Modulation and demodulation
AI-based modulation and demodulation methods optimize modulation schemes in higher dimensional spaces, addressing limitations of 4G and 5G by enhancing performance and reliability in wireless cellular networks.
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- ZTE CORP
- Filing Date
- 2025-03-18
- Publication Date
- 2026-06-11
AI Technical Summary
Existing 4G and 5G modulation schemes are limited to two-dimensional space, and the integration of AI technology has not been effectively utilized to enhance modulation schemes in higher dimensional spaces, leading to potential demodulation performance issues.
Implement AI-based modulation and demodulation methods that consider layer mapping, with paired models ensuring proper pairing, and utilize joint modulation and layer mapping/precoding to optimize modulation and demodulation processes.
Enhances modulation performance by adapting to channel status, increasing flexibility and reliability, and improving system throughput through AI-driven modulation and demodulation techniques.
Smart Images

Figure CN2025083073_11062026_PF_FP_ABST
Abstract
Description
MODULATION AND DEMODULATIONTECHNICAL FIELD
[0001] This disclosure generally relates to handling transmissions in a wireless cellular access network, and is specifically directed to mechanisms for configuring modulation and / or demodulation.BACKGROUND
[0002] The existing 4G and 5G systems mainly adopt Quadrature Amplitude Modulation (QAM) schemes. With this, the number of input bits of the modulation module is determined by the modulation order, modulation scheme, or Modulation Coding Scheme (MCS) index. For example, for Quadrature Phase Shift Keying (QPSK) , every 2 bits are mapped to one modulation symbol (e.g., complex-valued modulation symbol) ; for 16 QAM, every 4 bits are mapped to one complex-valued modulation symbol; for 64 QAM, every 6 bits are mapped to one modulation symbol; for 256 QAM, every 8 bits are mapped to one modulation symbol, etc. However, all the current modulation schemes in the 4G and 5G are mapping bits to two-dimensional space (i.e., modulation symbol) . With the introduction of Artificial Intelligence (AI) technology into communication systems, AI technology can be introduced to enhance the modulation schemes into higher dimensional space, e.g., by combining modulation with layer mapping and / or precoding.
[0003] [Rectified under Rule 91, 07.05.2025]FIG. 3 illustrates an example of the legacy modulation scheme. Assuming QPSK is adopted for a PDSCH transmission with four layers, two bits are input into the modulation module, and each of the two bits are mapped with a modulation symbol. In FIG. 3, bit b0 and b1 are mapped to modulation symbol MS0, bit b2 and b3 are mapped to modulation symbol MS1, bit b4 and b5 are mapped to modulation symbol MS2, and bit b6 and b7 are mapped to modulation symbol MS3. Then after layer mapping, the first modulation symbol MS0 is mapped to layer 0, the second modulation symbol MS1 is mapped to layer 1, the third modulation symbol MS2 is mapped to layer 2, and the fourth modulation symbol MS3 is mapped to layer 3.SUMMARY
[0004] This disclosure generally relates to handling transmissions in a wireless cellular access network, and is specifically directed to mechanisms for configuring modulation and / or demodulation.
[0005] As discussed above, legacy modulation and layer mapping are separately designed and implemented. However, in accordance with various embodiments disclosed herein, a solution optimizes the modulation and layering mapping as whole. Although the modulation and layering mapping can be implemented as separate modules, the input of the modulation may consider the layering mapping.
[0006] Additionally, in some embodiments, an AI-based solution can be applied to perform the modulation and demodulation. For example, an AI model can be applied to perform the modulation, while another AI model can be applied to perform demodulation. However, the model for modulation and the model for demodulation may need to be paired, otherwise demodulation performance may become negatively impacted. The present disclosure includes embodiments designed to ensure proper pairing of the models.
[0007] In some exemplary implementations, a method performed by a wireless terminal device (e.g., UE) includes communicating with a wireless access network node (WANN) (e.g., base station) using a modulation method via a data channel having a modulation order Q, where Q is an integer number larger than 0, wherein a number of layers of the data channel is L, and a number to control input bits is K, wherein L and K are positive integer numbers, wherein, in the modulation method, Mb bits of the data channel are mapped to Ms modulation symbols, wherein Mb is equal to Q·K·L, wherein Mb and Ms are positive integer numbers. In the method, a value of Ms is one of the following: Ms is equal to K·L; or Ms is equal to K·P, wherein P is a number of antenna ports of the data channel, and wherein P is an integer number larger than 0.
[0008] Similarly, a method performed by the WANN includes communicating with the wireless terminal device using a modulation method via a data channel having a modulation order Q, where Q is an integer number larger than 0, wherein a number of layers of the data channel is L, and a number to control input bits is K, wherein L and K are positive integer numbers, wherein, in the modulation method, Mb bits of the data channel are mapped to Ms modulation symbols, wherein Mb is equal to Q·K·L, wherein Mb and Ms are positive integer numbers. In the method, a value of Ms is one of the following: Ms is equal to K·L; or Ms is equal to K·P, wherein P is a number of antenna ports of the data channel, and wherein P is an integer number larger than 0.
[0009] In exemplary implementations of the methods, which may be combined with any of the other exemplary implementations disclosed herein, Ms is equal to K·L, wherein the Ms modulation symbols are d (0) , d (1) , ..., d (Ms-1) , and is a number of modulation symbols per layer, and wherein the modulation method comprises layer mapping, wherein the Ms modulation symbols are mapped onto the L layers according to one of the following alternatives: xk (i) =d (L·i+k) , wherein: k= 0, 1, …, L-1, and is equal to Ms / L. Or, wherein: k=0, 1, …, L-1, and is equal to Ms / L, wherein xk (i) is a modulation symbol with index i on a layer with index k, wherein both i and k are non-negative integer numbers.
[0010] In exemplary implementations of the methods, which may be combined with any of the other exemplary implementations disclosed herein, the methods include the WANN transmitting, and the wireless terminal device receiving, an indication of the modulation order Q and number of layer L via a control channel. In exemplary implementations of the methods, which may be combined with any of the other exemplary implementations disclosed herein, the methods include the WANN transmitting, and the wireless terminal device receiving, a configuration of mapping between the Mb bits of channel and the Ms modulation symbols for modulation order Q and / or number of layer L.
[0011] In exemplary implementations of the methods, which may be combined with any of the other exemplary implementations disclosed herein, the modulation mapper is a mapping between the Mb bits of channel and the Ms modulation symbols for the modulation order Q, and / or the number of layers L, and / or a number of antenna ports P, wherein a plurality of modulation mappers are predefined or are configured by the wireless access network node for the modulation order Q, and / or the number of layers L, and / or the number of antenna ports P. In various examples, the methods include the WANN transmitting, and the wireless terminal device receiving the modulation mapper for the data channel, wherein the transmitting or receiving comprises transmitting or receiving the mapping for the modulation mapper, or transmitting or receiving an index associated with one of the predefined modulation mappers.
[0012] In exemplary implementations of the methods, which may be combined with any of the other exemplary implementations disclosed herein, the index is associated with: the modulation order Q and the modulation mapper; the number of layers L and the modulation mapper; the modulation order Q, a number of layers L, and the modulation mapper; the number of antenna ports P and the modulation mapper; the number of antenna ports P, the modulation order Q, and the modulation mapper; the number of antenna ports P, the number of layers L, and the modulation mapper; or the number of antenna ports P, the modulation order Q, the number of layers L, and the modulation mapper.
[0013] In some exemplary implementations, a method performed by the wireless terminal device (e.g., UE) includes communicating with a wireless access network node (WANN) (e.g., base station) using a modulation method via a data channel having a modulation order Q, where Q is an integer number larger than 0, wherein a number of layers of the data channel is L, a number to control the input bits is K, and a number of antenna ports of the data channel is P, wherein L, K, and P are positive integer numbers. The method also includes performing the modulation method using a model to process Mb bits of the data channel to generate Ms modulation symbols mapped to the layers of the data channel or to a plurality of antenna ports P of the data channel, wherein Mb is equal to Q·K·L, or is equal to K·L, or is equal to K, wherein Ms is equal to K·L or is equal to K·P, and wherein Mb and Ms are positive integer numbers, wherein K is predefined or indicated by the WANN.
[0014] Similarly, a method performed by the WANN includes communicating with the wireless terminal device using a modulation method via a data channel having a modulation order Q, where Q is an integer number larger than 0, wherein a number of layers of the data channel is L, a number to control input bits is K, and a number of antenna ports of the data channel is P, wherein L, K, and P are positive integer numbers. The method also includes performing the modulation method using a model to process Mb bits of the data channel to generate Ms modulation symbols mapped to the layers of the data channel or to a plurality of antenna ports P of the data channel, wherein Mb is equal to Q·K·L, or is equal to K·L, or is equal to K, wherein Ms is equal to K·L or is equal to K·P, and wherein Mb and Ms are positive integer numbers, wherein K is predefined or indicated by the wireless access network node.
[0015] In exemplary implementations of the methods, which may be combined with any of the other exemplary implementations disclosed herein, the methods include the WANN transmitting, and the wireless terminal device receiving, model information, wherein the model information comprises dataset information and / or model parameter information. The dataset information comprises at least one of: a first part comprising a plurality of groups of bits, a second part comprising a plurality of groups of modulation symbols, and a third part comprising assistance information, wherein each group of bits is associated with a group of modulation symbols, or a first part comprising a plurality of groups of modulation symbols, and a second part comprising assistance information, wherein each group of modulation symbols is mapped to a group of bits, and wherein a pattern for the plurality of groups of modulation symbols are predefined or indicated by the wireless access network node, and are ordered according to the pattern. Or, the model parameter information comprises at least one of:a set of parameters for generating the model at the wireless terminal device, a model structure for the set of parameters, or assistance information.
[0016] In exemplary implementations of the methods, which may be combined with any of the other exemplary implementations disclosed herein, the assistance information comprises at least one of: a modulation order, a number of layers, a performance requirement, or a dataset ID, size of the dataset, quantization method of the dataset, quantization method or format of the set of parameters.
[0017] In exemplary implementations of the methods, which may be combined with any of the other exemplary implementations disclosed herein, the methods include the wireless terminal device transmitting, and the WANN receiving, a performance report, wherein the performance report comprises a value of a performance metric, wherein the performance metric comprises at least one of: Bit Error Rate (BER) , Block Error Rate (BLER) , Error Vector Magnitude (EVM) , number of successfully received Transmission Blocks (TB) , number of successfully received transmissions, number of unsuccessfully received TB, or number of unsuccessfully received transmissions.
[0018] In exemplary implementations of the methods, which may be combined with any of the other exemplary implementations disclosed herein, the methods include the WANN transmitting, and the wireless terminal device receiving, control information, wherein the control information at least one of: schedules an uplink transmission, where the control information comprises an indication of whether the modulation method is applied for the uplink transmission; schedules a downlink transmission, where the control information comprises an indication of whether the modulation method is applied for the downlink transmission; activates the modulation method for downlink transmission; activates the modulation method for uplink transmission; deactivates the modulation method for downlink transmission; or deactivates the modulation method for uplink transmission.
[0019] In exemplary implementations of the methods, which may be combined with any of the other exemplary implementations disclosed herein, the methods include the wireless terminal device reporting, and the WANN receiving reporting of, a total number of AI Processing Units (APU) available at the wireless terminal device and a required number of APU for the modulation method or the model at the wireless terminal device.
[0020] In exemplary implementations of the methods, which may be combined with any of the other exemplary implementations disclosed herein, for downlink transmission, the modulation method or the model of a downlink data channel occupies a required number APU from time T1 to time T2, wherein the time T1 is defined as one of the following: an end of a control channel scheduling the downlink data channel; a first time offset after the end of the control channel scheduling the downlink data channel; a second time offset before a start of the downlink data channel; or a start of the downlink data channel. The time T2 is defined as one of the following: an end of the downlink data channel; or a third time offset after the end of the downlink data channel.
[0021] In exemplary implementations of the methods, which may be combined with any of the other exemplary implementations disclosed herein, for uplink transmission, the modulation method or the model of an uplink data channel occupies a required number APU from time T3 to time T4, wherein the time T3 is defined as one of the following: an end of a control channel scheduling the uplink data channel; a first time offset after the end of the control channel scheduling the uplink data channel; or a second time offset before a start of the uplink data channel. The time T4 is defined as one of the following: a start of the uplink data channel, or a third time offset after the end of the uplink data channel.
[0022] In exemplary implementations of the methods, which may be combined with any of the other exemplary implementations disclosed herein, the methods include the WANN transmitting, and the wireless terminal device receiving, first channel weight information. Additionally or alternatively, the methods include the wireless terminal device transmitting, and the WANN receiving, second channel weight information. The first channel weight information and / or the second channel weight information indicates a channel weight of each layer.
[0023] In exemplary implementations of the methods, which may be combined with any of the other exemplary implementations disclosed herein, a channel weight of a first layer is a predefined value, and the first channel weight information and / or the second channel weight information comprises channel weights of layers other than the first layer relative to the predefined value of the channel weight of the first layer. In exemplary implementations of the methods, which may be combined with any of the other exemplary implementations disclosed herein, the first channel weight information and / or the second channel weight information comprises an index, wherein the index is associated with channel weights for the layers or a range of channel weights for each layer.
[0024] In exemplary implementations of the methods, which may be combined with any of the other exemplary implementations disclosed herein, the first channel weight information and / or the second channel weight information comprises W channel weights for the L layers, wherein at least one of the following is true: each channel weight corresponds to one layer; W is equal to L-1, and a channel weight of the first layer is predefined and each channel weight corresponds to a layer other than the first layer; each channel weight corresponds to layers; the channel weight of the first layer is predefined and each channel weight corresponds to layers other than the first layer; the first channel weight corresponds to a first S layers, and each of the other channel weights correspond to S1 layers in order, wherein S=mod (L, W) and the channel weight of the first layer is predefined, the first channel weight corresponds to the first S layers other than the first layer, and each of the other channel weight corresponds to S1 layers in order, wherein S=mod (L-1, W) and each of the channel weight among the first S channel weights corresponds to S1 layers, and each of the other channel weight corresponds to S2 layers, wherein S=mod (L, W) , and or the channel weight of the first layer is predefined, each of the channel weight among the first S channel weights corresponds to S1 layers other than the first layer, and each of the other channel weight corresponds to S2 layers, wherein S=mod (L-1, W) , and
[0025] In exemplary implementations of the methods, which may be combined with any of the other exemplary implementations disclosed herein, each modulation mapper is associated with a set of channel weights or a set of ranges of channel weights.
[0026] In some other implementations, an apparatus for wireless communication such as a network device is disclosed. The network device may include one or more processors and one or more memories, wherein the one or more processors are configured to read computer code from the one or more memories to implement any one of the methods above. The apparatus for wireless communication may be the wireless access network node (e.g., base station) or the wireless terminal device (e.g., UE) .
[0027] In yet some other implementations, a computer program product is disclosed. The computer program product may include a non-transitory computer-readable medium with computer code stored thereupon, the computer code, when executed by one or more processors, causing the one or more processors to implement any one of the methods above.
[0028] The above embodiments and other aspects and alternatives of their implementations are explained in greater detail in the drawings, the descriptions, and the claims below.BRIEF DESCRIPTION OF THE DRAWINGS
[0029] FIG. 1 shows a wireless access network with an exemplary uplink, downlink, and control channel configuration.
[0030] FIG. 2 shows various example processing components of the wireless terminal device and the wireless access network node of FIG. 1.
[0031] FIG. 3 illustrates an example of the legacy modulation scheme.
[0032] [Rectified under Rule 91, 07.05.2025]FIG. 4a shows a different modulation and layer mapping arrangement in accordance with various embodiments.[0032.1][Rectified under Rule 91, 07.05.2025]FIG. 4b shows another different modulation and layer mapping arrangement in accordance with various embodiments.
[0033] FIG. 5 shows an example of modulation and demodulation using AI in accordance with various embodiments.
[0034] FIG. 6 shows another example of modulation and demodulation using AI in accordance with various embodiments.
[0035] FIG. 7 shows a timing diagram illustrating the timing relationship for downlink transmission in accordance with various embodiments.
[0036] FIG. 8 shows a timing diagram illustrating the timing relationship for uplink transmission in accordance with various embodiments.
[0037] FIG. 9 shows a graph illustrating simulation results in accordance with various embodiments.DETAILED DESCRIPTION
[0038] The technology and examples of implementations and / or embodiments described in this disclosure can be used to facilitate over-the-air radio resource allocation, configuration, and signaling in wireless access networks as well as operational configuration of a UE and / or a base station within the wireless access networks. The term “exemplary” is used to mean “an example of” and unless otherwise stated, does not imply an ideal or preferred example, implementation, or embodiment. Section headers are used in the present disclosure to facilitate understanding of the disclosed implementations and are not intended to limit the disclosed technology in the sections only to the corresponding section. The disclosed implementations may be further embodied in a variety of different forms and, therefore, the scope of this disclosure or claimed subject matter is intended to be construed as not being limited to any of the embodiments set forth below. The various implementations may be embodied as methods, devices, components, systems, or non-transitory computer readable media. Accordingly, embodiments of this disclosure may, for example, take the form of hardware, software, firmware or any combination thereof.
[0039] This disclosure is directed to handling transmissions in a wireless cellular access network and is specifically directed to mechanisms for configuring modulation and / or demodulation.
[0040] Wireless Network Overview
[0041] A wireless communication network may include a radio access network for providing network access to wireless terminal devices, and a core network for routing data between the access networks or between the wireless network and other types of data networks. In a wireless access network, radio resources are provided for allocation and used for transmitting data and control information. FIG. 1 shows an exemplary wireless access network 100 including a wireless access network node (WANN) or wireless base station 102 (herein referred to as wireless base station, base station, wireless access node, wireless access network node, or WANN) and a wireless terminal device or user equipment (UE) 104 (herein referred to as user equipment, UE, terminal device, or wireless terminal device) that communicates with one another via over-the-air (OTA) radio communication resources 106. The wireless access network 100 may be implemented as, as for example, a 2G, 3G, 4G / LTE, or 5G cellular radio access network. Correspondingly, the base station 102 may be implemented as a 2G base station, a 3G node B, an LTE eNB, or a 5G New Radio (NR) gNB. The user equipment 104 may be implemented as mobile or fixed communication devices installed with mobile identity modules for accessing the base station 102. The user equipment 104 may include but is not limited to mobile phones, laptop computers, tablets, personal digital assistants, wearable devices, distributed remote sensor devices, and desktop computers. Alternatively, the wireless access network 100 may be implemented as other types of radio access networks, such as Wi-Fi, Bluetooth, ZigBee, and WiMax networks.
[0042] FIG. 2 further shows example processing components of the WANN 102 (e.g., base station) and the UE 104 of FIG. 1. The UE 104, for example, may include transceiver circuitry 206 coupled to one or more antennas 208 to effectuate wireless communication with the WANN 102 (or to other UEs) . The transceiver circuitry 206 may also be coupled to a processor 210, which may also be coupled to a memory 212 or other storage devices. The memory 212 may be transitory or non-transitory and may store therein computer instructions or code which, when read and executed by the processor 210, cause the processor 210 to implement various ones of the, functions, methods, and processes of the UE 104 described herein. The memory 212 may also store therein, and the processor 210 may also be configured to execute one or more models (e.g., Artificial Intelligence / Machine Learning (AI / ML) models) to perform one or more functionalities (e.g., AI / ML functionalities) . The memory 212 may also be utilized and allocated for buffering UL and DL transmissions in each band / carrier. The memory 212 may include multiple memory modules assigned to different functions (such as program memory, base band memory, and / or RF memory, to name a few) . Likewise, the WANN 102 may include transceiver circuitry 214 coupled to one or more antennas 216, which may include an antenna tower 218 in various forms, to effectuate wireless communications with the UE 104. The transceiver circuitry 214 may be coupled to one or more processors 220, which may further be coupled to a memory 222 or other storage devices. The memory 222 may be transitory or non-transitory and may store therein instructions or code that, when read and executed by the one or more processors 220, cause the one or more processors 220 to implement various functions, methods, and processes of the WANN 102 described herein.
[0043] Wireless Communication Resource Scheduling / Signaling
[0044] Returning to FIG. 1, the radio communication resources for the over-the-air interface 106 may include a combination of frequency, time, and / or spatial communication resources organized into various resource units or elements in frequency, time, and / or space. The radio communication resources 106 in frequency domain may include portions of licensed radio frequency bands, portions of unlicensed ration frequency bands, or portions of a mix of both licensed and unlicensed radio frequency bands. The radio communication resources 106 available for carrying the wireless communication signals between the base station 102 and user equipment 104 may be further divided into physical downlink channels 110 for transmitting wireless signals from the base station 102 to the user equipment 104 and physical uplink channels 120 for transmitting wireless signals from the user equipment 104 to the base station 102. The physical downlink channels 110 may further include physical downlink control channels (PDCCHs) 112 and physical downlink shared channels (PDSCHs) 114. Likewise, the physical uplink channels 120 may further include physical uplink control channels (PUCCHs) 122 and physical uplink shared channels (PUSCHs) 124. For simplification, other types of downlink and uplink channels are not shown in FIG. 1 but are within the scope of the current disclosure. The control channels PDCCHs 112 and PUCCHs 122 may be used for carrying control information in the form of control messages 116 and 126, herein referred to as Downlink Control Information (DCI) messages or Uplink Control Information (UCI) messages. The shared channels (shared between data and control information) PDSCHs 114 and PUSCHs 124 may be allocated and used for communicating downlink data transmissions 118 and uplink data transmissions 128 between the base station 102 and the user equipment 104.
[0045] The allocation and configuration of the radio communication resources associated with the data channels, such as the PDSCHs and the PUSCHs may be provided by one or more resource scheduling DCIs carried in the PDCCHs. The PDCCHs may be shared by a plurality of UEs in the access network. In various approaches, a particular UE may be configured to perform blind decode procedures on a preconfigured UE-specific Search Space (USS) to detect and identify a payload of a resource scheduling DCI carried in the PDCCH that specifically targets the particular UE. The blind decoding may be performed on preconfigured monitoring occasions of the PDCCH associated with USS. Such monitoring occasions may be referred to as a set of PDCCH candidates. Each PDCCH candidate may be associated with a set of Control Channel Elements (CCEs) . The UE may specifically use its Radio Network Temporary Identifier (RNTI) to decode the PDCCH candidates. The RNTI may be used to demask a PDCCH candidate’s CRC. If no CRC error is detected, the UE determines that PDCCH candidate carries its own control information. The UE may then process the DCI and extract the resource allocation information pertaining to the PDSCH and / or PUSCH for receiving and / or transmitting data.
[0046] Framework for Configuring Modulation and Demodulation
[0047] Joint Modulation and Layer Mapping / Precoding
[0048] In various embodiments, a modulation mapper takes binary digits, 0 or 1, as input and produces modulation symbols as output. In various embodiments, the base station 102 communicates with the UE 104 via a data channel, which may have a modulation order Q, where Q is integer number larger than 0 (e.g., Q is equal to 0.5, 2, 4, 6, 8, 10, 12, etc. ) . The data channel may be a downlink channel or an uplink channel. For this modulation method, the modulation order may be Q and the number of layers of the data channel may be L. L can be a number of layers, a number of symbols, or a number of resource elements of the data channel. In this disclosure, the embodiments are discussed assuming L is a number of layers of the data channel, however, these embodiments can be applied to the case when L is a number of symbols or a number of resource elements of the data channel when appropriately.
[0049] Mb bits of data channel are mapped to Ms symbols (e.g., complex-valued modulation symbols) . Mb and Ms may be positive integer numbers. Mb may be equal to Q·K·L, where L and K are positive integer numbers. K may be applied to adjust the bits of the input. K can be predefined (e.g., 1) or can be indicated by the base station 102. For example, if K is equal to 1, and L is equal to 4, then bits corresponding to 4 layers are input into the modulation method; if K is equal to 2 and L is equal to 4, then bits corresponding to 4 layers in 2 resource elements (or in 2 symbols) are input into the modulation method.
[0050] In various approaches, the value of Ms may be one of the following:
[0051] Alt. 1: Ms is equal to K·L; or
[0052] Alt. 2: Ms is equal to K·P, where P is an integer number larger than 0 and P is the number of antenna ports of the data channel.
[0053] Mb bits of data channel may be the original bits carried by the data channel or the bits after some processing, e.g., coding, scrambling, etc.
[0054] In summary, the first alternative (Alt. 1) above allows the UE 104 to jointly perform modulation and layer mapping in one method, while the second alternative (Alt. 2) above allows the UE 104 to jointly perform modulation, layer mapping, and precoding (e.g., mapping to antenna ports) in one method. Both of these two alternatives can increase the mapping dimension between bits and symbols.
[0055] The transmitter can learn the channel status of the downlink or uplink for each layer of the L layers. In order to make the best of the L layers, the transmitter can adjust the amplitude and / or phase of the modulation symbols on each layer to increase the modulation performance compared with the method with no adjustment of amplitude and / or phase of the modulation symbols of different layers.
[0056] In various embodiments, regarding the first alternative (Alt. 1) above, the modulation method may further comprise layer mapping, i.e., the Ms modulation symbols may be mapped onto L layers according to one of the following alternatives. Assume that Ms modulation symbols are d (0) , d (1) , …, d (Ms-1) , and is the number of modulation symbols per layer.
[0057] For the first alternative, xk (i) =d (L·i+k) , where xk (i) is the modulation symbol with index i on the layer with index k. Both of i and k are non-negative integer numbers, where and k=0, 1, …, L-1. Meanwhile, is equal to Ms / L.
[0058] For the second alternative, where xk (i) is the modulation symbol with index i on the layer with index k. Both of i and k are non-negative integer numbers, where and k=0, 1, …, L-1. Meanwhile, is equal to Ms / L.
[0059] In some typical examples, K may be equal to 1. K can be used to control the number of input bits of the modulation mapper. The number K and the number L together can be used to control the dimension of the modulation symbols. For example, if K is equal to 1 and L is equal to 4, then the Mb bits of data channel are mapped to 4 complex-value dimensions, which can increase the flexibility of the modulation and increase the minimum distance among the modulation symbols. In the end, it can increase the system reliability and / or throughput.
[0060] [Rectified under Rule 91, 07.05.2025]FIG. 4a shows a different modulation and layer mapping arrangement in accordance with various embodiments and FIG. 4b shows another different modulation and layer mapping arrangement in accordance with various embodiments. The legacy modulation and layer mapping are separately design (as seen in FIG. 3) . However, the solution proposed herein tries to optimize the modulation and layering mapping as a whole. Although the modulation and layering mapping can be implemented as separate modules, e.g., as shown in FIG. 4a, the input of the modulation considers the layering mapping. In the approach of FIG. 4a, assuming the modulation order is 2 and the number of layers is 4, then 8 bits are input into the modulation module every time and the 8 bits are mapped to 4 modulation symbols (i.e., MS0, MS1, MS2, and MS3) . These modulation symbols MS0, MS1, MS2 and MS3 are mapped to layer 0, layer 1, layer 2, and layer 3, respectively. This is more like a vector-based modulation since the modulation outputs a vector with dimension of 4.
[0061] In various implementations, the base station 102 may indicate the modulation order Q and number of layer L to the UE 104 via control channel or configuration. In one example, the base station 102 indicates the MCS index to the UE 104, where the modulation order Q is associated with the MCS index. In one example, the base station 102 indicates the reference signal ports (e.g., DMRS ports) to the UE 104, where the same ports are used for the data channel. Thus, the number of layers L may be equal to the number of reference signal ports. In another example, the base station 102 indicates the index of antenna port to the UE 104, where the index of antenna port may be associated with the number of layers.
[0062] In some implementations, the mapping between the Mb bits of channel and the Ms modulation symbols for modulation order Q and / or number of layers L is predefined. One goal is to make the modulation method adaptive to the channel status. Because the channel status may change fast and drastically, multiple modulation mappers may be predefined for the same modulation order Q. Thus, the base station 102 may need to indicate the modulation mapper to the UE 104, where the modulation mapper is the mapping between the Mb bits of channel and the Ms modulation symbols for modulation order Q and / or number of layers L.
[0063] In various implementations, the base station 102 may configure the mapping between the Mb bits of channel and the Ms modulation symbols for modulation order Q and / or number of layers L to the UE 104. One goal is to make the modulation method adaptive to the channel status. The modulation mapper may be the mapping between the Mb bits of channel and the Ms modulation symbols for modulation order Q and / or number of layers L. Similarly, the base station 102 may need to indicate a modulation mapper to the UE 104 from among the multiple modulation mappers configured by the base station 102.
[0064] The modulation mapper is the mapping between the Mb bits of channel and the Ms modulation symbols for modulation order Q and / or number of layer L. In some implementations, multiple modulation mappers are predefined for a modulation order Q and / or number of layers L. In another implementation, the base station 102 configures multiple modulation mappers for a modulation order Q and / or number of layer L to the UE 104.
[0065] The base station 102 may indicate a modulation mapper to the UE 104 for the data channel, where the modulation mapper may be the mapping between the Mb bits of channel and the Ms modulation symbols for modulation order Q and / or number of layers L.
[0066] In some implementations, the base station indicates an index to the UE 104, where the index is associated with a predefined modulation mapper. In another implementation, in order to reduce the signaling overhead, the base station 102 may indicate an index to the UE 104, where the index is associated with a modulation order and a mapper. In another implementation, in order to reduce the signaling overhead, the base station 102 may indicate an index to the UE 104, where the index is associated with a number of layers and a mapper. In another implementation, in order to reduce the signaling overhead, the base station 102 may indicate an index to the UE 104, where the index is associated with a modulation order, a number of layers, and a modulation mapper.
[0067] In various embodiments, the base station 102 may indicate the number of antenna ports of the data channel (i.e., P) to the UE 104.
[0068] In various embodiments, the modulation mapper is the mapping between the Mb bits of channel and the Ms modulation symbols for modulation order Q and / or number of layers L and / or number of antenna ports P. In various approaches, multiple modulation mappers are predefined for a modulation order Q and / or number of layer L and / or number of antenna ports P. In another implementation, the base station 102 can configure multiple modulation mappers for a modulation order Q and / or number of layers L and / or number of antenna ports P to the UE 104.
[0069] The base station 102 may indicate a modulation mapper to the UE 104 for the data channel, where the modulation mapper is the mapping between the Mb bits of channel and the Ms modulation symbols for modulation order Q and / or number of layers L and / or number of antenna ports P.
[0070] In various implementations, the base station 102 may indicate an index to the UE 104, where the index is associated with a predefined modulation mapper. In another implementation, in order to reduce the signaling overhead, the base station 102 may indicate an index to the UE 104, where the index is associated with a number of antenna ports and a modulation mapper. In another implementation, in order to reduce the signaling overhead, the base station 102 may indicate an index to the UE 104, where the index is associated with a number of antenna ports, a modulation order, and a modulation mapper. In another implementation, in order to reduce the signaling overhead, the base station 102 may indicate an index to the UE 104, where the index is associated with a number of antenna ports, a number of layers, and a modulation mapper. In another implementation, in order to reduce the signaling overhead, the base station 102 may indicate an index to the UE 104, where the index is associated with a number of antenna ports, a modulation order, a number of layers, and a modulation mapper.
[0071] As such, in accordance with various embodiments, a method performed by the wireless terminal device 104 (e.g., UE 104) includes communicating with a wireless access network node (WANN) 102 (e.g., base station 102) using a modulation method via a data channel having a modulation order Q, where Q is an integer number larger than 0, wherein a number of layers of the data channel is L, and a number to control input bits is K, wherein L and K are positive integer numbers, wherein, in the modulation method, Mb bits of the data channel are mapped to Ms modulation symbols, wherein Mb is equal to Q·K·L, wherein Mb and Ms are positive integer numbers. In the method, a value of Ms is one of the following: Ms is equal to K·L; or Ms is equal to K·P, wherein P is a number of antenna ports of the data channel, and wherein P is an integer number larger than 0.
[0072] Similarly, a method performed by the WANN 102 includes communicating with the wireless terminal device 104 using a modulation method via a data channel having a modulation order Q, where Q is an integer number larger than 0, wherein a number of layers of the data channel is L, and a number to control input bits is K, wherein L and K are positive integer numbers, wherein, in the modulation method, Mb bits of the data channel are mapped to Ms modulation symbols, wherein Mb is equal to Q·K·L, wherein Mb and Ms are positive integer numbers. In the method, a value of Ms is one of the following: Ms is equal to K·L; or Ms is equal to K·P, wherein P is a number of antenna ports of the data channel, and wherein P is an integer number larger than 0.
[0073] In accordance with various embodiments of the methods, Ms is equal to K·L, wherein the Ms modulation symbols are d (0) , d (1) , ..., d (Ms-1) , and is a number of modulation symbols per layer, and wherein the modulation method comprises layer mapping, wherein the Ms modulation symbols are mapped onto the L layers according to one of the following alternatives: xk (i) =d (L·i+k) , wherein: k=0,1, …, L-1, and is equal to Ms / L. Or, wherein: k=0, 1, …, L-1, and is equal to Ms / L, wherein xk (i) is a modulation symbol with index i on a layer with index k, wherein both i and k are non-negative integer numbers.
[0074] In accordance with various embodiments, the methods include the WANN 102 transmitting, and the wireless terminal device 104 receiving, an indication of the modulation order Q and number of layer L via a control channel or configuration. In accordance with various embodiments, the methods include the WANN 102 transmitting, and the wireless terminal device 104 receiving, a configuration of mapping between the Mb bits of channel and the Ms modulation symbols for modulation order Q and / or number of layer L.
[0075] In accordance with various embodiments of the methods, the modulation mapper is a mapping between the Mb bits of channel and the Ms modulation symbols for the modulation order Q, and / or the number of layers L, and / or a number of antenna ports P, wherein a plurality of modulation mappers are predefined or are configured by the wireless access network node for the modulation order Q, and / or the number of layers L, and / or the number of antenna ports P. In various examples, the methods include the WANN 102 transmitting, and the wireless terminal device 104 receiving the modulation mapper for the data channel, wherein the transmitting or receiving comprises transmitting or receiving the mapping for the modulation mapper, or transmitting or receiving an index associated with one of the predefined modulation mappers.
[0076] In accordance with various embodiments of the methods, the index is associated with: the modulation order Q and the modulation mapper; the number of layers L and the modulation mapper; the modulation order Q, a number of layers L, and the modulation mapper; the number of antenna ports P and the modulation mapper; the number of antenna ports P, the modulation order Q, and the modulation mapper; the number of antenna ports P, the number of layers L, and the modulation mapper; or the number of antenna ports P, the modulation order Q, the number of layers L, and the modulation mapper.
[0077] AI-Based Solutions
[0078] In various embodiments, an AI-based solution can be applied to perform the modulation and demodulation. For example, an AI model can be applied to perform the modulation, while another AI model can be applied to perform demodulation. However, the model for modulation and the model for demodulation may need to be paired, otherwise, it could impact the demodulation performance.
[0079] For a communication system with AI / ML technology, an AI / ML model is adopted, for example, to perform inference. Generally, a model may refer to a functionality, function, functionality module, function module, processing method, information processing method, implementation, feature, feature group, configuration, configuration set, dataset (e.g., for model training) , or data-driven algorithms. Generally, these models are performed, calculated, or processed by the UE 104, but may also be performed at the base station 102. In various examples, a model may be a data driven algorithm that applies AI / ML techniques to generate a set of outputs based on a set of inputs. Alternatively, a model can be linear or non-linear algorithms or combination of both algorithms. In addition, functionality may refer to a feature enabled by the AI / ML model. Alternatively, functionality may refer to a set of parameters or configurations for one feature. For example, a UE 104 may adopt a convolutional neural network (CNN) model to predict the beams for the communication, and the CNN model is the model and the beam prediction is the functionality. Different models and / or functionalities may be associated with different configurations (e.g., Radio Resource Control (RRC) configuration) . Model activation may refer to activating the corresponding configuration for the UE. Similarly, model deactivation, switching, and fallback may refer to deactivating the corresponding configuration, switching the configuration, and falling back to a configuration without the model, respectively.
[0080] FIG. 5 shows an example of modulation and demodulation using AI in accordance with various embodiments. Using FIG. 5 as an example, at the transmitter side, an AI model is applied to directly perform the modulation and layer mapping, while at the receive side, another AI model is applied to perform the demodulation and layer de-mapping. Note that FIG. 5 shows joint operation of modulation and layer mapping in one model, while separate AI models may be also be applied for modulation and layer mapping, respectively. Alternatively, the AI model may be performed for the modulation part only, but the AI model should take the number of layers into account.
[0081] In some embodiments, a model processes the bits (e.g., bits after scrambling) and generates modulation symbols that are mapped to several layers for a data channel. The modulation symbols that are mapped to several layers are then mapped to antenna ports. This corresponds to the first alternative (Alt. 1) in the embodiment discussed above.
[0082] In some embodiments, the model processes Mb bits and generates Ms modulation symbols, where Mb and Ms are positive integer numbers. Mb may be equal to Q·K·L, where L and K are positive integer numbers. The modulation order is Q and the number of layers of the data channel is L. Ms may be equal to K·L.
[0083] Alternatively, in another implementation, the model processes Mb bits and generates Ms modulation symbols, Mb and Ms are positive integer number. Mb may be equal to K·L, where L and K are positive integer numbers. The modulation order is Q and the number of layers of the data channel is L. Ms may be equal to K·L. K can be predefined or indicated by the base station 102. In this example, the modulation order may be implicitly merged with the integer number K and thus no need to explicitly indicate the modulation order Q.
[0084] FIG. 6 shows another example of modulation and demodulation using AI in accordance with various embodiments. In this implementation, as shown in FIG. 6, at the transmitter side, an AI model is applied to directly perform the modulation, layer mapping, and precoding (e.g., transform precoding) , while at the receive side, another AI model is applied to perform the equalization, demodulation, and layer de-mapping. Note that, the transmitter side (e.g., base station 102) may need to know the channel weight information in order to better fit the channel.
[0085] In some embodiments, the model processes the processed bits (e.g., bits after scrambling) and generates modulation symbols that are mapped to several antenna ports. The modulation symbols that are mapped to several antenna ports are then mapped to virtual resource blocks. In this case, the model is applied to jointly perform modulation, layer mapping, and precoding functions. This corresponds to the second alternative (Alt. 2) of the previous embodiment, above.
[0086] In various embodiments, the model processes Mb bits and generates Ms modulation symbols, where Mb and Ms are positive integer numbers. Mb may be equal to Q·K·L, where L and K are positive integer numbers. The modulation order is Q and the number of layers of the data channel is L. Ms may be equal to K·P, where P is an integer number larger than 0, and P is the number of antenna ports of the data channel.
[0087] Alternatively, in another implementation, the model processes Mb bits and generates Ms modulation symbols, where Mb and Ms are positive integer numbers. Mb may be equal to K·L, where L and K are positive integer numbers. The modulation order is Q and the number of layers of the data channel is L. Ms may be equal to K·P, where P is an integer number larger than 0, and P is the number of antenna ports of the data channel. K can be predefined or indicated by the base station 102. In this example, the modulation order is implicitly merged with the integer number K, and thus no need to explicitly indicate the modulation order Q.
[0088] Alternatively, in another implementation, the model processes Mb bits and generates Ms modulation symbols, Mb and Ms are positive integer numbers. Mb may be equal to K, where K is a positive integer number. The modulation order is Q. Ms may be equal to K·P, where P is an integer number larger than 0, and P is the number of antenna ports of the data channel. K can be predefined or indicated by the base station 102. In this example, the modulation order and number of layers may be implicitly merged with the integer number K, and thus no need to explicitly indicate the modulation order Q and the number of layers.
[0089] In order to make sure the AI model at the base station 102 side and the AI model at the UE 104 side can be paired together, the base station 102 may transmit the model information to the UE 104. The UE 104 performs modulation for uplink data channel or demodulation for downlink data channel based on the model information.
[0090] In one embodiment, the model information comprises dataset information.
[0091] In one alternative, the dataset information comprises three parts, where the first part comprises multiple groups of bits, the second part comprises multiple groups of modulation symbols, and the third part comprises assistance information. Each group of bits may be associated with a group of modulation symbols.
[0092] In one implementation, the UE 104 generates the model for modulation or demodulation based on dataset information and / or assistance information. For example, the UE 104 may train the model for modulation via considering the bits in the first part as model input and modulation symbols in the second part as model output. Or, the UE 104 may train the model for demodulation via considering the bits in the first part as model output and modulation symbols in the second part as model input.
[0093] In another alternative, the dataset information comprises two parts, where the first part comprises multiple groups of modulation symbols, and the second part comprises assistance information. Each group of modulation symbols may be mapped to a group of bits. A pattern for the groups of modulation symbols are predefined or indicated by the base station 102, and the multiple groups of modulation symbols are ordered according to the pattern. Similarly, for example, the UE 104 may train the model for modulation via considering the bits in the first part as model input and modulation symbols in the second part as model output. Or, the UE 104 may train the model for demodulation via considering the bits in the first part as model output and modulation symbols in the second part as model input. In this case, the overhead of the dataset information can be reduced.
[0094] In various implementations, the pattern for the groups of the modulation symbols is based on a pattern for the groups of bits. Assuming the modulation order is Q and the total number of groups of modulation symbols are MQ, there are two potential alternatives:
[0095] Alt. 1: Each group of modulation symbols correspond to Q bits, and the first 2Q groups of modulation symbols follow the increasing order of the value of the corresponding group of bits, and the second 2Q groups of modulation symbols follow the increasing order of the value of the corresponding group of bits, and so on.
[0096] Alt. 2: Each group of modulation symbols correspond to Q bits, the first groups of modulation symbols are for the group of bits with value “0, ” the second groups of modulation symbols are for the group of bits with value “1, ” and so on.
[0097] In various embodiments, the model information comprises model parameter information.
[0098] In some implementations, the model parameter information comprises a set of parameters for generating the model at the UE 104 side.
[0099] Normally, a model comprises two parts, i.e., the model structure and parameters. For example, a model structure is the predefined architecture of the model, and parameters are the learned values that adjust the model's behavior based on training dataset. In one implementation, the model parameter information comprises a model structure for the set of parameters. Multiple model structures may be predefined. The base station 102 may indicate one or more indexes or IDs (Identifications) of the predefined model structures.
[0100] Similarly, the model information may comprise assistance information. The UE 104 may need to know the assistance information for generating the model for modulation or demodulation.
[0101] In various implementations, the UE 104 generates the model for modulation or demodulation based on dataset information or model parameter information. The UE 104 may need to know the assistance information for generating the model for modulation or demodulation.
[0102] In various implementations, the assistance information comprises modulation order. Because different models may be applicable to different modulation orders, the base station 102 may need to indicate the modulation order of the model (e.g., model generated by the model parameters or model generated based on the dataset) .
[0103] In some implementations, the assistance information comprises a number of layers. Because different models may be applicable to different number of layers, the base station 102 may need to indicate the applicable number of layers of the model (e.g., model generated by the model parameters or model generated based on the dataset) .
[0104] In some implementations, the assistance information comprises a performance requirement. After generating the model for modulation or demodulation based on dataset information or model parameter information, the UE 104 may need to evaluate whether the generated model satisfies the performance requirement. The performance requirement may be a requirement based on Bit Error Rate (BER) , Block Error Rate (BLER) , Error Vector Magnitude (EVM) , etc.
[0105] In various implementations, the assistance information comprises a dataset ID, size of the dataset, quantization method of the dataset, quantization method of the parameter or format of the parameters. With this assistance information, the UE 104 can generate the model at the UE 104 side paired with the model at the base station 102 side.
[0106] As such, in accordance with various embodiments, a method performed by the wireless terminal device 104 (e.g., UE 104) includes communicating with a wireless access network node (WANN) 102 (e.g., base station 102) using a modulation method via a data channel having a modulation order Q, where Q is an integer number larger than 0, wherein a number of layers of the data channel is L, a number to control the input bits is K, and a number of antenna ports of the data channel is P, wherein L, K, and P are positive integer numbers. The method also includes performing the modulation method using a model to process Mb bits of the data channel to generate Ms modulation symbols mapped to the layers of the data channel or to a plurality of antenna ports P of the data channel, wherein Mb is equal to Q·K·L, or is equal to K·L, or is equal to K, wherein Ms is equal to K·L or is equal to K·P, and wherein Mb and Ms are positive integer numbers, wherein K is predefined or indicated by the WANN 102.
[0107] Similarly, a method performed by the WANN 102 includes communicating with the wireless terminal device 104 using a modulation method via a data channel having a modulation order Q, where Q is an integer number larger than 0, wherein a number of layers of the data channel is L, a number to control input bits is K, and a number of antenna ports of the data channel is P, wherein L, K, and P are positive integer numbers. The method also includes performing the modulation method using a model to process Mb bits of the data channel to generate Ms modulation symbols mapped to the layers of the data channel or to a plurality of antenna ports P of the data channel, wherein Mb is equal to Q·K·L, or is equal to K·L, or is equal to K, wherein Ms is equal to K·L or is equal to K·P, and wherein Mb and Ms are positive integer numbers, wherein K is predefined or indicated by the wireless access network node.
[0108] In accordance with various embodiments, the methods include the WANN 102 transmitting, and the wireless terminal device 104 receiving, model information, wherein the model information comprises dataset information and / or model parameter information. The dataset information comprises at least one of: a first part comprising a plurality of groups of bits, a second part comprising a plurality of groups of modulation symbols, and a third part comprising assistance information, wherein each group of bits is associated with a group of modulation symbols, or a first part comprising a plurality of groups of modulation symbols, and a second part comprising assistance information, wherein each group of modulation symbols is mapped to a group of bits, and wherein a pattern for the plurality of groups of modulation symbols are predefined or indicated by the wireless access network node, and are ordered according to the pattern. Or, the model parameter information comprises at least one of:a set of parameters for generating the model at the wireless terminal device, a model structure for the set of parameters, or assistance information.
[0109] In accordance with various embodiments of the methods, the assistance information comprises at least one of: a modulation order, a number of layers, a performance requirement, or a dataset ID, size of the dataset, quantization method of the dataset, quantization method or format of the set of parameters.
[0110] Performance Monitoring
[0111] In various embodiments, after applying the new modulation and / or demodulation method, including the layer mapping or precoding, the base station 102 and / or the UE 104 may need to guarantee the performance is acceptable. If it is not acceptable, the base station 102 can directly deactivate this new modulation and / or demodulation method.
[0112] For uplink transmission, the base station 102 knows the total number of scheduled uplink transmissions and the successfully received uplink transmissions. Based on this information, the base station 102 can determine the overall performance of the uplink transmission applying the new modulation and / or demodulation methods.
[0113] However, for downlink transmission, the base station 102 knows the total number of scheduled downlink transmissions, but it may not know the successfully received downlink transmissions at the UE 104 side. Thus, the UE 104 may transmit a performance report to the base station 102.
[0114] In some embodiments, the UE 104 may transmit a performance report to the base station 102, where the performance report comprises a value of a performance metric. The performance metric may be BER, BLER, EVM, number of successfully received Transmission Block (TB) , number of successfully received transmission, number of unsuccessfully received TB, number of unsuccessfully received transmission, etc. The value of the performance metric may be an average or absolute value over a period time. Alternatively, the value of the performance metric may be an average value over a number of transmissions.
[0115] Based on the performance monitoring result, the base station 102 may activate or deactivate the new modulation method.
[0116] In some embodiments, the base station 102 transmits control information to the UE 104 to schedule an uplink transmission, where the control information comprises an indication indicating whether to apply the modulation method for the uplink transmission.
[0117] In some embodiments, the base station 102 transmits control information to the UE 104 to schedule an uplink transmission, where the control information comprises an indication indicating the UE 104 to apply the modulation method for the uplink transmission.
[0118] In some embodiments, the base station 102 transmits control information to the UE 104 to schedule a downlink transmission, where the control information comprises an indication indicating whether the modulation method is applied for the downlink transmission.
[0119] In some embodiments, the base station 102 transmits control information to the UE 104 to schedule a downlink transmission, where the control information comprises an indication indicating to the UE 104 that the modulation method is applied for the downlink transmission.
[0120] In some embodiments, the base station 102 transmits control information to the UE 104 to activate the modulation method for downlink transmission. In some embodiments, the base station 102 transmits control information to the UE 104 to activate the modulation method for uplink transmission. Because the channel status of the downlink and uplink may be different, separate activation commands may be preferred for uplink and downlink transmissions.
[0121] In some embodiments, the base station 102 transmits control information to the UE 104 to deactivate the modulation method for downlink transmission. In some embodiments, the base station 102 transmits control information to the UE 104 to deactivate the modulation method for uplink transmission. Because the channel status of the downlink and uplink may be different, separate deactivation commands may be preferred for uplink and downlink transmissions.
[0122] As such, in accordance with various embodiments, the methods include the wireless terminal device 104 transmitting, and the WANN 102 receiving, a performance report, wherein the performance report comprises a value of a performance metric, wherein the performance metric comprises at least one of: Bit Error Rate (BER) , Block Error Rate (BLER) , Error Vector Magnitude (EVM) , number of successfully received Transmission Blocks (TB) , number of successfully received transmissions, number of unsuccessfully received TB, or number of unsuccessfully received transmissions.
[0123] In accordance with various embodiments, the methods include the WANN 102 transmitting, and the wireless terminal device 104 receiving, control information, wherein the control information at least one of: schedules an uplink transmission, where the control information comprises an indication of whether the modulation method is applied for the uplink transmission; schedules a downlink transmission, where the control information comprises an indication of whether the modulation method is applied for the downlink transmission; activates the modulation method for downlink transmission; activates the modulation method for uplink transmission; deactivates the modulation method for downlink transmission; or deactivates the modulation method for uplink transmission.
[0124] AI Processing Unit (APU)
[0125] In various embodiments, the UE 104 side processing units may be limited. In order to better manage the AI Processing Unit (APU) at the UE 104 side, the UE 104 can report the processing units required by the UE 104 to perform the modulation method. In addition, the occupation time of the APU may need to be aligned between the UE 104 and the base station 102.
[0126] In some embodiments, the UE 104 may report the total number of APU available at the UE 104 side and the required number of APU for the modulation method or the model at the UE 104 side. The APU may correspond to the computation unit and / or memory unit.
[0127] For downlink transmission, the modulation method or the model of the downlink data channel occupies the required number APU from time T1 to time T2. During this time duration, the required number of APU is reserved for the modulation method or the model, and other use cases can’t take it.
[0128] FIG. 7 is a timing diagram illustrating the timing relationship for downlink transmission in accordance with various embodiments.
[0129] The time T1 may be defined as one of the following:
[0130] Option 1: The time T1 is defined as the end of the control channel scheduling the downlink data channel, e.g., time T0 in FIG. 7. In this case, the UE 104 may reserve these APU for the modulation method or the model immediately after the control channel.
[0131] Option 2: The time T1 is defined as a first time offset after the end of the control channel scheduling the downlink data channel. The first time offset may be applied for the UE 104 to decode the control channel and obtain the information carried by the control channel.
[0132] Option 3: The time T1 is defined as a second time offset before the start of the downlink data channel. The second time offset may be applied for the UE 104 to prepare the modulation method or the model, e.g., loading the model into memory.
[0133] Option 4: The time T1 is defined as the start of downlink data channel.
[0134] The time T2 may be defined as one of the following:
[0135] Option 1: The time T2 is defined as the end of the downlink data channel. In this case, the UE 104 may release these APU for the modulation method or the model immediately after the downlink data channel.
[0136] Option 2: The time T2 is defined as a third time offset after the end of the downlink data channel. The third time offset may be applied for the UE 104 to demodulate the downlink data channel.
[0137] FIG. 8 is a timing diagram illustrating the timing relationship for uplink transmission in accordance with various embodiments. Similarly, for uplink transmission, the modulation method or the model of the uplink data channel occupies the required number APU from time T3 to time T4. During this time duration, the required number of APU is reserved for the modulation method or the model and other use cases can’ t take it.
[0138] The time T3 may be defined as one of the following:
[0139] Option 1: The time T3 is defined as the end of the control channel scheduling the uplink data channel, e.g., time T0 in FIG. 8. In this case, the UE 104 may reserve these APU for the modulation method or the model immediately after the control channel.
[0140] Option 2: The time T3 is defined as a first time offset after the end of the control channel scheduling the uplink data channel. The first time offset is applied for the UE 104 to decode the control channel and obtain the information carried by the control channel.
[0141] Option 3: The time T3 is defined as a second time offset before the start of uplink data channel. The second time offset may be applied for the UE 104 to prepare the modulation method or the model, e.g., loading the model into memory.
[0142] The time T4 may be defined as one of the following:
[0143] Option 1: The time T4 is defined as the start of the uplink data channel. In this case, the UE 104 releases these APU for the modulation method or the model immediately after the uplink data channel starts.
[0144] Option 2: The time T4 is defined as a third time offset after the end of the uplink data channel. The third time offset is applied for the UE 104 to modulate the uplink data channel.
[0145] As such, in accordance with various embodiments, the methods include the wireless terminal device 104 reporting, and the WANN 102 receiving reporting of, a total number of AI Processing Units (APU) available at the wireless terminal device and a required number of APU for the modulation method or the model at the wireless terminal device.
[0146] In accordance with various embodiments of the methods, for downlink transmission, the modulation method or the model of a downlink data channel occupies a required number APU from time T1 to time T2, wherein the time T1 is defined as one of the following: an end of a control channel scheduling the downlink data channel; a first time offset after the end of the control channel scheduling the downlink data channel; a second time offset before a start of the downlink data channel; or a start of the downlink data channel. The time T2 is defined as one of the following: an end of the downlink data channel; or a third time offset after the end of the downlink data channel.
[0147] In accordance with various embodiments of the methods, for uplink transmission, the modulation method or the model of an uplink data channel occupies a required number APU from time T3 to time T4, wherein the time T3 is defined as one of the following: an end of a control channel scheduling the uplink data channel; a first time offset after the end of the control channel scheduling the uplink data channel; or a second time offset before a start of the uplink data channel. The time T4 is defined as one of the following: a start of the uplink data channel, or a third time offset after the end of the uplink data channel.
[0148] Channel Weight Information and Measurement Report
[0149] In various embodiments, in order to facilitate the uplink transmission or the downlink reception at the UE 104 side, the base station 102 may indicate the first channel weight information to the UE 104. For example, for uplink transmission, the UE 104 can better understand the uplink channel based on the first channel weight information and choose the optimal modulation mapper. For example, for downlink transmission, the UE 104 can better understand the modulation mapper applied by the downlink transmission and facilitate the demodulation.
[0150] Similarly, for uplink, the base station 102 can obtain the uplink channel status via measurement of uplink reference signal, e.g., SRS or DMRS. For downlink, the base station 102 may need UE 104 assistance to obtain the downlink channel status, e.g., the UE 104 reporting the channel status to the base station 102. In one embodiment, the UE 104 transmits a measurement report to the base station 102, where the measurement report comprises the second channel weight information.
[0151] Thus, overall, the first channel weight information is indicated from the base station 102 to the UE 104 for uplink / downlink channel scheduling, while the second channel weight information is indicated from the UE 104 to the base station 102 to facilitate the uplink / downlink channel scheduling. The first channel weight information and second channel weight information can be indicated separately.
[0152] In one embodiment, the channel weight information (i.e., the first channel weight information or the second channel weight information) indicates channel weight of each layer. The channel weight may be derived by signal strength, channel status, channel capacity, etc. The channel status may comprise Signal-to-Interference-plus-Noise Ratio (SINR) , Reference Signal Received Power (RSRP) , Precoding Matrix Indicator (PMI) , and other measurement results of the reference signal.
[0153] In some embodiments, in order to reduce the overhead, the channel weight of the first layer may be predefined as a value, e.g., 1. The channel weight information (i.e., the first channel weight information or the second channel weight information) may comprise the channel weights of layers other than the first layer, where the indicated channel weights are relative to the predefined channel weight of the first layer. In one implementation, the UE 104 indicates the channel weights of layers other than the first layer to the base station 102, where the indicated channel weights are relative to the predefined channel weight of the first layer.
[0154] In another embodiment, in order to reduce the overhead, the channel weight information (i.e., the first channel weight information or the second channel weight information) may comprise an index, where the index is associated with channel weights for the layers. The channel weights may be relative to the channel weight of the first layer. Similar methods can be applied for the UE measurement report. An example of such an index is provided below in Table 1.
[0155] Table 1
[0156] In one embodiment, in order to reduce the overhead, the channel weight information (i.e., the first channel weight information or the second channel weight information) may comprise an index, where the index is associated with a range of channel weights for each layer. Similarly, the UE 104 may indicate an index to the base station 102, where the index is associated with a range of channel weights for each layer. The channel weights may be relative to the channel weight of the first layer. The range of channel weights may only comprise one value in some cases. An example of such an index including ranges of channel weights is provided below in Table 2.
[0157] Table 2
[0158] In practical, normally the channel weights between adjacent layers are similar. Normally, with an increase of the layer index, the channel weight becomes smaller. Thus, some adjacent layers can share the same channel weight to reduce the signaling overhead of indication of layer strength information.
[0159] FIG. 9 shows a graph illustrating simulation results for an instance of a Clustered Delay Line (CDL) channel with 32x4 dimension, e.g., where the base station 102 is equipped with 32 Tx antennas and the UE 104 is equipped with 4 Rx antennas. In this simulation, the channel weight of each layer is reflected as eigen value of the channel. Other simulation assumptions may have similar observations. Note that, in FIG. 9, the index refers to the layer index. The singular value magnitude is the eigen value that is not normalized.
[0160] In various embodiments, the base station 102 may indicate W channel weights to the UE 104 for a data channel with L layers, where W is an integer number larger than 0. Alternatively, the UE 104 may indicate W channel weights to the base station 102 for a rank indicator indicating L layers, where W is an integer number larger than 0. In other words, the channel weight information (i.e., the first channel weight information or the second channel weight information) comprises W channel weights for L layers.
[0161] In some implementations, when W is equal to L, each channel weight may correspond to one layer. For example, the first channel weight may correspond to the first layer, the second channel weight may correspond to the second layer, and so on.
[0162] In some implementations, W is equal to L-1, and the channel weight of the first layer may be predefined (e.g., 1) , and each channel weight indicated by the base station 102 may correspond to a layer (e.g., one layer) . For example, the first channel weight may correspond to the second layer, the second channel weight may correspond to the third layer, and so on.
[0163] In one implementation, if L is an integer multiple of W, each channel weight may correspond to layers. For example, if W is equal to 2 and L is equal to 4, the first channel weight corresponds to the first two layers (i.e., layer with index 0 and 1) , the second channel weight corresponds to the second two layers (layer with index 2 and 3) , and so on.
[0164] In one implementation, if L-1 is an integer multiple of W, the channel weight of the first layer is predefined (e.g., 1) , each channel weight corresponds to layers other than the first layer. For example, if W is equal to 2 and L is equal 5, the channel weight of the first layer (the layer with index 0) is q, the first channel weight corresponds to the first two layers after the first layer (i.e., layer with index 1 and 2) , the second channel weight corresponds to the second two subsequent layers (layer with index 3 and 4) , and so on.
[0165] As mentioned above, a layer with smaller index normally is associated with higher channel weights, which means it has better channel status or channel gain or is allocated with more power. Thus, in order to boost the overall system throughput, more accurate channel weights should be allocated for the layer with a smaller index.
[0166] In one implementation, assuming S=mod (L, W) , and the first channel weight may correspond to the first S layers, and each of the other channel weights corresponds to S1 layers in order. In this case, the layer with a smaller index has more accurate channel weight since less number of layers share the same channel weight.
[0167] In one implementation, assuming S=mod (L-1, W) , and the channel weight of the first layer is predefined (e.g., 1) , the first channel weight indicated by the base station 102 may correspond to the first S layers other than the first layer, and each of the other channel weight corresponds to S1 layers in order. In this case, the layer with a smaller index has more accurate channel weight since less number of layers share the same channel weight.
[0168] In one implementation, assuming S=mod (L, W) , and each of the channel weight among the first S channel weights may correspond to S1 layers, while each of the other channel weights correspond to S2 layers. In this case, the layer with a smaller index has more accurate channel weight since less number of layers share the same channel weight.
[0169] In one implementation, assuming S=mod (L-1, W) , and
[0170] the channel weight of the first layer is predefined (e.g., 1) , each of the channel weights among the first S channel weights indicated by the base station 102 corresponds to S1 layers other than the first layer, while each of the other channel weights correspond to S2 layers. In this case, the layer with a smaller index has more accurate channel weight since less number of layers share the same channel weight.
[0171] Note that mod refers the operation to calculate the remainder and the operation refers to the operation of round down, and refers to the operation of round up.
[0172] In some embodiments, each predefined mapper or mapper configured by the base station 102 is associated with a set of channel weights or a set of ranges of channel weights. The base station 102 and / or the UE 104 may determine the application scenario of each mapper according to the channel weights. This can facilitate the modulation and demodulation.
[0173] In some other scenarios, e.g., Single UE MIMO (SU-MIMO) , more power may be allocated for the layer with smaller channel weights because the main bottleneck of the UE 104 is the layer with smaller channel weights. In this case, more accurate power allocation for the layers with larger index may be required.
[0174] In various implementations, assuming S=mod (L, W) and the first channel weight may correspond to the last S layers, and each of the other channel weights may correspond to S1 layers.
[0175] In various implementations, assuming S=mod (L-1, W) and the channel weight of the first layer may be predefined (e.g., 1) , the first channel weight indicated by the base station 102 may correspond to the last S layers other than the first layer, and each of the other channel weights may correspond to S1 layers.
[0176] In various implementations, assuming S=mod (L, W) , and each of the channel weight among the first S channel weights may correspond to S2 layers, while each of the other channel weights may correspond to S1 layers.
[0177] In various implementations, assuming S=mod (L-1, W) , and the channel weight of the first layer may be predefined (e.g., 1) , each of the channel weights among the first S channel weights indicated by the base station 102 may correspond to S2 layers other than the first layer, while each of the other channel weights corresponds to S1 layers.
[0178] In this case, the layer with a larger index has more accurate channel weight since less number of layers share the same channel weight.
[0179] As such, in accordance with various embodiments, the methods include the WANN 102 transmitting, and the wireless terminal device 104 receiving, first channel weight information. Additionally or alternatively, the methods include the wireless terminal device 104 transmitting, and the WANN 102 receiving, second channel weight information. The first channel weight information and / or the second channel weight information indicates a channel weight of each layer.
[0180] In accordance with various embodiments of the methods, a channel weight of a first layer is a predefined value, and the first channel weight information and / or the second channel weight information comprises channel weights of layers other than the first layer relative to the predefined value of the channel weight of the first layer. In accordance with various embodiments of the methods, the first channel weight information and / or the second channel weight information comprises an index, wherein the index is associated with channel weights for the layers or a range of channel weights for each layer.
[0181] In accordance with various embodiments of the methods, the first channel weight information and / or the second channel weight information comprises W channel weights for the L layers, wherein at least one of the following is true: each channel weight corresponds to one layer; W is equal to L-1, and a channel weight of the first layer is predefined and each channel weight corresponds to a layer other than the first layer; each channel weight corresponds to layers; the channel weight of the first layer is predefined and each channel weight corresponds to layers other than the first layer; the first channel weight corresponds to a first S layers, and each of the other channel weights correspond to S1 layers in order, wherein S=mod (L, W) and the channel weight of the first layer is predefined, the first channel weight corresponds to the first S layers other than the first layer, and each of the other channel weight corresponds to S1 layers in order, wherein S=mod (L-1,W) and each of the channel weight among the first S channel weights corresponds to S1 layers, and each of the other channel weight corresponds to S2 layers, wherein S=mod (L, W) , and or the channel weight of the first layer is predefined, each of the channel weight among the first S channel weights corresponds to S1 layers other than the first layer, and each of the other channel weight corresponds to S2 layers, wherein S=mod (L-1, W) , and
[0182] In accordance with various embodiments of the methods, each modulation mapper is associated with a set of channel weights or a set of ranges of channel weights.
[0183] The description and accompanying drawings above provide specific example embodiments and implementations. The described subject matter may, however, be embodied in a variety of different forms and, therefore, covered or claimed subject matter is intended to be construed as not being limited to any example embodiments set forth herein. A reasonably broad scope for claimed or covered subject matter is intended. Among other things, for example, subject matter may be embodied as methods, devices, components, systems, or non-transitory computer-readable media for storing computer codes. Accordingly, embodiments may, for example, take the form of hardware, software, firmware, storage media or any combination thereof. For example, the method embodiments described above may be implemented by components, devices, or systems including memory and processors by executing computer codes stored in the memory.
[0184] Throughout the specification and claims, terms may have nuanced meanings suggested or implied in context beyond an explicitly stated meaning. Likewise, the phrase “in one embodiment / implementation / example / approach” as used herein does not necessarily refer to the same embodiment and the phrase “in another embodiment / implementation / example / approach” as used herein does not necessarily refer to a different embodiment. It is intended, for example, that claimed subject matter includes combinations of example embodiments in whole or in part.
[0185] In general, terminology may be understood at least in part from usage in context. For example, terms, such as “and” , “or” , or “and / or, ” as used herein may include a variety of meanings that may depend at least in part on the context in which such terms are used. Typically, “or” if used to associate a list, such as A, B or C, is intended to mean A, B, and C, here used in the inclusive sense, as well as A, B or C, here used in the exclusive sense. In addition, the term “one or more” as used herein, depending at least in part upon context, may be used to describe any feature, structure, or characteristic in a singular sense or may be used to describe combinations of features, structures or characteristics in a plural sense. Similarly, terms, such as “a, ” “an, ” or “the, ” may be understood to convey a singular usage or to convey a plural usage, depending at least in part upon context. In addition, the term “based on” may be understood as not necessarily intended to convey an exclusive set of factors and may, instead, allow for existence of additional factors not necessarily expressly described, again, depending at least in part on context.
[0186] Reference throughout this specification to features, advantages, or similar language does not imply that all of the features and advantages that may be realized with the present solution should be or are included in any single implementation thereof. Rather, language referring to the features and advantages is understood to mean that a specific feature, advantage, or characteristic described in connection with an embodiment is included in at least one embodiment of the present solution. Thus, discussions of the features and advantages, and similar language, throughout the specification may, but do not necessarily, refer to the same embodiment.
[0187] Furthermore, the described features, advantages and characteristics of the present solution may be combined in any suitable manner in one or more embodiments. One of ordinary skill in the relevant art will recognize, in light of the description herein, that the present solution can be practiced without one or more of the specific features or advantages of a particular embodiment. In other instances, additional features and advantages may be recognized in certain embodiments that may not be present in all embodiments of the present solution.
Claims
A method performed by a wireless terminal device comprising:communicating with a wireless access network node using a modulation method via a data channel having a modulation order Q, where Q is an integer number larger than 0, wherein a number of layers of the data channel is L, and a number to control input bits is K, wherein L and K are positive integer numbers,wherein, in the modulation method, Mb bits of the data channel are mapped to Ms modulation symbols, wherein Mb is equal to Q·K·L, wherein Mb and Ms are positive integer numbers, andwherein a value of Ms is one of the following:Ms is equal to K·L; orMs is equal to K·P, wherein P is a number of antenna ports of the data channel, and wherein P is an integer number larger than 0.The method according to claim 1,wherein Ms is equal to K·L,wherein the Ms modulation symbols are d (0) , d (1) , ..., d (Ms-1) , andis a number of modulation symbols per layer, andwherein the modulation method comprises layer mapping, wherein the Ms modulation symbols are mapped onto the L layers according to one of the following alternatives:xk (i) =d (L·i+k) , wherein:k=0, 1, ..., L-1, andis equal to Ms / L;orwherein:k=0, 1, ..., L-1, andis equal to Ms / L,wherein xk (i) is a modulation symbol with index i on a layer with index k, wherein both i and k are non-negative integer numbers.The method according to any of claims 1 to 2, comprising:receiving, from the wireless access network node, an indication of the modulation order Q and number of layer L via a control channel.The method according to any of claims 1 to 3, comprising:receiving, from the wireless access network node, a configuration of mapping between the Mb bits of channel and the Ms modulation symbols for modulation order Q and / or number of layer L.The method according to any of claims 1 to 4,wherein the modulation mapper is a mapping between the Mb bits of channel and the Ms modulation symbols for the modulation order Q, and / or the number of layers L, and / or a number of antenna ports P,wherein a plurality of modulation mappers are predefined or are configured by the wireless access network node for the modulation order Q, and / or the number of layers L, and / or the number of antenna ports P,wherein the method comprises:receiving, from the wireless access network node, the modulation mapper for the data channel,wherein the receiving comprises receiving the mapping for the modulation mapper, or receiving an index associated with one of the predefined modulation mappers.The method according to claim 5,wherein the index is associated with:the modulation order Q and the modulation mapper;the number of layers L and the modulation mapper;the modulation order Q, a number of layers L, and the modulation mapper;the number of antenna ports P and the modulation mapper;the number of antenna ports P, the modulation order Q, and the modulation mapper;the number of antenna ports P, the number of layers L, and the modulation mapper; orthe number of antenna ports P, the modulation order Q, the number of layers L, and the modulation mapper.A method performed by a wireless terminal device comprising:communicating with a wireless access network node using a modulation method via a data channel having a modulation order Q, where Q is an integer number larger than 0, wherein a number of layers of the data channel is L, a number to control the input bits is K, and a number of antenna ports of the data channel is P, wherein L, K, and P are positive integer numbers; andperforming the modulation method using a model to process Mb bits of the data channel to generate Ms modulation symbols mapped to the layers of the data channel or to a plurality of antenna ports P of the data channel, wherein Mb is equal to Q·K·L, or is equal to K·L, or is equal to K, wherein Ms is equal to K·L or is equal to K·P, and wherein Mb and Ms are positive integer numbers,wherein K is predefined or indicated by the wireless access network node.The method according to claim 7, comprising:receiving, from the wireless access network node, model information,wherein the model information comprises dataset information and / or model parameter information,wherein the dataset information comprises at least one of:a first part comprising a plurality of groups of bits, a second part comprising a plurality of groups of modulation symbols, and a third part comprising assistance information, wherein each group of bits is associated with a group of modulation symbols, ora first part comprising a plurality of groups of modulation symbols, and a second part comprising assistance information, wherein each group of modulation symbols is mapped to a group of bits, and wherein a pattern for the plurality of groups of modulation symbols are predefined or indicated by the wireless access network node, and are ordered according to the pattern,orwherein the model parameter information comprises at least one of:a set of parameters for generating the model at the wireless terminal device,a model structure for the set of parameters, orassistance information.The method according to claim 8,wherein the assistance information comprises at least one of:a modulation order,a number of layers,a performance requirement, ora dataset ID, size of the dataset, quantization method of the dataset, quantization method or format of the set of parameters.The method according to any of claims 7 to 9, comprising:transmitting, to the wireless access network node, a performance report, wherein the performance report comprises a value of a performance metric, wherein the performance metric comprises at least one of:Bit Error Rate (BER) ,Block Error Rate (BLER) ,Error Vector Magnitude (EVM) ,number of successfully received Transmission Blocks (TB) ,number of successfully received transmissions,number of unsuccessfully received TB, ornumber of unsuccessfully received transmissions.The method according to any of claims 7 to 10, comprising:receiving, from the wireless access network node, control information, wherein the control information at least one of:schedules an uplink transmission, where the control information comprises an indication of whether the modulation method is applied for the uplink transmission;schedules a downlink transmission, where the control information comprises an indication of whether the modulation method is applied for the downlink transmission;activates the modulation method for downlink transmission;activates the modulation method for uplink transmission;deactivates the modulation method for downlink transmission; ordeactivates the modulation method for uplink transmission.The method according to any of claims 7 to 11, comprising:reporting, to the wireless access network node, a total number of AI Processing Units (APU) available at the wireless terminal device and a required number of APU for the modulation method or the model at the wireless terminal device.The method according to claim 12,wherein, for downlink transmission, the modulation method or the model of a downlink data channel occupies a required number APU from time T1 to time T2,wherein the time T1 is defined as one of the following:an end of a control channel scheduling the downlink data channel;a first time offset after the end of the control channel scheduling the downlink data channel;a second time offset before a start of the downlink data channel; ora start of the downlink data channel;andwherein the time T2 is defined as one of the following:an end of the downlink data channel; ora third time offset after the end of the downlink data channel.The method according to any one of claims 12 to 13,wherein, for uplink transmission, the modulation method or the model of an uplink data channel occupies a required number APU from time T3 to time T4,wherein the time T3 is defined as one of the following:an end of a control channel scheduling the uplink data channel;a first time offset after the end of the control channel scheduling the uplink data channel; ora second time offset before a start of the uplink data channel;andwherein the time T4 is defined as one of the following:a start of the uplink data channel, ora third time offset after the end of the uplink data channel.The method according to any of claims 1 to 14, comprising:receiving, from the wireless access network node, first channel weight information; and / ortransmitting, to the wireless access network node, second channel weight information,wherein the first channel weight information and / or the second channel weight information indicates a channel weight of each layer.The method according to claim 15,wherein a channel weight of a first layer is a predefined value, andwherein the first channel weight information and / or the second channel weight information comprises channel weights of layers other than the first layer relative to the predefined value of the channel weight of the first layer.The method according to claim 15,wherein the first channel weight information and / or the second channel weight information comprises an index, wherein the index is associated with channel weights for the layers or a range of channel weights for each layer.The method according to claim 15,wherein the first channel weight information and / or the second channel weight information comprises W channel weights for the L layers,wherein at least one of the following is true:each channel weight corresponds to one layer;W is equal to L-1, and a channel weight of the first layer is predefined and each channel weight corresponds to a layer other than the first layer;each channel weight corresponds tolayers;the channel weight of the first layer is predefined and each channel weight corresponds tolayers other than the first layer;the first channel weight corresponds to a first S layers, and each of the other channel weights correspond to S1 layers in order, wherein S=mod (L, W) andthe channel weight of the first layer is predefined, the first channel weight corresponds to the first S layers other than the first layer, and each of the other channel weight corresponds to S1 layers in order, wherein S=mod (L-1, W) andeach of the channel weight among the first S channel weights corresponds to S1 layers, and each of the other channel weight corresponds to S2 layers, wherein S=mod (L, W) , andorthe channel weight of the first layer is predefined, each of the channel weight among the first S channel weights corresponds to S1 layers other than the first layer, and each of the other channel weight corresponds to S2 layers, wherein S=mod (L-1, W) , andThe method according to any of claims 15 to 18,wherein each modulation mapper is associated with a set of channel weights or a set of ranges of channel weights.A method performed by a wireless access network node comprising:communicating with a wireless terminal device using a modulation method via a data channel having a modulation order Q, where Q is an integer number larger than 0, wherein a number of layers of the data channel is L, and a number to control input bits is K, wherein L and K are positive integer numbers,wherein, in the modulation method, Mb bits of the data channel are mapped to Ms modulation symbols, wherein Mb is equal to Q·K·L, wherein Mb and Ms are positive integer numbers, andwherein a value of Ms is one of the following:Ms is equal to K·L; orMs is equal to K·P, wherein P is a number of antenna ports of the data channel, and wherein P is an integer number larger than 0.The method according to claim 20,wherein Ms is equal to K·L,wherein the Ms modulation symbols are d (0) , d (1) , …, d (Ms-1) , andis a number of modulation symbols per layer, andwherein the modulation method comprises layer mapping, wherein the Ms modulation symbols are mapped onto the L layers according to one of the following alternatives:xk (i) =d (L·i+k) , wherein:k=0, 1, …, L-1, andis equal to Ms / L;orwherein:k=0, 1, …, L-1, andis equal to Ms / L,wherein xk (i) is a modulation symbol with index i on a layer with index k, wherein both i and k are non-negative integer numbers.The method according to any of claims 20 to 21, comprising:transmitting, to the wireless terminal device, an indication of the modulation order Q and number of layer L via a control channel.The method according to any of claims 20 to 22, comprising:transmitting, to the wireless terminal device, a configuration of mapping between the Mb bits of channel and the Ms modulation symbols for modulation order Q and / or number of layer L.The method according to any of claims 20 to 23,wherein the modulation mapper is a mapping between the Mb bits of channel and the Ms modulation symbols for the modulation order Q, and / or the number of layers L, and / or a number of antenna ports P,wherein a plurality of modulation mappers are predefined or are configured by the wireless access network node for the modulation order Q, and / or the number of layers L, and / or the number of antenna ports P,wherein the method comprises:transmitting, to the wireless terminal device, the modulation mapper for the data channel,wherein the transmitting comprises transmitting the mapping for the modulation mapper, or transmitting an index associated with one of the predefined modulation mappers.The method according to claim 24,wherein the index is associated with:the modulation order Q and the modulation mapper;the number of layers L and the modulation mapper;the modulation order Q, a number of layers L, and the modulation mapper;the number of antenna ports P and the modulation mapper;the number of antenna ports P, the modulation order Q, and the modulation mapper;the number of antenna ports P, the number of layers L, and the modulation mapper; orthe number of antenna ports P, the modulation order Q, the number of layers L, and the modulation mapper.A method performed by a wireless access network node comprising:communicating with a wireless terminal device using a modulation method via a data channel having a modulation order Q, where Q is an integer number larger than 0, wherein a number of layers of the data channel is L, a number to control input bits is K, and a number of antenna ports of the data channel is P, wherein L, K, and P are positive integer numbers; andperforming the modulation method using a model to process Mb bits of the data channel to generate Ms modulation symbols mapped to the layers of the data channel or to a plurality of antenna ports P of the data channel, wherein Mb is equal to Q·K·L, or is equal to K·L, or is equal to K, wherein Ms is equal to K·L or is equal to K·P, and wherein Mb and Ms are positive integer numbers,wherein K is predefined or indicated by the wireless access network node.The method according to claim 26, comprising:transmitting, to the wireless terminal device, model information,wherein the model information comprises dataset information and / or model parameter information,wherein the dataset information comprises at least one of:a first part comprising a plurality of groups of bits, a second part comprising a plurality of groups of modulation symbols, and a third part comprising assistance information, wherein each group of bits is associated with a group of modulation symbols, ora first part comprising a plurality of groups of modulation symbols, and a second part comprising assistance information, wherein each group of modulation symbols is mapped to a group of bits, and wherein a pattern for the plurality of groups of modulation symbols are predefined or indicated by the wireless access network node, and are ordered according to the pattern,orwherein the model parameter information comprises at least one of:a set of parameters for generating the model at the wireless terminal device,a model structure for the set of parameters, orassistance information.The method according to claim 26,wherein the assistance information comprises at least one of:a modulation order,a number of layers,a performance requirement, ora dataset ID, size of the dataset, quantization method of the dataset, quantization method or format of the set of parameters.The method according to any of claims 26 to 28, comprising:receiving, from the wireless terminal device, a performance report, wherein the performance report comprises a value of a performance metric, wherein the performance metric comprises at least one of:Bit Error Rate (BER) ,Block Error Rate (BLER) ,Error Vector Magnitude (EVM) ,number of successfully received Transmission Blocks (TB) ,number of successfully received transmissions,number of unsuccessfully received TB, ornumber of unsuccessfully received transmissions.The method according to any of claims 26 to 29, comprising:transmitting, to the wireless terminal device, control information, wherein the control information at least one of:schedules an uplink transmission, where the control information comprises an indication of whether the modulation method is applied for the uplink transmission;schedules a downlink transmission, where the control information comprises an indication of whether the modulation method is applied for the downlink transmission;activates the modulation method for downlink transmission;activates the modulation method for uplink transmission;deactivates the modulation method for downlink transmission; ordeactivates the modulation method for uplink transmission.The method according to any of claims 26 to 30, comprising:receiving, from the wireless terminal device, a reporting of a total number of AI Processing Units (APU) available at the wireless terminal device and a required number of APU for the modulation method or the model at the wireless terminal device.The method according to claim 31,wherein, for downlink transmission, the modulation method or the model of a downlink data channel occupies a required number APU from time T1 to time T2,wherein the time T1 is defined as one of the following:an end of a control channel scheduling the downlink data channel;a first time offset after the end of the control channel scheduling the downlink data channel;a second time offset before a start of the downlink data channel; ora start of the downlink data channel;andwherein the time T2 is defined as one of the following:an end of the downlink data channel; ora third time offset after the end of the downlink data channel.The method according to any one of claims 31 to 32,wherein, for uplink transmission, the modulation method or the model of an uplink data channel occupies a required number APU from time T3 to time T4,wherein the time T3 is defined as one of the following:an end of a control channel scheduling the uplink data channel;a first time offset after the end of the control channel scheduling the uplink data channel; ora second time offset before a start of the uplink data channel;andwherein the time T4 is defined as one of the following:a start of the uplink data channel, ora third time offset after the end of the uplink data channel.The method according to any of claims 20 to 33, comprising:transmitting, to the wireless terminal device, first channel weight information; and / orreceiving, from the wireless terminal device, second channel weight information,wherein the first channel weight information and / or the second channel weight information indicates a channel weight of each layer.The method according to claim 34,wherein a channel weight of a first layer is a predefined value, andwherein the first channel weight information and / or the second channel weight information comprises channel weights of layers other than the first layer relative to the predefined value of the channel weight of the first layer.The method according to claim 34,wherein the first channel weight information and / or the second channel weight information comprises an index, wherein the index is associated with channel weights for the layers or a range of channel weights for each layer.The method according to claim 34,wherein the first channel weight information and / or the second channel weight information comprises W channel weights for the L layers,wherein at least one of the following is true:each channel weight corresponds to one layer;W is equal to L-1, and a channel weight of the first layer is predefined and each channel weight corresponds to a layer other than the first layer;each channel weight corresponds tolayers;the channel weight of the first layer is predefined and each channel weight corresponds tolayers other than the first layer;the first channel weight corresponds to a first S layers, and each of the other channel weights correspond to S1 layers in order, wherein S=mod (L, W) andthe channel weight of the first layer is predefined, the first channel weight corresponds to the first S layers other than the first layer, and each of the other channel weight corresponds to S1 layers in order, wherein S=mod (L-1, W) andeach of the channel weight among the first S channel weights corresponds to S1 layers, and each of the other channel weight corresponds to S2 layers, wherein S=mod (L, W) , andorthe channel weight of the first layer is predefined, each of the channel weight among the first S channel weights corresponds to S1 layers other than the first layer, and each of the other channel weight corresponds to S2 layers, wherein S=mod (L-1, W) , andThe method according to any of claims 34 to 37,wherein each modulation mapper is associated with a set of channel weights or a set of ranges of channel weights.An apparatus for wireless communication comprising a processor that is configured to carry out the method of any of claims 1 to 38.A non-transitory computer readable medium having code stored thereon, the code when executed by a processor, causing the processor to implement the method recited in any of claims 1 to 38.
Citation Information
Patent Citations
Apparatus and method for transmitting data in a multi-antenna system
US20120027004A1
Method and device for transmitting downlink control information
US20140313994A1
Signal transmission method and apparatus
US20230261921A1
Multi-carrier data processing method and apparatus
WO2024125491A1