Downlink pilot signal compression

Abstract

A method is disclosed, comprising: receiving a configuration for downlink pilot signal compression from a radio access network node; based on the configuration, compressing one or more downlink pilot signals received from the radio access network node; and transmitting information related to the one or more compressed downlink pilot signals to the radio access network node.

Description

Technical Field

[0001] The following example embodiments relate to wireless communication. Background Technology

[0002] Pilot signals are known data sequences transmitted within a communication system that can be used to facilitate the estimation of channel state information (CSI). Summary of the Invention

[0003] The scope of protection sought by the various exemplary embodiments is set forth in the independent claims. Exemplary embodiments and features (if any) described in this specification that do not fall within the scope of the independent claims are to be interpreted as examples useful for understanding the various embodiments.

[0004] According to one aspect, an apparatus is provided, comprising at least one processor and at least one memory storing instructions, the instructions, when executed by the at least one processor, causing the apparatus to at least: receive from a radio access network node a configuration for downlink pilot signal compression; compress one or more downlink pilot signals received from the radio access network node based on the configuration; and transmit to the radio access network node information relating to the one or more compressed downlink pilot signals.

[0005] According to another aspect, an apparatus is provided, comprising: means for receiving from a radio access network node a configuration for downlink pilot signal compression; means for compressing one or more downlink pilot signals received from the radio access network node based on the configuration; and means for transmitting to the radio access network node information relating to the one or more compressed downlink pilot signals.

[0006] According to another aspect, a method is provided, comprising: receiving from a radio access network node a configuration for downlink pilot signal compression; compressing one or more downlink pilot signals received from the radio access network node based on the configuration; and sending to the radio access network node information relating to the one or more compressed downlink pilot signals.

[0007] According to another aspect, a computer program is provided, including instructions that, when executed by a device, cause the device to at least: receive a configuration for downlink pilot signal compression from a radio access network node; compress one or more downlink pilot signals received from the radio access network node based on the configuration; and send information relating to the one or more compressed downlink pilot signals to the radio access network node.

[0008] According to another aspect, a computer-readable medium is provided, including program instructions that, when executed by a device, cause the device to at least: receive from a radio access network node a configuration for downlink pilot signal compression; compress one or more downlink pilot signals received from the radio access network node based on the configuration; and transmit to the radio access network node information relating to the one or more compressed downlink pilot signals.

[0009] According to another aspect, a non-transitory computer-readable medium is provided, including program instructions that, when executed by a device, cause the device to at least: receive from a radio access network node a configuration for downlink pilot signal compression; compress one or more downlink pilot signals received from the radio access network node based on the configuration; and transmit to the radio access network node information related to the one or more compressed downlink pilot signals.

[0010] According to another aspect, an apparatus is provided, comprising at least one processor and at least one memory storing instructions, the instructions, when executed by the at least one processor, causing the apparatus to at least: send configuration for downlink pilot signal compression to a user equipment; receive information from the user equipment relating to one or more compressed downlink pilot signals; construct one or more downlink pilot signals based on the information; and perform downlink channel estimation based at least on one or more constructed downlink pilot signals.

[0011] According to another aspect, an apparatus is provided, comprising: means for transmitting to a user equipment a configuration for downlink pilot signal compression; means for receiving from the user equipment information relating to one or more compressed downlink pilot signals; means for constructing one or more downlink pilot signals based on the information; and means for performing downlink channel estimation based at least on one or more constructed downlink pilot signals.

[0012] According to another aspect, a method is provided, comprising: sending configuration for downlink pilot signal compression to a user equipment; receiving information from the user equipment relating to one or more compressed downlink pilot signals; constructing one or more downlink pilot signals based on the information; and performing downlink channel estimation based at least on one or more constructed downlink pilot signals.

[0013] According to another aspect, a computer program is provided, including instructions that, when executed by a device, cause the device to at least: send a configuration for downlink pilot signal compression to a user equipment; receive information from the user equipment relating to one or more compressed downlink pilot signals; construct one or more downlink pilot signals based on the information; and perform downlink channel estimation based at least on one or more constructed downlink pilot signals.

[0014] According to another aspect, a computer-readable medium is provided, including program instructions that, when executed by a device, cause the device to at least: transmit a configuration for downlink pilot signal compression to a user equipment; receive information from the user equipment relating to one or more compressed downlink pilot signals; construct one or more downlink pilot signals based on the information; and perform downlink channel estimation based at least on one or more constructed downlink pilot signals.

[0015] According to another aspect, a non-transitory computer-readable medium is provided, including program instructions that, when executed by an apparatus, cause the apparatus to at least: send a configuration for downlink pilot signal compression to a user equipment; receive information from the user equipment relating to one or more compressed downlink pilot signals; construct one or more downlink pilot signals based on the information; and perform downlink channel estimation based at least on one or more constructed downlink pilot signals. Attached Figure Description

[0016] In the following description, various exemplary embodiments will be described in more detail with reference to the accompanying drawings, wherein Figure 1 An example of a wireless communication network is shown; Figure 2A An example of channel state information compression using a type I or type II codebook is shown; Figure 2B An example of channel state information compression based on an autoencoder is shown; Figure 3A A system according to an example embodiment is shown; Figure 3B A system according to an example embodiment is shown; Figure 3C A system according to an example embodiment is shown; Figure 4 A signal flow diagram according to an example embodiment is shown; Figure 5 A signal flow diagram according to an example embodiment is shown; Figure 6 A signal flow diagram according to an example embodiment is shown; Figure 7A flowchart according to an example embodiment is shown; Figure 8 A flowchart according to an example embodiment is shown; Figure 9 An example of the device is shown; and Figure 10 An example of the device is shown. Detailed Implementation

[0017] The following embodiments are exemplary. Although the specification may refer to "a," "an," or "some" embodiments in several places in the text, this does not necessarily mean that the same embodiment is mentioned every time, or that a particular feature applies only to a single embodiment. Individual features of different embodiments may also be combined to provide other embodiments.

[0018] Some example embodiments described herein can be implemented in wireless communication networks, including radio access networks based on one or more of the following radio access technologies (RATs): Global System for Mobile Communications (GSM) or any other second-generation radio access technology, Universal Mobile Telecommunications System (UMTS, 3G) based on Basic Wideband Code Division Multiple Access (W-CDMA), High-Speed ​​Packet Access (HSPA), Long Term Evolution (LTE), LTE Advanced, Fourth Generation (4G), Fifth Generation (5G), 5G New Radio (NR), Advanced 5G (i.e., 3GPP NR Rel-18 and above), or Sixth Generation (6G). Some examples of radio access networks include Universal Mobile Telecommunications System (UMTS) Radio Access Network (UTRAN), Evolved Universal Terrestrial Radio Access Network (E-UTRA), or Next Generation Radio Access Network (NG-RAN). The wireless communication network may also include a core network, and some example embodiments may also be applied to the network functions of the core network.

[0019] It should be noted that the embodiments are not limited to the wireless communication networks given as examples, but those skilled in the art can apply the solutions to other wireless communication networks or systems with the necessary properties. For example, some example embodiments can also be applied to communication systems based on the IEEE 802.11 standard or the IEEE 802.15 standard. IEEE is an abbreviation for the Institute of Electrical and Electronics Engineers.

[0020] Figure 1 An example of a simplified wireless communication network is depicted, showing some physical and logical entities. Figure 1 The connection shown can be a physical connection or a logical connection. It will be apparent to those skilled in the art that the wireless communication network may also include, in addition to… Figure 1 Other physical and logical entities besides those shown.

[0021] However, the exemplary embodiments described herein are not limited to the wireless communication networks given as examples, but those skilled in the art can apply the exemplary embodiments described herein to other wireless communication networks that provide the necessary properties.

[0022] Figure 1 The example wireless communication network shown includes a radio access network (RAN) and a core network 110.

[0023] Figure 1 User equipment (UE) 100, 102 is shown that is configured to wirelessly connect to access node 104 of radio access network on one or more communication channels in radio cell.

[0024] Access node 104 may include a computing device configured to control the radio resources of access node 104 and to wirelessly connect to one or more UEs 100, 102. Access node 104 may also be referred to as a base station, base transceiver unit (BTS), access point, cell site, network node, radio access network node, or RAN node. Access node 104 may be, for example, an evolved Node B (eNB or eNodeB) providing a radio cell, or a next-generation evolved Node B (ng-eNB), or a next-generation Node B (gNB or gNodeB). Access node 104 may include or be coupled to a transceiver. A connection from the transceiver of access node 104 to an antenna element may be provided, which establishes a bidirectional radio link to one or more UEs 100, 102. The antenna element may include an antenna or antenna element, or multiple antennas or antenna elements.

[0025] The radio connection (e.g., a radio link) from UE 100, 102 to access node 104 may be referred to as an uplink (UL) or reverse link, and the radio connection (e.g., a radio link) from access node 104 to UE 100, 102 may be referred to as a downlink (DL) or forward link. UE 100 may also communicate directly with another UE 102 via a radio connection commonly referred to as a side link (SL), and vice versa. It should be understood that access node 104, or its functionality, can be implemented using any node, host, server, access point, or other entity suitable for providing such functionality.

[0026] A radio access network may include more than one access node 104, in which case the access nodes may also be configured to communicate with each other via wired or wireless links. These links between access nodes may be used to send and receive control plane signaling, and also to route data from one access node to another.

[0027] Access node 104 may also be connected to core network (CN) 110. Core network 110 may include an evolved packet core (EPC) network and / or a 5th generation core network (5GC). EPC may include network entities such as a serving gateway (S-GW for routing and forwarding data packets), a packet data network gateway (P-GW) for providing connectivity to external packet data networks for the UE, and / or a mobility management entity (MME). 5GC may include one or more network functions such as at least one of the following: user plane function (UPF), access and mobility management function (AMF), location management function (LMF), and / or session management function (SMF).

[0028] The core network 110 may also be able to communicate with or utilize services provided by one or more external networks 113 (such as the public switched telephone network or the Internet). For example, in a 5G wireless communication network, the UPF of the core network 110 may be configured to communicate with an external data network via an N6 interface. In an LTE wireless communication network, the P-GW of the core network 110 may be configured to communicate with an external data network.

[0029] It should also be understood that, compared to LTE or 5G, the functional distribution between core network operations and access node operations may differ in future wireless communication networks, or may not even exist.

[0030] The illustrated UEs 100 and 102 are a type of apparatus to which resources on the air interface can be allocated and assigned. UEs 100 and 102 may also be referred to as wireless communication devices, subscriber units, mobile stations, remote terminals, access terminals, user terminals, terminal equipment, or user equipment, to name just a few. UEs 100 and 102 may be computing devices operating with or without a Subscriber Identity Module (SIM), including but not limited to the following types of computing devices: mobile phones, smartphones, personal digital assistants (PDAs), handheld devices, computing devices including wireless modems (e.g., alarm or measuring devices), laptop computers, desktop computers, tablet devices, game consoles, laptops, multimedia devices, redcap devices, wearable devices with radio components (e.g., watches, headphones, or glasses), sensors including wireless modems, or computing devices including wireless modems integrated into vehicles.

[0031] It should be understood that UEs 100 and 102 can also be almost dedicated uplink-only devices, examples of which could be cameras or camcorders that load image or video clips onto the network. UEs 100 and 102 can also be devices capable of operating in Internet of Things (IoT) networks, which are scenarios where objects can be provided with the ability to transmit data over the network without requiring human-to-human or human-to-computer interaction.

[0032] Wireless communication networks can also support the use of cloud services. For example, at least a portion of core network operations can be performed as a cloud service (this is in...). Figure 1 (Depicted by "Cloud" 114). UEs 100 and 102 can also utilize Cloud 114. In some applications, computations for a given UE can be performed in Cloud 114 or another UE.

[0033] Wireless communication networks may also include a central control entity, such as a Network Management System (NMS). An NMS is a centralized suite of software and hardware used to monitor, control, and manage network infrastructure. The NMS is responsible for a wide range of tasks, such as fault management, configuration management, security management, performance management, and accounting management. The NMS enables network operators to effectively manage and optimize network resources, ensuring that the network delivers high performance, reliability, and security.

[0034] 5G enables the use of multiple-input multiple-output (MIMO) antennas in access nodes 104 and / or UEs 100, 102, and far more base stations or access nodes than LTE networks (the so-called small cell concept), including macro sites that cooperate with smaller stations and employ various radio technologies depending on service requirements, use cases, and / or available spectrum. 5G wireless communication networks can support a wide range of use cases and related applications, including video streaming, augmented reality, different data sharing methods, and various forms of machine-type applications such as (massive) machine-type communication (mMTC), including vehicle safety, various sensors, and real-time control.

[0035] In 5G wireless communication networks, access nodes and / or UEs can have multiple radio interfaces, such as sub-6 GHz, centimeter wave (cmWave), and millimeter wave (mmWave), and can also be integrated with traditional radio access technologies (such as LTE). For example, integration with LTE can be implemented as a system where macro coverage can be provided by LTE, and 5G radio interface access can be aggregated to LTE from small cells. In other words, 5G wireless communication networks can support inter-RAT interoperability (such as interoperability between LTE and 5G) and inter-RI interoperability (interoperability between radio interfaces, such as between sub-6 GHz, cmWave, and mmWave).

[0036] 5G wireless communication networks can also apply network slicing, in which multiple independent and dedicated virtual sub-networks (network instances) can be created within the same physical infrastructure to run services with different requirements for latency, reliability, throughput and mobility.

[0037] In one embodiment, access node 104 may include: radio units (RUs) including radio transceivers (TRXs), i.e., transmitters (Tx) and receivers (Rx); one or more distributed units (DUs) 105, which can be used for so-called Layer 1 (L1) processing and real-time Layer 2 (L2) processing; and a central unit (CU) 108 (also called a centralized unit), which can be used for non-real-time L2 and Layer 3 (L3) processing. CU 108 may be connected to one or more DUs 105, for example, via an F1 interface. Such an embodiment of access node 104 allows for the centralization of CUs relative to cell sites and DUs, while DUs can be more distributed and may even remain at the cell site. CUs and DUs together may also be referred to as baseband or baseband unit (BBU). CUs and DUs may also be included in a radio access point (RAP).

[0038] CU 108 may be a logical node hosting the Radio Resource Control (RRC), Service Data Adaptation Protocol (SDAP), and / or Packet Data Convergence Protocol (PDCP) for the NR protocol stack used by access node 104. CU 108 may include a control plane (CU-CP), which may be a logical node hosting the RRC and control plane portions of the PDCP protocol for the NR protocol stack used by access node 104. CU 108 may also include a user plane (CU-UP), which may be a logical node hosting the user plane portions of the PDCP and SDAP protocols for the CU used by access node 104.

[0039] DU 105 can be a logical node hosting the Radio Link Control (RLC), Media Access Control (MAC), and / or Physical (PHY) layers of the NR protocol stack used by Access Node 104. The operation of DU 105 can be controlled at least partially by CU 108. It should also be understood that the functional distribution between DU 105 and CU 108 can vary depending on the implementation.

[0040] Cloud computing systems can also be used to provide CU 108 and / or DU 105. CUs provided by cloud computing systems can be referred to as virtualized CUs (vCUs). In addition to vCUs, virtualized DUs (vDUs) provided by cloud computing systems can also exist. Furthermore, combinations can exist where DUs can be implemented on so-called bare-metal solutions, such as application-specific integrated circuits (ASICs) or customer-specific standard product (CSSP) system-on-chips (SoCs).

[0041] By leveraging Network Functions Virtualization (NFV) and Software-Defined Networking (SDN), edge cloud can be brought into the radio access network. Using edge cloud can mean that access node operations will be performed, at least partially, on a computing system operatively coupled to a Remote Radio Head (RRH) or Radio Unit (RU) at access node 104. Access node operations can also be performed on a distributed computing system or cloud computing system located at access node 104. The application of a cloud RAN architecture enables the execution of real-time RAN functions at the radio access network (e.g., in DU 105) and (e.g., in CU 108) the centralized execution of non-real-time functions.

[0042] 5G (or New Radio, NR) wireless communication networks can support multiple tiers, where multi-access edge computing (MEC) servers can be placed between the core network 110 and access nodes 104. It should be understood that MEC can also be applied to LTE wireless communication networks.

[0043] 5G wireless communication networks (“5G networks”) may also include non-terrestrial communication networks, such as satellite communication networks, to enhance or supplement the coverage of 5G radio access networks. For example, satellite communications can support data transmission between the 5G radio access network and the core network 110, thereby achieving broader network coverage. Possible use cases may include providing service continuity for machine-to-machine (M2M) or Internet of Things (IoT) devices or for passengers on transportation vehicles, or ensuring the service availability of critical communications and future rail, sea, or air communications. Satellite communications can utilize geostationary Earth orbit (GEO) satellite systems, but can also utilize low Earth orbit (LEO) satellite systems, particularly mega-constellations (i.e., systems in which hundreds of (nanometer) satellites are deployed). A given satellite 106 in a mega-constellation can cover several satellite-enabled network entities that create terrestrial cells. Terrestrial cells can be created by terrestrial relay access nodes or by access nodes located on the ground or in satellites.

[0044] It is obvious to those skilled in the art that Figure 1 The access node 104 depicted is merely an example of a portion of a radio access network, and in practice, a radio access network may include multiple access nodes 104, UEs 100 and 102 may access multiple radio cells, and the radio access network may also include other devices, such as physical layer relay access nodes or other entities. At least one of the access nodes may be a home eNodeB or a home gNodeB. A home gNodeB or home eNodeB is a type of access node that can be used to provide indoor coverage in a home, office, or other indoor environment.

[0045] In addition, multiple different types of radio cells and multiple radio cells can be provided within the geographical area of ​​the radio access network. Radio cells can be macrocells (or umbrella cells), which can be large cells with diameters of up to tens of kilometers, or smaller cells such as microcells, femtocells, or picocells. Figure 1 Multiple access nodes 104 can provide any type of these cells. A cellular radio network can be implemented as a multi-layered access network comprising several types of radio cells. In a multi-layered access network, one access node can provide one or more types of radio cells, thus multiple access nodes may be required to provide such a multi-layered access network.

[0046] To meet the need for improved performance in radio access networks, the concept of "plug-and-play" access nodes can be introduced. In addition to home eNodeBs or home gNodeBs, radio access networks capable of using "plug-and-play" access nodes can also include home node B gateways (HNB-GW). Figure 1 (Not shown in the image). An HNB-GW, which can be installed within an operator's radio access network, can aggregate traffic from a large number of home eNodeBs or home gNodeBs back to the operator's core network 110.

[0047] Precoding in massive MIMO communication using a Frequency Division Duplex (FDD) scheme may require Channel State Information (CSI). Accurate CSI can be used by RAN node 104 to achieve a higher signal-to-noise ratio (SNR) and channel capacity. However, in an FDD network, only UEs 100 and 102 are able to estimate the downlink CSI. Therefore, the estimated CSI may need to be shared with RAN node 104, introducing overhead to the network.

[0048] To reduce overhead, various vector quantization techniques can be used to generate codebooks that achieve a low compression ratio (CR) (i.e., the ratio of uncompressed size to compressed size). CR is [1, ... The scalar values ​​are within a range, where a higher CR implies more compression. However, these techniques alone cannot provide sufficient accuracy for CSI reconstruction with limited feedback overhead.

[0049] Compressed sensing (CS) techniques can be used to compress CSI based on its spatial and temporal correlation. However, the channel may not be sparse, as assumed for CS-based methods. Furthermore, CS-based techniques use random projection, which can lead to significant reconstruction loss at RAN node 104.

[0050] For compression and reconstruction tasks, autoencoder (AE) architectures from deep learning (DL) techniques can be applied to CSI feedback applications. For example, a CSI sensing and reconstruction architecture called CsiNet can be used to perform compression and reconstruction tasks by using an encoder and a decoder. The encoder generates a compressed representation of the input CSI, and the decoder reconstructs the CSI from the compressed information. Through joint training of the encoder and decoder, CsiNet learns the channel structure and provides more accurate reconstructions compared to CS-based techniques. A modified version of the CsiNet architecture, called CsiNet+, can be achieved by modifying the convolutional kernel size and reconstruction blocks.

[0051] Furthermore, compared to previous techniques, CSI feedback based on fully convolutional neural networks (FullyConv) can be used to enhance the quality of reconstructed CSI and reduce the number of trainable parameters and computational resources. Although CsiNet, CsiNet+, and FullyConv techniques may outperform traditional techniques (e.g., CS), these architectures are designed for fixed CR.

[0052] To further reduce the feedback payload, the encoder output can be quantized. The quantizer output bits represent the encoder output. UEs 100 and 102 can transmit these bits over the air, and RAN node 104 receives them. Then, the dequantizer at RAN node 104 can use the received bits to construct the decoder input. Finally, the decoder at RAN node 104 processes the compressed signal and reconstructs the complete CSI.

[0053] In CSI compression using two-sided model use cases, the following collaborative training of artificial intelligence (AI) or machine learning (ML) models is possible: jointly training two-sided models at a single side or entity (e.g., UE side or network side); jointly training two-sided models at the network side and UE side respectively; and training them separately at the network side and UE side, wherein the UE side CSI generation part and the network side CSI reconstruction part are trained by the UE side and the network side respectively.

[0054] Joint training means that the generative model and the reconstructed model should be trained in the same loop for forward and backward propagation. Joint training can be performed at a single node or across multiple nodes (e.g., through gradient exchange between nodes).

[0055] Individual training can include sequential training starting from the UE side, sequential training starting from the network side, or parallel training on both the UE and network sides.

[0056] However, it should be noted that other types of collaboration besides those mentioned above are also possible.

[0057] To evaluate AI / ML-based CSI feedback enhancement, for channel estimation, the ideal DL channel estimate can optionally be incorporated into the baseline of the error vector magnitude (EVM) for calibration and / or comparison of intermediate results (e.g., the accuracy of the AI / ML output CSI). The actual channel estimate should be considered in the performance evaluation.

[0058] Figure 2A An example of CSI compression using type I or type II codebook 200, 220 is shown.

[0059] Figure 2B An example of CSI compression based on an autoencoder is shown.

[0060] exist Figure 2A and Figure 2B In this process, UE 100 estimates DL CSI 203 based on the received DL pilot signal 201 and uses a UE-specific channel estimation algorithm 202.

[0061] exist Figure 2A In this context, type I or type II codebook 200 is used to generate a compressed representation of the input CSI 203.

[0062] exist Figure 2B In this process, encoder 204 generates a compressed representation of input CSI 203. Because the input CSI 203 to encoder 204 is obtained using UE-specific channel estimation algorithm 202, the distribution of encoder input CSI and therefore the distribution of compressed CSI can be changed by using different channel estimators.

[0063] Quantizer 205 converts the compressed signal Z from encoder 204 or codebook 200 into a quantizer. e Mapped to representation Z q The function of compressed bit sequences.

[0064] In block 206, UE 100 transmits the compressed bit sequence Z of quantizer 205 to RAN node 104 via the air interface using orthogonal frequency division multiplexing (OFDM). q .

[0065] In box 207, RAN node 104 receives OFDM transmission from UE 100 and obtains a representation of Y from that transmission. q The compressed bit sequence (corresponding to bit sequence Z) q ).

[0066] When UE 100 transmits bit sequence Z over the air q At that time, in the bit sequence Y received by RAN node 104 qThere may be some errors in this. However, depending on the channel encoders used in the OFDM transmit and receive chains (such as low-density parity check (LDPC)), the bit sequence Y... q The error probability in the received bit sequence Y is likely to be very low. Therefore, in most cases, the error probability in the received bit sequence Y is low. q It can be used with the transmitted bit sequence Z q same.

[0067] The de-quantizer 208 uses a compressed bit sequence Y q The compressed signal Y is constructed as input. e (corresponding to Z) e ).

[0068] Codebook 220 or decoder 209 is used to process the compressed signal Y received from dequantizer 208. e It outputs the reconstructed DL CSI 210 (corresponding to the estimated DL CSI 203 for UE 100).

[0069] As mentioned above, different UEs can use different algorithms for channel estimation tasks, resulting in different levels of accuracy for estimated channels. Additionally, due to the high computational complexity and / or limited power involved in some UEs, they may not use complex channel estimators. The UE-specific channel estimator 202 adds another generalization requirement to the encoder 204 and decoder 209. Since the compressed CSI may differ depending on the channel estimator, it is necessary to train the encoder and decoder to adapt themselves to different channel estimators.

[0070] Furthermore, the channel reconstruction at RAN node 104 depends on the channel estimator 202 used at UE 100, which may affect the beamforming performance of RAN node 104. Additionally, even when Channel State Information Reference Signal (CSI-RS) is received at UE 100, the UE vendor may not always use CSI-RS-based channel estimation for CSI quantity determination, and they may fine-tune the CSI quantity using other channels and past measurements before sending it to RAN node 104. Since the standard does not restrict this possibility, this processing step can alter the actual channel characteristics that RAN node 104 expects to know from the UE side.

[0071] However, the following description of some example embodiments uses the principles and terminology of 5G radio access technology, without limiting the example embodiments to 5G radio access technology.

[0072] Some example embodiments can provide solutions to the problem of the dependence of the CSI compression task on the channel estimation algorithm considered at the UE. Some example embodiments provide the signaling required to achieve direct compression of the received CSI-RS. The CSI-RS is based on a pseudo-random sequence, which is multiplied by a weighted sequence in both the time and frequency domains. Furthermore, it is then scaled by a power scaling factor and mapped to a specific set of resource elements in the resource grid.

[0073] In some example embodiments, the UE can directly compress the received DL pilot signal (e.g., CSI-RS). Here, the DL pilot signal refers to the received sequence after demapping from resource elements in the resource grid. The RAN node receives the compressed information and (re)constructs the DL pilot signal. The RAN node can then use a channel estimator to estimate the DLCSI.

[0074] Depending on the capabilities of the UE and RAN nodes for compression, (re)construction, and channel estimation tasks, the UE can be configured by the RAN nodes with different operating modes, such as a separate quantization scheme (SQS) or an automatic encoder quantization scheme (AQS) associated with direct pilot signal compression and feedback.

[0075] In the SQS scheme, RAN nodes share the necessary preprocessing functions (e.g., normalization, shaping, etc.) on the measured DL pilot signals. The UE follows the quantization configuration (scalar or vector quantization) indicated by the RAN node. In the case of vector quantization, the RAN node can use the channel coherence time and bandwidth expected by the RAN node to provide the quantizer configuration (e.g., providing the grouping techniques and parameters for the pilot resource elements). Additionally, RAN nodes can share the vector quantization codebook for quantizing the pilot resource elements used for grouping.

[0076] In the AQS scheme, RAN nodes share the necessary preprocessing functions (e.g., normalization, shaping, etc.) on the measured DL pilot signals. The UE is configured to compress the DL pilot signals using a trained encoder. The UE follows the quantization configuration (scalar or vector quantization) received from the RAN nodes.

[0077] Furthermore, when the channel estimator processes the UL pilot signal as an additional input, the RAN node can be configured with a UL pilot pattern to coordinate the UL and DL pilot signals in order to maximize channel estimation accuracy and / or monitor the performance of the autoencoder model.

[0078] RAN nodes can also configure UL transmissions (such as sounding reference signals (SRS)) as monitoring or auxiliary resources to enable monitoring of channel estimation or to enhance the accuracy of channel estimation.

[0079] In addition, RAN nodes can use the traditional CSI reporting framework to switch between CSI reporting modes and select the appropriate mode based on monitoring of direct pilot compression.

[0080] like Figure 3A , Figure 3B and Figure 3C As shown, the UE can use different methods to compress the received DL pilot signal. Depending on the compression method used at the UE, the RAN node can use different blocks for the reconstruction task.

[0081] Figure 3A A system according to an example embodiment for an SQS scheme is illustrated, wherein UE 100 uses only a scalar or vector quantizer 303 to compress the received DL pilot signal 301, and RAN node 104 uses only a scalar or vector dequantizer 306 to (re)construct the DL pilot signal 301. RAN node 104 can use an advanced channel estimator 308 to estimate the DL channel based on the (re)constructed DL pilot signal.

[0082] The DL channel estimation 308 at RAN node 104 can be accomplished using various options. For example, RAN node 104 can use non-ML-based algorithms such as Linear Least Mean Square Error (LMMSE), Least Squares (LS), etc., to perform DL channel estimation.

[0083] As another example, RAN node 104 can use an ML-based solution for the DL channel estimation task 308. For example, the ML-based solution could include a fully connected neural network, a convolutional neural network, a transformer neural network, or any other suitable architecture. To obtain labels during the training phase of the ML-based channel estimator 308, RAN node 104 can transmit CSI-RS at maximum power to increase the signal-to-noise ratio (SNR). Additionally, RAN node 104 can require UE 100 to share both uncompressed and compressed DL pilot signals for training.

[0084] Figure 3B A system according to an example embodiment of an AQS scheme is illustrated, wherein UE 100 first uses encoder 302 to reduce the dimensionality of the received DL pilot signal 301, and then UE 100 uses scalar or vector quantizer 303 for further compression. After using scalar or vector dequantizer 306, RAN node 104 uses decoder 307 to (re)construct the DL pilot signal 301.

[0085] Figure 3CA system according to an example embodiment is shown, wherein the uplink pilot signal (in addition to the (re)constructed DL pilot signal) is also used for downlink channel estimation 308 at RAN node 104. In other words, RAN node 104 can use the uplink pilot signal as additional information for DL ​​channel estimation 308.

[0086] Figure 4 It shows that according to having corresponding Figure 3A The following is a signal flow diagram of an example embodiment of the SQS compression scheme. In other words, in this example embodiment, UE 100 may use only the scalar or vector quantizer 303 for the compression task, and RAN node 104 may accordingly use only the scalar or vector dequantizer 306 for the reconstruction task.

[0087] refer to Figure 4 At position 401, UE 100 sends capability information to RAN node 104 (e.g., gNB), which indicates at least the UE 100's capability to support downlink pilot signal compression. RAN node 104 receives the capability information.

[0088] This capability can be indicated as similar to Type II reporting, CSI compression, or any other CSI reporting mode. UE100 can also indicate any specific conditions under which downlink pilot signal compression is supported. For example, UE100 can set at least one of the following conditions: the number of antennas supported at RAN node 104, the supported CR range, and / or the supported payload size range.

[0089] At position 402, RAN node 104 sends a configuration for downlink pilot signal compression to UE 100. RAN node 104 can determine the configuration based on capability information received from UE 100. UE 100 receives this configuration.

[0090] In other words, RAN node 104 can select and configure direct downlink pilot signal compression as the CSI reporting mode for UE 100. UE 100 can support different modes simultaneously (e.g., pilot compression, traditional reporting, CSI compression, etc.), but with different CSI reporting configurations.

[0091] As an example, RAN node 104 can configure the CSI reporting mode based on the CSI reporting configuration (e.g., assuming CSI_reportconfig 1 is used for direct pilot signal compression), where there may be associated parameters or configurations within the CSI reporting configuration to identify that CSI_reportconfig 1 has a CSI reporting mode different from other modes.

[0092] At point 403, UE 100 sends an indication to RAN node 104 indicating capabilities for the SQS and / or AQS schemes. In this example embodiment, UE 100 may indicate capabilities for at least the SQS scheme. RAN node 104 receives this indication.

[0093] At 404, RAN node 104 sends a configuration to UE 100 for a compression scheme to be used at UE 100. In this example embodiment, RAN node 104 may configure SQS as a compression scheme to be used at UE 100. For example, the configuration may indicate at least one of the following: one or more preprocessing functions (e.g., normalization and / or shaping), a grouping technique for a set of resource elements of one or more downlink pilot signals, or a quantization codebook and parameters for quantizing the set of resource elements of one or more downlink pilot signals.

[0094] In other words, RAN node 104 can share the information needed for aligning compression, compression ratio, and quantization schemes and configurations, as well as potential preprocessing procedures.

[0095] At position 405, RAN node 104 transmits one or more downlink pilot signals to UE 100. UE 100 receives one or more downlink pilot signals. For example, the one or more downlink pilot signals may include one or more Channel State Information Reference Signals (CSI-RS) or any other type of reference signal.

[0096] At 406, UE 100 may preprocess one or more downlink pilot signals according to one or more preprocessing functions indicated by RAN node 104 at 404 before compression. For example, UE 100 may normalize and / or shape one or more downlink pilot signals.

[0097] At 407, UE 100 compresses one or more downlink pilot signals received from RAN node 104 based on the configuration received at 402 and 404. Compression can be performed using quantizer 303, which includes either a scalar quantizer or a vector quantizer. UE 100 can quantize one or more downlink pilot signals using a compression scheme (i.e., SQS in this case) indicated by RAN node 104 at 404.

[0098] In other words, UE 100 can measure one or more downlink pilot signals and directly compress the received (noisy) one or more downlink pilot signals.

[0099] At 408, UE 100 sends information to RAN node 104 relating to one or more compressed downlink pilot signals. This information may be referred to herein as a compressed CSI report. This information may include, for example, a compressed bit sequence representing one or more downlink pilot signals. For example, UE 100 may use channel coding, modulation schemes (such as Quadrature Amplitude Modulation (QAM)), and data transmission techniques (such as Orthogonal Frequency Division Multiplexing (OFDM)) to send one or more downlink pilot signals as a compressed bit sequence.

[0100] At 409, RAN node 104 obtains or extracts compressed bit sequences from the received information by using, for example, OFDM demodulation, QAM demapper and channel decoder.

[0101] At 410, RAN node 104 constructs or reconstructs one or more downlink pilot signals based on this information. In other words, the goal of RAN node 104 is to create a signal similar to what is observed or measured at UE 100. In this case, (re)construction is performed by dequantizing the compressed bit sequence using dequantizer 306. In other words, RAN node 104 uses the corresponding dequantizer based on the selected compression scheme (i.e., SQS in this case) and quantization properties. Dequantizer 306 may include a scalar dequantizer or a vector dequantizer. RAN node 104 can obtain one or more downlink pilot signals using the inverse function of the normalization function.

[0102] At 411, RAN node 104 performs downlink channel estimation based on at least one or more (re)constructed downlink pilot signals. In other words, RAN node 104 estimates the downlink channel between RAN node 104 and UE 100.

[0103] For example, downlink channel estimation can be performed using non-machine learning-based algorithms such as linear minimum mean square error or least squares.

[0104] As another example, downlink channel estimation can be performed using machine learning algorithms. Machine learning algorithms can include, for example, one of the following: fully connected neural networks, convolutional neural networks, transformer neural networks, or any other suitable architecture.

[0105] Downlink channel estimation can also be performed based on at least one of the following: one or more uplink pilot signals received from UE 100, or uplink channel correlation functions.

[0106] The channel correlation function (CCF) is a time-averaged function that indicates the correlation between the channel responses of antenna elements. The uplink channel correlation function refers to the correlation of the uplink channel between UE 100 and RAN node 104.

[0107] At 412, RAN node 104 can use the estimated downlink channel for targeted applications, such as beamforming. For example, based on the estimated downlink channel, RAN node 104 can transmit a signal in a specific direction that maximizes the quality of the received signal at UE 100.

[0108] Figure 5 It shows that according to having corresponding Figure 3B The following is a signal flow diagram of an example embodiment of the AQS compression scheme. In other words, in this example embodiment, UE 100 can first use encoder 302 to reduce the dimensionality of the received DL pilot signal(s), and then UE 100 can use scalar or vector quantizer 303 for further compression. After using scalar or vector dequantizer 306, RAN node 104 can use decoder 307 to reconstruct the DL pilot signal(s).

[0109] refer to Figure 5 At point 501, UE 100 sends capability information to RAN node 104 (e.g., gNB), which at least indicates UE 100's capability to support downlink pilot signal compression. RAN node 104 receives this capability information.

[0110] This capability can be indicated as similar to Type II reporting, CSI compression, or any other CSI reporting mode. UE100 can also indicate any specific conditions under which downlink pilot signal compression is supported.

[0111] At position 502, RAN node 104 sends a configuration for downlink pilot signal compression to UE 100. RAN node 104 can determine the configuration based on capability information received from UE 100. UE 100 receives this configuration.

[0112] In other words, RAN node 104 can select and configure direct downlink pilot signal compression as the CSI reporting mode for UE 100. UE 100 can support different modes simultaneously (e.g., pilot compression, traditional reporting, CSI compression, etc.), but with different CSI reporting configurations.

[0113] As an example, RAN node 104 can configure the CSI reporting mode based on the CSI reporting configuration (e.g., assuming CSI_reportconfig 1 is used for direct pilot signal compression), where there may be associated parameters or configurations within the CSI reporting configuration to identify that CSI_reportconfig 1 has a CSI reporting mode different from other modes.

[0114] At point 503, UE 100 sends an indication to RAN node 104 indicating its capabilities for the SQS and / or AQS schemes. In this example embodiment, UE 100 may indicate capabilities for at least the AQS scheme. RAN node 104 receives this indication.

[0115] At 504, RAN node 104 sends a configuration of the compression scheme to be used at UE 100. In this example embodiment, RAN node 104 may configure AQS as the compression scheme to be used at UE 100. For example, the configuration may indicate at least one of the following: one or more preprocessing functions (e.g., normalization and / or shaping), a grouping technique for a set of resource elements of one or more downlink pilot signals, or a quantization codebook and parameters for quantizing the set of resource elements of one or more downlink pilot signals.

[0116] In other words, RAN node 104 can share the information needed for aligning compression, compression ratio, and quantization schemes and configurations, as well as potential preprocessing procedures.

[0117] At 505, depending on the autoencoder training method (e.g., joint or individual training), UE 100 and RAN node 104 can align their machine learning models (i.e., encoder 302 and decoder 307).

[0118] For example, in joint training, an entity (e.g., RAN node 104 or UE 100) can train both encoder 302 and decoder 307. The entity can then share the trained encoder 302 or the trained decoder 307 with another entity (e.g., RAN node 104 can send the trained encoder 302 to UE 100, or UE 100 can send the trained decoder 307 to RAN node 104).

[0119] As another example, in separate training, the first entity (e.g., RAN node 104 or UE 100) trains its own encoder 302 and decoder 307, and then shares the training dataset with another entity (e.g., UE 100 or RAN node 104) for alignment. Each sample in the dataset may include a pair of input CSIs and a corresponding compressed (and quantized) CSI.

[0120] At point 506, RAN node 104 sends one or more downlink pilot signals to UE 100. UE 100 receives one or more downlink pilot signals. For example, the one or more downlink pilot signals may include one or more Channel State Information Reference Signals (CSI-RS) or any other type of reference signal.

[0121] At 507, UE 100 may preprocess one or more downlink pilot signals according to one or more preprocessing functions indicated by RAN node 104 at 504 before compression. For example, UE 100 may normalize and / or shape one or more downlink pilot signals.

[0122] At 508, UE 100 compresses one or more downlink pilot signals received from RAN node 104 based on the configuration received at 502 and 504. UE 100 can compress one or more downlink pilot signals by using a compression scheme (i.e., AQS in this case) indicated by RAN node 104 at 504. In this case, compression is performed using encoder 302 and quantizer 303, where encoder 302 is used to reduce the dimensionality of one or more downlink pilot signals, and quantizer 303 is used to further compress one or more downlink pilot signals. Encoder 302 is trained (or has been trained) to compress one or more downlink pilot signals.

[0123] In other words, UE 100 can measure one or more downlink pilot signals and directly compress the received (noisy) one or more downlink pilot signals.

[0124] At point 509, UE 100 sends information to RAN node 104 relating to one or more compressed downlink pilot signals. This information may be referred to herein as a compressed CSI report. This information may include, for example, a compressed bit sequence representing one or more downlink pilot signals. For example, UE 100 may use channel coding, modulation schemes (such as Quadrature Amplitude Modulation (QAM)), and data transmission techniques (such as Orthogonal Frequency Division Multiplexing (OFDM)) to send one or more downlink pilot signals as a compressed bit sequence.

[0125] At 510, RAN node 104 obtains or extracts compressed bit sequences from the received information by using, for example, OFDM demodulation, QAM demapper and channel decoder.

[0126] At 511, RAN node 104 constructs or reconstructs one or more downlink pilot signals based on this information. In other words, the goal of RAN node 104 is to create a signal similar to what is observed or measured at UE 100. In this case, (re)construction is performed using dequantizer 306 and decoder 307 according to the selected compression scheme (i.e., AQS in this case). RAN node 104 uses dequantizer 306 to dequantize the compressed bit sequence according to the quantization attributes indicated at 504, and RAN node 104 uses decoder 307 to decode the output of dequantizer 306. Dequantizer 306 may include a scalar dequantizer or a vector dequantizer. RAN node 104 may use the inverse function of the normalization function to obtain one or more downlink pilot signals.

[0127] At 512, RAN node 104 performs downlink channel estimation based on at least one or more (re)constructed downlink pilot signals. In other words, RAN node 104 estimates the downlink channel between RAN node 104 and UE 100.

[0128] For example, downlink channel estimation can be performed using non-machine learning-based algorithms such as linear minimum mean square error or least squares.

[0129] As another example, downlink channel estimation can be performed using machine learning algorithms. Machine learning algorithms can include, for example, one of the following: fully connected neural networks, convolutional neural networks, transformer neural networks, or any other suitable architecture.

[0130] Downlink channel estimation can also be performed based on at least one of the following: one or more uplink pilot signals received from UE 100, or uplink channel correlation functions.

[0131] At 513, RAN node 104 can use the estimated downlink channel for targeted applications, such as beamforming. For example, based on the estimated downlink channel, RAN node 104 can transmit a signal in a specific direction that maximizes the quality of the received signal at UE 100.

[0132] Figure 6 A signal flow diagram is shown for an example embodiment with an AQS compression scheme, using received UL pilot signals(multiple) as additional information for DL ​​channel estimation at RAN node 104. Figure 3C ).

[0133] refer to Figure 6At point 601, UE 100 sends capability information to RAN node 104 (e.g., gNB), which at least indicates UE 100's capability to support downlink pilot signal compression. RAN node 104 receives this capability information.

[0134] This capability can be indicated as similar to Type II reporting, CSI compression, or any other CSI reporting mode. UE100 can also indicate any specific conditions under which downlink pilot signal compression is supported.

[0135] At step 602, RAN node 104 sends a configuration for downlink pilot signal compression to UE 100. RAN node 104 can determine this configuration based on capability information received from UE 100. UE 100 receives this configuration.

[0136] In other words, RAN node 104 can select and configure direct downlink pilot signal compression as the CSI reporting mode for UE 100. UE 100 can support different modes simultaneously (e.g., pilot compression, traditional reporting, CSI compression, etc.), but with different CSI reporting configurations.

[0137] As an example, RAN node 104 can configure the CSI reporting mode based on the CSI reporting configuration (e.g., assuming CSI_reportconfig 1 is used for direct pilot signal compression), where there may be associated parameters or configurations within the CSI reporting configuration to identify that CSI_reportconfig 1 has a CSI reporting mode different from other modes.

[0138] At point 603, UE 100 sends an indication to RAN node 104 indicating capabilities for the SQS and / or AQS schemes. In this example embodiment, UE 100 may indicate capabilities for at least the AQS scheme. RAN node 104 receives this indication.

[0139] At 604, RAN node 104 sends a configuration for a compression scheme to be used at UE 100. In this example embodiment, RAN node 104 may configure AQS as a compression scheme to be used at UE 100. For example, the configuration may indicate at least one of the following: one or more preprocessing functions (e.g., normalization and / or shaping), a grouping technique for a set of resource elements of one or more downlink pilot signals, or a quantization codebook and parameters for quantizing such set of resource elements of one or more downlink pilot signals.

[0140] In other words, RAN node 104 can share the information needed for aligning compression, compression ratio, and quantization schemes and configurations, as well as potential preprocessing procedures.

[0141] At 605, depending on the autoencoder training method (e.g., joint or individual training), UE 100 and RAN node 104 can align their machine learning models (i.e., encoder 302 and decoder 307).

[0142] At 606, RAN node 104 sends downlink pilot signal patterns and uplink pilot signal patterns to UE 100 for coordination between downlink and uplink pilot signals to optimize channel estimation accuracy and / or monitor the performance of the autoencoder model (which includes encoder 302 and decoder 307). UE 100 receives the downlink pilot signal patterns and uplink pilot signal patterns.

[0143] An uplink pilot signal pattern refers to a predefined structure or sequence of pilot symbols to be transmitted from UE 100 to RAN node 104. These pilot symbols are known at both the transmitter (i.e., UE 100) and the receiver (i.e., RAN node 104) and can be used for channel estimation. The pattern in which these pilot symbols are inserted into the uplink signal defines the uplink pilot signal pattern in terms of timing, frequency, and spatial dimensions.

[0144] Similarly, a downlink pilot signal pattern refers to a specific arrangement or sequence of pilot symbols to be transmitted from RAN node 104 to UE 100.

[0145] At 607, RAN node 104 transmits one or more downlink pilot signals to UE 100 according to the downlink pilot signal pattern. UE 100 receives one or more downlink pilot signals. For example, the one or more downlink pilot signals may include one or more channel state information reference signals (CSI-RS) or any other type of reference signal.

[0146] At 608, UE 100 may preprocess one or more downlink pilot signals according to one or more preprocessing functions indicated by RAN node 104 at 604 before compression. For example, UE 100 may normalize and / or shape one or more downlink pilot signals.

[0147] At 609, UE 100 compresses one or more downlink pilot signals received from RAN node 104 based on the configuration received at 602 and 604. UE 100 can compress one or more downlink pilot signals by using a compression scheme (i.e., AQS in this case) indicated by RAN node 104 at 604. In this case, compression is performed using encoder 302 and quantizer 303, where encoder 302 is used to reduce the dimensionality of one or more downlink pilot signals, and quantizer 303 is used to further compress one or more downlink pilot signals. Encoder 302 is trained (or has been trained) to compress one or more downlink pilot signals.

[0148] In other words, UE 100 can measure one or more downlink pilot signals and directly compress the received (noisy) one or more downlink pilot signals.

[0149] At 610, UE 100 sends information to RAN node 104 relating to one or more compressed downlink pilot signals. This information may be referred to herein as a compressed CSI report. This information may include, for example, a compressed bit sequence representing one or more downlink pilot signals. For example, UE 100 may use channel coding, modulation schemes (such as Quadrature Amplitude Modulation (QAM)), and data transmission techniques (such as Orthogonal Frequency Division Multiplexing (OFDM)) to send one or more downlink pilot signals as a compressed bit sequence.

[0150] At point 611, UE 100 sends one or more uplink pilot signals to RAN node 104 according to the uplink pilot signal pattern. RAN node 104 receives one or more uplink pilot signals.

[0151] The one or more uplink pilot signals may be transmitted together with information related to the one or more compressed downlink pilot signals, or the one or more uplink pilot signals may be transmitted separately from the information. The one or more compressed pilot signals may be part of uplink control information (UCI), and depending on the circumstances, the UCI may be carried by the Physical Uplink Control Channel (PUCCH) or the Physical Uplink Shared Channel (PUSCH).

[0152] At 612, RAN node 104 obtains or extracts compressed bit sequences from the received information by using, for example, OFDM demodulation, QAM demapper and channel decoder.

[0153] At 613, RAN node 104 constructs or reconstructs one or more downlink pilot signals based on this information. In other words, the goal of RAN node 104 is to create a signal similar to what is observed or measured at UE 100. In this case, (re)construction is performed using dequantizer 306 and decoder 307 according to the selected compression scheme (i.e., AQS in this case). RAN node 104 uses dequantizer 306 to dequantize the compressed bit sequence according to the quantization attributes indicated at 504, and RAN node 104 uses decoder 307 to decode the output of dequantizer 306. Dequantizer 306 may include a scalar dequantizer or a vector dequantizer. RAN node 104 may use the inverse function of the normalization function to obtain one or more downlink pilot signals.

[0154] At 614, RAN node 104 (in the case where one or more uplink pilot signals are transmitted together with one or more compressed downlink pilot signals) extracts one or more uplink pilot signals from the received signals.

[0155] At 615, RAN node 104 performs downlink channel estimation based on at least one or more (reconstructed) downlink pilot signals and at least one of the following: one or more uplink pilot signals or uplink channel correlation functions received from UE 100.

[0156] In other words, RAN node 104 estimates the downlink channel between RAN node 104 and UE 100.

[0157] For example, downlink channel estimation can be performed using non-machine learning-based algorithms such as linear minimum mean square error or least squares.

[0158] As another example, downlink channel estimation can be performed using machine learning algorithms. Machine learning algorithms can include, for example, one of the following: fully connected neural networks, convolutional neural networks, transformer neural networks, or any other suitable architecture.

[0159] At 616, RAN node 104 can use the estimated downlink channel for targeted applications, such as beamforming. For example, based on the estimated downlink channel, RAN node 104 can transmit a signal in a specific direction that maximizes the quality of the received signal at UE 100.

[0160] At 617, RAN node 104 can monitor the performance of at least one of the following based on one or more downlink pilot signals and one or more uplink pilot signals: an encoder for compressing one or more downlink pilot signals, or a decoder for constructing one or more downlink pilot signals. Performance is related to the correlation between the downlink and uplink channels. RAN node 104 can monitor performance by comparing the correlation to a threshold.

[0161] Based on this monitoring, RAN node 104 can select an appropriate CSI reporting mode for UE 100. For example, if the encoder 302 and / or decoder 307 perform well (e.g., correlation is above a threshold), RAN node 104 can decide to continue using direct downlink pilot signal compression as the CSI reporting mode for UE 100. As another example, if the encoder 302 and / or decoder 307 perform poorly (e.g., correlation is below a threshold), UE 100 and RAN node 104 can switch to using type II codebooks 200, 220 for CSI compression (e.g., as...). Figure 2A (as shown), instead of continuing to use direct downlink pilot signal compression as the CSI reporting mode.

[0162] Figure 7 It shows that according to the Figure 9 The flowchart illustrates an example embodiment of a method performed by the device 900 depicted herein. For example, the device 900 may be, or include, user equipment (UE) 100, 102, or be included in, user equipment (UE) 100, 102.

[0163] Reference Figure 7 In frame 701, device 900 receives configuration for downlink pilot signal compression from radio access network node 104.

[0164] In block 702, device 900 uses this configuration to compress one or more downlink pilot signals received from radio access network node 104.

[0165] In block 703, device 900 transmits information relating to the one or more compressed downlink pilot signals to radio access network node 104.

[0166] The device 900 can send capability information to the radio access network node 104, which indicates at least the capability to support downlink pilot signal compression, wherein the configuration can be received based on or in response to the transmission of the capability information.

[0167] The device 900 can preprocess one or more downlink pilot signals according to one or more preprocessing functions indicated by the radio access network node 104 before compression.

[0168] As an example, compression can be performed using at least one quantizer 303, which may include a scalar quantizer or a vector quantizer.

[0169] The device 900 may receive configuration for the quantizer 303 from the radio access network node 104, wherein the configuration for the quantizer 303 may indicate at least one of the following: a grouping technique for a set of resource elements of one or more downlink pilot signals, or a quantization codebook for quantizing the set of resource elements of one or more downlink pilot signals.

[0170] As another example, compression can be performed using encoder 302 and quantizer 303, wherein encoder 302 can be used to reduce the dimension of one or more downlink pilot signals, and wherein quantizer 303 can be used to further compress one or more downlink pilot signals.

[0171] Encoder 302 can be trained to compress one or more downlink pilot signals. In other words, encoder 302 can include a pre-trained machine learning model configured to compress one or more downlink pilot signals.

[0172] The device 900 can receive an uplink pilot signal pattern from the radio access network node 104, the uplink pilot signal pattern being used to coordinate between one or more downlink pilot signals and one or more uplink pilot signals; and transmit one or more uplink pilot signals to the radio access network node 104 according to the uplink pilot signal pattern.

[0173] Figure 8 It shows that according to the Figure 10 The flowchart illustrates an example embodiment of the method performed by the device 1000 depicted herein. For example, the device 1000 may be, include, or be included in a radio access network node 104.

[0174] Reference Figure 8 In box 801, device 1000 sends a configuration for downlink pilot signal compression to user equipment 100.

[0175] In block 802, device 1000 receives information from user equipment 100 relating to one or more compressed downlink pilot signals.

[0176] In block 803, device 1000 constructs or reconstructs one or more downlink pilot signals based on this information.

[0177] In block 804, device 1000 performs downlink channel estimation based at least on one or more (re)constructed downlink pilot signals.

[0178] The device 1000 can receive capability information from the user equipment 100, which at least indicates the capability to support downlink pilot signal compression; and determine the configuration based on the capability information.

[0179] As an example, (re)construction can be performed using at least one dequantizer 306, wherein the dequantizer 306 may include a scalar dequantizer or a vector dequantizer.

[0180] As another example, (re)construction can be performed using dequantizer 306 and decoder 307.

[0181] Downlink channel estimation can be performed using non-machine learning-based algorithms.

[0182] Alternatively, downlink channel estimation can be performed using machine learning algorithms. Machine learning algorithms can include, for example, one of the following: fully connected neural networks, convolutional neural networks, transformer neural networks, or any other suitable architecture.

[0183] Downlink channel estimation can also be performed based on at least one of the following: one or more uplink pilot signals or uplink channel correlation functions received from user equipment 100.

[0184] The device 1000 can send an uplink pilot signal pattern to the user equipment 100, which is used to coordinate between one or more downlink pilot signals and one or more uplink pilot signals.

[0185] The device 1000 can monitor the performance of at least one of the following based on one or more downlink pilot signals and one or more uplink pilot signals: an encoder 302 for compressing one or more downlink pilot signals, or a decoder 307 for (re)constructing one or more downlink pilot signals.

[0186] The above passed Figures 4 to 8The described boxes, related functions, and information exchanges (messages) are not in an absolute chronological order, and some of them may be executed concurrently or in a different order than described. Other functions may also be executed between or within them, and other information may be sent, and / or other rules may be applied. Some boxes, or parts of boxes, or one or more messages may be omitted or replaced by corresponding boxes, or parts of boxes, or one or more messages.

[0187] As used herein, “at least one of the following: a list of two or more elements” and “at least one of the following: a list of two or more elements” and similar wording (where a list of two or more elements is connected by “and” or “or”) means at least any one of the elements, or at least any two or more of the elements, or at least all of the elements.

[0188] Figure 9 An example of an apparatus 900 is shown, comprising components for performing one or more of the example embodiments described above. For example, apparatus 900 may be, for example, a user equipment (UE) 100, 102, or an apparatus that includes, or is included in, user equipment (UE) 100, 102. The user equipment may also be referred to as a wireless communication device, subscriber unit, mobile station, remote terminal, access terminal, user terminal, terminal equipment, or user equipment.

[0189] The device 900 may include circuitry or chipsets suitable for implementing one or more of the example embodiments described above. For example, the device 900 may include at least one processor 910. The at least one processor 910 interprets instructions (e.g., computer program instructions) and processes data. The at least one processor 910 may include one or more programmable processors. The at least one processor 910 may include programmable hardware with embedded firmware and may alternatively or additionally include one or more application-specific integrated circuits (ASICs).

[0190] At least one processor 910 is coupled to at least one memory 920. The at least one processor is configured to read data from and write data to the at least one memory 920. The at least one memory 920 may include one or more memory cells. Memory cells may be volatile or non-volatile. It should be noted that one or more non-volatile memory cells and one or more volatile memory cells may be present, or alternatively, one or more non-volatile memory cells, or alternatively, one or more volatile memory cells. Volatile memory may be, for example, random access memory (RAM), dynamic random access memory (DRAM), or synchronous dynamic random access memory (SDRAM). Non-volatile memory may be, for example, read-only memory (ROM), programmable read-only memory (PROM), electrically erasable programmable read-only memory (EEPROM), flash memory, optical storage, or magnetic storage. Generally, memory may be referred to as a non-transitory computer-readable medium. As used herein, the term "non-transitory" is a limitation on the medium itself (i.e., tangible, not tactile), rather than a limitation on the persistence of data storage (e.g., RAM and ROM). At least one memory 920 stores computer-readable instructions that are executed by at least one processor 910 to perform one or more of the example embodiments described above. For example, non-volatile memory stores computer-readable instructions, and at least one processor 910 uses volatile memory to execute instructions for temporary storage of data and / or instructions. Computer-readable instructions may refer to computer program code.

[0191] Computer-readable instructions may have been pre-stored in at least one memory 920, or alternatively or additionally, they may be received by the device via an electromagnetic carrier signal and / or copied from a physical entity such as a computer program product. Execution of the computer-readable instructions by at least one processor 910 causes the device 900 to perform one or more of the example embodiments described above. That is, at least one processor and at least one memory storing the instructions can provide components for providing or causing execution of any of the methods and / or blocks described above.

[0192] In the context of this document, "memory" or "computer-readable medium" or "computer-readable media" can be any non-transitory medium or component that can contain, store, communicate, propagate, or transmit instructions for use by or in connection with an instruction execution system, apparatus, or device, such as a computer. As used herein, the term "non-transitory" is a limitation on the medium itself (i.e., tangible, not tactile) rather than a limitation on the persistence of data storage (e.g., RAM versus ROM).

[0193] The device 900 may also include or be connected to the input unit 930. The input unit 930 may include one or more interfaces for receiving input. The one or more interfaces may include, for example, one or more temperature, motion, and / or orientation sensors, one or more cameras, one or more accelerometers, one or more microphones, one or more buttons, and / or one or more touch detection units. In addition, the input unit 930 may include interfaces to which external devices can be connected.

[0194] The device 900 may also include an output unit 940. The output unit may include or be connected to one or more displays capable of displaying visual content, such as a light-emitting diode (LED) display, a liquid crystal display (LCD), and / or a liquid crystal on silicon (LCoS) display. The output unit 940 may also include one or more audio outputs. The one or more audio outputs may be, for example, speakers.

[0195] Device 900 also includes a connection unit 950. Connection unit 950 enables wireless connectivity to one or more external devices. Connection unit 950 includes at least one transmitter and at least one receiver, which may be integrated into device 900 or connected to device 900. The at least one transmitter includes at least one transmitting antenna, and the at least one receiver includes at least one receiving antenna. Connection unit 950 may include an integrated circuit or a set of integrated circuits providing wireless communication capabilities to device 900. Alternatively, the wireless connection may be a hardwired application-specific integrated circuit (ASIC). Connection unit 950 may also provide components for performing at least some blocks or functions of one or more of the above example embodiments. Connection unit 950 may include one or more components controlled by a corresponding control unit, such as: a power amplifier, a digital front-end (DFE), an analog-to-digital converter (ADC), a digital-to-analog converter (DAC), a frequency converter, a (de)modulator, and / or encoder / decoder circuitry.

[0196] It should be noted that device 900 may also include Figure 9 Various components are not shown. These components can be hardware components and / or software components.

[0197] Figure 10 An example of an apparatus 1000 including components for performing one or more of the example embodiments described above is shown. For example, apparatus 1000 may be, for example, a radio access network node 104, or an apparatus including or included in radio access network node 104.

[0198] Radio access network nodes can also be referred to as, for example, network elements, next-generation radio access network (NG-RAN) nodes, node B, eNB, gNB, base transceiver unit (BTS), base station, NR base station, 5G base station, access node, access point (AP), cell site, relay node, repeater, integrated access and backhaul (IAB) node, IAB donor node, distributed unit (DU), central unit (CU), baseband unit (BBU), or transmit and receive point (TRP).

[0199] Device 1000 may include, for example, circuitry or chipsets suitable for implementing one or more of the example embodiments described above. Device 1000 may be an electronic device including one or more electronic circuits. Device 1000 may include communication control circuitry 1010 (such as at least one processor) and at least one memory 1020 storing instructions 1022, which, when executed by at least one processor, cause device 1000 to perform one or more example embodiments described above. Such instructions 1022 may, for example, include computer program code (software). At least one processor and at least one memory storing instructions may provide components for providing or causing execution of any of the methods and / or blocks described above.

[0200] A processor is coupled to memory 1020. The processor is configured to read data from memory 1020 and write data to memory 1020. Memory 1020 may include one or more memory cells. Memory cells may be volatile or non-volatile. It should be noted that one or more non-volatile memory cells and one or more volatile memory cells may be present, or alternatively, one or more non-volatile memory cells, or alternatively, one or more volatile memory cells. Volatile memory may be, for example, random access memory (RAM), dynamic random access memory (DRAM), or synchronous dynamic random access memory (SDRAM). Non-volatile memory may be, for example, read-only memory (ROM), programmable read-only memory (PROM), electrically erasable programmable read-only memory (EEPROM), flash memory, optical storage, or magnetic storage. Generally, memory may be referred to as a non-transitory computer-readable medium. As used herein, the term "non-transitory" is a limitation on the medium itself (i.e., tangible, not tactile), rather than a limitation on the persistence of data storage (e.g., RAM versus ROM). Memory 1020 stores computer-readable instructions that are executed by the processor. For example, non-volatile memory stores computer-readable instructions, and the processor uses volatile memory to execute instructions for temporary storage of data and / or instructions.

[0201] The computer-readable instructions may have been pre-stored in memory 1020, or alternatively or additionally, they may be received by the device via an electromagnetic carrier signal and / or copied from a physical entity such as a computer program product. Execution of the computer-readable instructions causes the device 1000 to perform one or more of the functions described above.

[0202] The memory 1020 can be implemented using any suitable data storage technology, such as semiconductor-based memory devices, flash memory, magnetic memory devices and systems, optical memory devices and systems, fixed memory, and / or removable memory. The memory may include a configuration database for storing configuration data, such as a current list of neighboring cells, and, in some example embodiments, the structure of frames used in detected neighboring cells.

[0203] The device 1000 may also include or be connected to a communication interface 1030, such as a radio unit, which includes hardware and / or software for establishing a communication connection with one or more wireless communication devices according to one or more communication protocols. The communication interface 1030 includes at least one transmitter (Tx) and at least one receiver (Rx), which may be integrated into the device 1000 or the device 1000 may be connected to at least one transmitter (Tx) and at least one receiver (Rx). The communication interface 1030 may provide components for performing some of the blocks of the above-described example embodiments. The communication interface 1030 may include one or more components controlled by a corresponding control unit, such as: a power amplifier, a digital front end (DFE), an analog-to-digital converter (ADC), a digital-to-analog converter (DAC), a frequency converter, a (de)modulator, and / or encoder / decoder circuitry.

[0204] Communication interface 1030 provides the device with radio communication capabilities for communication in a wireless communication network. The communication interface may, for example, provide a radio interface to one or more UEs 100, 102. Device 1000 may also include or be connected to another interface toward core network 110, such as a network coordinator device or AMF, and / or to access node 104 connected to the wireless communication network.

[0205] The apparatus 1000 may also include a scheduler 1040 configured to allocate radio resources. The scheduler 1040 may be configured together with the communication control circuitry 1010 or may be configured separately.

[0206] It should be noted that device 1000 may also include Figure 10 Various components are not shown. These components can be hardware components and / or software components.

[0207] As used in this application, the term "circuit" may refer to one or more or all of the following: a) a hardware circuit implementation (such as an implementation in a purely analog and / or digital circuit); and b) a combination of hardware circuitry and software, such as (if applicable): i) a combination of analog and / or digital hardware circuitry with software / firmware; and ii) (multiple) hardware processors with any part of the software (including (multiple) digital signal processors, software, and (multiple) memories working together to enable a device such as a mobile phone to perform various functions); and c) (multiple) hardware circuitry and / or (multiple) processors, such as (multiple) microprocessors or a portion thereof, which require software (e.g., firmware) to operate, but may be absent when operation is not required.

[0208] This definition of "circuit" applies to all uses of the term in this application (including in any claim). As another example, as used in this application, the term "circuit" also covers only hardware circuitry or processors (or processors) or a portion thereof and their accompanying software and / or firmware implementations. For example, if applicable to a particular claim element, the term "circuit" also covers baseband integrated circuits or processor integrated circuits for mobile devices, or similar integrated circuits in servers, cellular network devices, or other computing or network devices.

[0209] The techniques and methods described herein can be implemented by various means. For example, these techniques can be implemented in hardware (one or more devices), firmware (one or more devices), software (one or more modules), or a combination thereof. For hardware implementation, the apparatus of the example embodiments can be implemented within one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), graphics processing units (GPUs), processors, controllers, microcontrollers, microprocessors, other electronic units designed to perform the functions described herein, or a combination thereof. For firmware or software, the implementation can be executed by a module of at least one chipset (e.g., procedures, functions, etc.) that performs the functions described herein. Software code can be stored in memory cells and executed by a processor. Memory cells can be implemented within or outside the processor. In the latter case, as is known in the art, it can be communicatively coupled to the processor via various means. Additionally, as those skilled in the art will understand, the components of the systems described herein can be rearranged and / or supplemented by additional components to facilitate the implementation of the various aspects described herein, and they are not limited to the precise configurations illustrated in the given figures.

[0210] It will be apparent to those skilled in the art that, with advancements in technology, the inventive concept can be implemented in various ways within the scope of the claims. Embodiments are not limited to the exemplary embodiments described above, but can vary within the scope of the claims. Therefore, all words and expressions should be interpreted broadly, and they are intended to illustrate rather than limit the embodiments.

Claims

1. An apparatus comprising at least one processor and at least one memory storing instructions, the instructions, when executed by said at least one processor, causing the apparatus to at least: Receive configuration for downlink pilot signal compression from the radio access network node; Based on the configuration, one or more downlink pilot signals received from the radio access network node are compressed; as well as Information relating to one or more compressed downlink pilot signals is sent to the radio access network node.

2. The apparatus according to claim 1 is further configured such that: The radio access network node is sent capability information, which at least indicates the capability to support the downlink pilot signal compression. The configuration mentioned above is based on receiving the capability information sent.

3. The apparatus according to any one of the preceding claims is further configured such that: Prior to the compression, the one or more downlink pilot signals are preprocessed according to one or more preprocessing functions indicated by the radio access network node.

4. The apparatus according to any one of the preceding claims, wherein the compression is performed by using at least one quantizer, wherein the quantizer includes a scalar quantizer or a vector quantizer.

5. The apparatus according to claim 4, further comprising: Receive configuration for the quantizer from the radio access network node, wherein the configuration for the quantizer indicates at least one of the following: Grouping technology, used for a group of resource elements of the one or more downlink pilot signals, or A quantization codebook is used to quantize the set of resource elements of the one or more downlink pilot signals.

6. The apparatus according to any one of claims 4 to 5, wherein the compression is performed using an encoder and the quantizer. The encoder is used to reduce the dimensionality of the one or more downlink pilot signals, and The quantizer is used for further compression of the one or more downlink pilot signals.

7. The apparatus of claim 6, wherein the encoder is trained to compress the one or more downlink pilot signals.

8. The apparatus according to any one of the preceding claims is further configured such that: Receives an uplink pilot signal pattern from the radio access network node, the uplink pilot signal pattern being used for coordination between the one or more downlink pilot signals and the one or more uplink pilot signals; and The uplink pilot signal is transmitted to the radio access network node according to the uplink pilot signal pattern.

9. An apparatus comprising at least one processor and at least one memory storing instructions, the instructions, when executed by said at least one processor, causing the apparatus to at least: Send the configuration for downlink pilot signal compression to the user equipment; Receive information relating to one or more compressed downlink pilot signals from the user equipment; Based on the information, construct one or more downlink pilot signals; as well as Downlink channel estimation is performed based on at least one or more constructed downlink pilot signals.

10. The apparatus according to claim 9, further comprising: Receive capability information from the user equipment, the capability information indicating at least the capability to support the downlink pilot signal compression; and The configuration is determined based on the capability information.

11. The apparatus according to any one of claims 9 to 10, wherein the configuration is performed by using at least one dequantizer, wherein the dequantizer includes a scalar dequantizer or a vector dequantizer.

12. The apparatus of claim 11, wherein the configuration is performed using the dequantizer and decoder.

13. The apparatus of any one of claims 9 to 12, wherein the downlink channel estimation is performed using a non-machine learning-based algorithm.

14. The apparatus of any one of claims 9 to 12, wherein the downlink channel estimation is performed using a machine learning algorithm.

15. The apparatus of any one of claims 9 to 14, wherein the downlink channel estimation is further performed based on at least one of: one or more uplink pilot signals received from the user equipment, or an uplink channel correlation function.

16. The apparatus of claim 15, further comprising: The uplink pilot signal pattern is sent to the user equipment, and the uplink pilot signal pattern is used to coordinate between the one or more downlink pilot signals and the one or more uplink pilot signals.

17. The apparatus according to any one of claims 15 to 16, further comprising: The performance of at least one of the following is monitored based on the one or more downlink pilot signals and the one or more uplink pilot signals: an encoder for compressing the one or more downlink pilot signals, or a decoder for constructing the one or more downlink pilot signals.

18. A method comprising: Receive configuration for downlink pilot signal compression from the radio access network node; Based on the configuration, one or more downlink pilot signals received from the radio access network node are compressed; as well as Information relating to one or more compressed downlink pilot signals is sent to the wireless access network node.

19. A method comprising: Send the configuration for downlink pilot signal compression to the user equipment; Receive information relating to one or more compressed downlink pilot signals from the user equipment; Based on the information, construct one or more downlink pilot signals; as well as Downlink channel estimation is performed based on at least one or more constructed downlink pilot signals.

20. A non-transitory computer-readable medium comprising program instructions that, when executed by a device, cause the device to perform at least the following: Receive configuration for downlink pilot signal compression from the radio access network node; Based on the configuration, one or more downlink pilot signals received from the radio access network node are compressed; as well as Information relating to one or more compressed downlink pilot signals is sent to the wireless access network node.

21. A non-transitory computer-readable medium comprising program instructions that, when executed by a device, cause the device to perform at least the following: Send the configuration for downlink pilot signal compression to the user equipment; Receive information relating to one or more compressed downlink pilot signals from the user equipment; Based on the information, construct one or more downlink pilot signals; as well as Downlink channel estimation is performed based on at least one or more constructed downlink pilot signals.

Images