Adaptive compression rate for machine-learning based channel state information-compression
The adaptive compression rate mechanism using AI-driven autoencoders in 5G wireless systems addresses the balance between CSI compression rate and accuracy, reducing overhead and improving reconstruction quality by dynamically adjusting compression rates based on UE-specific link conditions.
Patent Information
- Application Number
- PCT/EP2024/060107
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-05-12
- Filing Date
- 2024-04-15
- Publication Date
- 2024-11-21
AI Technical Summary
Current methods for compressing channel state information (CSI) in 5G wireless communication systems face challenges in balancing compression rate and accuracy, leading to high overhead and significant reconstruction loss, especially in non-sparse channels and limited feedback scenarios.
The implementation of an adaptive compression rate (CR) mechanism using artificial intelligence markup language (AIML) and autoencoder structures, such as CsiNet and FullyConv, which allow user equipment (UE) to select optimal CR based on link conditions, reducing overhead and improving CSI reconstruction accuracy by dynamically adjusting compression rates.
This approach reduces tunable signaling overhead and enhances the trade-off between CSI feedback accuracy and overhead, optimizing compression rates based on UE-specific conditions for improved network performance.
Smart Images

Figure EP2024060107_21112024_PF_FP_ABST
Abstract
Description
TITLEADAPTIVE COMPRESSION RATE FOR MACHINE-LEARNING BASED CHANNEL STATE INFORMATION-COMPRESSIONCROSS REFERENCE TO RELATED APPLICATION
[0001] This application claims the benefit of US provisional application No. 63 / 466000 filed 12 May 2023, which is incorporated herein by reference in its entirety.TECHNICAL FIELD
[0002] Some example embodiments may generally relate to mobile or wireless telecommunication systems, such as 3rdGeneration Partnership Project (3GPP) Long Term Evolution (LTE), 5thgeneration (5G) radio access technology (RAT), new radio (NR) access technology, 6thgeneration (6G), and / or other communications systems. For example, certain example embodiments may relate to systems and / or methods to indicate capabilities for compression rate (CR) adaptation.BACKGROUND
[0003] Examples of mobile or wireless telecommunication systems may include radio frequency (RF) 5G RAT, the Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access Network (UTRAN), LTE Evolved UTRAN (E-UTRAN), LTE-Advanced (LTE-A), LTE-A Pro, NR access technology, and / or MulteFire Alliance. 5G wireless systems refer to the next generation (NG) of radio systems and network architecture. A 5G system is typically built on a 5G NR, but a 5G (or NG) network may also be built on E-UTRA radio. It is expected that NR can support service categories such as enhanced mobile broadband (eMBB), ultra-reliable low-latency- communication (URLLC), and massive machine-type communication (mMTC). NR is expected to deliver extreme broadband, ultra-robust, low-latency connectivity, and massive networking to support the Internet of Things (IoT). The next generation radio access network (NG-RAN) represents the radio access network (RAN) for 5G, which may provide radio access for NR, LTE, and LTE-A. It is noted that the nodes in 5Gproviding radio access functionality to a user equipment (e.g, similar to the Node B in UTRAN or the Evolved Node B (eNB) in LTE) may be referred to as next-generation Node B (gNB) when built on NR radio, and may be referred to as next-generation eNB (NG-eNB) when built on E-UTRA radio.SUMMARY
[0004] In accordance with some example embodiments, a method may include transmitting to a network entity at least one indication of at least one user equipmentspecific capability or availability for compression rate adaptation. The method may further include receiving from the network entity at least one user equipment-specific compression rate constraint. The method may further include determining a compression rate adaptive to the at least one user equipment-specific compression rate constraint.
[0005] In accordance with certain example embodiments, an apparatus may include means for transmitting to a network entity at least one indication of at least one user equipment-specific capability or availability for compression rate adaptation. The apparatus may further include means for receiving from the network entity at least one user equipment-specific compression rate constraint. The apparatus may further include means for determining a compression rate adaptive to the at least one user equipmentspecific compression rate constraint.
[0006] In accordance with various example embodiments, a non-transitory computer readable medium may include program instructions that, when executed by an apparatus, cause the apparatus to perform at least a method. The method may include transmitting to a network entity at least one indication of at least one user equipmentspecific capability or availability for compression rate adaptation. The method may further include receiving from the network entity at least one user equipment-specific compression rate constraint. The method may further include determining a compression rate adaptive to the at least one user equipment-specific compression rate constraint.
[0007] In accordance with some example embodiments, a computer program product may perform a method. The method may include transmitting to a network entity at least one indication of at least one user equipment-specific capability or availability for compression rate adaptation. The method may further include receiving from the network entity at least one user equipment-specific compression rate constraint. The method may further include determining a compression rate adaptive to the at least one user equipment-specific compression rate constraint.
[0008] In accordance with certain example embodiments, an apparatus may include at least one processor and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to transmit to a network entity at least one indication of at least one user equipment-specific capability or availability for compression rate adaptation. The at least one memory and instructions, when executed by the at least one processor, may further cause the apparatus at least to receive from the network entity at least one user equipment-specific compression rate constraint. The at least one memory and instructions, when executed by the at least one processor, may further cause the apparatus at least to determine a compression rate adaptive to the at least one user equipment-specific compression rate constraint.
[0009] In accordance with various example embodiments, an apparatus may include transmitting circuitry configured to transmit to a network entity at least one indication of at least one user equipment-specific capability or availability for compression rate adaptation. The apparatus may further include receiving circuitry configured to receive from the network entity at least one user equipment-specific compression rate constraint. The apparatus may further include determining circuitry configured to determine a compression rate adaptive to the at least one user equipment-specific compression rate constraint.
[0010] In accordance with some example embodiments, a method may include receiving from a user equipment at least one indication of at least one user equipmentspecific capability or availability for compression rate adaptation. The method may further include setting at least one user equipment-specific compression rate constraint.The method may further include transmitting the at least one user equipment-specific compression rate constraint to the user equipment.
[0011] In accordance with certain example embodiments, an apparatus may include means for receiving from a user equipment at least one indication of at least one user equipment-specific capability or availability for compression rate adaptation. The apparatus may further include means for setting at least one user equipment-specific compression rate constraint. The apparatus may further include means for transmitting the at least one user equipment-specific compression rate constraint to the user equipment.
[0012] In accordance with various example embodiments, a non-transitory computer readable medium may include program instructions that, when executed by an apparatus, cause the apparatus to perform at least a method. The method may include receiving from a user equipment at least one indication of at least one user equipmentspecific capability or availability for compression rate adaptation. The method may further include setting at least one user equipment-specific compression rate constraint. The method may further include transmitting the at least one user equipment-specific compression rate constraint to the user equipment.
[0013] In accordance with some example embodiments, a computer program product may perform a method. The method may include receiving from a user equipment at least one indication of at least one user equipment-specific capability or availability for compression rate adaptation. The method may further include setting at least one user equipment-specific compression rate constraint. The method may further include transmitting the at least one user equipment-specific compression rate constraint to the user equipment.
[0014] In accordance with certain example embodiments, an apparatus may include at least one processor and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to receive from a user equipment at least one indication of at least one user equipment-specific capability or availability for compression rate adaptation. The at least one memory and instructions, when executed by the at least one processor, may further cause the apparatus at least to set atleast one user equipment-specific compression rate constraint. The at least one memory and instructions, when executed by the at least one processor, may further cause the apparatus at least to transmit the at least one user equipment-specific compression rate constraint to the user equipment.
[0015] In accordance with various example embodiments, an apparatus may include receiving circuitry configured to receive from a user equipment at least one indication of at least one user equipment-specific capability or availability for compression rate adaptation. The apparatus may further include setting circuitry configured to set at least one user equipment-specific compression rate constraint. The apparatus may further include transmitting circuitry configured to transmit the at least one user equipmentspecific compression rate constraint to the user equipment.BRIEF DESCRIPTION OF THE DRAWINGS
[0016] For a proper understanding of example embodiments, reference should be made to the accompanying drawings, wherein:
[0017] FIG. 1 depicts a block diagram of an auto-encoder channel state informationcompression with quantization and de-quantization blocks;
[0018] FIG. 2 depicts an example of vector quantization over the encoder output and reconstruction of the input of the decoder;
[0019] FIG. 3 illustrates an example of a signaling diagram according to certain example embodiments;
[0020] FIG. 4 illustrates an example of another signaling diagram according to certain example embodiments;
[0021] FIG. 5 illustrates an example of another signaling diagram according to certain example embodiments;
[0022] FIG. 6 illustrates an example of a flow diagram of a method according to various example embodiments;
[0023] FIG. 7 illustrates an example of a flow diagram of another method according to various example embodiments;
[0024] FIG. 8 illustrates an example of various network devices according to some example embodiments; and
[0025] FIG. 9 illustrates an example of a 5G network and system architecture according to certain example embodiments.DETAILED DESCRIPTION
[0026] It will be readily understood that the components of certain example embodiments, as generally described and illustrated in the figures herein, may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of some example embodiments of systems, methods, apparatuses, and computer program products to indicate capabilities for CR adaptation is not intended to limit the scope of certain example embodiments, but is instead representative of selected example embodiments.
[0027] Channel state information (CSI) may be used for precoding in massive multiple-input multiple-output (MIMO) communications with frequency division duplex (FDD) schemes. Accurate CSI can be used by a network entity (e.g, eNB, gNB) to obtain higher signal-to-noise-ratio (SNR) and channel capacity. However, in FDD networks, only the UE can estimate the downlink CSI. Thus, the estimated CSI may need to be shared with the NE, which can require additional resources from the network.
[0028] To reduce the overhead, several vector quantization (VQ) methods may generate a codebook that achieves a high CR (z.e., the ratio of compressed size to uncompressed size). Thus, CR is a scalar in the range of (0, 1], and lower CR may result in more compression. However, these methods cannot provide enough accuracy for CSI reconstruction with limited feedback overhead. Compressive sensing (CS)-based methods may compress the CSI based on its spatial and temporal correlation. However, channels may not be sparse, which is a key assumption for the CS-based approach. Furthermore, CS-based methods may use random projections, could lead to significant reconstruction loss in the NE.
[0029] In order to improve compression and reconstruction, an autoencoder (AE) structure from deep learning (DL) methods may be applied to the CSI-feedback application, such as with a CsiNet AE architecture (z.e., AE to compress MIMO full channels) with an encoder and a decoder. The encoder may generate a compressed representation of the input CSI, and the decoder may reconstruct the CSI from the compressed information. By joint training the encoder and decoder, the encoder and decoder may learn channel properties, and provide more accurate reconstruction compared to the CS-based methods. A modified version of the CsiNet structure (e.g, CsiNet+) may include a modified convolution kernel size and reconstruction blocks. A fully convolutional neural network (FullyConv)-based CSI feedback may also enhance the quality of reconstructed CSI, and decrease the number of trainable parameters and computational resources compared to some previous methods. Although the CsiNet, CsiNet+, and FullyConv methods may improve traditional methods, their structures are designed for a fixed CR.
[0030] To reduce the feedback payload even more, the outputs of encoder may be quantized, where the quantizer outputs bits may represent the encoder outputs. The UE may communicate the bits over the air, and the NE may receive the bits. The dequantizer may construct the decoder input using the received bits. Finally, the decoder may process the compressed signal, and reconstruct the full CSI.
[0031] Several quantization types can be used for quantization, such as uniform scalar quantization (SQ), non-uniform SQ, and VQ, as mentioned above. In SQ, each encoder output entry (z.e., element) may be quantized based on its own value and the quantization type and properties. However, in VQ, the encoder outputs may be divided into segments, and the quantization may then be applied to each segment separately. FIG. 1 depicts an example of AE-based CSI-compression, where the channel information is first compressed and then quantized at the UE. The quantized bits are transmitted over the air and received by the gNB. The decoder input is obtained by de-quantization of the received bits. As the last block, the decoder reconstructs the channel information by processing the de-quantized signal. FIG. 2 depicts an example of segmented encoder latent space with segment size (z.e.,codeword length) of three, where a codebook with 8 codewords may be considered for VQ, wherein each segment is quantized with 3 bits. The VQ codebook may include 23=8 codewords. Thus, for every three elements, 3 bits may be sent to select the proper codeword from the VQ codebook, and the overall payload size would be 2x3=6 bits.
[0032] Certain example embodiments described herein may have various benefits and / or advantages to overcome the disadvantages described above. For example, certain example embodiments may reduce overhead from sharing estimated CSI with a NE. Specifically, some example embodiments may reduce tunable signaling overhead, and improve the tradeoff between accuracy of the reconstruction and signaling overhead. Thus, certain example embodiments discussed below are directed to improvements in computer-related technology.
[0033] Various example embodiments may use artificial intelligence markup language (AIML) CSI feedback, wherein the UE encodes CSI using a CR indicated by the NE. The NE may then decode the code provided by the UE, and reconstruct the original CSI. The selection of the CR by the NE may be transparent to the UE, and may be NE-implementation specific. For example, the NE may select a fixed CR, the most conservative CR using information about the UE past link conditions, or it may select a single CR for all UEs that it serves. Nevertheless, the CR selection may optimize between CSI feedback overhead and CSI reconstruction accuracy. The CR selection may take into account the current link conditions of each target UE; thus, the CR selection may be UE- and / or time-period-specific.
[0034] Certain example embodiments may include an adaptive-CR AIML CSI feedback procedure in which a UE is assisted by the NW in selecting the best CR based upon experienced link conditions. Thus, the UE may ultimately perform CR selection tasks, while the NW may only support and constrain the selection of the CR by the UE.
[0035] FIG. 3 illustrates an example of a signaling diagram for a UE to indicate its capability for CR adaptation to a NE. The NE may then select UE-specific constraints, such as a minimum squared generalized cosine similarity (SGCS),minimum CR, and / or maximum CR, that a CR should ensure, and / or when the UE- selected CR should be applied. The CR selection and CR application to the CSI encoding may be performed for the same CSI-RS instance. Alternatively, the CR selection may be performed for a current CSI-RS instance, and the utilization of the selected CR may follow in the future CSI-RS instance. Thus, future instances may be explicitly indexed. During these periods, the UE may not be expected to perform the CR adaptation dynamically, but instead may use the previously selected CR. The UE receiving these constraints / requirements may then select the best CR that fulfills the respective requirements. NE 320 and UE 310 may be similar to NE 810 and UE 820, as illustrated in FIG. 8, according to certain example embodiments.
[0036] At operation 301, UE 310 may transmit an indication of its capabilities and / or availability to adapt CR for a CSI encoder to NE 320. For example, UE 310 may indicate (if not already known) which CR(s) it may support, and / or if UE 310 can dynamically adapt CR or whether such adaption may be performed for future CSI feedback.
[0037] At operation 302, NE 320 may use at least the indication received at operation 301 by setting any combination of the following: minimum CR and / or maximum CR (e.g., selected to constrain the reporting overhead), SGCS threshold (or any other metric) indicating the CSI reconstruction error associated with a selected CR, CSI feedback instances for which the CR adaptation is allowed, and / or any other CR constraints.
[0038] At operation 303, NE 320 may transmit to UE 310 the CR constraints from operation 302.
[0039] At operation 304, based upon the transmission at operation 303, UE 310 may use a current estimated CSI to select a set of test CRs that are within the minimum and / or maximum CR; use an available encoder with each test CR(j) to produce a test code(j); use a nominal decoder to decode code(j) and reconstruct rCSI(j); and compute the SGCS(j) between CSI and rCSI(j). In addition, after obtaining SGCS for all test codes, UE 310 may select the CR which satisfies the SGCS threshold (or any other metric) indicating the CSI reconstruction error associated with a selected CR at operation 302. In various example embodiments, the set of test CRs may be selectedbased on the properties of the estimated CSI (e.g., how frequency selective the estimated channel is) and performance of the encoder, which may be known to UE 310.
[0040] In some example embodiments, UE 310 may generate a list of test CRs, and auto-encode (using a UE-specific encoder and a nominal decoder used to train the former encoder) the CSI-RS using each test CR. UE 310 may select the CR associated with the best reconstruction error (but no lower than the minimum SGCS), and transfer it to NE 320 together with the resulting code.
[0041] At operation 305, UE 310 may apply the selected CR to the CSI feedback instances defined at operation 302.
[0042] At operation 306, UE 310 may use the selected CR to produce a code for each feedback instance. Specifically, when transferring the resulting code, UE 310 may append to the message the selected CR.
[0043] Alternatively, if the SGCS threshold cannot be fulfilled with any CR in the minimum-maximum CR, UE 310 may trigger a signal to inform NE 320. NE 320 may use the received code and UE-selected CR to decode and reconstruct the original CSI.
[0044] FIG. 4 illustrates an example of a signaling diagram for a UE to indicate its capability for CR adaptation to a NE, which may be similar to the signaling diagram of FIG. 3. However, in contrast to the signaling diagram of FIG. 3, FIG. 4 depicts a signaling diagram wherein the UE requests a CR grant from NE. The NE then evaluates the request and may accept or decline the UE CR proposal. NE 420 and UE 410 may be similar to NE 810 and UE 820, as illustrated in FIG. 8, according to certain example embodiments.
[0045] Operations 401-405 may be similar to operations 301-305.
[0046] At operation 406, UE 410 may transmit to NE 420 CSI encoding which may include the selected CR.
[0047] At operation 407, NE 420 may transmit to UE 410 at least one grant selected CR for a specific feedback instance.
[0048] FIG. 5 illustrates an example of a signaling diagram for a UE to indicate its capability for CR adaptation to a NE, which may be similar to the signaling diagrams of FIGs. 3 and 4. However, in contrast to the signaling diagrams of FIGs. 3 and 4, FIG. 5 depicts a signaling diagram wherein a UE that fails to obtain a CR complying with the requirements (e.g, either SGCS threshold, or min / max CR thresholds etc.) informs the NE about the highest CR, as well as a cause of failure (e.g, the SGCS associated with the highest CR selection. The NE may then evaluate the selected CR and either accept it, reject it and propose another CR, or adapt the CR selection requirements for that UE. NE 520 and UE 510 may be similar to NE 810 and UE 820, as illustrated in FIG. 8, according to certain example embodiments.
[0049] Operations 501-504 may be similar to operations 301-304.
[0050] At operation 505, if UE 510 determines that no CR fulfills the threshold, UE 510 may select the CR with the highest performance.
[0051] At operation 506, UE 510 may transmit to NE 520 an CR adaptation according to a constraint failed with a highest CR and / or associated SGCS.
[0052] At operation 507, NE 520 may assess the CR and SGCS, and may select a CR.
[0053] At operation 508, NE 520 may transmit to UE 510 the CR selected by NE 520 at operation 507.
[0054] FIG. 6 illustrates an example of a flow diagram of a method 600 that may be performed by a UE, such as UE 820 illustrated in FIG. 8, according to various example embodiments.
[0055] At step 601, the method may include transmitting to a NE, such as NE 810 illustrated in FIG. 8, at least one indication of at least one UE-specific capability or availability for CR adaptation. The at least one indication may indicate at least one supported CR, and / or whether the UE is configured for dynamic CR adaptation.
[0056] At step 602, the method may further include receiving from the NE at least one UE-specific CR constraint.
[0057] At step 603, the method may further include determining a CR adaptive to the at least one UE-specific CR constraint.
[0058] At step 604, the method may further include transmitting to the NE at least one of the following: the at least one determined CR or at least one indication indicating whether CR adaptation is successful.
[0059] At step 605, the method may further include selecting at least one CR that satisfies the at least one UE-specific CR constraint.
[0060] At step 606, the method may further include selecting the at least one CR which satisfies a SGCS threshold indicating at least one CSI reconstruction error associated with a selected CR. The at least one UE-specific CR constraint may include at least one of a minimum range of a CR, a maximum range of a CR, and / or the SGCS threshold.
[0061] FIG. 7 illustrates an example of a flow diagram of a method 700 that may be performed by a NE, such as NE 810 illustrated in FIG. 8, according to various example embodiments.
[0062] At step 701, the method may include receiving from a UE, such as UE 820 illustrated in FIG. 8, at least one indication of at least one UE-specific capability or availability for CR adaptation.
[0063] At step 702, the method may further include setting at least one UE-specific CR constraint. The at least one UE-specific CR constraint may be based upon at least one of minimum CR, maximum CR, a SGCS threshold, and / or at least one CSI feedback.
[0064] At step 703, the method may further include transmitting the at least one UE- specific CR constraint to the UE.
[0065] At step 704, the method may further include generating a code for at least one feedback instance.
[0066] At step 705, the method may further include receiving CSI encoded according to a selected CR.
[0067] At step 706, the method may further include transmitting to the UE at least one grant selected CR for a specific feedback instance.
[0068] At step 707, the method may further include receiving a CR adaptation according to a constraint failed with at least one of a highest compression rate or anassociated SGCS, assessing the at least one of a highest CR or an associated SGCS, and selecting a CR, and transmitting to the UE the selected CR.
[0069] FIG. 8 illustrates an example of a system according to certain example embodiments. In one example embodiment, a system may include multiple devices, such as, for example, NE 810 and / or UE 820.
[0070] NE 810 may be one or more of a base station (e.g., 3G UMTS NodeB, 4G LTE Evolved NodeB, or 5G NR Next Generation NodeB), a serving gateway, a server, and / or any other access node or combination thereof.
[0071] NE 810 may further include at least one gNB-centralized unit (CU), which may be associated with at least one gNB-distributed unit (DU). The at least one gNB-CU and the at least one gNB-DU may be in communication via at least one Fl interface, at least one Xn-C interface, and / or at least one NG interface via a 5thgeneration core (5GC).
[0072] UE 820 may include one or more of a mobile device, such as a mobile phone, smart phone, personal digital assistant (PDA), tablet, or portable media player, digital camera, pocket video camera, video game console, navigation unit, such as a global positioning system (GPS) device, desktop or laptop computer, single-location device, such as a sensor or smart meter, or any combination thereof. Furthermore, NE 810 and / or UE 820 may be one or more of a citizens broadband radio service device (CBSD).
[0073] NE 810 and / or UE 820 may include at least one processor, respectively indicated as 811 and 821. Processors 811 and 821 may be embodied by any computational or data processing device, such as a central processing unit (CPU), application specific integrated circuit (ASIC), or comparable device. The processors may be implemented as a single controller, or a plurality of controllers or processors.
[0074] At least one memory may be provided in one or more of the devices, as indicated at 812 and 822. The memory may be fixed or removable. The memory may include computer program instructions or computer code contained therein. Memories 812 and 822 may independently be any suitable storage device, such as a non-transitory computer-readable medium. The term “non-transitory,” as used herein, may correspond to a limitation of the medium itself (z. e. , tangible, not a signal) as opposedto a limitation on data storage persistency (e.g, random access memory (RAM) vs. read-only memory (ROM)). A hard disk drive (HDD), random access memory (RAM), flash memory, or other suitable memory may be used. The memories may be combined on a single integrated circuit as the processor, or may be separate from the one or more processors. Furthermore, the computer program instructions stored in the memory, and which may be processed by the processors, may be any suitable form of computer program code, for example, a compiled or interpreted computer program written in any suitable programming language.
[0075] Processors 811 and 821, memories 812 and 822, and any subset thereof, may be configured to provide means corresponding to the various blocks of FIGs. 3-7. Although not shown, the devices may also include positioning hardware, such as GPS or micro electrical mechanical system (MEMS) hardware, which may be used to determine a location of the device. Other sensors are also permitted, and may be configured to determine location, elevation, velocity, orientation, and so forth, such as barometers, compasses, and the like.
[0076] As shown in FIG. 8, transceivers 813 and 823 may be provided, and one or more devices may also include at least one antenna, respectively illustrated as 814 and 824. The device may have many antennas, such as an array of antennas configured for multiple input multiple output (MIMO) communications, or multiple antennas for multiple RATs. Other configurations of these devices, for example, may be provided. Transceivers 813 and 823 may be a transmitter, a receiver, both a transmitter and a receiver, or a unit or device that may be configured both for transmission and reception.
[0077] The memory and the computer program instructions may be configured, with the processor for the particular device, to cause a hardware apparatus, such as UE, to perform any of the processes described above (z.e., FIGs. 3-7). Therefore, in certain example embodiments, a non-transitory computer-readable medium may be encoded with computer instructions that, when executed in hardware, perform a process such as one of the processes described herein. Alternatively, certain example embodiments may be performed entirely in hardware.
[0078] In certain example embodiments, an apparatus may include circuitry configured to perform any of the processes or functions illustrated in FIGs. 3-7. As used in this application, the term “circuitry” may refer to one or more or all of the following: (a) hardware-only circuit implementations (such as implementations in only analog and / or digital circuitry), (b) combinations of hardware circuits and software, such as (as applicable): (i) a combination of analog and / or digital hardware circuit(s) with software / firmware and (ii) any portions of hardware processor(s) with software (including digital signal processor(s)), software, and memory(ies) that work together to cause an apparatus, such as a mobile phone or server, to perform various functions), and (c) hardware circuit(s) and or processor(s), such as a microprocessor(s) or a portion of a microprocessor(s), that requires software (e.g, firmware) for operation, but the software may not be present when it is not needed for operation. This definition of circuitry applies to all uses of this term in this application, including in any claims. As a further example, as used in this application, the term circuitry also covers an implementation of merely a hardware circuit or processor (or multiple processors) or portion of a hardware circuit or processor and its (or their) accompanying software and / or firmware. The term circuitry also covers, for example and if applicable to the particular claim element, a baseband integrated circuit or processor integrated circuit for a mobile device or a similar integrated circuit in server, a cellular network device, or other computing or network device.
[0079] FIG. 9 illustrates an example of a 5G network and system architecture according to certain example embodiments. Shown are multiple network functions that may be implemented as software operating as part of a network device or dedicated hardware, as a network device itself or dedicated hardware, or as a virtual function operating as a network device or dedicated hardware. The NE and UE illustrated in FIG. 9 may be similar to NE 810 and UE 820, respectively. The user plane function (UPF) may provide services such as intra-RAT and inter-RAT mobility, routing and forwarding of data packets, inspection of packets, user plane quality of service (QoS) processing, buffering of downlink packets, and / or triggering of downlink data notifications. The applicationfunction (AF) may primarily interface with the core network to facilitate application usage of traffic routing and interact with the policy framework.
[0080] According to certain example embodiments, processors 811 and 821, and memories 812 and 822, may be included in or may form a part of processing circuitry or control circuitry. In addition, in some example embodiments, transceivers 813 and 823 may be included in or may form a part of transceiving circuitry.
[0081] In some example embodiments, an apparatus (e.g, NE 810 and / or UE 820) may include means for performing a method, a process, or any of the variants discussed herein. Examples of the means may include one or more processors, memory, controllers, transmitters, receivers, and / or computer program code for causing the performance of the operations.
[0082] In various example embodiments, apparatus 820 may be controlled by memory 822 and processor 821 to transmit to a network entity at least one indication of at least one user equipment-specific capability or availability for compression rate adaptation, receive from the network entity at least one user equipment-specific compression rate constraint, and determine a compression rate adaptive to the at least one user equipmentspecific compression rate constraint.
[0083] Certain example embodiments may be directed to an apparatus that includes means for performing any of the methods described herein including, for example, means for transmitting to a network entity at least one indication of at least one user equipment-specific capability or availability for compression rate adaptation, means for receiving from the network entity at least one user equipment-specific compression rate constraint, and means for determining a compression rate adaptive to the at least one user equipment-specific compression rate constraint.
[0084] In various example embodiments, apparatus 810 may be controlled by memory 812 and processor 811 to receive from a user equipment at least one indication of at least one user equipment-specific capability or availability for compression rate adaptation, set at least one user equipment-specific compression rate constraint, and transmit the at least one user equipment-specific compression rate constraint to the user equipment.
[0085] Certain example embodiments may be directed to an apparatus that includes means for performing any of the methods described herein including, for example, means for receiving from a user equipment at least one indication of at least one user equipment-specific capability or availability for compression rate adaptation, means for setting at least one user equipment-specific compression rate constraint, and means for transmitting the at least one user equipment-specific compression rate constraint to the user equipment.
[0086] The features, structures, or characteristics of example embodiments described throughout this specification may be combined in any suitable maimer in one or more example embodiments. For example, the usage of the phrases “various embodiments,” “certain embodiments,” “some embodiments,” or other similar language throughout this specification refers to the fact that a particular feature, structure, or characteristic described in connection with an example embodiment may be included in at least one example embodiment. Thus, appearances of the phrases “in various embodiments,” “in certain embodiments,” “in some embodiments,” or other similar language throughout this specification does not necessarily all refer to the same group of example embodiments, and the described features, structures, or characteristics maybe combined in any suitable manner in one or more example embodiments.
[0087] As used herein, “at least one of the following: ” and “at least one of ” and similar wording, where the list of two or more elements are joined by “and” or “or,” mean at least any one of the elements, or at least any two or more of the elements, or at least all the elements.
[0088] Additionally, if desired, the different functions or procedures discussed above may be performed in a different order and / or concurrently with each other. Furthermore, if desired, one or more of the described functions or procedures may be optional or may be combined. As such, the description above should be considered as illustrative of the principles and teachings of certain example embodiments, and not in limitation thereof.
[0089] One having ordinary skill in the art will readily understand that the example embodiments discussed above may be practiced with procedures in a different order,and / or with hardware elements in configurations which are different than those which are disclosed. Therefore, although some embodiments have been described based upon these example embodiments, it would be apparent to those of skill in the art that certain modifications, variations, and alternative constructions would be apparent, while remaining within the spirit and scope of the example embodiments.
[0090] Partial Glossary
[0091] 3GPP 3rdGeneration Partnership Project
[0092] 5G 5thGeneration
[0093] 5GC 5thGeneration Core
[0094] 6G 6thGeneration
[0095] AE Autoencoder
[0096] AF Application Function
[0097] AIML Artificial Intelligence Markup Language
[0098] ASIC Application Specific Integrated Circuit
[0099] BS Base Station
[0100] CBSD Citizens Broadband Radio Service Device
[0101] CPU Central Processing Unit
[0102] CR Compression Rate
[0103] CSI Channel State Information
[0104] CU Centralized Unit
[0105] DL Deep Learning
[0106] DU Distributed Unit
[0107] eMBB Enhanced Mobile Broadband
[0108] eNB Evolved Node B
[0109] FDD Frequency Division Duplex
[0110] gNB Next Generation Node B
[0111] GPS Global Positioning System
[0112] HDD Hard Disk Drive
[0113] loT Internet of Things
[0114] LTE Long-Term Evolution[0115J LTE-A Long-Term Evolution Advanced
[0116] MEMS Micro Electrical Mechanical System
[0117] MIMO Multiple Input Multiple Output
[0118] mMTC Massive Machine Type Communication[0119JNE Network Entity
[0120] NG Next Generation
[0121] NG-eNB Next Generation Evolved Node B
[0122] NG-RAN Next Generation Radio Access Network
[0123] NR New Radio
[0124] PDA Personal Digital Assistance
[0125] QoS Quality of Service
[0126] RAM Random Access Memory
[0127] RAN Radio Access Network
[0128] RAT Radio Access Technology
[0129] RF Radio Frequency
[0130] ROM Read-Only Memory
[0131] SGCS Squared Generalized Cosine Similarity
[0132] SNR Signal-to-Noise-Ratio
[0133] SQ Scalar Quantization
[0134] UE User Equipment
[0135] UMTS Universal Mobile Telecommunications System
[0136] UPF User Plane Function
[0137] URLLC Ultra-Reliable and Low-Latency Communication
[0138] UTRAN Universal Mobile Telecommunications System TerrestrialRadio Access Network
[0139] VQ Vector Quantization
[0140] WLAN Wireless Local Area Network
Claims
WE CLAIM:
1. An apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: transmit to a network entity at least one indication of at least one user equipmentspecific capability or availability for compression rate adaptation; receive from the network entity at least one user equipment-specific compression rate constraint; and determine a compression rate adaptive to the at least one user equipment-specific compression rate constraint.
2. The apparatus of claim 1, wherein the at least one indication indicates at least one supported compression rate.
3. The apparatus of claim 1 or 2, wherein the at least one indication indicates whether the apparatus is configured for dynamic compression rate adaptation.
4. The apparatus of any of claims 1-3, wherein the at least one memory and the instructions, when executed by the at least one processor, further cause the apparatus at least to: transmit to the network entity at least one of the following: the at least one determined compression rate or at least one indication indicating whether compression rate adaptation is successful.
5. The apparatus of any of claims 1-4, wherein the at least one memory and the instructions, when executed by the at least one processor, further cause the apparatus at least to:select at least one compression rate that satisfies the at least one user equipmentspecific compression rate constraint.
6. The apparatus of any of claims 1-5, wherein the at least one user equipment-specific compression rate constraint comprises at least one of the following: a minimum range of a compression ratio; a maximum range of a compression ratio; or a squared generalized cosine similarity threshold.
7. The apparatus of claim 6, wherein the at least one memory and the instructions, when executed by the at least one processor, further cause the apparatus at least to: select the at least one compression rate which satisfies the squared generalized cosine similarity threshold indicating at least one channel state information reconstruction error associated with the at least one selected compression rate.
8. An apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: receive from a user equipment at least one indication of at least one user equipment-specific capability or availability for compression rate adaptation; set at least one user equipment-specific compression rate constraint; and transmit the at least one user equipment-specific compression rate constraint to the user equipment.
9. The apparatus of claim 8, wherein the at least one user equipment-specific compression rate constraint is based upon at least one of the following: a minimum compression rate, maximum compression rate, a squared generalized cosine similarity threshold, or at least one channel state information feedback.
10. The apparatus of claim 8 or 9, wherein the at least one memory and the instructions, when executed by the at least one processor, further cause the apparatus at least to: generate a code for at least one feedback instance.
11. The apparatus of any of claims 8-10, wherein the at least one memory and the instructions, when executed by the at least one processor, further cause the apparatus at least to: receive channel state information encoded according to a selected compression rate.
12. The apparatus of any of claims 8-11, wherein the at least one memory and the instructions, when executed by the at least one processor, further cause the apparatus at least to: transmit to the user equipment at least one grant selected compression rate for a specific feedback instance.
13. The apparatus of any of claims 8-12, wherein the at least one memory and the instructions, when executed by the at least one processor, further cause the apparatus at least to: receive a compression rate adaptation according to a constraint failed with at least one of a highest compression rate or an associated squared generalized cosine similarity; assess the at least one of a highest compression rate or the associated squared generalized cosine similarity, and select a compression rate; and transmit to the user equipment the selected compression rate.
14. An apparatus comprising:means for transmitting to a network entity at least one indication of at least one user equipment-specific capability or availability for compression rate adaptation; means for receiving from the network entity at least one user equipment-specific compression rate constraint; and means for determining a compression rate adaptive to the at least one user equipment-specific compression rate constraint.
15. The apparatus of claim 14, wherein the at least one indication indicates at least one supported compression rate.
16. The apparatus of claim 14 or 15, wherein the at least one indication indicates whether the apparatus is configured for dynamic compression rate adaptation.
17. The apparatus of any of claims 14-16, further comprising: means for transmitting to the network entity at least one of the following: the at least one determined compression rate or at least one indication indicating whether compression rate adaptation is successful.
18. The apparatus of any of claims 14-17, further comprising: means for selecting at least one compression rate that satisfies the at least one user equipment-specific compression rate constraint.
19. The apparatus of any of claims 14-18, wherein the at least one user equipment-specific compression rate constraint comprises at least one of the following: a minimum range of a compression ratio; a maximum range of a compression ratio; or a squared generalized cosine similarity threshold.
20. The apparatus of claim 19, further comprising:means for selecting the at least one compression rate which satisfies the squared generalized cosine similarity threshold indicating at least one channel state information reconstruction error associated with the at least one selected compression rate.
21. An apparatus comprising : means for receiving from a user equipment at least one indication of at least one user equipment-specific capability or availability for compression rate adaptation; means for setting at least one user equipment-specific compression rate constraint; and means for transmitting the at least one user equipment-specific compression rate constraint to the user equipment.
22. The apparatus of claim 21, wherein the at least one user equipmentspecific compression rate constraint is based upon at least one of the following: minimum compression rate, maximum compression rate, a squared generalized cosine similarity threshold, or at least one channel state information feedback.
23. The apparatus of claim 21 or 22, further comprising: means for generating a code for at least one feedback instance.
24. The apparatus of any of claims 21-23, further comprising: means for receiving channel state information encoded according to a selected compression rate.
25. The apparatus of any of claims 21-24, further comprising: means for transmitting to the user equipment at least one grant selected compression rate for a specific feedback instance.
26. The apparatus of any of claims 21-25, further comprising:means for receiving a compression rate adaptation according to a constraint failed with at least one of a highest compression rate or an associated squared generalized cosine similarity; means for assessing the at least one of a highest compression rate or an associated squared generalized cosine similarity, and select a compression rate; and means for transmitting to the user equipment the selected compression rate.
27. A method comprising: transmitting, by a user equipment, to a network entity at least one indication of at least one user equipment-specific capability or availability for compression rate adaptation; receiving from the network entity at least one user equipment-specific compression rate constraint; and determining a compression rate adaptive to the at least one user equipmentspecific compression rate constraint.
28. The method of claim 27, wherein the at least one indication indicates at least one supported compression rate.
29. The method of claim 27 or 28, wherein the at least one indication indicates whether the user equipment is configured for dynamic compression rate adaptation.
30. The method of any of claims 27-29, further comprising: transmitting to the network entity at least one of the following: the at least one determined compression rate or at least one indication indicating whether compression rate adaptation is successful.
31. The method of any of claims 27-30, further comprising:selecting at least one compression rate that satisfies the at least one user equipment-specific compression rate constraint.
32. The method of any of claims 27-31, wherein the at least one user equipment-specific compression rate constraint comprises at least one of the following: a minimum range of a compression ratio; a maximum range of a compression ratio; or a squared generalized cosine similarity threshold.
33. The method of claim 32, further comprising: selecting the at least one compression rate which satisfies the squared generalized cosine similarity threshold indicating at least one channel state information reconstruction error associated with the at least one selected compression rate.
34. A method comprising: receiving from a user equipment at least one indication of at least one user equipment-specific capability or availability for compression rate adaptation; setting at least one user equipment-specific compression rate constraint; and transmitting the at least one user equipment-specific compression rate constraint to the user equipment.
35. The method of claim 34, wherein the at least one user equipment-specific compression rate constraint is based upon at least one of the following: minimum compression rate, maximum compression rate, a squared generalized cosine similarity threshold, or at least one channel state information feedback.
36. The method of claim 34 or 35, further comprising: means for generating a code for at least one feedback instance.
37. The method of any of claims 34-36, further comprising:receiving channel state information encoded according to a selected compression rate.
38. The method of any of claims 34-37, further comprising: transmitting to the user equipment at least one grant selected compression rate for a specific feedback instance.
39. The method of any of claims 34-38, further comprising: receiving a compression rate adaptation according to a constraint failed with at least one of a highest compression rate or an associated squared generalized cosine similarity; assessing the at least one of a highest compression rate or an associated squared generalized cosine similarity, and select a compression rate; and transmitting to the user equipment the selected compression rate.
40. A non-transitory computer readable medium comprising program instructions that, when executed by an apparatus, cause the apparatus to perform at least a method according to any of claims 27-39.
41. An apparatus comprising circuitry configured to perform a method according to any of claims 27-39.
42. A computer program comprising instructions, which, when executed by an apparatus, cause the apparatus to perform the method of any of claims 27-39.
Citation Information
Patent Citations
Method and apparatus for support of machine learning or artificial intelligence techniques for CSI feedback in FDD MIMO systems
US20220338189A1
Methods and apparatuses for multi-resolution CSI feedback for wireless systems
WO2023081187A1
Method and apparatus for transceiving CSI feedback in cellular systems
WO2024063536A1
Method and device for reporting CSI based on ai model in wireless communication system
WO2024096355A1
