach may yield a slightly different solution for s due to the reduced data; however, it significantly decreases the estimation overhead and can be strategically implemented to maximize efficiency.
[0219] The choice of which elements to sample depends on the specific application needs and can be optimized for various scenarios within the wireless communication framework.
[0220] Some embodiments of the present disclosure are designed for advanced wireless communication systems, particularly applicable to 6G and beyond network architectures. For example, in some embodiments, the present disclosure provides a system architecture that revolves around a two-sided communication model that optimizes CSI feedback and compression, featuring dynamic management of a codebook dictionary and basis matrix for dimensionality reduction. In such embodiments, the system may consist of base stations (BS) , user equipment (UE) , core network servers, and, where applicable, edge computing nodes, all operating within a distributed and collaborative framework. This structure may enable efficient data compression, sparse representation, and adaptive communication capabilities across various application scenarios. Example System Components
[0221] The following provides a non-limiting example of system components that may be used in some embodiments of the present disclosure: 1. Base station (BS) : o Function: The BS manages core tasks of the present disclosure, including codebook dictionary initialization, basis matrix distribution, CSI compression, and dictionary updates. The BS distributes the initial basis matrix or codebook dictionary to UEs and transmits CSI reference signals (CSI-RS) for channel estimation. o Structure: Equipped with multiple antennas for MIMO processing, a processor for signal processing, and storage units for dictionary storage and management, the BS includes transceivers to communicate with UEs and core networks. It is also linked to core network servers and, in some implementations, edge computing resources for optimized data processing. o Protocol Details: The BS periodically broadcasts System Information Blocks (SIBs) that include codebook dictionary specifications and configuration details. Additionally, it responds to UEs’ RRCConnectionRequest messages and distributes updated basis matrices as part of the RRCConnectionSetup messages. 2. User equipment (UE) : o Function: The UE performs channel state estimation based on CSI-RS received from the BS and leverages the pre- distributed basis matrix to reduce dimensionality and compress the CSI data before transmission. It executes sparse approximation algorithms (e.g., LASSO) to create a compressed sparse representation of the CSI data. o Structure: The UE comprises antennas, transceivers, processors for CSI estimation and compression, and memory for storing received basis matrices and codebooks. It may also store and compute on partial basis matrices as determined by BS configurations. o Protocol Details: The UE initiates the RRCConnectionRequest for connection setup, indicating its capability for sparse CSI compression. Upon successful setup, it periodically receives updated basis matrix details from the BS, performs compression, and sends sparse representation data back to the BS for further processing. 3. Core Network Server: o Function: Core network servers support communication and coordination between base stations, handling data routing and network configuration updates. They may also manage cross-base station dictionary updates to ensure consistency and interoperability across the network. o Structure: Consists of high-performance processors, storage units, and data management systems designed to facilitate CSI dictionary synchronization and data compression processes. o Protocol Details: Core network servers assist in synchronizing updated codebooks across different base stations and managing handover scenarios where CSI information must remain consistent for seamless communication between cells. Example System Workflow
[0222] The following provides a non-limiting example of a system workflow that may be used in some embodiments of the present disclosure: 1. Initialization and Basis Matrix Distribution: o The BS initializes the system by calculating an optimized basis matrix through SVD or QR decomposition of a pre- existing dictionary and then broadcasts this matrix information via System Information Blocks (SIBs) . This informs UEs of the BS’s sparse compression capability, preparing them for further CSI processing tasks. 2. Connection Setup and Model Sharing: o When a UE initiates communication, it sends an RRCConnectionRequest, indicating its capability to perform sparse CSI compression and whether it requires the basis matrix. The BS responds with an RRCConnectionSetup message, providing downlink resources to transmit the matrix data if necessary. This step ensures that the UE has the required basis information for effective CSI compression. 3. Channel State Estimation and Compression at the UE: o The BS periodically transmits CSI-RS, which the UE receives to estimate the current channel state. Using the basis matrix, the UE computes a projection in the compressed subspace, then performs sparse approximation to obtain a reduced CSI representation. The UE transmits this sparse data back to the BS. 4. CSI Data Processing and Storage at the BS: o The BS receives the compressed CSI data from the UE, verifies its quality, and stores the sparse representation. If the data quality is insufficient, the BS may request additional resources or initiate a dictionary update process. Otherwise, it uses the CSI data for ongoing tasks like beamforming or resource allocation. 5. Dictionary Update and Synchronization: o The BS periodically updates the dictionary based on accumulated CSI data, adjusting the basis matrix if significant channel environment changes are detected. Updated dictionaries are shared with connected UEs and, if necessary, with core network servers to maintain consistency across the network. Example Application Scenarios
[0223] The following provides a non-limiting examples of application scenario according to some embodiments of the presentdisclosure:1. Urban Cellular Networks with High Density:o In dense urban environments, the system’s adaptive basis matrix and efficient compression protocols are particularly useful for managing frequent channel updates and interference. The distributed sparse compression reduces the overhead, allowing the network to maintain performance in highly congested areas.2. High-Speed Rail and Automotive Networks:o Aspects of the present disclosure may be ideal for high-mobility scenarios like trains or vehicles, where UEs frequently experience dynamic channel changes. By reducing dimensionality and leveraging fast basis updates, the system minimizes delay and computational burden, supporting reliable high-speed communication.3. Industrial IoT and Smart Factory Networks:o In industrial networks, where machines and devices communicate continuously, this system architecture supports efficient data compression and reliable connectivity. The edge node and BS collaboration allow real-time adjustments to network resources and adaptable CSI handling within confined factory environments.
[0224] This flexible and adaptable architecture may allow embodiments of the present disclosure to support a broad range of wireless network scenarios and specialized applications, establishing it as a versatile solution for next-generation communication systems. Example Products Involved in Aspects of the Present Disclosure
[0225] Some embodiments of the present disclosure pertain to advanced wireless communication products and systems, particularly targeting infrastructure and device components in 6G networks and beyond. Non-limiting example of the products that may be involved in such embodiments include: o Base stations (BS) with Enhanced CSI Processing and Compression Capabilities: Base stations leveraging the two-sided CSI feedback model with adaptive basis matrix management for efficient data compression and transmission, according to the present disclosure. In some implementations, these base stations may be equipped with algorithms for SVD / QR decomposition, dictionary management, and dynamic sparse encoding techniques. o User equipment (UE) Enabled with Sparse Compression Models: UEs (such as smartphones, IoT devices, and vehicular communication modules) that integrate mechanisms for CSI estimation, subspace projection, and sparse compression using pre-shared basis matrices. In some implementations, the UEs may process incoming CSI reference signals, compress channel data, and use sparse representation to report channel states efficiently. o Core Network Servers for Cross-Network Synchronization and Resource Management: Core network servers coordinating multi-cell network architectures, including managing distributed dictionaries, performing inter-cell handovers, and handling cross-network compatibility with adaptive codebook dictionaries and model-based updates. Possible Product Forms
[0226] Aspects of the present disclosure may provide products for mobile operators, device manufacturers, and industrial IoT solution providers. Possible product forms may include: o Base Station and Network Equipment Modules: Saleable as firmware or hardware modules designed for integration into existing base station architectures. These modules may contain specialized algorithms for CSI processing, dictionary management, and real-time compression for optimizing 6G network performance. o Software Licenses for Embedded UEs and IoT Devices: Software licenses enabling sparse compression and CSI feedback mechanisms can be embedded into user devices, such as mobile phones, industrial IoT sensors, and connected vehicle systems. These licenses may provide device manufacturers with software libraries for performing sparse data representations compatible with network architectures. o Edge Node Packages for Private Networks and High-Density Applications: A complete package including edge computing hardware, pre-installed software, and service agreements to deploy edge nodes that provide local subspace adaptation and CSI data processing for high-density environments or private enterprise networks. o Cloud-Based Network Management Solutions: Software solutions for core network servers that perform inter-cell synchronization, dictionary updates, and network resource management for adaptive dictionary models in multi-cell environments. These solutions are aimed at network operators seeking enhanced CSI management capabilities in 6G networks. Example Embodiment 1 of the Present Disclosure
[0227] This implementation leverages singular-value decomposition (SVD) for dimension reduction, reducing computational complexity and improving efficiency in processing channel state information (CSI) . Specifically, let the thin SVD of the codebook dictionary Ψ be represented as Ψ=USV*, where n is the channel dimension, and r is the rank of Ψ. The columns of U form an orthonormal basis for the column space of Ψ. This implementation utilizes U* as a core element of the pre-processing matrix A described previously, enabling the system to reduce dimensionality effectively before sparse approximation. Furthermore, selecting random columns of U* to be zeroed out allows for optimized resource allocation, mapping these columns to certain resources not being probed for channel estimation (e.g., certain frequency bands, or certain transmit antennas) . The reduced-dimension codebook dictionary may be denoted by Ψ′=SV*.
[0228] The following steps outline a non-limiting example implementation in detail. Step 1: Pre-Connection
[0229] During this step, the base-station (BS) periodically broadcasts information about the codebook dictionary Ψ it utilizes in System Information Blocks (SIBs) . The BS transmits details such as the dimensions of the matrices U and Ψ′, informing the user equipments (UEs) about the sparsity-based CSI compression scheme. This information enables the UEs to allocate memory, assess processing complexity, and interpret additional specifications based on the matrices’ dimensions. The UEs receive, parse and store these specifications, preparing to receive the matrices once a connection with the BS is established. Step 2: RRC Connection and Initial Model Sharing
[0230] During this step, the UE initiates a connection with the BS, requesting the CSI model components, specifically U and Ψ′.The following actions take place: -RRC Connection Request: When connecting to the BS, the UE sends an RRCConnectionRequest Message containing all standard information and an indication of whether it can compute the BS’s indicated CSI compression. If the UE lacks this capability, the BS may fall back to a standard communication protocol requiring less computation on the UE side. The UE also specifies whether it requires BS to transmit the matrices or already possess them (e.g., from a previous connection) . -Fields in RRCConnectionRequest: -Response from the BS: Upon receiving the `RRCConnectionRequest` message, the BS initiates the standard RRC Connection Setup. Based on `BasisRequest` and `DictionaryRequest`, it allocates downlink resources for transmission of the compression matrices and responds with the `RRCConnectionSetup` message, including information on downlink resources for transmission of U and Ψ′.
[0231] The BS then transmits the requested matrices (U and / or Ψ′) to the UE, which parses and stores these matrices for further CSI processing.
[0232] FIG. 6 illustrates an example procedure for RRC connection and initial model sharing in a communication network, according to some implementations of Step 2 of Example Embodiment 1 of the present disclosure. Step 3: CSI Estimation
[0233] Periodically, the BS transmits a CSI reference signal (CSI-RS) to the connected UEs. This CSI-RS may be transmitted by a subset of the transmit antennas, and may be transmitted only in some frequency bands. In this implementation, the CSI-RS is transmitted over randomly selected transmit antennas and frequency bands at each CSI estimation step. The UE utilizes the received CSI-RS to estimate the channel h, possibly zero-padding the elements that are not probed. Techniques to estimate the CSI based on the CSI-RS are not discussed in detail in the present disclosure, but the UE may utilize known methods such as least squares, minimum mean squared error, machine learning methods, or it may utilize proprietary methods. Step 4: CSI Compression
[0234] After channel estimation, the UE utilizes the matrix U to project h into the subspace of Ψ , obtaining a reduced-dimensional representation h′= U*h. The UE then performs sparse approximation by solving the optimization problem:
[0235] Various optimization algorithms, such as matching pursuit, iterative soft-shrinkage methods, coordinate descent, may be applied to solve for the optimal sparse vector s*.
[0236] FIG. 7 illustrates an example procedure for CSI estimation and compression at a user device in a communication network, according to some implementations of Steps 3 and 4 of Example Embodiment 1 of the present disclosure. Step 5: CSI Report
[0237] Following sparse representation, the UE may verify statistics of s*, (e.g., sparsity and distribution) , to assess the quality of channel estimation and compression. If the UE identifies anomalies such as an outlier solution or inadequate compression quality, it sends a `CompressionFailure` signal to the BS. Otherwise, the UE requests uplink resources from the BS, with resource quantity depending on the sparsity level of s*and UE’s sparse vector representation method. The UE then transmits the location of non-zero values and their positions within s*.
[0238] Upon receiving either `CompressionFailure` message or the uplink resource request, the BS has two options: -In case of failure: the BS can transmit a new CSI-RS across different resource elements, increase the resource allocation for CSI estimation, or initiate a dictionary update process for Ψ, thereby updating U and Ψ′. The procedure is exemplified by way of a non-limiting example in Step 7 described below. -In case of success, the BS allocates the requested uplink resources and responds with the resource allocation information, allowing the UE to transmit the sparse vector s* in the allocated uplink resources.
[0239] FIG. 8 illustrates an example procedure for CSI reporting in a communication network, according to some implementations of Step 5 of Example Embodiment 1 of the present disclosure. Step 6: Base Station Processing
[0240] In case of success in Step 5, the BS receives the sparse vector s* and utilizes it to reconstruct the CSI The BS then can utilize the CSI reconstruction in downlink transmissions, for example, utilizing it to efficiently schedule users and allocate downlink resources, and to design a precoder for multi-user MIMO communication. Step 7: Codebook Dictionary Update
[0241] When the BS decides to update its codebook dictionary, it can initiate a data collection protocol, increasing CSI-RS transmission frequency and allocating resources for UEs to report the full channel data h without compression. The BS utilizes this data to possibly update the (original) dictionary Ψ , which subsequently updates the basis matrix U and the dictionary Ψ′. The BS then notifies all the connected UEs of the dictionary update and repeats the transmission described in Step 2.
[0242] If the dictionary update is minor (it is possible that the update to U and Ψ′is small) , the BS may utilize a differential update method, transmitting only modified columns or specific value changes. This approach minimizes overhead and ensures UEs remain synchronized with the latest dictionary updates efficiently. Example Embodiment 2 of the Present Disclosure
[0243] Example Embodiment 2 builds on Example Embodiment 1 but utilizes QR decomposition rather than SVD for dimension reduction. Specifically, let Ψ=QR, where Q is an orthogonal matrix and R is an upper triangle matrix. In this case, the BS transmits both Q and R to the UE.
[0244] In Step 3, instead of zeroing out columns of U as in Example Embodiment 1, this embodiment zeros the columns of Q, focusing on compressing CSI data to align with the structure provided by Q.
[0245] In Step 4, the UE uses Q to project h into a reduced subspace, yielding h′=Q*h. The UE then performs sparse approximation by solving the optimization problem:
[0246] The UE may leverage optimization methods such as matching pursuit or iterative soft-shrinkage to find the sparse vector s*, which is then used in subsequent reporting and processing steps. This QR decomposition approach offers a flexible and computationally efficient alternative to SVD, with potential advantages in scenarios where real-time processing and low-latency are prioritized. Example Embodiment 3 of the Present Disclosure
[0247] Example Embodiment 3 modifies Example Embodiments 1 and 2 by fixing the resource elements where the CSI-RS is transmitted rather than dynamically selecting them at each estimation step.
[0248] In this approach, the BS transmits only the columns of U (Q) that correspond to the predetermined resource elements for CSI-RS transmission, with other elements zeroed. This change reduces overhead by allowing UEs to focus on a known, fixed subset of channels or resources for estimation.
[0249] Example Embodiment 3 may be ideal for scenarios where the channel characteristics or resource configurations remain stable, such as fixed-location base stations or controlled environments. The UE leverages the fixed resources to perform efficient CSI estimation, reducing the need for continuous updates to the transmitted basis matrix. Example Embodiment 4 of the Present Disclosure
[0250] Example Embodiment 4 may further enhance efficiency by periodically transmitting only selected columns of the basis matrix (U or Q) i to the connected UEs.
[0251] In dynamic environments, only the columns associated with current CSI-RS resource elements are sent at each interval, enabling the BS to periodically refresh the UE’s matrix without requiring the entire basis matrix. This may reduce the initial communication overhead and minimize UE memory requirements by limiting storage to a few selected columns.
[0252] Instead of randomly choosing resource elements for CSI-RS in each transmission, the BS may employ optimized algorithms to determine the best probing locations. In cases where these locations are stable over multiple transmissions, the BS can use a differential approach for updates. For example, if one column is removed and a new one added, the BS may transmit only the indices of the changes, streamlining the update process.
[0253] Example Embodiment 4 may be particularly suitable for scenarios involving brief, high-efficiency communications, such as burst transmissions in high-speed environments, where minimizing UE memory load and initial configuration time is critical. Example Embodiment 5 of the Present Disclosure
[0254] Example Embodiment 5 incorporates user-specific customization into the basis matrix and codebook dictionary, tailored to geographic or environmental factors.
[0255] The BS clusters different geographic areas and associates a distinct basis matrix and dictionary with each area based on local channel characteristics, user density, or interference patterns. When a UE connects within a specific area, the BS provides the corresponding matrix specific to that region.
[0256] This area-specific basis may be a sub-dictionary of a larger ( “reference” or “global” ) dictionary. For example, a subset of columns of Ψ from Embodiment 1 may be allocated to a geographical area, generating Ψ1, and another subset (which may overlap with the first subset) may be allocated to a different area, generating Ψ2. The BS then utilizes Ψ1 in any previous embodiment when connecting to a UE in the area associated with this sub-dictionary, and Ψ2 when connecting to UEs in the second area.
[0257] This approach allows for dynamic adaptability to environmental or spatial factors, such as urban vs. rural settings, which may have different multipath and fading characteristics. By customizing the matrices, the BS may be able to ensure that each UE operates with the most relevant basis for its location, potentially enhancing accuracy in CSI compression and estimation.
[0258] Since each cluster uses a tailored codebook dictionary, the BS may be able to manage resources more effectively, reducing the need for UEs in diverse regions to adopt a generic dictionary that might not suit their channel conditions. Example Embodiment 5 may be particularly useful in heterogeneous network deployments where different areas require unique channel handling strategies. Example Embodiment 6 of the Present Disclosure
[0259] The base station (BS) continuously monitors environmental indicators such as user density, interference levels, and user mobility. When changes in these parameters exceed predefined thresholds, the BS initiates a basis matrix adaptation protocol. An example procedure for Triggering and Distributing Updates may be as follows: Step 1: Environmental Assessment and Threshold Detection
[0260] The BS periodically analyzes environmental data to detect significant variations. For example, if user movement data indicates a shift in spatial correlation, or if interference levels surpass a threshold, the BS recognizes the need for a basis update. Step 2: Basis Matrix Recalculation and Encoding
[0261] The BS recalculates the matrices U, Ψ′or Q, R (using SVD or QR decomposition) to align with the new conditions. If recalculated, the BS encodes the differential update information. Step 3: Differential Basis Update Messaging
[0262] A message, `UpdateNotification`, is sent to the connected UEs. This message indicates the reason for the update, the type of the update, e.g., whether it is a full update or a differential update, and the update itself, which may be the full matrices, or only rows / columns that changed. Step 4: UE Acknowledgment
[0263] UEs acknowledge the receipt of the update with a UpdateAck message, allowing the BS to track UEs that have successfully applied the new compression matrices.
[0264] By dynamically adapting the compression matrices to the environment, this protocol may maintain high-quality CSI compression while reducing network congestion from excessive data transmission.
[0265] FIG. 9 illustrates an example procedure for basis matrix update messaging and acknowledgement in a communication network, according to some implementations of Steps 3 and 4 of Example Embodiment 6 of the present disclosure. Example Embodiment 7 of the Present Disclosure
[0266] During the initial connection, the BS evaluates each UE’s processing capability, storing this information in a UE Capability Profile. The BS then customizes the basis matrix based on each UE’s profile to ensure compatibility with resource-constrained devices. An example procedure for Basis Customization and Transmission may be as follows: Step 1: UE Capability Exchange
[0267] Upon connection, each UE sends a CapabilityReport message detailing its memory, computational limits, and supported operations. Step 2: Reduced Basis Matrix Generation
[0268] The BS generates a reduced basis matrix (RBM) by selecting only the essential basis vectors from U or Q. For instance, for lower-complexity devices, fewer columns of U are included. Step 3: RBM Transmission and Acknowledgment
[0269] The BS transmits the customized RBM to the UE with a ReducedBasisMatrix message, including: -BasisMatrixType field (e.g., "Reduced SVD" or "Reduced QR" ) . -MatrixSize field indicating reduced dimensionality. Step 4: UE Confirmation
[0270] UEs respond with ReducedBasisAck to confirm successful reception and readiness to apply the RBM.
[0271] FIG. 10 illustrates an example procedure for basis matrix customization and transmission in a communication network, according to some implementations of Steps 1-4 of Example Embodiment 7 of the present disclosure. Step 5: On-Demand Expansion Protocol
[0272] If a low-complexity UE’s power resources increase (e.g., during charging) , the UE can send a ResourceUpgradeRequest to the BS. The BS can then transmit additional basis components, expanding the basis matrix dynamically.
[0273] FIG. 11 illustrates an example procedure for on-demand basis matrix expansion in a communication network, according to some implementations of Step 5 of Example Embodiment 7 of the present disclosure.
[0274] Example Embodiment 7 may reduce computational requirements on resource-limited devices while ensuring robust CSI compression, adaptable to fluctuating UE resources. Example Embodiment 8 of the Present Disclosure
[0275] The BS maintains a hierarchical codebook structure, updating dictionaries across network layers (macro, micro, and pico cells) based on current traffic and mobility patterns. An example of procedural steps for Layered Codebook Management may be as follows: Step 1: Codebook Hierarchy Creation
[0276] The BS or core network constructs separate codebook dictionaries for each network layer, assigning unique identifiers to each (e.g., MacroLayerDict, MicroLayerDict) . Step 2: Inter-Layer Dictionary Synchronization
[0277] When a UE transitions from one layer to another, the BS triggers a LayerTransitionRequest that includes: -CurrentLayerDictID field, identifying the dictionary in use. -TargetLayerDictID field, identifying the new dictionary. Step 3: Layered Dictionary Transition
[0278] If a UE enters a new layer, the BS transmits an updated codebook dictionary with a DictionarySync message, detailing any differences between the current and target dictionaries. Step 4: UE Confirmation
[0279] The UE confirms the dictionary transition with a LayerSyncAck message, allowing the BS to ensure successful inter-layer synchronization.
[0280] FIG. 12 illustrates an example procedure for layered dictionary codebook management in a communication network, according to some implementations of Steps 2-4 of Example Embodiment 8 of the present disclosure.
[0281] Multi-layer dictionary synchronization minimizes handover disruptions and ensures that UEs maintain high compression performance across layers, ideal for dense urban and multi-cell environments.
[0282] The following table lists some of the technical innovations and potentially advantageous effects that may be provided by at least some implementations of the present disclosure.
[0283] Each of the innovative points listed in the table above directly addresses one or more of the technical challenges described earlier, such as high-dimensional data processing, network efficiency, and CSI compression quality, while providing specific advantages that distinguish the present disclosure from existing approaches. Additional features, such as secure transmission and environment-adaptive updates, may contribute further advantages by enabling the system to be both robust and adaptable to varying conditions and requirements across different wireless communication environments.
[0284] FIG. 13 illustrates a method 1300 performed by an apparatus 310 (e.g., a UE) and an apparatus 320 (e.g., a network device, such as a TRP) , according to some implementations. For example, in some implementations, apparatus 310 shown in FIG. 13 may be similar to the apparatus 310 illustrated in FIG. 3, and apparatus 320 shown in FIG. 13 may be similar to the apparatus 320 illustrated in FIG. 3.
[0285] The example method 1300 is comprised of steps 1302 to 1312. It shall be understood that not all of these steps are needed in the method 1300. As one example, in some implementations, the method 1300 may only include step 1302 and / or step 1304. In other words, one or more of the steps 1302 to 1312 may be optional.
[0286] At step 1302, the apparatus 320 transmits encoder information for sparsity-based compression of information. For example, in some implementations the encoder information may include a basis function operable as a dimension reduction function to reduce a dimension of information at the apparatus 310. In some implementations, the encorder information transmitted at 1302 may also or instead include a reduced-dimension codebook dictionary function that has reduced dimensions relative to a higher-dimension codebook dictionary function.
[0287] In some implementations, the method 1300 may further comprise the apparatus 310 transmitting (and the apparatus 320 receiving) a connection request. In some implementations, the apparatus 320 may transmit the encoder information at step 1302 responsive to receiving the connection request. In some implementations, the connection request may be indicative of at least one of: whether the sparsity-based compression can be performed; whether the basis function is requested; or whether the reduced-dimension codebook dictionary function is requested. In some implementations, the connection request is received via RRC signaling.
[0288] At step 1304, the apparatus 310 receives the encoder information that was transmitted at step 1302.
[0289] At step 1306, the apparatus 310 uses the encoder information to compress information such that the compressed information comprises a sparse representation of the information. For example, as noted above, in some implementations the encoder information that the apparatus 310 receives at step 1304 may include a basis function and a reduced-dimension codebook dictionary function that has reduced dimensions relative to a higher-dimension codebook dictionary function. In such implementations, compressing the information at step 1306 may include using the basis function and the reduced-dimension codebook dictionary function to compress the information at the apparatus 310.
[0290] At step 1308, the apparatus 310 transmits the compressed information comprising the sparse representation of the information.
[0291] At step 1310, the apparatus 320 receives the compressed information.
[0292] At step 1312, the apparatus 1320 decompresses the compressed information to recover uncompressed information. For example, as noted above, in some implementations compressing the information at step 1306 may include using a basis function and a reduced-dimension codebook dictionary function that that has reduced dimensions relative to a higher-dimension codebook dictionary function. In such implementations, decompressing the compressed information at step 1312 may include decompressing the sparse representation of the information to recover uncompressed information using the higher-dimension codebook dictionary function.
[0293] In some implementations, the information compressed at step 1306 includes CSI. For example, in some implementations, the method 1300 may further include the apparatus 320 transmitting (and the apparatus 310 receiving) CSI-RS, and the apparatus 310 utilizing the received CSI-RS to estimate CSI. In such implementations, the apparatus 310 may use the encoder information transmitted at 1302 and received at 1304 to compress the CSI at step 1306. For example, in some implementations the apparatus 310 may use the basis matrix and the reduced-dimension codebook dictionary function included in the encoder information to compress the CSI such that the compressed CSI includes a sparse representation of the CSI. For example, in some implementations, the apparatus 310 may use the basis function to project the CSI into a reduced dimension subspace to obtain a reduced-dimension representation of the CSI, and perform sparse approximation using the reduced-dimension codebook dictionary function and the reduced-dimension representation of the CSI to solve for the sparse representation of the CSI. In such implementations, decompressing the compressed information at step 1312 may include decompressing the sparse representation of the CSI to recover a reconstruction of the CSI using the higher-dimension codebook dictionary function.
[0294] In some implementations, the compressed information that is transmitted in step 1308 and received in step 1310 is transmitted / received on uplink resources. In some implementations, the method 1300 may further comprise the apparatus 320 transmitting (and the apparatus 310 receiving) an uplink resource allocation indicating the uplink resources. In some implementations, the compressed information transmitted in step 1308 and received in step 1310 may be received on an uplink resource indicated in the uplink resource allocation. In some implementations, the apparatus 320 may transmit an uplink resource allocation responsive to the apparatus 320 receiving an uplink resource request from the apparatus 310.
[0295] In some implementations, the method 1300 may further comprise the apparatus 310 assessing the quality of channel estimation and compression based on statistics of the compressed CSI. In such implementations, the apparatus 310 may transmit an uplink resources request in response to determining the quality of channel estimation and compression is acceptable. On the other hand, in some implementations, if the apparatus 310 determines that the quality of channel estimation or compression is not acceptable, the apparatus 310 may transmit (and the apparatus 320 may receive) a signal indicative of a compression failure indicating a compression failure of the CSI. In some implementations, after receiving a signal indicative of a compression failure, the apparatus 320 may take one or more of the following actions: transmit a new CSI-RS across different resource elements; increase the resource allocation for CSI estimation; or initiate a codebook dictionary update process for the higher-dimension codebook dictionary function.
[0296] In some implementations, the basis function and the reduced-dimension codebook dictionary function are derived from the higher-dimension codebook dictionary function.
[0297] In some implementations, the basis function includes a basis matrix, the higher-dimension codebook dictionary function includes a higher-dimension codebook dictionary matrix, and the reduced-dimension codebook dictionary function includes a reduced-dimension codebook dictionary matrix that has reduced dimensions relative to the higher-dimension codebook dictionary matrix.
[0298] In some implementations, the method 1300 may further include transmitting dimension information indicative of: dimensions of the basis matrix; and dimensions of the reduced-dimension codebook dictionary matrix. For example, in some implementations the dimension information may be broadcast in one or more SIBs.
[0299] In some implementations, the higher-dimension codebook dictionary matrix defines a reduced-dimension subspace projection of an information space of the information to be compressed.
[0300] In some implementations, the method 1300 may further include the apparatus 320 determining the basis matrix and the reduced-dimension codebook dictionary matrix through matrix decomposition of the higher-dimension codebook dictionary matrix. For example, in some implementations, the matrix decomposition may be done such that rows of the basis matrix form an orthonormal basis for a column space of the higher-dimension codebook dictionary matrix. In some implementations, the matrix decomposition may include SVD or QR decomposition.
[0301] In some implementations, the matrix decomposition includes SVD according to: Ψ=USV*, and Ψ′=SV*, where: Ψ is the higher-dimension code book dictionary matrix; U is the basis matrix, wherein U is a unitary matrix, where n is the channel dimension, and r is the rank of Ψ; S is a diagonal matrix; V is a unitary matrix, wherein V* is the Hermitian transpose of V; and Ψ′is the reduced-dimension codebook dictionary matrix.
[0302] In such implementations, compressing the CSI at step 1306 may include the apparatus 310 using the matrix U to project h into the subspace of Ψ to obtaining a reduced-dimension representation of the CSI according to: h′= U*h, where: h is the CSI; and h′is the reduced-dimension representation of the CSI.
[0303] In such implementations, compressing the CSI at step 1306 may further include the apparatus 310 performing sparse approximation to solve for the sparse representation of the CSI by solving an optimization problem according to: where: s* is the optimal sparse vector representation of the CSI; and α is a sparsity-inducing parameter.
[0304] In some implementations, the matrix decomposition includes QR decomposition according to: Ψ=QR, and Ψ′=R, where: Ψ is the higher-dimension code book dictionary matrix; Q is the basis matrix, wherein Q is an orthogonal matrix; R is an upper triangular matrix; and Ψ′is the reduced-dimension codebook dictionary matrix.
[0305] In such implementations, compressing the CSI at step 1306 may include the apparatus 310 using the matrix U to project h into the subspace of Ψ to obtaining a reduced-dimension representation of the CSI according to: h′= Q*h, where: h is the CSI; and h′is the reduced-dimension representation of the CSI.
[0306] In such implementations, compressing the CSI at step 1306 may further include the apparatus 310 performing sparse approximation to solve for the sparse representation of the CSI by solving an optimization problem according to: where: s* is the optimal sparse vector representation of the CSI; and α is a sparsity-inducing parameter.
[0307] As noted above, in some implementations the information to be compressed includes CSI. In such implementations, the higher-dimension codebook dictionary matrix may define a reduced-dimension subspace projection of the channel space. For example, in some implementations, the compressed CSI transmitted at 1308 and received at 1310 may include a sparse vector representation of the CSI, and decompressing the compressed information at step 1312 may include decompressing the sparse vector representation of the CSI to recover a reconstruction of the CSI according to: where: is the CSI reconstruction; Ψ is the higher-dimension code book dictionary matrix; and s* is the sparse vector representation of the CSI.
[0308] In some implementations, the apparatus 320 may transmit the CSI-RS using a partial subset of resource elements that the apparatus 320 dynamically selected from a set of resource elements. In some implementations, columns of the basis matrix corresponding to resource elements not used for transmitting the CSI-RS may be zeroed. In some implementations, the set of resource elements may include a set of transmit antennas and a set of frequency bands. In such implementations, the apparatus 320 may dynamically select the partial subset of resource elements by: dynamically selecting a partial subset of transmit antennas from the set of transmit antennas; and dynamically selecting a partial subset of frequency bands from the set of frequency bands. In such implementations, the apparatus 320 may transmit the CSI-RS by the selected subset of transmit antennas in the selected subset of frequency bands.
[0309] In some implementations, the method 1300 may further include the apparatus 320 transmitting (and the apparatus 310 receiving) signaling indicative of the selected subset of resource elements. In some implementations, the signaling indicative of the selected subset of resource elements may include DCI or higher layer signaling.
[0310] In some implementations, the encoder information transmitted at 1302 and received at 1304 may include, for the basis matrix, only columns of the basis matrix that correspond to the dynamically-selected subset of resource elements, and columns of the basis matrix corresponding to resource elements other than the dynamically-selected subset of resource elements may be zeroed.
[0311] In some implementations, the encoder information transmitted at 1302 and received at 1304 may include, for the basis matrix, only columns of the basis matrix that: i) correspond to the dynamically-selected subset of resource elements; and ii) have been changed since a preceding CSI-RS transmission.
[0312] In some implementations, the apparatus 320 may transmit CSI-RS using a pre-selected subset of resource elements. In such implementations, the encoder information transmitted at 1302 and received at 1304 may include, for the basis matrix, only the columns of the basis matrix that correspond to the pre-selected subset of resource elements, and columns of the basis matrix corresponding to resource elements other than the pre-selected subset of resource elements may be zeroed.
[0313] In some implementations, the basis matrix and the reduced-dimension codebook dictionary matrix included in the encoder information transmitted at 1302 and received at 1304 are one pair of a plurality of pairs of such matrices, each pair of such matrices being associated with a different geographic region. In such implementations, the encoder information transmitted at 1302 and received at 1304 may include the basis matrix and the reduced-dimension codebook dictionary matrix associated with a specific geographic region in which the apparatus 310 is located when the apparatus 310 connects to the apparatus 320.
[0314] In some implementations, the plurality of pairs of such matrices includes at least two pairs of such matrices in which each pair of the at least two pairs of such matrices is determined based on matrix decomposition of a respective subset of columns of a common higher-dimension codebook dictionary matrix. In such implementations, each respective subset of columns of the common higher-dimension codebook dictionary matrix, and the respective pair of matrices determined based on matrix decomposition thereof, may be associated with a different geographic region.
[0315] In some implementations, the at least two pairs of such matrices include: a first pair of such matrices determined based on matrix decomposition of a first subset of columns of the common higher-dimension codebook dictionary matrix; and a second pair of such matrices determined based on matrix decomposition of a second subset of columns of the common higher-dimension codebook dictionary matrix. For example, in some implementations, the first subset of columns may be associated with a first geographic region, and the second subset of columns may be associated with a second geographic region. In some implementations, the first subset of columns may partially overlap with the second subset of columns.
[0316] In some implementations, the method 1300 may further include the apparatus 320 monitoring one or more environmental indicators for one or more trigger conditions. In such implementations, the apparatus 320 may transmit update information for the encoder in response to detecting an occurrence of at least one of the one or more trigger conditions. In some implementations, the update information for the encoder may include update information for the basis matrix based on the at least one detected trigger condition. In some implementations, the update information for the encoder further includes update information for the reduced-dimension codebook dictionary matrix. For example, in some implementations, the apparatus 320 may transmit the update information for the encoder by transmitting an update notification message that includes: information indicating a reason for the update; information indicating whether the update is a full update or a differential update; and the update information for the encoder.
[0317] In some implementations, the method 1300 may further include the apparatus 310 transmitting an update acknowledgement message to confirm whether the apparatus 310 has successfully applied the update information for the encoder. In such implementations, the apparatus 320 may monitor for the update acknowledgement message after transmitting the update notification message.
[0318] In some implementations, the method 1300 may further include the apparatus 310 transmitting (and the apparatus 320 receiving) a capability report. For example, in some implementations the capability report may include processing capability information indicative of a processing capability of the apparatus 310. In such implementations, the encoder information transmitted at 1302 and received at 1304 may include, for the basis matrix, a reduced basis matrix based on the processing capability indicated by the processing capability information included in the capability report. The reduced basis matrix may include a subset of columns of the basis matrix. In some implementations, the encoder information transmitted at 1302 and received at 1304 may include reduced basis matrix information. For example, in some implementations the reduced basis matrix information may include: type information indicating a type of the reduced basis matrix; and size information indicating a size of the reduced basis matrix.
[0319] In some implementations, the method 1300 may further include the apparatus 310 transmitting a reduced basis acknowledgement message to confirm whether the reduced basis matrix for the encoder has been successfully applied by the apparatus 310. In such implementations, the apparatus 320 may monitor for the reduced basis acknowledgement message after transmitting the reduced basis matrix information.
[0320] In some implementations, the method 1300 may further include the apparatus 310 transmitting (and the apparatus 320 receiving) a request for a larger basis matrix. In such implementations, the apparatus 320 may transmit (and the apparatus 310 may receive) update information for the reduced basis matrix based on the request. For example, in some implementations, the update information for the reduced basis matrix may include additional columns of the basis matrix to expand the reduced basis matrix.
[0321] In some implementations, each network layer of a plurality of network layers of the communication network in which the apparatuses 310 and 320 operate may have a respective codebook dictionary according to a hierarchical codebook structure. In such implementations, each respective codebook dictionary may have associated therewith a unique identifier.
[0322] In some implementations, the basis matrix and the reduced-dimension codebook dictionary matrix indicated in the encoder information are based on matrix decomposition of the respective codebook dictionary matrix of the network layer in which the apparatus 310 operates.
[0323] In some implementations, the method 1300 may further include the apparatus 320 transmitting (and the apparatus 310 receiving) inter-layer transition information in response to the apparatus 310 transitioning from a current network layer of the plurality of network layers to a target network layer of the plurality of network layers. In such implementations, the inter-layer transition information may include: current layer codebook dictionary information indicating the unique identifier associated with the respective codebook dictionary of the current network layer from which the apparatus 310 is transitioning; and / or target layer codebook dictionary information indicating the unique identifier associated with the respective codebook dictionary of the target network layer to which the apparatus 310 is transitioning.
[0324] In some implementations, the method 1300 may further include the apparatus 320 transmitting (and the apparatus 310 receiving) codebook dictionary synchronization information in response to the apparatus 310 entering the target network layer. For example, in some implementations, the codebook dictionary synchronization information may indicate differences between the respective codebook dictionary of the current network layer the apparatus 310 has transitioned from and the respective codebook dictionary of the target network layer the apparatus 310 has transitioned to.
[0325] In some implementations, the method 1300 may further include the apparatus 310 transmitting a dictionary synchronization acknowledgement message to confirm whether the apparatus 310 has successfully transitioned to the respective codebook dictionary of the target network layer. In such implementations, the apparatus 320 may monitor for the dictionary synchronization acknowledgement message after transmitting the codebook dictionary synchronization information.
[0326] The technical solutions of the present disclosure described above, which mainly focus on dimensionality reduction, efficient sparse approximation, and adaptive basis matrix management in wireless communication, have substantial potential for future commercial applications. The following list provides non-limiting examples of other cross-domain applications in which this technology may be leveraged to provide the same or similar benefits. In particular, non-limiting examples of potential cross-domain applications may include: o Fixed Network and Wi-Fi Applications: The dimensionality reduction techniques, sparse representation, and basis matrix distribution protocol of the present disclosure may be adapted for use in fixed networks, Wi-Fi, and other local wireless technologies. Wi-Fi networks, for instance, often face fluctuating channel conditions and interference, similar to cellular networks. By adapting the basis matrix management and sparse compression techniques, Wi-Fi networks may optimize bandwidth usage, improve CSI compression for dense environments, and enhance performance in high-interference settings such as public Wi-Fi hotspots or enterprise networks. o IoT and Low-Power Wide Area Networks (LPWANs) : IoT devices, which are generally resource-constrained, may benefit from the efficient CSI compression and sparse approximation mechanisms of the present disclosure, especially in LPWANs like LoRa, Sigfox, or NB-IoT. Applying these techniques may help minimize transmission costs, lower power consumption, and enhance battery life in IoT networks. A tailored, simplified version of the sparse approximation and adaptive basis management could optimize data transmission in devices where frequent channel feedback may not be feasible due to power and resource limitations. o Satellite and Non-Terrestrial Networks: In satellite networks, where communication latency and large geographical coverage may be significant factors, the protocols for adaptive basis updates and secure basis matrix distribution of the present disclosure may be beneficial. For example, in low-Earth orbit satellite constellations, environment-adaptive basis updates according to the present disclosure may account for variable channel conditions due to atmospheric effects and changing positions, enhancing data compression and transmission efficiency over large areas. o Industrial and Enterprise Private Networks: Private networks in industrial and enterprise environments, especially those with automated systems or robotics, may benefit from the environment-adaptive basis matrix and compression techniques of the present disclosure. These networks, often deployed in factories or smart buildings, typically have specific physical layouts and interference patterns. The system could potentially provide high-accuracy CSI feedback, enabling more reliable connectivity for industrial IoT devices, automated guided vehicles (AGVs) , and machine-to-machine (M2M) communication within the network.
[0327] In the present disclosure, the terms “a” or “an” are defined to mean “at least one” , that is, these terms do not exclude a plural number of items, unless stated otherwise.
[0328] In the present disclosure, terms such as “substantially” , “generally” and “about” , which modify a value, condition or characteristic of a feature of an example embodiment, should be understood to mean that the value, condition or characteristic is defined within tolerances that are acceptable for the proper operation of the example embodiment for its intended application.
[0329] In the present disclosure, unless stated otherwise, the terms “connected” and “coupled” , and derivatives and variants thereof, refer herein to any structural or functional connection or coupling, either direct or indirect, between two or more elements. For example, the connection or coupling between the elements can be acoustical, mechanical, optical, electrical, thermal, logical, or any combinations thereof.
[0330] In the present disclosure, expressions such as “match” , “matching” and “matched” , including variants and derivatives thereof, are intended to refer herein to a condition in which two or more elements are either the same or within some predetermined tolerance of each other. That is, these terms are meant to encompass not only “exactly” or “identically” matching the two elements but also “substantially” , “approximately” or “subjectively” matching the two or more elements, as well as providing a higher or best match among a plurality of matching possibilities.
[0331] In the present disclosure, the expression “based on” is intended to mean “based at least partly on” , that is, this expression can mean “based solely on” or “based partially on” , and so should not be interpreted in a limited manner. More particularly, the expression “based on” could also be understood as meaning “depending on” , “representative of” , “indicative of” , “associated with” or similar expressions.
[0332] In the present disclosure, the terms "system" and "network" may be used interchangeably in different embodiments of this application. "At least one" means one or more, and "a plurality of" means two or more. The term "and / or" describes an association relationship of associated objects, and indicates that three relationships may exist. For example, A and / or B may indicate the following three cases: Only A exists, both A and B exist, and only B exists, where A and B may be singular or plural. The character " / " indicates an "or" relationship between associated objects. "At least one of the following items (pieces) " or a similar expression thereof indicates any combination of these items, including a single item (piece) or any combination of a plurality of items (pieces) . For example, "at least one of A, B, or C" includes: only A; only B; only C; A and B; A and C; B and C; or A, B, and C, and "at least one of A, B, and C" may also be understood as including: only A; only B; only C; A and B; A and C; B and C; or A, B, and C. In addition, unless otherwise specified, ordinal numbers such as "first" and "second" in embodiments of this application are used to distinguish between a plurality of objects, and are not used to limit a sequence, a time sequence, priorities, or importance of the plurality of objects.
[0333] A person skilled in the art should understand that embodiments of this application may be provided as a method, an apparatus (or system) , computer-readable storage medium, or a computer program product. Therefore, this application may use a form of a hardware-only embodiment, a software-only embodiment, or an embodiment with a combination of software and hardware. Moreover, this application may use a form of a computer program product that is implemented on one or more computer-usable storage media (including but not limited to a disk memory, an optical memory, and the like) that include computer-usable program code.
[0334] This application is described with reference to the flowcharts and / or block diagrams of the method, the device (system) , and the computer program product according to this application. It should be understood that computer program instructions may be used to implement each process and / or each block in the flowcharts and / or the block diagrams and a combination of a process and / or a block in the flowcharts and / or the block diagrams. The computer program instructions may be provided for a general-purpose computer, a dedicated computer, an embedded processor, or a processor of another programmable data processing device and enable a machine to execute the instructions. When executed by any computer or the processor of a programmable data processing device, he instructions cause the apparatus to implement specific functions as described in one or more procedures in the flowcharts and / or one or more blocks in the block diagrams. The computer program instructions may alternatively be stored in a computer-readable memory that can indicate a computer or another programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate an artifact that includes an instruction apparatus. The instruction apparatus implements a specific function in one or more procedures in the flowcharts and / or one or more blocks in the block diagrams.
[0335] The computer program instructions may alternatively be loaded onto a computer or another programmable data processing device, so that a series of operations and steps are performed on the computer or the another programmable device, so that computer-implemented processing is generated. Therefore, the instructions executed on the computer or on another programmable device provide steps for implementing specific functions as described in one or more procedures in the flowcharts and / or one or more blocks in the block diagrams.
[0336] It is clear that a person skilled in the art can make various modifications and variations to this application without departing from the scope of present disclosure. ACRONYMS AND ABBREVIATIONS
Claims
1.A method comprising:transmitting encoder information for sparsity-based compression of information, the encoder information comprising:a basis function operable as a dimension reduction function to reduce a dimension of the information at a user device; anda reduced-dimension codebook dictionary function that has reduced dimensions relative to a higher-dimension codebook dictionary function.2.The method of claim 1, further comprising receiving a connection request, wherein transmitting the encoder information comprises transmitting the encoder information responsive to receiving the connection request.3.The method of claim 2, wherein the connection request is indicative of at least one of:whether the sparsity-based compression can be performed;whether the basis function is requested; orwhether the reduced-dimension codebook dictionary function is requested.4.The method of claim 2 or claim 3, wherein the connection request is received via radio resource control (RRC) signaling.5.The method of any of claims 1 to 4, further comprising:receiving compressed information, the compressed information comprising a sparse representation of the information; anddecompressing the sparse representation of the information to recover uncompressed information using the higher-dimension codebook dictionary function.6.The method of any of claims 1 to 4, wherein the information to be compressed comprises channel state information (CSI) .7.The method of claim 6, further comprising:transmitting a CSI reference signal (CSI-RS) ;the receiving compressed information comprising: receiving compressed CSI, the compressed CSI comprising a sparse representation of the CSI; andthe decompressing the sparse representation of the information to recover uncompressed information using the higher-dimension codebook dictionary function comprising: decompressing the sparse representation of the CSI to recover a reconstruction of the CSI using the higher-dimension codebook dictionary function.8.The method of claim 7, further comprising:receiving an uplink resources request; andtransmitting uplink resources allocation information indicating uplink resources allocated for uplink transmission,wherein receiving the compressed CSI comprises receiving the compressed CSI over the allocated uplink resources.9.The method of claim 6, further comprising:transmitting a CSI-RS; andreceiving a signal indicative of a compression failure indicating a compression failure of the CSI.10.The method of claim 9, further comprising, after receiving the signal indicative of the compression failure, at least one of:transmitting a new CSI-RS across different resource elements;increasing the resource allocation for CSI estimation; orinitiating a codebook dictionary update process for the higher-dimension codebook dictionary function.11.The method of any of claims 1 to 4, wherein the basis function and the reduced-dimension codebook dictionary function are derived from the higher-dimension codebook dictionary function.12.The method of claim 11, wherein:the basis function comprises a basis matrix;the higher-dimension codebook dictionary function comprises a higher-dimension codebook dictionary matrix; andthe reduced-dimension codebook dictionary function comprises a reduced-dimension codebook dictionary matrix that has reduced dimensions relative to the higher-dimension codebook dictionary matrix.13.The method of claim 12, further comprising transmitting dimension information indicative of:dimensions of the basis matrix; anddimensions of the reduced-dimension codebook dictionary matrix.14.The method of claim 13, wherein transmitting the dimension information comprises broadcasting the dimension information in one or more system information blocks (SIBs) .15.The method of any of claims 12 to 14, wherein the higher-dimension codebook dictionary matrix defines a reduced-dimension subspace projection of an information space of the information to be compressed.16.The method of claim 15, further comprising:determining the basis matrix and the reduced-dimension codebook dictionary matrix through matrix decomposition of the higher-dimension codebook dictionary matrix.17.The method of claim 16, wherein the matrix decomposition is such that rows of the basis matrix form an orthonormal basis for a column space of the higher-dimension codebook dictionary matrix.18.The method of claim 16 or claim 17, wherein the matrix decomposition comprises singular value decomposition (SVD) or QR decomposition.19.The method of claim 18, wherein:the information to be compressed comprises CSI; andthe higher-dimension codebook dictionary matrix defines a reduced-dimension subspace projection of the channel space.20.The method of claim 19, wherein the matrix decomposition comprises SVD according to: Ψ=USV*, and Ψ′=SV*,where:Ψ is the higher-dimension code book dictionary matrix;U is the basis matrix, wherein U is a unitary matrix, wheren is the channel dimension, and r is the rank of Ψ;S is a diagonal matrix;V is a unitary matrix, wherein V* is the Hermitian transpose of V; andΨ′ is the reduced-dimension codebook dictionary matrix.21.The method of claim 19, wherein the matrix decomposition comprises QR decomposition according to: Ψ=QR, and Ψ′=R,where:Ψ is the higher-dimension code book dictionary matrix;Q is the basis matrix, wherein Q is an orthogonal matrix;R is an upper triangular matrix; andΨ′ is the reduced-dimension codebook dictionary matrix.22.The method of claim 20 or claim 21, further comprising:transmitting a CSI-RS;receiving compressed CSI, the compressed CSI comprising a sparse vector representation of the CSI; anddecompressing the sparse representation of the CSI to recover a reconstruction of the CSI according to:where:is the CSI reconstruction;Ψ is the higher-dimension code book dictionary matrix; ands* is the sparse vector representation of the CSI.23.The method of claim 22, wherein transmitting the CSI-RS comprises:dynamically selecting a subset of resource elements from a set of resource elements; andtransmitting the CSI-RS using the selected subset of resource elements.24.The method of claim 23, wherein columns of the basis matrix corresponding to resource elements not used for transmitting the CSI-RS are zeroed.25.The method of claim 23 or claim 24, wherein:the set of resource elements comprises a set of transmit antennas and a set of frequency bands;dynamically selecting a partial subset of resource elements comprises:dynamically selecting a partial subset of transmit antennas from the set of transmit antennas; anddynamically selecting a partial subset of frequency bands from the set of frequency bands; andtransmitting the CSI-RS using the selected subset of resource elements comprises:transmitting the CSI-RS by the selected subset of transmit antennas in the selected subset of frequency bands.26.The method of any of claims 23 to 25, further comprising transmitting signaling indicative of the selected subset of resource elements.27.The method of claim 26, wherein the signaling indicative of the selected subset of resource elements comprises download control information (DCI) or higher layer signaling.28.The method of claim 22, wherein:transmitting the CSI-RS comprises transmitting the CSI-RS using a pre-selected subset of resource elements;transmitting the encoder information comprises transmitting, for the basis matrix, only the columns of the basis matrix that correspond to the pre-selected subset of resource elements; andcolumns of the basis matrix corresponding to resource elements other than the pre-selected subset of resource elements are zeroed.29.The method of claim 23, wherein:transmitting the CSI-RS comprises:dynamically selecting a subset of resource elements from a set of resource elements; andtransmitting the CSI-RS using the selected subset of resource elements;transmitting the encoder information comprises transmitting, for the basis matrix, only columns of the basis matrix that correspond to the dynamically-selected subset of resource elements; andcolumns of the basis matrix corresponding to resource elements other than the dynamically-selected subset of resource elements are zeroed.30.The method of claim 29, wherein transmitting the encoder information comprises transmitting, for the basis matrix, only columns of the basis matrix that:i) correspond to the dynamically-selected subset of resource elements; andii) have been changed since a preceding CSI-RS transmission.31.The method of any one of claims 16 to 30, wherein:the basis matrix and the reduced-dimension codebook dictionary matrix included in the encoder information are one pair of a plurality of pairs of such matrices, each pair of such matrices being associated with a different geographic region; andtransmitting the encoder information comprises transmitting, by a network device to the user device, the basis matrix and the reduced-dimension codebook dictionary matrix associated with a specific geographic region in which the user device is located when the user device connects to the network device.32.The method of claim 31, wherein:the plurality of pairs of such matrices comprises at least two pairs of such matrices in which each pair of the at least two pairs of such matrices is determined based on matrix decomposition of a respective subset of columns of a common higher-dimension codebook dictionary matrix; andeach respective subset of columns of the common higher-dimension codebook dictionary matrix, and the respective pair of matrices determined based on matrix decomposition thereof, is associated with a different geographic region.33.The method of claim 32, wherein:the at least two pairs of such matrices comprise:a first pair of such matrices determined based on matrix decomposition of a first subset of columns of the common higher-dimension codebook dictionary matrix, the first subset of columns being associated with a first geographic region; anda second pair of such matrices determined based on matrix decomposition of a second subset of columns of the common higher-dimension codebook dictionary matrix, the second subset of columns being associated with a second geographic region; andthe first subset of columns partially overlaps with the second subset of columns.34.The method of any of claims 16 to 33, further comprising:monitoring one or more environmental indicators for one or more trigger conditions; andin response to detecting an occurrence of at least one of the one or more trigger conditions, transmitting update information for the encoder, the update information for the encoder comprising update information for the basis matrix based on the at least one detected trigger condition.35.The method of claim 33, wherein the update information for the encoder further comprises update information for the reduced-dimension codebook dictionary matrix.36.The method of claim 34 or claim 35, wherein transmitting the update information for the encoder comprises transmitting an update notification message, the update notification message comprising:information indicating a reason for the update;information indicating whether the update is a full update or a differential update; andthe update information for the encoder.37.The method of any of claims 34 to 36, further comprising:monitoring for an update acknowledgement message to confirm whether the update information for the encoder has been successfully applied.38.The method of any of claims 16 to 27, further comprising:receiving a capability report, the capability report comprising processing capability information indicative of a processing capability;wherein transmitting the encoder information comprises transmitting, for the basis matrix, a reduced basis matrix based on the processing capability, the reduced basis matrix including a subset of columns of the basis matrix.39.The method of claim 38, wherein transmitting the reduced basis matrix comprises transmitting reduced basis matrix information, the reduced basis matrix information comprising:type information indicating a type of the reduced basis matrix; andsize information indicating a size of the reduced basis matrix.40.The method of claim 38 or claim 39, further comprising:monitoring for a reduced basis acknowledgement message to confirm whether the reduced basis matrix for the encoder has been successfully applied.41.The method of any of claims 38 to 40, further comprising:receiving a request for a larger basis matrix; andtransmitting update information for the reduced basis matrix based on the request, the update information for the reduced basis matrix comprising additional columns of the basis matrix to expand the reduced basis matrix.42.The method of any of claims 16 to 27, wherein each network layer of a plurality of network layers of a communication network has a respective codebook dictionary according to a hierarchical codebook structure, each respective codebook dictionary having associated therewith a unique identifier.43.The method of claim 42, wherein the basis matrix and the reduced-dimension codebook dictionary matrix indicated in the encoder information are based on matrix decomposition of the respective codebook dictionary matrix of the network layer in which the user device operates.44.The method of claim 42 or claim 43, further comprising:in response to the user device transitioning from a current network layer of the plurality of network layers to a target network layer of the plurality of network layers, transmitting inter-layer transition information, the inter-layer transition information comprising:current layer codebook dictionary information indicating the unique identifier associated with the respective codebook dictionary of the current network layer from which the user device is transitioning; andtarget layer codebook dictionary information indicating the unique identifier associated with the respective codebook dictionary of the target network layer to which the user device is transitioning.45.The method of claim 44, further comprising:in response to the user device entering the target network layer, transmitting codebook dictionary synchronization information, the codebook dictionary synchronization information indicating differences between the respective codebook dictionary of the current network layer the user device has transitioned from and the respective codebook dictionary of the target network layer the user device has transitioned to.46.The method of claim 45, further comprising:monitoring for a dictionary synchronization acknowledgement message to confirm whether the user device has successfully transitioned to the respective codebook dictionary of the target network layer.47.An apparatus comprising:at least one processor; anda memory storing processor-executable instructions that, when executed by the at least one processor, cause the apparatus to perform the method of any one of claims 1 to 46.48.A non-transitory computer-readable storage medium having instructions stored thereon that, when executed by at least one processor of an apparatus, cause the apparatus to perform the method of any one of claims 1 to 46.49.A computer program product storing instructions that, when executed by at least one processor of an apparatus, cause the apparatus to perform the method of any one of claims 1 to 46.50.A method comprising:receiving encoder information for sparsity-based compression of information at a user device, the encoder information comprising:a basis function operable as a dimension reduction function to reduce a dimension of the information at the user device; anda reduced-dimension codebook dictionary function that has reduced dimensions relative to a higher-dimension codebook dictionary function.51.The method of claim 50, further comprising transmitting a connection request, wherein receiving the encoder information comprises receiving the encoder information after transmitting the connection request.52.The method of claim 51, wherein the connection request is indicative of at least one of:whether the sparsity-based compression can be performed;whether the basis function is requested; orwhether the reduced-dimension codebook dictionary function is requested.53.The method of claim 51 or claim 52, wherein the connection request is transmitted via radio resource control (RRC) signaling.54.The method of any of claims 50 to 53, further comprising:using the basis function and the reduced-dimension codebook dictionary function to compress information at the user device; andtransmitting the compressed information, the compressed information comprising a sparse representation of the information.55.The method of claim 54, wherein the compressed information comprises compressed channel state information (CSI) .56.The method of claim 55, further comprising:receiving, a CSI reference signal (CSI-RS) ;utilizing the received CSI-RS to estimate CSI;using the basis matrix and the reduced-dimension codebook dictionary function to compress the CSI, the compressed CSI comprising a sparse representation of the CSI.57.The method of claim 56, wherein using the basis matrix and the reduced-dimension codebook dictionary function to compress the CSI comprises:using the basis function to project the CSI into a reduced dimension subspace to obtain a reduced-dimension representation of the CSI; andperforming sparse approximation using the reduced-dimension codebook dictionary function and the reduced-dimension representation of the CSI to solve for the sparse representation of the CSI.58.The method of claim 57, wherein transmitting the compressed information comprises transmitting the compressed CSI.59.The method of claim 58, further comprising:assessing the quality of channel estimation and compression based on statistics of the compressed CSI;in response to determining the quality of channel estimation and compression is acceptable, transmitting an uplink resources request; andreceiving uplink resources allocation information indicating uplink resources allocated to the user device for uplink transmission,wherein transmitting the compressed CSI comprises transmitting the compressed CSI over the allocated uplink resources.60.The method of claim 57, further comprising:assessing the quality of channel estimation and compression based on statistics of the compressed CSI; andin response to determining the quality of channel estimation or compression is not acceptable, transmitting a signal indicative of a compression failure indicating a compression failure of the CSI.61.The method of claim 60, further comprising, after transmitting the signal indicative of the compression failure, at least one of:receiving a new CSI-RS across different resource elements;receiving information indicating an increase in the resource allocation for CSI estimation; orreceiving updated encoder information based on an update to the higher-dimension codebook dictionary function.62.The method of any of claims 57 to 61, wherein the basis function and the reduced-dimension codebook dictionary function are derived from the higher-dimension codebook dictionary function.63.The method of claim 62, wherein:the basis function comprises a basis matrix;the higher-dimension codebook dictionary function comprises a higher-dimension codebook dictionary matrix; andthe reduced-dimension codebook dictionary function comprises a reduced-dimension codebook dictionary matrix that has reduced dimensions relative to the higher-dimension codebook dictionary matrix.64.The method of claim 63, further comprising receiving dimension information indicative of:dimensions of the basis matrix; anddimensions of the reduced-dimension codebook dictionary matrix.65.The method of claim 64, wherein receiving the dimension information comprises receiving the dimension information in one or more system information blocks (SIBs) .66.The method of any of claims 63 to 65, wherein the higher-dimension codebook dictionary matrix defines a reduced-dimension subspace projection of the channel space.67.The method of claim 66, wherein the basis matrix and the reduced-dimension codebook dictionary matrix are determined through matrix decomposition of the higher-dimension codebook dictionary matrix such that rows of the basis matrix form an orthonormal basis for a column space of the higher-dimension codebook dictionary matrix.68.The method of claim 67, wherein the matrix decomposition comprises singular value decomposition (SVD) or QR decomposition.69.The method of claim 68, wherein:the matrix decomposition comprises SVD according to:Ψ=USV*, andΨ′=SV*,where:Ψ is the higher-dimension code book dictionary matrix;U is the basis matrix, wherein U is a unitary matrix, wheren is the channel dimension, and r is the rank of Ψ;S is a diagonal matrix;V is a unitary matrix, wherein V* is the Hermitian transpose of V; andΨ′ is the reduced-dimension codebook dictionary matrix;using the basis matrix to project the CSI into a reduced dimension subspace to obtain a reduced-dimension representation of the CSI comprises using the matrix U to project h into the subspace of Ψ to obtaining a reduced-dimension representation of the CSI according to:h′= U*h,where:h is the CSI; andh′ is the reduced-dimension representation of the CSI; andperforming sparse approximation using the reduced-dimension codebook dictionary matrix and the reduced-dimension representation of the CSI to solve for the sparse representation of the CSI comprises performing sparse approximation by solving an optimization problem according to:where:s* is the optimal sparse vector representation of the CSI; andα is a sparsity-inducing parameter.70.The method of claim 68, wherein:the matrix decomposition comprises QR decomposition according to:Ψ=QR, andΨ′=R,where:Ψ is the higher-dimension code book dictionary matrix;Q is the basis matrix, wherein Q is an orthogonal matrix;R is an upper triangular matrix; andΨ′ is the reduced-dimension codebook dictionary matrix;using the basis matrix to project the CSI into a reduced dimension subspace to obtain a reduced-dimension representation of the CSI comprises using the matrix U to project h into the subspace of Ψ to obtaining a reduced-dimension representation of the CSI according to:h′= Q*h,where:h is the CSI; andh′ is the reduced-dimension representation of the CSI; andperforming sparse approximation using the reduced-dimension codebook dictionary matrix and the reduced-dimension representation of the CSI to solve for the sparse representation of the CSI comprises performing sparse approximation by solving an optimization problem according to:where:s* is the optimal sparse vector representation of the CSI; andα is a sparsity-inducing parameter.71.The method of claim 69 or claim 70, wherein receiving the CSI-RS comprises:receiving the CSI-RS using a subset of resource elements from a set of resource elements.72.The method of claim 71, wherein columns of the basis matrix corresponding to resource elements not used for transmitting the CSI-RS are zeroed.73.The method of claim 71 or claim 72, wherein:the set of resource elements comprises a set of transmit antennas and a set of frequency bands; andreceiving the CSI-RS using the selected subset of resource elements comprises receiving the CSI-RS transmitted by a partial subset of transmit antennas from the set of transmit antennas in a partial subset of frequency bands dynamically selected from the set of frequency bands.74.The method of any of claims 71 to 73, further comprising receiving signaling indicative of the subset of resource elements.75.The method of claim 74, wherein the signaling indicative of the subset of resource elements comprises downlink control information (DCI) or higher layer signaling.76.The method of claim 69 or claim 70, wherein:receiving the CSI-RS comprises receiving the CSI-RS transmitted using a pre-selected subset of resource elements;receiving the encoder information comprises receiving, for the basis matrix, only the columns of the basis matrix that correspond to the pre-selected subset of resource elements; andzero-padding columns of the basis matrix corresponding to resource elements other than the pre-selected subset of resource elements.77.The method of claim 71, wherein:receiving the CSI-RS comprises receiving the CSI-RS transmitted using a subset of resource elements from a set of resource elements;receiving the encoder information comprises receiving, for the basis matrix, only columns of the basis matrix that correspond to the subset of resource elements; andzero-padding columns of the basis matrix corresponding to resource elements other than the subset of resource elements.78.The method of claim 77, wherein receiving the encoder information comprises receiving, for the basis matrix, only columns of the basis matrix that:i) correspond to the dynamically-selected subset of resource elements; andii) have been changed since a preceding CSI-RS transmission.79.The method of any one of claims 67 to 78, wherein:the basis matrix and the reduced-dimension codebook dictionary matrix included in the encoder information are one pair of a plurality of pairs of such matrices, each pair of such matrices being associated with a different geographic region; andreceiving the encoder information comprises receiving from a network device, the basis matrix and the reduced-dimension codebook dictionary matrix associated with a specific geographic region in which the user device is located when the user device connects to the network device.80.The method of claim 79, wherein:the plurality of pairs of such matrices comprises at least two pairs of such matrices in which each pair of the at least two pairs of such matrices is determined based on matrix decomposition of a respective subset of columns of a common higher-dimension codebook dictionary matrix; andeach respective subset of columns of the common higher-dimension codebook dictionary matrix, and the respective pair of matrices determined based on matrix decomposition thereof, is associated with a different geographic region.81.The method of claim 80, wherein:the at least two pairs of such matrices comprise:a first pair of such matrices determined based on matrix decomposition of a first subset of columns of the common higher-dimension codebook dictionary matrix, the first subset of columns being associated with a first geographic region; anda second pair of such matrices determined based on matrix decomposition of a second subset of columns of the common higher-dimension codebook dictionary matrix, the second subset of columns being associated with a second geographic region; andthe first subset of columns partially overlaps with the second subset of columns.82.The method of any of claims 67 to 81, further comprising:receiving update information for the encoder, the update information for the encoder comprising update information for the basis matrix based on at least one trigger condition detected based on one or more environmental indicators.83.The method of claim 82, wherein the update information for the encoder further comprises update information for the reduced-dimension codebook dictionary matrix.84.The method of claim 82 or claim 83, wherein receiving the update information for the encoder comprises receiving an update notification message, the update notification message comprising:information indicating a reason for the update;information indicating whether the update is a full update or a differential update; andthe update information for the encoder.85.The method of any of claims 82 to 84, further comprising:applying the update information for the encoder; andtransmitting an update acknowledgement message to confirm the user device has successfully applied the update information for the encoder.86.The method of any of claims 67 to 75, further comprising:transmitting a capability report, the capability report comprising processing capability information indicative of a processing capability;wherein receiving the encoder information comprises receiving, for the basis matrix, a reduced basis matrix based on the processing capability, the reduced basis matrix including a subset of columns of the basis matrix.87.The method of claim 86, wherein receiving the reduced basis matrix comprises receiving reduced basis matrix information, the reduced basis matrix information comprising:type information indicating a type of the reduced basis matrix; andsize information indicating a size of the reduced basis matrix.88.The method of claim 86 or claim 87, further comprising:transmitting a reduced basis acknowledgement message to confirm the user device has successfully received the reduced basis matrix and is ready to apply the reduced basis matrix.89.The method of any of claims 86 to 88, further comprising:transmitting a request for a larger basis matrix; andreceiving update information for the reduced basis matrix based on the request, the update information for the reduced basis matrix comprising additional columns of the basis matrix to expand the reduced basis matrix.90.The method of any of claims 67 to 75, wherein each network layer of a plurality of network layers of a communication network has a respective codebook dictionary according to a hierarchical codebook structure, each respective codebook dictionary having associated therewith a unique identifier.91.The method of claim 90, wherein the basis matrix and the reduced-dimension codebook dictionary matrix indicated in the encoder information are based on matrix decomposition of the respective codebook dictionary matrix of the network layer in which the user device operates.92.The method of claim 90 or claim 91, further comprising:in response to transitioning from a current network layer of the plurality of network layers to a target network layer of the plurality of network layers, receiving inter-layer transition information, the inter-layer transition information comprising:current layer codebook dictionary information indicating the unique identifier associated with the respective codebook dictionary of the current network layer from which the transitioning is performed; andtarget layer codebook dictionary information indicating the unique identifier associated with the respective codebook dictionary of the target network layer to which the transitioning is performed.93.The method of claim 92, further comprising:in response to entering the target network layer, receiving codebook dictionary synchronization information, the codebook dictionary synchronization information indicating differences between the respective codebook dictionary of the current network layer and the respective codebook dictionary of the target network layer.94.The method of claim 93, further comprising:transmitting a dictionary synchronization acknowledgement message to confirm the respective codebook dictionary of the target network layer has been successfully transitioned to.95.An apparatus comprising:at least one processor; anda memory storing processor-executable instructions that, when executed by the at least one processor, cause the apparatus to perform the method of any one of claims 50 to 94.96.A non-transitory computer-readable storage medium having instructions stored thereon that, when executed by at least one processor of an apparatus, cause the apparatus to perform the method of any one of claims 50 to 94.97.A computer program product storing instructions that, when executed by at least one processor of an apparatus, cause the apparatus to perform the method of any one of claims 50 to 94.98.A communication system, wherein the communication system comprises a network device configured to perform the method of any one of claims 1 to 46 and a user device configured to perform the method of any one of claims 50 to 94.99.A communication system comprising a network device and a user device, wherein:the network device is configured to:transmit, to the user device, encoder information for sparsity-based compression of information at the user device, the encoder information comprising:a basis matrix operable as a dimension reduction matrix to reduce a dimension of channel state information (CSI) at the user device; anda reduced-dimension codebook dictionary matrix that has reduced dimensions relative to a higher-dimension codebook dictionary matrix; andtransmit, to the user device, a CSI reference signal (CSI-RS) ; andthe user device is configured to:receive the encoder information;receive the CSI-RS;utilize the received CSI-RS to estimate CSI;use the basis matrix to project the CSI into a reduced dimension subspace to obtain a reduced-dimension representation of the CSI;perform sparse approximation using the reduced-dimension codebook dictionary matrix and the reduced-dimension representation of the CSI to solve for a sparse representation of the CSI; andtransmit, to the network device, the sparse representation of the CSI.