Exchange of probabilistic shaped constellation information for wireless networks

Abstract

A method includes determining, by a first node of a wireless network, constellation point probabilities for a plurality of constellation points of a probabilistic shaped constellation; determining a s

Description

[0001] This description relates to wireless communications. BACKGROUND

[0002] A communication system may be a facility that enables communication between two or more nodes or devices, such as fixed or mobile communication devices. Signals can be carried on wired or wireless carriers.

[0003] An example of a cellular communication system is an architecture that is being standardized by the 3rd Generation Partnership Project (3GPP). EUTRA (evolved Universal Mobile Telecommunications System Terrestrial Radio Access) is the air interface of 3 GPP's Long Term Evolution (LTE) upgrade path for mobile networks. In LTE, base stations or access points (APs), which are referred to as enhanced Node B (eNBs), provide wireless access within a coverage area or cell. In LTE, mobile devices, or mobile stations are referred to as user equipments (UE). LTE has included a number of improvements or developments.

[0004] 5G New Radio (NR) development is part of a continued mobile broadband evolution process to meet the requirements of 5G, similar to earlier evolution of 3G and 4G wireless networks. In addition, 5G is also targeted at the new emerging use cases in addition to mobile broadband. A goal of 5G is to provide significant improvement m wireless performance, which may include new levels of data rate, latency, reliability, and security. 5G NR may also scale to efficiently connect the massive Internet of Things (loT) and may offer new types of mission-critical services. For example, ultra-reliable and low-latency communications (URLLC) devices may require high reliability and very low latency. 6G and other networks are also being developed. SUMMARY

[0005] In some aspects, the techniques described herein relate to an apparatus including: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: determine, by a first node of a wireless network, based at least on channel measurement information, constellation point probabilities for a plurality of constellation points of a probabilistic shaped constellation; transmit, by the first node to a second node of the wireless network, probabilistic shaped constellation information indicative of the constellation point probabilities; and transmit and / or receive, by the first node, a signal based on the probabilistic shaped constellation.

[0006] In some aspects, the techniques described herein relate to a method including: determining, by a first node of a wireless network, based at least on channel measurement information, constellation point probabilities for a plurality of constellation points of a probabilistic shaped constellation; transmitting, by the first node to a second node of the wireless network, probabilistic shaped constellation information indicative of the constellation point probabilities; and transmitting and / or receiving, by the first node, a signal based on the probabilistic shaped constellation.

[0007] In some aspects, the techniques described herein relate to an apparatus including: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: determine, by a first node of a wireless network, constellation point probabilities for a plurality of constellation points of a probabilistic shaped constellation; determine a symmetry property for the probabilistic shaped constellation; determine a strict subset of the constellation point probabilities based on the symmetry property; transmit, by the first node to a second node of the wireless network, probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities; and transmit and / or receive, by the first node, a signal based on the probabilistic shaped constellation.

[0008] In some aspects, the techniques described herein relate to an apparatus including: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: determine, by a second node of a wireless network, a symmetry property for a probabilistic shaped constellation, wherein the probabilistic shaped constellation includes constellation point probabilities for a plurality of constellation points; receive, by the second node from a first node of the wireless network, probabilistic shaped constellation information indicative of a strict subset of the constellation point probabilities; determine, by the second node based on the symmetry property and the probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities, the probabilistic shaped constellation including the plurality of constellation point probabilities; and transmit and / or receive, by the second node, a signal based on the probabilistic shaped constellation.

[0009] In some aspects, the techniques described herein relate to a method including: determining, by a first node of a wireless network, constellation point probabilities for a plurality of constellation points of a probabilistic shaped constellation; determining a symmetry property for the probabilistic shaped constellation; determining a strict subset of the constellation point probabilities based on the symmetry property; transmitting, by the first node to a second node of the wireless network, probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities; and transmitting and / or receiving, by the first node, a signal based on the probabilistic shaped constellation.

[0010] In some aspects, the techniques described herein relate to a method including: determining, by a second node of a wireless network, a symmetry property for a probabilistic shaped constellation, wherein the probabilistic shaped constellation includes constellation point probabilities for a plurality of constellation points; receiving, by the second node from a first node of the wireless network, probabilistic shaped constellation information indicative of a strict subset of the constellation point probabilities; determining, by the second node based on the symmetry property and the probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities, the probabilistic shaped constellation including the plurality of constellation point probabilities; and transmitting and / or receiving, by the second node, a signal based on the probabilistic shaped constellation.

[0011] In some aspects, the techniques described herein relate to an apparatus including: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: determine, by a first node of a wireless network, constellation point probabilities for a plurality of constellation points of a first probabilistic shaped constellation; determine, by the first node, a transformation function for deriving the first probabilistic shaped constellation from a reference constellation; transmit, by the first node to a second node of the wireless network, an indication of the transformation function; and transmit and / or receive, by the first node, a signal based on the first probabilistic shaped constellation.

[0012] In some aspects, the techniques described herein relate to an apparatus including: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: determine, by a second node of a wireless network, constellation point probabilities of a plurality of constellation points of a reference constellation; receive, by the second node from a first node of the wireless network, an indication of a transformation function for deriving a first probabilistic shaped constellation from the reference probabilistic shaped constellation; determine, by the second first node, constellation point probabilities of a plurality of constellation points of the first probabilistic shaped constellation based on the constellation point probabilities of the plurality of constellation points of the reference probabilistic shaped constellation and the transformation function; and transmit and / or receive, by the second node, a signal based on the first probabilistic shaped constellation.

[0013] In some aspects, the techniques described herein relate to a method including: determining, by a first node of a wireless network, constellation point probabilities for a plurality of constellation points of a first probabilistic shaped constellation; determining, by the first node, a transformation function for deriving the first probabilistic shaped constellation from a reference constellation; transmitting, by the first node to a second node of the wireless network, an indication of the transformation function; and transmitting and / or receiving, by the first node, a signal based on the first probabilistic shaped constellation.

[0014] In some aspects, the techniques described herein relate to a method including: determining, by a second node of a wireless network, constellation point probabilities of a plurality of constellation points of a reference constellation; receiving, by the second node from a first node of the wireless network, an indication of a transformation function for deriving a first probabilistic shaped constellation from the reference probabilistic shaped constellation; determining, by the second first node, constellation point probabilities of a plurality of constellation points of the first probabilistic shaped constellation based on the constellation point probabilities of the plurality of constellation points of the reference probabilistic shaped constellation and the transformation function; and transmitting and / or receiving, by the second node, a signal based on the first probabilistic shaped constellation.

[0015] Other example embodiments are provided or described for each of the example methods, including: an apparatus including means for performing any of the example methods; an apparatus including a non-transitory computer-readable storage medium comprising instructions stored thereon that, when executed by at least one processor, are configured to cause a computing system to perform any of the example methods; and an apparatus including at least one processor, and at least one memory including computer program code, the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus at least to perform any of the example methods.

[0016] The details of one or more examples of embodiments are set forth in the accompanying drawings and the description below. Other features will be apparent from the description and drawings, and from the claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] FIG. 1 is a block diagram of a wireless network.

[0018] FIG. 2 is a diagram of an example constellation 210 (or constellation diagram).

[0019] FIG. 3 is a diagram of a wireless transceiver chain, which may include a transmitter and a receiver.

[0020] FIG. 4 is a diagram illustrating sharing of probabilistic shaped constellation information between nodes according to an example embodiment, in which floating-point constellation point probabilities are shared or communicated between nodes.

[0021] FIG. 5 is a diagram illustrating sharing or communicating of probabilistic shaped constellation information between nodes according to an example embodiment, in which quantized constellation point probabilities are shared or communicated between nodes.

[0022] FIG. 6 is a diagram illustrating a complex plane for a constellation in which different zones are assigned different probabilities.

[0023] FIG. 7 is a diagram illustrating sharing or communicating of probabilistic shaped constellation information based on a symmetry property of a probabilistic shaped constellation.

[0024] FIG. 8 is a diagram illustrating sharing of constellation information in which one node determines probabilistic shape of a constellation and another node determines a geometric shape of the constellation.

[0025] FIG. 9 is a diagram illustrating use of an index to a lookup table (LUT) to communicate a probabilistic shaped constellation according to an example embodiment.

[0026] FIG. 10 is a diagram illustrating use of a machine learning (ML) model to determine to derive or determine a first probabilistic shaped constellation from (or with respect to) a reference probabilistic shaped constellation according to an example embodiment.

[0027] FIG. 11 is a diagram illustrating an updated constellation in which an initial neighborhood (or position(s)) of probability values has been preserved or maintained.

[0028] FIG. 12 is a diagram illustrating quantized probabilities for each constellation point of a constellation geometry according to an example embodiment.

[0029] FIG. 13 is a flow chart illustrating operation of a node according to an example embodiment.

[0030] FIG. 14 is a flow chart illustrating operation of a node in which a symmetry property for a probabilistic shaped constellation is used according to an example embodiment.

[0031] FIG. 15 is a flow chart illustrating operation of a node in which a symmetry property for a probabilistic shaped constellation is used according to another example embodiment.

[0032] FIG. 16 is a flow chart illustrating operation of a node in which a transformation function for a probabilistic shaped constellation is used according to an example embodiment.

[0033] FIG. 17 is a flow chart illustrating operation of a node in which a transformation function for a probabilistic shaped constellation is used according to another example embodiment.

[0034] FIG. 18 is a block diagram of a wireless station or node (e.g., UE, user device, AP, BS, eNB, gNB, RAN node, network node, TRP, or other node) 1800 according to an example embodiment. DETAILED DESCRIPTION

[0035] It shall be understood that although the terms “first,” “second,”..., etc. in front of noun(s) and the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another and they do not limit the order of the noun(s). For example, a first element could be termed a second element, and similarly, a second element could be termed a first element, without departing from the scope of example embodiments. As used herein, the term “and / or” includes any and all combinations of one or more of the listed terms.

[0036] As used herein, unless stated explicitly, performing a step “in response to A” does not indicate that the step is performed immediately after “A” occurs and one or more intervening steps may be included.

[0037] FIG. 1 is a block diagram of a wireless network 130. In the wireless network 130 of FIG. 1, user devices 131, 132, 133 and 135, which may also be referred to as mobile stations (MSs), user equipment (UEs) or loT devices, may be connected (and in communication) with a base station (BS) 134, which may also be referred to as an access point (AP), an enhanced Node B (eNB), a gNB or a network node. The terms user device and user equipment (UE) may be used interchangeably. A BS may also include or may be referred to as a RAN (radio access network) node, and may include a portion of a BS or a portion of a RAN node, such as e.g., such as a centralized unit (CU) and / or a distributed unit (DU) in the case of a split BS or split gNB. At least part of the functionalities of a BS (e.g., access point (AP), base station (BS) or (e)Node B (eNB), gNB, RAN node) may also be carried out by any node, server or host which may be operably coupled to a transceiver, such as a remote radio head. BS (or AP) 134 provides wireless coverage within a cell 136, including to user devices (or UEs) 131, 132, 133 and 135. Although only four user devices (or UEs) are shown as being connected or attached to BS 134, any number of user devices may be provided. BS 134 is also connected to a core network 150 via a SI interface 151. This is merely one simple example of a wireless network, and others may be used.

[0038] A base station (e.g., such as BS 134) is an example of a radio access network (RAN) node within a wireless network. A BS (or a RAN node) may be or may include (or may alternatively be referred to as), e.g., an access point (AP), a gNB, an eNB, or portion thereof (such as a centralized unit (CU) and / or a distributed unit (DU) in the case of a split BS or split gNB), or other network node.

[0039] Some functionalities of the communication network may be carried out, at least partly, in a central / centralized unit, CU, (e.g., server, host or node) operationally coupled to distributed unit, DU, (e.g., a radio head / node). Thus, 5G networks architecture may be based on a so-called CU-DU split. The gNB-CU (central node) may control a plurality of spatially separated gNB-DUs, acting at least as transmit / receive (Tx / Rx) nodes. In some embodiments, however, the gNB-DUs (also called DU) may comprise e.g., a radio link control (RLC), medium access control (MAC) layer and a physical (PHY) layer, whereas the gNB-CU (also called a CU) may comprise the layers above RLC layer, such as a packet data convergence protocol (PDCP) layer, a radio resource control (RRC) and an internet protocol (IP) layers. Other functional splits are possible too.

[0040] According to an illustrative example, a BS node (e.g., BS, eNB, gNB, CU / DU, ...) or a radio access network (RAN) may be part of a mobile telecommunication system. A RAN (radio access network) may include one or more BSs or RAN nodes that implement a radio access technology, e.g., to allow one or more UEs to have access to a network or core network (CN). Thus, for example, the RAN (RAN nodes, such as BSs or gNBs) may reside between one or more user devices or UEs and a core network. According to an example embodiment, each RAN node (e.g., BS, eNB, gNB, CU / DU,...) or BS may provide one or more wireless communication services for one or more UEs or user devices, e.g., to allow the UEs to have wireless access to a network, via the RAN node. Each RAN node or BS may perform or provide wireless communication services, e.g., such as allowing UEs or user devices to establish a wireless connection to the RAN node, and sending data to and / or receiving data from one or more of the UEs. For example, after establishing a connection to a UE, a RAN node or network node (e.g., BS, eNB, gNB, CU / DU, ...) may forward data to the UE that is received from a network or the core network, and / or forward data received from the UE to the network or core network. RAN nodes or network nodes (e.g., BS, eNB, gNB, CU / DU, ...) may perform a wide variety of other wireless functions or services, e.g., such as broadcasting control information (e.g., such as system information or on-demand system information) to UEs, paging UEs when there is data to be delivered to the UE, assisting in handover of a UE between cells, scheduling of resources for uplink data transmission from the UE(s) and downlink data transmission to UE(s), sending control information to configure one or more UEs, and the like. These are a few examples of one or more functions that a RAN node or BS may perform.

[0041] A user device or user node (user terminal, user equipment (UE), mobile terminal, handheld wireless device, etc.) may refer to a portable computing device that includes wireless mobile communication devices operating either with or without a subscriber identification module (SIM), including, but not limited to, the following types of devices: a mobile station (MS), a mobile phone, a cell phone, a smartphone, a personal digital assistant (PDA), a handset, a device using a wireless modem (alarm or measurement device, etc.), a laptop and / or touch screen computer, a tablet, a phablet, a game console, a notebook, a vehicle, a sensor, an loT device, and a multimedia device, as examples, or any other wireless device. It should be appreciated that a user device may also be (or may include) a nearly exclusive uplink only device, of which an example is a camera or video camera loading images or video clips to a network. Also, a user node may include a user equipment (UE), a user device, a user terminal, a mobile terminal, a mobile station, a mobile node, a subscriber device, a subscriber node, a subscriber terminal, or other user node. For example, a user node may be used for wireless communications with one or more network nodes (e g., gNB, eNB, BS, AP, CU, DU, CU / DU) and / or with one or more other user nodes, regardless of the technology or radio access technology (RAT). In LTE (as an illustrative example), core network 150 may be referred to as Evolved Packet Core (EPC), which may include a mobility management entity (MME) which may handle or assist with mobility / handover of user devices between BSs, one or more gateways that may forward data and control signals between the BSs and packet data networks or the Internet, and other control functions or blocks. Other types of wireless networks, such as 5G (which may be referred to as New Radio (NR)) may also include a core network

[0042] In addition, the techniques described herein may be applied to various types of user devices or data service types, or may apply to user devices that may have multiple applications running thereon that may be of different data service types. New Radio (5G) development may support a number of different applications or a number of different data service types, such as for example: machine type communications (MTC), enhanced machine type communication (eMTC), Internet of Things (loT), and / or narrowband loT user devices, enhanced mobile broadband (eMBB), and ultra-reliable and low-latency communications (URLLC). Many of these new 5G (NR) - related applications may require generally higher performance than previous wireless networks.

[0043] loT may refer to an ever-growing group of objects that may have Internet or network connectivity, so that these objects may send information to and receive information from other network devices. For example, many sensor type applications or devices may monitor a physical condition or a status and may send a report to a server or other network device, e.g., when an event occurs. Machine Type Communications (MTC, or Machine to Machine communications) may, for example, be characterized by fully automatic data generation, exchange, processing and actuation among intelligent machines, with or without intervention of humans. Enhanced mobile broadband (eMBB) may support much higher data rates than currently available in LTE.

[0044] Ultra-reliable and low-latency communications (URLLC) is a new data service type, or new usage scenario, which may be supported for New Radio (5G) systems. This enables emerging new applications and services, such as industrial automations, autonomous driving, vehicular safety, e-health services, and so on. 3 GPP targets in providing connectivity with reliability corresponding to block error rate (BLER) of 10-5 and up to 1 ms U-Plane (user / data plane) latency, by way of illustrative example. Thus, for example, URLLC user devices / UEs may require a significantly lower block error rate than other types of user devices / UEs as well as low latency (with or without requirement for simultaneous high reliability). Thus, for example, a URLLC UE (or URLLC application on a UE) may require much shorter latency, as compared to an eMBB UE (or an eMBB application running on a UE).

[0045] The techniques described herein may be applied to a wide variety of wireless technologies or wireless networks, such as 5G (New Radio (NR)), cmWave, and / or mmWave band networks, loT, MTC, eMTC, eMBB, URLLC, 6G, etc., or any other wireless network or wireless technology. These example networks, technologies or data service types are provided only as illustrative examples.

[0046] In digital communications, information (e.g., one or more bits) may be transmitted as one of N symbols according to a constellation (or constellation diagram). A constellation or constellation diagram is a representation of a signal modulated by a digital modulation scheme, e.g., such as phase-shift keying (PSK), quadrature amplitude modulation (QAM). A constellation includes a plurality of (or N) constellation points, wherein each constellation point has or corresponds to a different amplitude and / or phase. Information (e.g., one or more bits) transmitted according to a constellation may be transmitted as one of N symbols, where each different symbol has an amplitude and / or phase according to an associated constellation point. The constellation displays the constellation points in a complex plane (e.g., with In-phase and quadrature phase components indicated along horizontal and vertical axes, respectively). At a transmitter (or transmitting device), a group of one or more bits may be encoded to a specific or different combination of amplitude and phase (referred to as a symbol), according to the different constellation points of the constellation.

[0047] FIG. 2 is a diagram of an example constellation 210 (or constellation diagram). In the constellation 210 of FIG. 2, constellation points are placed on a complex plane that includes a horizontal axis 216 (or real axis) representing an In-phase (I) component, and a vertical axis 218 (or imaginary axis) representing a quadrature (Q) component. The constellation shown in FIG. 2 is 8-PSK (8 constellation points, based on phase-shift keying). Therefore, constellation 210 includes N=8 different constellation points, e.g., such as constellation points 212 and 214, with each constellation point associated with a different symbol (which may have different amplitudes and / or phases, in general). According to an 8-PSK constellation, each group of three bits (or each different 3-bit value) may encoded to a symbol having a different phase, according to the constellation shown in FIG. 2. In PSK (as an example), the constellation points have a constant amplitude, but different phases. Although in general, constellation points of a constellation (e.g., such as QAM) may have different amplitudes and different phases. In the example 8-PSK constellation 210 shown in FIG. 2, each of 8 symbols (associated with the 8 different constellation points) are associated with a different phase shift of a carrier sine wave, with respect to a reference phase. Thus, in the constellation 210 of FIG. 2, each 3-bit value (e.g., 000, 001,010, Oil, ...111) may be encoded as a different phase, as shown by the 8 constellation points of the 8-PSK diagram in FIG. 2. In 16-QAM, for example, each 4-bit value may be encoded as one of 16 symbols (associated with the 16 constellation points), with each symbol having a different amplitude / phase combination. The constellation 210 shown in FIG. 2 is a simple example, and many other types and sizes of constellations may be used. A constellation may include a plurality of (or multiple) constellation points. The constellation may have a geometric shape (e.g., a number and position of the constellation points in the complex (I, Q) plane), and a probabilistic shape (e.g., the constellation point probabilities of the constellation points of the constellation). A constellation may include constellation point probabilities (or probability information) of the constellation points of the constellation. The constellation point probability of each of the constellation points indicates a probability or likelihood that a symbol for that constellation point will be transmitted (e.g., a probability that a set of bits will be mapped to that symbol or constellation point for transmission). In traditional or classical constellations (which have not been shaped), such as QAM, the geometric shape (indicating a number and position of the constellation points in the complex plane) of the constellation is typically fixed, and the constellation point probabilities typically have a uniform distribution (uniformly distributed constellation point probabilities), e.g., where constellation point probabilities are uniform or the same for all of the constellation points of the constellation.

[0048] Constellation shaping (constellation adjusting) may be performed, for example, to improve network performance, such as to improve transmission throughput to be closer to the channel capacity. Shaping of constellations may involve adjusting or changing (e.g., optimizing) the positions or locations of the constellation points in the complex plane (geometric shaping of a constellation) and / or adjusting or changing (e.g., optimizing) the probabilities of occurrence of the constellation points (probabilistic shaping of a constellation). A probabilistic shape of a constellation may refer to (or may include) the probabilities (or constellation point probabilities) of the constellation points. A geometric shape of a constellation may refer to (or may include) the positions in the complex plane of the constellation points of the constellation. Thus, geometric shaping may involve changing or adjusting locations of one or more of the constellation points or symbols within the complex plane, while probabilistic shaping may involve changing or adjusting a transmission probability (or constellation point probability) of one or more constellation points or symbols of the constellation.

[0049] A constellation may be a probabilistic shaped constellation, e.g., a constellation in which constellation point probabilities (probabilities of the constellation points of the constellation) have been changed or adjusted (shaped), e.g., a constellation in which probabilistic shaping has been performed. Thus, in a probabilistic shaped constellation, the constellation point probabilities have been adjusted or shaped (or changed) and, e.g., are typically no longer uniformly distributed constellation point probabilities.

[0050] By performing probabilistic shaping of a constellation (e.g., adjusting or changing the constellation point probabilities of the constellation points of the constellation), this may adjust or change the probability a particular set of bits will be mapped (e g., by a bit-to-symbol mapper at a transmitting device) to a particular symbol (or constellation point) at a transmitter, and may likewise adjust or change the probability a received symbol will be de-mapped (e.g., by a symbol-to-bit demapper) to a particular set of bits. According to an example, probabilistic shaping of constellation points may be performed using a constant-composition distributionmatcher (CCDM) with forward error correction (FEC) encoding. Other techniques that may be used for probabilistic shaping may include, e.g., multiset-partition distribution matcher (MPDM), enumerative sphere shaping (ESS) and / or shell mapping (SM). These are some examples, and other techniques may be used to perform probabilistic shaping of a constellation.

[0051] FIG. 3 is a diagram of a wireless transceiver chain, which may include a transmitter and a receiver. Referring to FIG. 3, at 310, at a transmitter or transmitting device or node within a wireless network, a plurality of bits are input to encoder 312, which encodes the bits. A bit-to-symbol 314 mapper receives as inputs, a constellation geometry C, a symbol distribution p& (constellation point probabilities) indicating probabilistic shape of the constellation, and the encoded bits. For example, a transmit bit vector (bits 310) may be encoded by encoder 312 and mapped to the symbols S, so that symbol(s) S appears with a frequency given by the symbol distribution p& (or constellation point probabilities), and based on geometric shape C of the constellation. Bit-to-symbol mapper 314 maps the received encoded bits to a symbol, based on the geometric constellation C and the symbol distribution pfs (e.g., constellation point probabilities or probabilistic shape of the constellation). A symbol(s) S is output to OFDM (orthogonal frequency division multiplexing) modulator 316. OFDM modulator 316 performs OFDM modulation on the symbol(s) S. The OFDM modulated symbol(s) is then transmitted over a channel 318. A receiver or receiving device or node within the wireless network may receive the modulated and transmitted symbol. At the receiver, an OFDM demodulator 320 demodulates the received symbol. A symbol-to-bits demapper 322 demaps (or converts) the symbol to a group of bits, based on the geometric constellation C and the symbol distribution pfs (or constellation point probabilities) for the constellation. Decoder 324 decodes the bits, to output estimated bits 326. Thus, both the transmitter (or transmitting node) and the receiver (or receiving node) within the wireless network may typically need to know both the geometric shape and probabilistic shape of the constellation to correctly perform bit-to-symbol mapping 314 and symbol-to-bits demapping 322.

[0052] According to an illustrative example, one or more of the blocks in the transceiver (or transmitter and receiver nodes) shown in FIG. 3 may be implemented as an AI (artificial intelligence) machine learning (ML) models. For example, the bit-to-symbol mapper 314 and / or the symbol-to-bits demapper 322 may be implemented using a ML model. Also, there may be multiple constellations that may be selected for use, each with different geometric shape and / or probabilistic shape. Also, a probabilistic shape of a constellation may be updated by a gNB or other node. The transmitter and receiver nodes (e.g., UEs and / or gNBs) should be able to communicate regarding probabilistic shaped constellations, e.g., the nodes should be able to provide or share with other nodes the probabilistic shaped constellation (or constellation point probabilities of a constellation) that is being used for transmitting and receiving of information.

[0053] In an example, two (or multiple) nodes within a wireless network, such as a UE (or user device) and a gNB (or a network node) may use a constellation, such as a probabilistic shaped constellation, to exchange or communicate data or information. The constellation may include a geometric shape, which is or includes a number and location of constellation points within the complex plane, and a probabilistic shape, which is or includes the constellation point probabilities of the constellation points of the constellation. Both geometric shaping (adjusting or shaping the number or location of constellation points within the complex plane) and / or probabilistic shaping (adjusting or shaping the constellation point probabilities of the constellation points) may be performed (or may have already been performed on the constellation). For example, geometric shaping may be performed by one of the nodes (e.g., determining the geometric shape of the constellation), and then probabilistic shaping (determining or adjusting constellation point probabilities of the constellation points) may be performed by the other node based on that selected or determined geometric shape of the constellation. Or, one of the nodes in the wireless network may perform both geometric shaping and probabilistic shaping of the constellation (e.g., determining both the geometric shape and the probabilistic shape of the constellation). Or a geometric shape may be known or agreed upon by the nodes in advance, and then information regarding or indicative of the probabilistic shape or constellation point probabilities may be determined by one node and shared with or provided to another node. But both nodes should use the same constellation (including the same geometric shape and probabilistic shape) for communication, including for performing bit-to-symbol mapping and symbol-to-bit demapping.

[0054] Therefore, various techniques are described herein that allow a node (e.g., UE or gNB) to share or provide to a second node or another node (e.g., gNB or UE) probabilistic shaped constellation information that is indicative of the constellation point probabilities of a probabilistic shaped constellation. This will allow both nodes to use the same constellation (including same constellation point probabilities) for communication. Also, for example, a first node may transmit or may indicate to a second node the constellation point probabilities as, e.g., a floating point value for each of the constellation point probabilities. Several techniques may be used to reduce overhead of sharing or communicating a probabilistic shaped constellation or constellation point probabilities of a constellation. For example, the constellation point probabilities may be quantized and transmitted as quantized constellation point probabilities. Or, the first node may transmit or may indicate to a second node an index to a lookup table to indicate a probabilistic shaped constellation (or constellation point probabilities) of a plurality of constellations. Or a symmetry property of the probabilistic shaped constellation may be used to allow the first node to provide to the second node information indicating a strict subset of the constellation point probabilities of the constellation. Or the first node may transmit or indicate to the second node a transformation function for deriving a first probabilistic shaped constellation from a reference constellation. Other techniques are described and may be used as well.

[0055] According to an example embodiment, a first node may determine, e.g., based at least on channel measurement information, constellation point probabilities for a plurality of constellation points of a probabilistic shaped constellation. As noted, a probabilistic shaped constellation may be or may include the constellation point probabilities, which have been shaped (e.g., changed or adjusted) from uniformly distributed constellation probabilities. The first node may transmit to a second node of the wireless network probabilistic shaped constellation information indicative of the constellation point probabilities. At this point, both the first node and the second node know or have the constellation point probabilities of the probabilistic shaped constellation, and thus, both nodes may transmit and / or receive data or information with or to the other node based on this probabilistic shaped constellation. Thus, the first node may transmit and / or receive (e.g., with the second node) a signal based on the probabilistic shaped constellation.

[0056] Also, the first node may transmit to and / or receive from the second node: a message enabling sharing of the probabilistic shaped constellation information, and / or a message configuring one or more parameters for sharing of the probabilistic shaped constellation information. Also, the first and second nodes may share or may indicate to the other node the geometric shape of the probabilistic shaped constellation. Thus, the first node may transmit to the second node, or may receive from the second node, geometric shape information indicative of a geometric shape of the probabilistic shaped constellation. The transmitting of the probabilistic shaped constellation information may include transmitting at least one of: full values of the constellation point probabilities; delta or difference values of the constellation point probabilities indicating a difference of constellation point probabilities with respect to a reference or previous constellation; or one or more parameters of a known or agreed upon probability distribution for constellation points.

[0057] Also, the probabilistic shaped constellation information (indicative of the constellation point probabilities) may be provided in various forms or formats, such as full values, delta values, or may be indicated via lookup table, or by providing one or more parameters of a known or agreed upon probability distribution (of constellation point probabilities) for the constellation points (e.g., by indicating a mean and / or variance of a 1-D (one-dimensional) or 2-D (two-dimensional) Gaussian distribution). The first node transmitting the probabilistic shaped constellation information may include the first node transmitting to the second node at least one of the following: quantized constellation point probabilities for the plurality of constellation points; or floating point constellation point probabilities for the plurality of constellation points. One or more parameters of the quantized or floating point constellation point probabilities may be configured by one node to the other node. Thus, for example, the first node may transmit or receive a message configuring one or more parameters of the quantized constellation point probabilities or the floating point constellation point probabilities for the plurality of constellation points.

[0058] Also, the first node transmitting the probabilistic shaped constellation information may include the first node transmitting an index to a lookup table of a plurality of probabilistic shaped constellations, wherein the index points to or indicates the probabilistic shaped constellation of the plurality of probabilistic shaped constellations. For example, the first node may transmit an index to a lookup table of a plurality of probabilistic shaped constellations, wherein index k points to or indicates a k-th probabilistic shaped constellation of the plurality of probabilistic shaped constellations, wherein the k-th probabilistic shaped constellation is associated with or characterized by a probabilistic shape p(k) and a geometric shape C(k). Thus, each of these plurality of probabilistic shaped constellations (which may be provided or indexed in the lookup table) may have a different geometric shape and / or a different probabilistic shape.

[0059] Also, according to an example embodiment, a symmetry property for the probabilistic shaped constellation may be determined by the first node and provided or shared with the second node, e.g., which may allow the first node only to transmit or provide probabilistic shaped constellation information (information indicative of the constellation point probabilities) for only a strict subset of the constellation point probabilities, where a strict subset is a subset of the constellation point probabilities that is less than all of the constellation point probabilities. Thus, a strict subset is less than all of the set (e.g., strict subset is less than all of the constellation point probabilities of the probabilistic shaped constellation). Based on the symmetry property for the probabilistic shaped constellation, the second node may be able to determine all of the constellation point probabilities based on only the probabilistic shaped constellation information for the strict subset of the constellation point probabilities. Thus, use of a symmetry property for the probabilistic shaped constellation may improve efficiency for communicating or providing the constellation point probabilities to the second node.

[0060] Therefore, the first node may determine constellation point probabilities for a plurality of constellation points of a probabilistic shaped constellation. The first node may determine a symmetry property for the probabilistic shaped constellation. If not already known by the second node, the first node may transmit to the second node probabilistic shaped constellation symmetry information indicative of the symmetry property for the probabilistic shaped constellation. The first node may determine a strict subset of the constellation point probabilities based on the symmetry property (e.g., constellation point probabilities for a quadrant of the constellation, or half of the probabilistic shaped constellation, based on symmetry about horizontal and / or vertical axis of the complex plane of the probabilistic shaped constellation). The first node may transmit to the second node probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities.

[0061] The first node may also transmit to the second node, probabilistic shaped constellation symmetry information indicative of the symmetry property for the probabilistic shaped constellation. The symmetry property may include one or more types of symmetry, e.g., including symmetry about one or more axes of the complex plane of the constellation. At this point, both the first node and the second node have or know both the subset of constellation point probabilities (e.g., for half or for one of the quadrants of the probabilistic shaped constellation) and the symmetry property for the probabilistic shaped constellation. The second node may determine, based on the symmetry property and the probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities, the probabilistic shaped constellation including the plurality of constellation point probabilities. Therefore, at this point, both the first and second nodes know or can determine the full set of constellation point probabilities for the probabilistic shaped constellation, and thus, can transmit and / or receive information or data with each other based on this probabilistic shaped constellation. Thus, the first node may also transmit and / or receive a signal based on the probabilistic shaped constellation.

[0062] When using the symmetry property, the second node may: determine a symmetry property for a probabilistic shaped constellation, receive from the first node probabilistic shaped constellation information indicative of a strict subset of the constellation point probabilities, and determine, based on the symmetry property and the probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities, the probabilistic shaped constellation including the plurality of constellation point probabilities. Because the second node now knows or has determined the probabilistic shaped constellation, the second node may transmit to and / or receive from the first node, a signal (e.g., information, data), based on the probabilistic shaped constellation.

[0063] Also, according to an example embodiment, a transformation function may be used for deriving a first probabilistic shaped constellation from (or with respect to) a reference probabilistic shaped constellation (e.g., the transformation function may allow a second node to determine constellation point probabilities of a first probabilistic shaped constellation based on known constellation point probabilities of a reference probabilistic shaped constellation). In some cases, the reference probabilistic shaped constellation may be already known (or determined) by both the first node and the second node, or may have been already communicated or provided to the first node and / or second node.

[0064] The first node may determine constellation point probabilities for a plurality of constellation points of a first probabilistic shaped constellation. The first node may determine the transformation function for deriving the first probabilistic shaped constellation from the reference probabilistic shaped constellation. The first node may transmit an indication of the transformation function to the second node. The second node, which may already know or already have the reference probabilistic shaped constellation, may determine constellation point probabilities of a plurality of constellation points of the first probabilistic shaped constellation based on the constellation point probabilities of a plurality of constellation points of the reference probabilistic shaped constellation and the transformation function. At this point, both the first node and the second node know the constellation point probabilities for the first probabilistic shaped constellation, and the first node and the second node may communicate data or information with each other using the first probabilistic shaped constellation. Thus, use of a transformation function for deriving the first probabilistic shaped constellation may improve efficiency for communicating or providing the first probabilistic shaped constellation or constellation point probabilities of the first probabilistic shaped constellation to the second node.

[0065] The first node may determine the transformation function based on constellation point probabilities of the plurality of constellation points of the first probabilistic shaped constellation with respect to constellation point probabilities of respective constellation points of the reference constellation. Also, the first node may determine the transformation function based on the geometric shape and the probabilistic shape of the first probabilistic shaped constellation, with respect to the geometric shape and the probabilistic shape of the reference constellation. The transformation function may be determined by a machine learning (ML) model, e.g., provided at the first node. Also, the first node may transmit an indication of the transformation function to the second node by transmitting, to the second node, an index to a lookup table of a plurality of transformation functions, wherein the index points to or indicates the transformation function of the plurality of transformation functions.

[0066] When using the transformation function, the second node may: determine constellation point probabilities of a plurality of constellation points of a reference constellation, receive an indication of the transformation function for deriving a first probabilistic shaped constellation from the reference constellation, and determine constellation point probabilities of a plurality of constellation points of the first probabilistic shaped constellation based on the constellation point probabilities of the plurality of constellation points of the reference constellation and the transformation function. The second node may transmit to the first node and / or receive from the first node, a signal (e.g., signal, information, data) using the first probabilistic shaped constellation, since the second node now knows or has determined the constellation point probabilities of the first probabilistic shaped constellation.

[0067] Further details and / or illustrative examples will be briefly described.

[0068] A first node (e.g., UE or gNB) may share or may provide (or may indicate) to a second node (e.g., gNB or UE, respectively) the constellation point probabilities of the constellation, e.g., as floating point values for the constellation point probabilities of the constellation. The total overhead of sharing the assigned constellation point probabilities of a constellation may depend on, for example, the following parameters: M: Modulation order (or number of constellation points in the constellation), such as 16 for 16 QAM, and 64 for 64 QAM; and, K: Number of allocated bits for sharing or indicating the probability (constellation point probability) of a constellation point; where the total overhead of sharing the M constellation point probabilities is K*M bits. If the first node shares the floating-point version of the constellation point probabilities of the M=16 constellation points (or symbols), K=32 bits, and consequently, K*M bits = 32*16 =512 bits are required to share or provide (communicate to the other node) the constellation point probabilities for the constellation. Note: For joint probabilistic and geometric constellation shaping (e.g., where the first node may determine or adjust both the location of each constellation point and the constellation point probability of each of the M constellation points), besides the constellation point probabilities, real and imaginary parts of the constellation points (indicating positions of the constellation points within the complex plane) also need to be shared or provided, which results m higher overhead.

[0069] FIG. 4 is a diagram illustrating sharing of probabilistic shaped constellation information between nodes according to an example embodiment, in which floating-point constellation point probabilities are shared or communicated between nodes. Two nodes may be in communication, including, e.g., node 1 (e.g., a gNB or UE) and node 2 (e.g., UE or gNB). At step 410, node 1 may transmit a message to node 2 enabling probabilistic shaped constellation sharing (or communication between nodes) over the air (OTA) or via wireless communications. Although not shown in FIG. 4, node 1 and / or node 2 may indicate to the other node its capability to share (transmit and / or receive) a probabilistic shaped constellation (or constellation point probabilities). At step 420, node 1 may transmit a message to node 2 configuring (or providing a configuration for) sharing of constellation point probabilities, e.g., wherein the configuration may indicate that constellation point probabilities should be or will be communicated as floatingpoint values, with, e.g., K=32 bits per constellation point, for example. K=32 bits is merely an example, and other numbers of bits per floating-point constellation point probability may be used.

[0070] At step 430 of FIG. 4, node 1 may determine or select floating-point probabilities (floating-point constellation point probabilities) for the M constellation points of the constellation. For example, node 1 may determine or select the floating-point probabilities for the M constellation points based on a channel condition or feedback, or other information, such as based on signal to interference plus noise ratio (SINK), channel quality indication (CQI), hybrid automatic repeat request (HARQ) Ack / Nak feedback, or other information or conditions. At step 440, node 1 shares (provides or transmits) the constellation point probabilities for the M constellation points of the constellation to node 2. In this illustrative example of FIG. 4, at step 460, node 1 transmits the K*M bits (where K is number of bits per constellation point, and M is the number of constellation points or symbols) to indicate the floating-point constellation point probabilities for the M constellation points of the constellation. As noted, the constellation geometry (or geometric constellation, indicating the positions in the complex plane of the M constellation points of the constellation) of the constellation may be already known by node 2, may be communicated by node 1, and / or may be determined by node 2. At 450, node 2 receives the K*M bits indicating probabilities of the constellation points of the constellation, and determines the floating-point constellation point probabilities for the M constellation points based on the received K*M bits.

[0071] At 460 of FIG. 4, node 2 has information to be transmitted to node 1 using the constellation (wherein the constellation point probabilities of the constellation were received by node 2 via step 440). At step 460, node 2 transmits information bits using the obtained probabilistic shaped constellation (using the obtain constellation point probabilities of the constellation). For example, based on a geometric constellation (or constellation geometry, indicating positions of the M constellation points in the complex plane of the constellation, which may be known in advance by node 2, may be determined and provided or indicated by node 1 to node 2, or may be determined by node 2), and the probabilistic shaped constellation (or constellation point probabilities of the M constellation points of the constellation, received by node 2 via step 440), node 2 may use a bit-to-symbol mapper 314 (FIG. 3) to map a plurality of bits to one or more symbols or constellation points. The symbols may, for example, be modulated using an OFDM modulator 316 (FIG. 3), for example, and then transmitted to node 1 via step 460. At step 470, node 1 may demodulate and decode the received signal (received via step 460) using the probabilistic shaped constellation (e.g., constellation point probabilities for the M constellation points of the constellation) that was communicated by node 1 to node 2 via step 440. For example, at step 470, node 1 may perform OFDM demodulation on the received signal using OFDM demodulator 320 (FIG. 3), perform symbol-to-bit demapping of the demodulated symbols using symbol-to-bit demapper 322 (FIG. 3) (e.g., based on the geometric constellation and probabilistic shaped constellation of the constellation), and then perform decoding using decoder 324 (FIG. 3), to estimate or recover the transmitted information or bits.

[0072] To reduce the overhead of sharing a probabilistic shaped constellation, the constellation point probabilities may be quantized (converted to quantized values) before transmission, and then transmitted as quantized constellation point probabilities. Quantization may generally refer to or include mapping process of mapping input values from a large set to output values in a smaller set. In this case, the quantization may include quantizing floating-point probabilities to one of a fewer set (e.g., 1 of 8 quantization values) of quantized probability values. Quantization of constellation point probabilities may reduce overhead in sharing or providing the probabilistic shaped constellation or constellation point probabilities with another node. In this approach, the UE and gNB may coordinate (e.g., may exchange messages to agree on) on a quantization scheme to quantize the probabilities of constellation points and reduce the overhead of sharing such information. Also, the receiver of such information may use the corresponding de-quantization scheme to reconstruct the constellation’s constellation point probabilities based on the received bits. The quantization scheme may include, for example, the type of quantization (uniform or non-uniform quantization), range of quantization (minimum and maximum of quantized values), and the number of allocated bits for reporting probability of a constellation point (K-bits). For example, a uniform quantization in range of (0, 1] with K-bits. the quantized grid with 2K members can be written as 1 2^ — 1

[0073] Q={±.....

[0074] So, each constellation point can take (or be assigned) a probability (or quantized constellation point probability) from the 2AK possibilities in set Q. For example, for a constellation with modulation order of 16 (M=16, or 16 constellation points), UE and gNB may agree to use uniform quantization with K=3 bits, where each quantized constellation point probability can be selected from the 2AK=2A3=8 possibilities (8 possible quantization values or quantized constellation point probability values). Thus, this example quantization scheme requires K*M=48 bits to communicate the quantized constellation point probabilities (3 bits per constellation point) for the M=16 constellation points or symbols, significantly reducing the overhead compared to the original constellation sharing with floating-point precision requiring 32*M =512 bits. Note that a signaling can be considered to indicate whether the constructed constellation point probabilities need to be (or should be) normalized to have unit sum. Thus, signaling or a control signal may indicate whether the quantized constellation point probabilities should be or are to be normalized (e.g., for each constellation point probability to have a value between 0 and 1, and the sum or summation of the constellation point probabilities of the constellation be 1 ).

[0075] FIG. 5 is a diagram illustrating sharing or communicating of probabilistic shaped constellation information between nodes according to an example embodiment, in which quantized constellation point probabilities are shared or communicated between nodes. Referring to FIG. 5, node 1 (e.g., UE or gNB) and node 2 (e.g., gNB or UE) may be in communication. At step 510, node 2 transmits a message to node 1 enabling quantized probabilistic shaped constellation sharing via wireless communications or over the air (OTA). This message at step 510 may enable sharing or communication of quantized constellation point probabilities of constellation points of a probabilistic shaped constellation between node 1 and node 2. At step 512, node 1 transmits to node 2 a configuration for quantization of constellation point probabilities, e.g., including a configuration of or indication of a quantization type (uniform quantization or non-uniform quantization), a number of bits (K) per constellation point or symbol to indicate a probability, and a normalization flag indicating whether normalized or nonnormalized quantized probabilities will be used or communicated. At step 514, node 1 determines constellation point probabilities for the M constellation points of the probabilistic shaped constellation, and determines or generates the quantized constellation point probabilities based on the configuration provided via step 512. At step 514, node 2 transmits to node 2 the quantized constellation point probabilities for the M constellation points of the constellation. There may be a list or multiple (e.g., N) possible probabilistic shaped constellations, and node 1 may indicate (or may provide information indicative of) quantized constellation point probabilities of the constellation points for one or more of the N possible probabilistic shaped constellations. For example, there may be N geometric constellations, and at step 514, node 1 may provide (transmit or share) the quantized constellation point probabilities for the constellation points for each of the N geometric constellations.

[0076] At step 516 of FIG. 5, based on the configuration received at step 512 (e.g., based on the quantization type, number of bits (K), normalization flag,...), node 2 may de-quantize the quantized constellation point probabilities, for each of the 1 or more probabilistic shaped constellations. At step 518, node 2 may select one of the shared or coordinated N probabilistic shaped constellations, to be used for communication between node 1 and node 2, e.g., based on node 1 SINR, CQI, HARQ, or other information or channel condition. At step 520, node 2 configures (provides a configuration or indication of) the selected constellation for data / information transmissions from node I to node 2. At step 522, node 1 modulates and transmits the data bits using the configured or selected probabilistic shaped constellation (including based on the constellation point probabilities of the configured constellation). After constellation point probabilities for the probabilistic shaped constellations have been shared by node 1 with node 2 at step 514, and these constellation point probabilities have been dequantized by node 2 at step 516, a selected one of these shared probabilistic shaped constellations may be used for transmission of information or data between node 1 and node 2, at steps 526-536.

[0077] At step 526, node 1 may measure a channel and obtain or determine a CQI (or other channel measurements, such as SINK) of the channel, and may provide or share the CQI or other channel measurement to node 2 at step 528. At step 530, node 2 selects one of the N shared or coordinated probabilistic constellations, e.g., based on the received CQI or channel measurement from node 1. At step 532, node 2 sends or transmits a message configuring (or a messing indicating a configuration of) the selected probabilistic constellation. As noted, based on the sharing of constellation point probabilities for these plurality of probabilistic shaped constellations at step 514, both node 1 and node 2 know the constellation point probabilities for the selected probabilistic shaped constellation. At step 534, node 1 modulates and transmits data or information bits using the configured (or selected) probabilistic shaped constellation (e.g., including based on the constellation point probabilities of constellation points of the configured / selected probabilistic shaped constellation, provided by node 1 to node 2 at step 514). At step 536, node 2 demodulates and / or decodes the received signal using the configured or selected probabilistic shaped constellation.

[0078] In another embodiment, the gNB may guide the quantization of the constellation point probabilities by setting probability zones. FIG. 6 is a diagram illustrating a complex plane for a constellation in which different zones are assigned different probabilities. For example, zone 1 is associated with highest probability and zone N with lowest probability. Thus, the UE may use the zones to either learn a quantized probabilistic shape, or to modify a previously learned shape, and adapt it to the zones defined by the gNB. Thus, for example, constellation point probabilities for a constellation or probabilistic shaped constellation may be assigned probabilities associated with or based on the probability zones, or the assigned constellation point probabilities for a constellation may be adjusted based on the probability zones of FIG. 6, for example. Thus, those constellation points within zone 1 may have their constellation point probabilities increased by 10%, constellation points within a zone 2 (not shown) may have their constellation points probabilities increased by 9%, ... and constellation points within zone N have their constellation point probabilities increased by a lower amount (e.g., by 1%) or even decreased, for example.

[0079] As noted, a constellation, such as a probabilistic shaped constellation, may include M constellation points provided at positions in a complex plane. The probabilistic shaped constellation includes the constellation points in a complex plane (e.g., with In-phase and quadrature phase components indicated along horizontal and vertical axes, respectively). In some cases, there may be a symmetry property of a probabilistic shaped constellation, e.g., in which there is a symmetry of the constellation point probabilities of the constellation points of the constellation. A figure or object may be said to have symmetry if a rotation about an axis or point maps it back onto itself. In mathematics, symmetry may mean that one shape is identical to the other shape when it is moved, rotated, or flipped (e.g., rotated or flipped about an axis). Symmetry may be or may include a mapping of the object onto itself which preserves the structure. Or, an object is said to have symmetry if it can be divided into two identical halves (or two portions, or multiple portions). These examples of symmetry refer to geometric symmetry. In this case, as an example, for a symmetry property of the probabilistic shaped constellation, the symmetry of the constellation point probabilities may be or may include geometric and probabilistic symmetry, in which the position (in the complex plane) and probability values of a strict subset (for less than all of the constellation points or constellation point probabilities) of the constellation point probabilities are the same when rotated or folded about one or more axes, or with respect to one or more axes. For example, a symmetry property for the probabilistic shaped constellation may mean or indicate that there is a symmetry of the constellation point probabilities about (or with respect to) one or more axes.

[0080] For example, the symmetry property for the constellation point probabilities (or for the probabilistic shaped constellation) may include at least one of the following: a symmetry about an X-axis of the probabilistic shaped constellation (e.g., symmetry about the X-axis of the complex plane of the constellation); a symmetry about a Y-axis of the probabilistic shaped constellation (e.g., in complex plane); a symmetry about both the X-axis and the Y-axis of the probabilistic shaped constellation (e.g., quadrant symmetry, in complex plane); a symmetry about a real-axis of the probabilistic shaped constellation (in complex plane); a symmetry about an imaginary-axis of the probabilistic shaped constellation (e.g., in complex plane for the constellation); a symmetry about both the real-axis and the imaginary axis of the probabilistic shaped constellation (e.g., quadrant symmetry for the probabilistic shaped constellation); a quadrant symmetry of the probabilistic shaped constellation; a symmetry about a predefined axis in a transformed space; or a symmetry about a predefined axis in a transformed space, the transformed space being defined by a kernel function.

[0081] If there is a symmetry property for the probabilistic shaped constellation, then the probabilistic shaped constellation may be shared or communicated by only providing a strict subset (a subset that includes the constellation point probabilities for less than all of the constellation points of the constellation) of the probabilistic shaped constellation, since the remaining (not provided) constellation point probabilities can be determined based on the symmetry property and the provided strict subset of the constellation point probabilities. Thus, a symmetry property of a probabilistic shaped constellation may reduce signaling overhead in sharing or communicating of the probabilistic shaped constellation.

[0082] For example, a 50% reduction in signaling overhead can be obtained when sharing or providing a probabilistic shaped constellation to another node if the probabilistic shaped constellation or constellation point probabilities have symmetry about (or with respect to) one axis (e.g., symmetry about either horizontal or vertical axis of the complex plane), and may obtain a 75% reduction in signaling overhead if there is a symmetry about two axis, e.g., there is symmetry about both horizontal and vertical axis of complex plane for the constellation point probabilities. In the first case (50% signaling overhead reduction, based on symmetry about only one axis of the probabilistic shaped constellation in complex plane), a first node may only need to provide or transmit to a second node the constellation point probabilities for only half (or 50%) of the constellation points (e.g., M / 2 constellation points) of the constellation, and the second node may determine or recover the constellation point probabilities of the remaining (not provided) constellation points based on the strict subset of constellation point probabilities that are provided, and the symmetry property for the probabilistic shaped constellation. In the second case (75% signaling overhead reduction, based on symmetry about two axes (e.g., symmetry with respect to both horizontal and vertical axes) of the probabilistic shaped constellation), a first node may only need to provide the second node with constellation point probabilities for only one quarter or one quadrant of the constellation points (e.g., constellation point probabilities for M / 4 or one quadrant of the constellation points, where M is the number of constellation points) of the constellation, and the second node can recover or determine the constellation point probabilities of the remaining (or 75%) (not provided) constellation points, or can determine or recover the other three quadrants of the probabilistic shaped constellation that were not shared or communicated.

[0083] FIG. 7 is a diagram illustrating sharing or communicating of probabilistic shaped constellation information based on a symmetry property of a probabilistic shaped constellation. Multiple nodes, e.g., node 1 and node 2, may be in communication. At step 710, node 2 sends or transmits a message to node 1 to enable probabilistic shaped constellation sharing (PCS) over the air or over a wireless link or wireless communications. At 712, node 1 may determine one or more (e.g., N) probabilistic shaped constellations, including constellation point probabilities for constellation points of each of the N constellations. Node 1 may determine a symmetry property for each of the N probabilistic shaped constellations. Also at step 712, node 1 may signal or transmit to node 2 information indicating the symmetry property for each of one or more or N constellations. Or, node 2 may already know or be aware of the symmetry property(ies) of the one or more or N probabilistic shaped constellations, and thus, there may be no need for node 1 to signal or indicate the symmetry property for the probabilistic shaped constellation.

[0084] Also, at 714 of FIG. 7, node 1 may transmit a message to node 2 indicating constellation point probabilities of a strict subset of constellation points for each of a plurality of (e.g., N) probabilistic shaped constellations. The strict subset of probabilities may include constellation point probabilities for a subset of constellation points that is less than all of the constellation points of a probabilistic shaped constellation, e.g., probabilities for half of the constellation points in case of a symmetry about one axis of the constellation, or, e.g., probabilities for one-quarter of the constellation points of a probabilistic shaped constellation for symmetry about two axes of the constellation (e.g., quadrant symmetry).

[0085] At step 716 of FIG. 7, node 2 de-quantizes constellation point probabilities of the strict subset of constellation points for each of the N (or each of one or more) constellations. At step 718 of FIG. 7, node 2 may recover or determine the constellation point probabilities of the remaining (non-provided or non-communicated) constellation points for the one or more (e.g., N) probabilistic shaped constellations, based on the corresponding provided strict subset of constellation point probabilities and the symmetry property for that probabilistic shaped constellation, for each of the N probabilistic shaped constellations. For example, node 1 may provide to node 2 a first quadrant (or M / 4) of constellation point probabilities for a probabilistic shaped constellation, and may indicate a symmetry property indicating symmetry about or with respect to both horizontal and vertical axes (the symmetry property may be provided / signaled, or may already be known by node 2), and then node 2 may determine the constellation point probabilities for the probabilistic shaped constellation points of the other three quadrants that were not provided, based on the symmetry property and the received probabilities of the one quadrant (or M / 4) constellation points of the probabilistic shaped constellation).

[0086] Once the probabilistic shaped constellations have been configured at node 2, one of the N probabilistic shaped constellations may be selected for use, and configured or indicated to node 2, for use in communicating information from node 1 to node 2 (or between node 1 and node 2), at steps 720 - 730. At step 720, node 1 may measure a channel condition and determine a CQL SINK, H AR, etc. At step 722, node 1 may signal or provide the channel condition measurement to node 2. At step 724, node 2 may select one of the configured N probabilistic shaped constellations based on the received channel measurement (e.g., CQI, SINR, HARQ) received from node 1. At step 726, node 2 sends a message to node 1 configuring (or indicating a configuration of) the selected probabilistic shaped constellation. At step 728, node 1 transmits information bits using the selected probabilistic shaped constellation. At step 730, node 2 receives and demodulates / decodes the received signal using the selected or configured probabilistic shaped constellation.

[0087] FIG. 8 is a diagram illustrating sharing of constellation information in which one node determines probabilistic shape of a constellation and another node determines a geometric shape of the constellation. In this example, node 1 (e.g., UE) may determine the geometric shape of the constellation (step 816), while the node 2 (e.g., gNB or network node) may determine (step 814) the probabilistic shape of the constellation. Node 2 may then indicate or signal the probabilistic shaped constellation (or constellation point probabilities for the constellation points of the constellation), and then request the geometric shape, via step 818. At step 822, node 1 may indicate or signal the geometric shape of the constellation to node 2. This approach may be beneficial, e.g., when first node (or UE) may determine or must determine the geometric shape based on UE hardware or other UE limitations, while the second node (e.g., gNB) may determine the probabilistic shape of the constellation based on channel conditions, such as SINR or CQI. In the diagram of FIG. 8, the node 2 (e.g., gNB) may request the geometric shape from node 1 (e.g., UE). Then, once the node 2 (e.g., gNB) shares the probabilistic state with node 1 (e.g., UE), the node 1 (e.g., UE) will respond by sharing the geometric shape of the constellation with node 2 (e.g., gNB). Node 1 (e.g., UE) can determine the geometric shape of the constellation based on the probabilistic shape it received from node 2 (e.g., gNB). Alternatively, node 2 (e.g., gNB) may first request the geometric shape from node 1, determine the probabilistic shape based on the received geometric shape, and then node 2 share the determined probabilistic shape with node 1.

[0088] An index to a lookup table may also be used to provide an efficient signaling technique for a node to indicate a probabilistic shaped constellation to another node. To reduce overhead of constellation sharing, the probabilistic shaped constellations in the constellation list (or list of probabilistic shaped constellations) can be defined in terms of the pair (probabilistic shape, geometric shape) and indexed accordingly, e.g.: index k points to the k-th probabilistic shaped constellation, characterized by (or associated with) the probabilistic shape p(k) and geometric shape C(k). Then, selection of one of the probabilistic shaped constellations can be signaled or indicated by a node to another node, e.g., using a common look-up table (LUT) and by exchanging an index (of a few bits) in (or into) the LUT.

[0089] For example, node 1 may communicate a probabilistic shaped constellation (or information indicative of the probabilistic shaped constellation), e.g., by transmitting an index to a lookup table (LUT) of a plurality of probabilistic shaped constellations, wherein the index points to or indicates the probabilistic shaped constellation of the plurality of probabilistic shaped constellations. For example, node 1 may transmit to node 2 an index to a lookup table (LUT) of a plurality of probabilistic shaped constellations, wherein index k points to or indicates a k-th probabilistic shaped constellation of the plurality of probabilistic shaped constellations, wherein the k-th probabilistic shaped constellation is associated with or characterized by a probabilistic shape p(k) and a geometric shape C(k).

[0090] FIG. 9 is a diagram illustrating use of an index to a lookup table (LUT) to communicate a probabilistic shaped constellation according to an example embodiment. Node 1 (E.g., UE or gNB) may be in communication with node 2 (e.g., gNB or UE). At step 910, node 1 and node 2 may generate and exchange a lookup table (LUT) of a plurality of probabilistic shaped constellations. An index may be generated to point to or indicate each of the different probabilistic shaped constellations. At step 912, node 2 may send or transmit a message to node 1 enabling a LUT based constellation sharing between the nodes. At step 914, node 2 selects a probabilistic shaped constellation having index k in the LUT, e.g., based on channel condition, such as based on CQI, SINK, or other information or measurement. At step 916, node 2 transmits or sends a message to node 1 indicating index k, which indicates or points to the k-th probabilistic shaped constellation in the lookup table of probabilistic shaped constellations. At step 918, based on node 1 receiving the indication of index k, node 1 may use index k of the LUT to retrieve constellation shape, e.g., including probabilistic shape p(k) and geometric shape C(k) of the k-th probabilistic shaped constellation. At step 920, node 1 transmits data or information to node 2 using the k-th probabilistic shaped constellation. At step 922, node 2 demodulates and / or decodes the received signal using the selected probabilistic shaped constellation.

[0091] In addition, a transformation function may be used to signal or indicate a probabilistic shaped constellation. The transformation function may be used for deriving a first probabilistic shaped constellation from (or with respect to) a reference constellation (e.g., the transformation function may allow a second node to determine constellation point probabilities of a first probabilistic shaped constellation based on known constellation point probabilities of a reference constellation). In some cases, the reference constellation may be already known (or determined) by both the first node and the second node, or may have been already communicated or provided to the first node and / or second node.

[0092] The first node may determine constellation point probabilities for a plurality of constellation points of a first probabilistic shaped constellation. The first node may determine the transformation function for deriving the first probabilistic shaped constellation from the reference constellation. The first node may transmit an indication of the transformation function to the second node. The second node, which may already know or already have the reference constellation, may determine constellation point probabilities of a plurality of constellation points of the first probabilistic shaped constellation based on the constellation point probabilities of a plurality of constellation points of the reference constellation and the transformation function. At this point, both the first node and the second node know the constellation point probabilities for the first probabilistic shaped constellation, and the first node and the second node may communicate data or information with each other using the first probabilistic shaped constellation. Thus, use of a transformation function for deriving the first probabilistic shaped constellation may improve efficiency for communicating or providing the first probabilistic shaped constellation or constellation point probabilities of the first probabilistic shaped constellation to the second node.

[0093] The first node may determine the transformation function based on constellation point probabilities of the plurality of constellation points of the first probabilistic shaped constellation with respect to constellation point probabilities of respective constellation points of the reference constellation. Also, the first node may determine the transformation function based on the geometric shape and the probabilistic shape of the first probabilistic shaped constellation, with respect to the geometric shape and the probabilistic shape of the reference constellation. The transformation function may be determined by a machine learning (ML) model, e.g., provided at the first node. Also, the first node may transmit an indication of the transformation function to the second node by transmitting, to the second node, an index to a lookup table of a plurality of transformation functions, wherein the index points to or indicates the transformation function of the plurality of transformation functions.

[0094] According to an example, a constellation may be defined as or by a learned transformation function (or learned transformation) between an initial or reference constellation and a target learned constellation (e.g., a first probability shaped constellation) as shown in FIG. 10. FIG. 10 is a diagram illustrating use of a machine learning (ML) model to determine to derive or determine a first probabilistic shaped constellation from (or with respect to) a reference probabilistic constellation according to an example embodiment. One example is to use a reference constellation (e.g., such as a conventional QAM constellation) as the input to ML model 1040, wherein the input reference constellation may include an input probabilistic shape 1010, an input geometric shape 1020. The ML model may be trained (based on the inputs of the reference constellation, and possibly based on other assistance information 1030) to determine the transformation function (at 1040) which transforms (or would transform) the original or reference constellation to the desired new shape (1060) and probabilities (1050), e.g., which may be the geometric shape and probabilistic shape of the first probabilistic constellation (e.g., outputs of the ML model including output probabilistic shape p out 1050 and output geometric shape c out 1060). Separate transformations (or separate transformation functions) can be used for each modulation order or, alternatively, a single transformation can be used for all or multiple modulation orders. The transformation function(s) can be collected to a LUT and communicated to the other node using an index to the LUT, as shown in FIG. 9. Alternatively, it is also possible to communicate the transformations (or transformation functions) directly similar to what is shown in FIG. 4 (sharing of probabilities 440 would be replaced by sharing of the transformation function). The use of a transformation function to indicate or signal a probabilistic shaped constellation may be especially efficient if the transformation contains less parameters than the actual probabilistic constellation (a very likely scenario with higher modulation orders). To be able to communicate ML models, there may be a predefined format for sharing the weights and the neural network architecture.

[0095] In case a node (UE or gNB) decide to update a constellation (e.g., constellation point probabilities of constellation points), the update can be done in absolute scheme (providing the full or new updated constellation point probabilities) or in a differential scheme, e.g., in which only a difference (or delta) of the updated probability values with respect to the previous probability values are indicated or provided, which may be more efficient and / or require fewer bits per constellation point, as compared to providing full probability values for each constellation point for the updated constellation. Thus, to reduce the overhead and enable a periodic update, nodes (e.g., UE and gNB) can coordinate to use a differential update, where the updated constellation points are in a neighborhood (both probabilistically and geometrically) of the original constellation point. FIG. 11 is a diagram illustrating an updated constellation m which an initial neighborhood (or position(s)) of probability values has been preserved or maintained. For example, probability values 111 0A, 1120A, and 1130A of an initial constellation may be updated in an updated constellation that includes corresponding updated probability values 1 HOB, 1120B and I 130B in about the same positions or neighborhoods in complex plane as initial constellation. The circles of the updated probabilities 1 HOB, 1120B, and 1130B in updated constellation are of different sizes or diameters of circles for initial probabilities of initial constellation to indicate updated or changed probabilities, e.g., a larger circle indicates a higher probability.

[0096] FIG. 12 is a diagram illustrating quantized probabilities for each constellation point of a constellation geometry according to an example embodiment. Referring to FIG. 12, a constellation may include a constellation geometry indicating number and position of each of the constellation points, whereas quantized probability of the probabilistic shaped constellation indicates a probability of one of eight levels (e.g., based on 3 bits, indicating 8 possible quantized values), including level 1, level 2, level 3, ... level 8.

[0097] In a MU MIMO (multiple input, multiple output) case, the gNB may coordinate or assist the learning of the probabilistic shape and / or geometric shape of the constellation in a per layer approach. For example, the gNB may use the same geometric shape for all layers and learn (or request the UE to learn) a probabilistic shape for each layer. A layer specific probabilistic shaping may be beneficial in controlling the PAPR (peak to average power ratio) per layer. Conversely, the gNB may use the same probabilistic shape for all layers and learn a geometric shape for each of the layers.

[0098] Also a progressive and / or on-demand sharing of learned probabilistic shaped constellation may be used. For example, a gNB may inform the UE about the SINR conditions, and the UE signals back the learned probabilistic shaped constellations for those SINR conditions only. In this scheme, the gNB triggers the UE to refresh the constellation information by indicating the expected SINR conditions. In an alternative embodiment, the constellation is learned in connection to a code rate, i.e., for the same constellation order, train the constellation under different code rates (note that this is valid if the loss function is computed using at least the output of the decoder) and evaluate the similarity between the resulting constellations. If sufficiently different from each other, then each learned probabilistic shaped constellation may be signaled together with the code rate(s) for which it has been obtained.

[0099] FIG. 13 is a flow chart illustrating operation of a node according to an example embodiment. Operation 1310 includes determining, by a first node of a wireless network, based at least on channel measurement information, constellation point probabilities for a plurality of constellation points of a probabilistic shaped constellation. Operation 1320 includes transmitting, by the first node to a second node of the wireless network, probabilistic shaped constellation information indicative of the constellation point probabilities. And, operation 1330 includes transmitting and / or receiving, by the first node, a signal based on the probabilistic shaped constellation.

[0100] With respect to the method of FIG. 13, the method may further include measuring, by the first node, a channel to obtain the channel measurement information; or receiving, by the first node from the second node, the channel measurement information.

[0101] With respect to the method of FIG. 13, the method may further include transmitting and / or receiving, by the first node, a message enabling sharing of the probabilistic shaped constellation information.

[0102] With respect to the method of FIG. 13, the method may further include transmitting and / or receiving, by the first node, a message configuring one or more parameters for sharing of the probabilistic shaped constellation information.

[0103] With respect to the method of FIG. 13, the method may further include receiving, by the first node from the second node, geometric shape information indicative of a geometric shape of the probabilistic shaped constellation; or transmitting, by the first network node to the second network node, geometric shape information indicative of a geometric shape of the probabilistic shaped constellation.

[0104] With respect to the method of FIG. 13, the transmitting the probabilistic shaped constellation information may include transmitting at least one of the following: full values of the constellation point probabilities; delta or difference values of the constellation point probabilities indicating a difference of constellation point probabilities with respect to a reference or previous constellation; and / or one or more parameters of a known or agreed upon probability distribution for constellation points.

[0105] With respect to the method of FIG. 13, the transmitting the probabilistic shaped constellation information may include transmitting at least one of the following: quantized constellation point probabilities for the plurality of constellation points; or floating point constellation point probabilities for the plurality of constellation points.

[0106] With respect to the method of FIG. 13, the method may further include receiving, by the first node from the second node, a message configuring one or more parameters of the quantized constellation point probabilities or the floating point constellation point probabilities for the plurality of constellation points.

[0107] With respect to the method of FIG. 13, the transmitting the probabilistic shaped constellation information may include: transmitting an index to a lookup table of a plurality of probabilistic shaped constellations, wherein the index points to or indicates the probabilistic shaped constellation of the plurality of probabilistic shaped constellations.

[0108] With respect to the method of FIG. 13, the transmitting the probabilistic shaped constellation information may include: transmitting an index to a lookup table of a plurality of probabilistic shaped constellations, wherein index k points to or indicates a k-th probabilistic shaped constellation of the plurality of probabilistic shaped constellations, wherein the k-th probabilistic shaped constellation is associated with or characterized by a probabilistic shape p(k) and a geometric shape C(k).

[0109] FIG. 14 is a flow chart illustrating operation of a node in which a symmetry property for a probabilistic shaped constellation is used according to an example embodiment. Operation 1410 includes determining, by a first node of a wireless network, constellation point probabilities for a plurality of constellation points of a probabilistic shaped constellation. Operation 1420 includes determining a symmetry property for the probabilistic shaped constellation. Operation 1430 includes determining a strict subset of the constellation point probabilities based on the symmetry property. Operation 1440 includes transmitting, by the first node to a second node of the wireless network, probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities. And, operation 1450 includes transmitting and / or receiving, by the first node, a signal based on the probabilistic shaped constellation.

[0110] With respect to the method of FIG. 14, the method may further include transmitting, by the first node to the second node, probabilistic shaped constellation symmetry information indicative of the symmetry property for the probabilistic shaped constellation.

[0111] With respect to the method of FIG. 14, the method may further include determining, by the first node, channel measurement information of a channel; and determining, by the first node, the symmetry property based on the channel measurement information.

[0112] With respect to the method of FIG. 14, the determining channel measurement information may include at least one of: measuring the channel to obtain the channel measurement information; or receiving the channel measurement information from the second node.

[0113] With respect to the method of FIG. 14, the symmetry property may include at least one of the following: a symmetry about an X-axis of the probabilistic shaped constellation; a symmetry about a Y-axis of the probabilistic shaped constellation; a symmetry about both the X-axis and the Y-axis of the probabilistic shaped constellation; a symmetry about a real-axis of the probabilistic shaped constellation; a symmetry about an imaginary-axis of the probabilistic shaped constellation; a symmetry about both the real-axis and the imaginary axis of the probabilistic shaped constellation; a quadrant symmetry of the probabilistic shaped constellation; a symmetry about a predefined axis in a transformed space; or a symmetry about a predefined axis in a transformed space, the transformed space being defined by a kernel function.

[0114] With respect to the method of FIG. 14, the method may further include transmitting and / or receiving, by the first node, a message configuring one or more parameters for sharing of the probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities.

[0115] With respect to the method of FIG. 14, the method may further include receiving, by the first node from the second node, geometric shape information indicative of a geometric shape of the probabilistic shaped constellation; or transmitting, by the first node to the second node, geometric shape information indicative of a geometric shape of the probabilistic shaped constellation.

[0116] With respect to the method of FIG. 14, the transmitting the probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities may include transmitting at least one of the following: full values for the strict subset of the constellation point probabilities; or delta or difference values for the strict subset of the constellation point probabilities indicating a difference of constellation point probabilities with respect to a reference or previous constellation; or one or more parameters of a known or agreed upon probability distribution of the strict subset of the constellation point probabilities.

[0117] With respect to the method of FIG. 14, the transmitting the probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities may include transmitting at least one of the following: quantized constellation point probabilities for the strict subset of the constellation point probabilities; or floating point constellation point probabilities for the strict subset of the constellation point probabilities.

[0118] With respect to the method of FIG. 14, the method may further include receiving, by the first node from the second node, a message configuring one or more parameters of the quantized constellation point probabilities or the floating point constellation point probabilities for at least the strict subset of the constellation point probabilities.

[0119] With respect to the method of FIG. 14, the the transmitting the probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities may include: transmitting an index to a lookup table of a plurality of strict subsets of constellation point probabilities, wherein the index points to or indicates the strict subset of the constellation point probabilities of the plurality of strict subsets.

[0120] FIG. 15 is a flow chart illustrating operation of a node in which a symmetry property for a probabilistic shaped constellation is used according to another example embodiment. Operation 1510 includes determining, by a second node of a wireless network, a symmetry property for a probabilistic shaped constellation, wherein the probabilistic shaped constellation includes constellation point probabilities for a plurality of constellation points. Operation 1520 includes receiving, by the second node from a first node of the wireless network, probabilistic shaped constellation information indicative of a strict subset of the constellation point probabilities. Operation 1530 includes determining, by the second node based on the symmetry property and the probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities, the probabilistic shaped constellation including the plurality of constellation point probabilities. And, operation 1540 includes transmitting and / or receiving, by the second node, a signal based on the probabilistic shaped constellation.

[0121] With respect to the method of FIG. 15, the strict subset of the constellation point probabilities indicate only a portion and less than all of the constellation point probabilities of the probabilistic shaped constellation, and wherein the determining the probabilistic shaped constellation including the plurality of constellation point probabilities may include determining, by the second node, based on the symmetry property and the strict subset of the constellation point probabilities, a remaining portion of the constellation point probabilities (that was not part of the strict subset of the constellation point probabilities) of the probabilistic shaped constellation, such that all constellation point probabilities of the probabilistic shaped constellation are known by the second node. In this manner, the second node can determine or derive all of the constellation point probabilities of the probabilistic shaped constellation based on the symmetry property and the received strict subset of constellation point probabilities (e.g., for one of the four quadrants). Thus, as an illustrative example, the complex plane (and thus constellation points of the constellation) may be divided into four quadrants, based on X (horizontal) and Y (vertical) axes of the complex plane, and there may be symmetry (for the constellation point probabilities for the constellation points) about both X and Y axis of complex plane for the constellation point probabilities of the probabilistic shaped constellation, and the first node may provide or transmit to the second node only a first quadrant of constellation point probabilities (within the complex plane for the constellation), and the second node may determine the constellation point probabilities of the other three quadrants (which were not provided or signaled to second node, and thus lower signaling overhead) of the probabilistic shaped constellation based on the (e.g., either already known or received) symmetry property and the received strict subset of constellation point probabilities. In this example, the strict subset may include constellation point probabilities for only one of the four quadrants of the probabilistic shaped constellation. The second node may already know the symmetry property (e.g., symmetry about both X and Y axis of complex plane, or quadrant symmetry) for the probabilistic shaped constellation, or may receive from the first node an indication of the symmetry property.

[0122] With respect to the method of FIG. 15, the symmetry property may include at least one of the following: a symmetry about an X-axis of the probabilistic shaped constellation; a symmetry about a Y-axis of the probabilistic shaped constellation; a symmetry about both the X-axis and the Y-axis of the probabilistic shaped constellation; a symmetry about a real-axis of the probabilistic shaped constellation; a symmetry about an imaginary-axis of the probabilistic shaped constellation; a symmetry about both the real-axis and the imaginary axis of the probabilistic shaped constellation; a quadrant symmetry of the probabilistic shaped constellation; a symmetry about a predefined axis in a transformed space; or a symmetry about a predefined axis in a transformed space, the transformed space being defined by a kernel function.

[0123] With respect to the method of FIG. 15, the method may further include transmitting and / or receiving, by the second node to the first node, a message configuring one or more parameters for sharing of the probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities.

[0124] With respect to the method of FIG. 15, the method may further include receiving, by the second node from the first node, geometric shape information indicative of a geometric shape of the probabilistic shaped constellation; or transmitting, by the second node to the first node, geometric shape information indicative of a geometric shape of the probabilistic shaped constellation.

[0125] With respect to the method of FIG. 15, the receiving the probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities may include receiving at least one of the following: full values for the strict subset of the constellation point probabilities; delta or difference values for the strict subset of the constellation point probabilities indicating a difference of constellation point probabilities with respect to a reference or previous constellation; or one or more parameters of a known or agreed upon probability distribution of the strict subset of the constellation point probabilities.

[0126] With respect to the method of FIG. 15, the receiving the probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities may include receiving at least one of the following: quantized constellation point probabilities for the strict subset of the constellation point probabilities; or floating point constellation point probabilities for the strict subset of the constellation point probabilities.

[0127] FIG. 16 is a flow chart illustrating operation of a node m which a transformation function for a probabilistic shaped constellation is used according to an example embodiment. Operation 1610 includes determining, by a first node of a wireless network, constellation point probabilities for a plurality of constellation points of a first probabilistic shaped constellation. Operation 1620 includes determining, by the first node, a transformation function for deriving the first probabilistic shaped constellation from a reference constellation. Operation 1630 includes transmitting, by the first node to a second node of the wireless network, an indication of the transformation function. And, operation 1640 includes transmitting and / or receiving, by the first node, a signal based on the first probabilistic shaped constellation.

[0128] With respect to the method of FIG. 16, the method may further include determining, by the first node, constellation point probabilities of a plurality of constellation points of the reference constellation, wherein the constellation point probabilities of the plurality of constellation points of the first probabilistic shaped constellation can be derived based on the transformation function and respective constellation points of the reference constellation.

[0129] With respect to the method of FIG. 16, the determining constellation point probabilities for the plurality of constellation points of the first probabilistic shaped constellation may include: determining, by the first node based on channel measurement information, the constellation point probabilities for the plurality of constellation points of the first probabilistic shaped constellation.

[0130] With respect to the method of FIG. 16, the method may further include determining the channel measurement information of a channel.

[0131] With respect to the method of FIG. 16, the determining channel measurement information comprises at least one of: measuring the channel to obtain the channel measurement information; or receiving the channel measurement information from the second node.

[0132] With respect to the method of FIG. 16, the determining the transformation function for deriving the first probabilistic shaped constellation from the reference constellation may include: determining a geometric shape and a probabilistic shape of the first probabilistic shaped constellation, wherein the probabilistic shape of the first probabilistic shaped constellation comprises the constellation point probabilities of the first probabilistic shaped constellation; determining a geometric shape and a probabilistic shape of the reference constellation; and determining the transformation function based on the geometric shape and the probabilistic shape of the first probabilistic shaped constellation, with respect to the geometric shape and the probabilistic shape of the reference constellation.

[0133] With respect to the method of FIG. 16, the determining the transformation function for deriving the first probabilistic shaped constellation from the reference constellation may include: determining constellation point probabilities of a plurality of constellation points of the reference constellation, wherein the reference constellation and the first probabilistic shaped constellation have a same geometric shape; and determining the transformation function based on constellation point probabilities of the plurality of constellation points of the first probabilistic shaped constellation with respect to constellation point probabilities of respective constellation points of the reference constellation.

[0134] With respect to the method of FIG. 16, the determining the transformation function for deriving the first probabilistic shaped constellation from the reference constellation is performed by a machine learning model.

[0135] With respect to the method of FIG. 16, the method may further include transmitting and / or receiving, by the first node, a message configuring one or more parameters for sharing of the transformation function.

[0136] With respect to the method of FIG. 16, the indication of the transformation function may include: transmitting an index to a lookup table of a plurality of transformation functions, wherein the index points to or indicates the transformation function of the plurality of transformation functions.

[0137] FIG. 17 is a flow chart illustrating operation of a node in which a transformation function for a probabilistic shaped constellation is used according to another example embodiment. Operation 1710 includes determining, by a second node of a wireless network, constellation point probabilities of a plurality of constellation points of a reference constellation. Operation 1720 includes receiving, by the second node from a first node of the wireless network, an indication of a transformation function for deriving a first probabilistic shaped constellation from the reference probabilistic shaped constellation. Operation 1730 includes determining, by the second first node, constellation point probabilities of a plurality of constellation points of the first probabilistic shaped constellation based on the constellation point probabilities of the plurality of constellation points of the reference probabilistic shaped constellation and the transformation function. And, operation 1740 includes transmitting and / or receiving, by the second node, a signal based on the first probabilistic shaped constellation.

[0138] With respect to the method of FIG. 17, the receiving the indication of the transformation function may include: receiving an index to a lookup table of a plurality of transformation functions, wherein the index points to or indicates the transformation function of the plurality of transformation functions.

[0139] Example Al. An apparatus including: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: determine, by a first node of a wireless network, based at least on channel measurement information, constellation point probabilities for a plurality of constellation points of a probabilistic shaped constellation; transmit, by the first node to a second node of the wireless network, probabilistic shaped constellation information indicative of the constellation point probabilities; and transmit and / or receive, by the first node, a signal based on the probabilistic shaped constellation.

[0140] Example A2. The apparatus of example Al, wherein the apparatus is further caused to: measure, by the first node, a channel to obtain the channel measurement information; or receive, by the first node from the second node, the channel measurement information.

[0141] Example A3. The apparatus of any of any of examples A1-A2, wherein the apparatus is further caused to: transmit and / or receive, by the first node, a message enabling sharing of the probabilistic shaped constellation information.

[0142] Example A4. The apparats of any of examples A1-A3, wherein the apparatus is further caused to: transmit and / or receive, by the first node, a message configuring one or more parameters for sharing of the probabilistic shaped constellation information.

[0143] Example A5. The apparatus of any of claims A1-A4, wherein the apparatus is further caused to: receive, by the first node from the second node, geometric shape information indicative of a geometric shape of the probabilistic shaped constellation; or transmit, by the first network node to the second network node, geometric shape information indicative of a geometric shape of the probabilistic shaped constellation.

[0144] Example A6. The apparatus of any of examples A1-A5, wherein the apparatus caused to transmit the probabilistic shaped constellation information comprises the apparatus caused to transmit at least one of the following: full values of the constellation point probabilities; delta or difference values of the constellation point probabilities indicating a difference of constellation point probabilities with respect to a reference or previous constellation; or one or more parameters of a known or agreed upon probability distribution for constellation points.

[0145] Example A7. The apparatus of any of examples A1-A6, wherein the apparatus caused to transmit the probabilistic shaped constellation information comprises the apparatus caused to transmit at least one of the following: quantized constellation point probabilities for the plurality of constellation points; or floating point constellation point probabilities for the plurality of constellation points.

[0146] Example A8. The apparatus of Example A7, wherein the apparatus is further caused to: receive, by the first node from the second node, a message configuring one or more parameters of the quantized constellation point probabilities or the floating point constellation point probabilities for the plurality of constellation points.

[0147] Example A9. The apparatus of any of examples A1-A8, wherein the apparatus caused to transmit the probabilistic shaped constellation information comprises the apparatus caused to: transmit an index to a lookup table of a plurality of probabilistic shaped constellations, wherein the index points to or indicates the probabilistic shaped constellation of the plurality of probabilistic shaped constellations.

[0148] Example A10. The apparatus of any of examples A1-A8, wherein the apparatus caused to transmit the probabilistic shaped constellation information comprises the apparatus caused to: transmit an index to a lookup table of a plurality of constellations, wherein index k points to or indicates a k-th probabilistic shaped constellation of the plurality of probabilistic shaped constellations, wherein the k-th probabilistic shaped constellation is associated with or characterized by a probabilistic shape p(k) and a geometric shape C(k).

[0149] Example Al 1. The apparatus of any of examples Al - Al 0, wherein: the first node comprises a user equipment (UE), and the second node comprises a network node or gNB; or the second node comprises a user equipment (UE), and the first node comprises a network node or gNB.

[0150] Example A12. A method comprising: determining, by a first node of a wireless network, based at least on channel measurement information, constellation point probabilities for a plurality of constellation points of a probabilistic shaped constellation; transmitting, by the first node to a second node of the wireless network, probabilistic shaped constellation information indicative of the constellation point probabilities; and transmitting and / or receiving, by the first node, a signal based on the probabilistic shaped constellation.

[0151] Example A13. The method of example A12, wherein the method further comprises: measuring, by the first node, a channel to obtain the channel measurement information; or receiving, by the first node from the second node, the channel measurement information.

[0152] Example A14. The method of any of examples A12-A13, further comprising: transmitting and / or receiving, by the first node, a message enabling sharing of the probabilistic shaped constellation information.

[0153] Example A15. The method of any of examples A12-A14, further comprising: transmitting and / or receiving, by the first node, a message configuring one or more parameters for sharing of the probabilistic shaped constellation information.

[0154] Example A16. The method of any of examples A12-A15, further comprising: receiving, by the first node from the second node, geometric shape information indicative of a geometric shape of the probabilistic shaped constellation; or transmitting, by the first network node to the second network node, geometric shape information indicative of a geometric shape of the probabilistic shaped constellation.

[0155] Example A 17. The method of any of examples Al 2-Al 6, wherein the transmitting the probabilistic shaped constellation information comprises transmitting at least one of the following: full values of the constellation point probabilities; delta or difference values of the constellation point probabilities indicating a difference of constellation point probabilities with respect to a reference or previous constellation; or one or more parameters of a known or agreed upon probability distribution for constellation points.

[0156] Example A18. The method of any of examples A12-A17, wherein the transmitting the probabilistic shaped constellation information comprises transmitting at least one of the following: quantized constellation point probabilities for the plurality of constellation points; or floating point constellation point probabilities for the plurality of constellation points.

[0157] Example Al 9. The method of example Al 8, further comprising: receiving, by the first node from the second node, a message configuring one or more parameters of the quantized constellation point probabilities or the floating point constellation point probabilities for the plurality of constellation points.

[0158] Example A20. The method of any of examples A12-A19, wherein the transmitting the probabilistic shaped constellation information comprises: transmitting an index to a lookup table of a plurality of probabilistic shaped constellations, wherein the index points to or indicates the probabilistic shaped constellation of the plurality of probabilistic shaped constellations.

[0159] Example A21. The method of any of examples A12-A20, wherein the transmitting the probabilistic shaped constellation information comprises: transmitting an index to a lookup table of a plurality of probabilistic shaped constellations, wherein index k points to or indicates a k-th probabilistic shaped constellation of the plurality of probabilistic shaped constellations, wherein the k-th probabilistic shaped constellation is associated with or characterized by a probabilistic shape p(k) and a geometric shape C(k).

[0160] Example A22. An apparatus comprising: means for performing any of the methods of examples A12-A21.

[0161] Example A23. An apparatus comprising: a non-transitory computer-readable storage medium comprising instructions stored thereon that, when executed by at least one processor, are configured to cause a computing system to perform any of the methods of examples A12-A21.

[0162] Example BE An apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: determine, by a first node of a wireless network, constellation point probabilities for a plurality of constellation points of a probabilistic shaped constellation; determine a symmetry property for the probabilistic shaped constellation; determine a strict subset of the constellation point probabilities based on the symmetry property; transmit, by the first node to a second node of the wireless network, probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities; and transmit and / or receive, by the first node, a signal based on the probabilistic shaped constellation.

[0163] Example B2. The apparatus of example Bl, wherein the apparatus is further caused to: transmit, by the first node to the second node, probabilistic shaped constellation symmetry information indicative of the symmetry property for the probabilistic shaped constellation.

[0164] Example B3. The apparatus of any of examples B1-B2, wherein the apparatus is further caused to: determine, by the first node, channel measurement information of a channel; and determine, by the first node, the symmetry property based on the channel measurement information.

[0165] Example B4. The apparatus of example B3, wherein the apparatus caused to determine channel measurement information comprises the apparatus caused to perform at least one of: measuring the channel to obtain the channel measurement information; or receiving the channel measurement information from the second node.

[0166] Example B5. The apparatus of any of examples B1-B4, wherein the symmetry property comprises at least one of the following: a symmetry about an X-axis of the probabilistic shaped constellation; a symmetry about a Y-axis of the probabilistic shaped constellation; a symmetry about both the X-axis and the Y-axis of the probabilistic shaped constellation; a symmetry about a real-axis of the probabilistic shaped constellation; a symmetry about an imaginary-axis of the probabilistic shaped constellation; a symmetry about both the real-axis and the imaginary axis of the probabilistic shaped constellation; a quadrant symmetry of the probabilistic shaped constellation; a symmetry about a predefined axis in a transformed space; or a symmetry about a predefined axis in a transformed space, the transformed space being defined by a kernel function.

[0167] Example B6. The apparatus of any of examples B1-B5, wherein the apparatus is further caused to: transmit and / or receive, by the first node, a message configuring one or more parameters for sharing of the probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities.

[0168] Example B7. The apparatus of any of examples B1-B6, wherein the apparatus is further caused to: receive, by the first node from the second node, geometric shape information indicative of a geometric shape of the probabilistic shaped constellation; or transmit, by the first node to the second node, geometric shape information indicative of a geometric shape of the probabilistic shaped constellation.

[0169] Example B8. The apparatus of any of examples B1-B7, wherein the apparatus caused to transmit the probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities comprises the apparatus caused to transmit at least one of the following: full values for the strict subset of the constellation point probabilities; delta or difference values for the strict subset of the constellation point probabilities indicating a difference of constellation point probabilities with respect to a reference or previous constellation; or one or more parameters of a known or agreed upon probability distribution for constellation points of the strict subset.

[0170] Example B9. The apparatus of any of examples B1-B8, wherein the apparatus caused to transmit the probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities comprises the apparatus caused to transmit at least one of the following: quantized constellation point probabilities for the strict subset of the constellation point probabilities; or floating point constellation point probabilities for the strict subset of the constellation point probabilities.

[0171] Example B10. The apparatus of example B9, wherein the apparatus is further caused to: receive, by the first node from the second node, a message configuring one or more parameters of the quantized constellation point probabilities or the floating point constellation point probabilities for at least the strict subset of the constellation point probabilities.

[0172] Example Bl 1. The apparatus of any of examples B1-B10 wherein the apparatus caused to transmit the probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities comprises the apparatus caused to: transmit an index to a lookup table of a plurality of strict subsets of constellation point probabilities, wherein the index points to or indicates the strict subset of the constellation point probabilities of the plurality of strict subsets.

[0173] Example B12. An apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: determine, by a second node of a wireless network, a symmetry property for a probabilistic shaped constellation, wherein the probabilistic shaped constellation includes constellation point probabilities for a plurality of constellation points; receive, by the second node from a first node of the wireless network, probabilistic shaped constellation information indicative of a strict subset of the constellation point probabilities; determine, by the second node based on the symmetry property and the probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities, the probabilistic shaped constellation including the plurality of constellation point probabilities; and transmit and / or receive, by the second node, a signal based on the probabilistic shaped constellation.

[0174] Example B13. The apparatus of example B12, wherein the strict subset of the constellation point probabilities indicate only a portion and less than all of the constellation point probabilities of the probabilistic shaped constellation, and wherein the apparatus caused to determine the probabilistic shaped constellation including the plurality of constellation point probabilities comprises the apparatus caused to determine, by the second node, based on the symmetry property and the strict subset of the constellation point probabilities, a remaining portion of the constellation point probabilities of the probabilistic shaped constellation, such that all constellation point probabilities of the probabilistic shaped constellation are known by the second node.

[0175] Example B14. The apparatus of any of examples B12-B13, wherein the symmetry property comprises at least one of the following: a symmetry about an X-axis of the probabilistic shaped constellation; a symmetry about a Y-axis of the probabilistic shaped constellation; a symmetry about both the X-axis and the Y-axis of the probabilistic shaped constellation; a symmetry about a real-axis of the probabilistic shaped constellation; a symmetry about an imaginary-axis of the probabilistic shaped constellation; a symmetry about both the real-axis and the imaginary axis of the probabilistic shaped constellation; a quadrant symmetry of the probabilistic shaped constellation; a symmetry about a predefined axis in a transformed space; or a symmetry about a predefined axis in a transformed space, the transformed space being defined by a kernel function.

[0176] Example B15. The apparatus of any of examples B12-B14, wherein the apparatus is further caused to: transmit and / or receive, by the second node to the first node, a message configuring one or more parameters for sharing of the probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities.

[0177] Example B16. The apparatus of any of examples B12-B15, wherein the apparatus is further caused to: receive, by the second node from the first node, geometric shape information indicative of a geometric shape of the probabilistic shaped constellation; or transmit, by the second node to the first node, geometric shape information indicative of a geometric shape of the probabilistic shaped constellation.

[0178] Example B17. The apparatus of any of examples B12-B16, wherein the apparatus caused to receive the probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities comprises the apparatus caused to receive at least one of the following: full values for the strict subset of the constellation point probabilities; delta or difference values for the strict subset of the constellation point probabilities indicating a difference of constellation point probabilities with respect to a reference or previous constellation; or one or more parameters of a known or agreed upon probability distribution of the strict subset of the constellation point probabilities.

[0179] Example B18. The apparatus of any of examples B12-B17, wherein the apparatus caused to receive the probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities comprises the apparatus caused to transmit at least one of the following: quantized constellation point probabilities for the strict subset of the constellation point probabilities; or floating point constellation point probabilities for the strict subset of the constellation point probabilities.

[0180] Example B19. The apparatus of any of examples Bl-Bl 8, wherein: the first node comprises a user equipment (UE), and the second node comprises a network node or gNB; or the second node comprises a user equipment (UE), and the first node comprises a network node or gNB.

[0181] Example B20. A method comprising: determining, by a first node of a wireless network, constellation point probabilities for a plurality of constellation points of a probabilistic shaped constellation; determining a symmetry property for the probabilistic shaped constellation; determining a strict subset of the constellation point probabilities based on the symmetry property; transmitting, by the first node to a second node of the wireless network, probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities; and transmitting and / or receiving, by the first node, a signal based on the probabilistic shaped constellation.

[0182] Example B21. The method of example B20, further comprising: transmitting, by the first node to the second node, probabilistic shaped constellation symmetry information indicative of the symmetry property for the probabilistic shaped constellation.

[0183] Example B22. The method of any of examples B20-B21, further comprising: determining, by the first node, channel measurement information of a channel; and determining, by the first node, the symmetry property based on the channel measurement information.

[0184] Example B23. The method of example B22, wherein the determining channel measurement information comprises at least one of: measuring the channel to obtain the channel measurement information; or receiving the channel measurement information from the second node.

[0185] Example B24. The method of any of examples B20-B23, wherein the symmetry property comprises at least one of the following: a symmetry about an X-axis of the probabilistic shaped constellation; a symmetry about a Y-axis of the probabilistic shaped constellation; a symmetry about both the X-axis and the Y-axis of the probabilistic shaped constellation; a symmetry about a real-axis of the probabilistic shaped constellation; a symmetry about an imaginary-axis of the probabilistic shaped constellation; a symmetry about both the real-axis and the imaginary axis of the probabilistic shaped constellation; a quadrant symmetry of the probabilistic shaped constellation; a symmetry about a predefined axis in a transformed space; or a symmetry about a predefined axis in a transformed space, the transformed space being defined by a kernel function.

[0186] Example B25. The method of any of examples B20-B24, further comprising: transmitting and / or receiving, by the first node, a message configuring one or more parameters for sharing of the probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities.

[0187] Example B26. The method of any of examples B20-B25, further comprising: receiving, by the first node from the second node, geometric shape information indicative of a geometric shape of the probabilistic shaped constellation; or transmitting, by the first node to the second node, geometric shape information indicative of a geometric shape of the probabilistic shaped constellation.

[0188] Example B27. The method of any of examples B20-B26, wherein the transmitting the probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities comprises transmitting at least one of the following: full values for the strict subset of the constellation point probabilities; or delta or difference values for the strict subset of the constellation point probabilities indicating a difference of constellation point probabilities with respect to a reference or previous constellation; or one or more parameters of a known or agreed upon probability distribution of the strict subset of the constellation point probabilities.

[0189] Example B28. The method of any of examples B20-B27, wherein the transmitting the probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities comprises transmitting at least one of the following: quantized constellation point probabilities for the strict subset of the constellation point probabilities; or floating point constellation point probabilities for the strict subset of the constellation point probabilities.

[0190] Example B29. The method of example B28, further comprising: receiving, by the first node from the second node, a message configuring one or more parameters of the quantized constellation point probabilities or the floating point constellation point probabilities for at least the strict subset of the constellation point probabilities.

[0191] Example B30. The method of any of examples B20-B29 wherein the transmitting the probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities comprises: transmitting an index to a lookup table of a plurality of strict subsets of constellation point probabilities, wherein the index points to or indicates the strict subset of the constellation point probabilities of the plurality of strict subsets.

[0192] Example B31. A method comprising: determining, by a second node of a wireless network, a symmetry property for a probabilistic shaped constellation, wherein the probabilistic shaped constellation includes constellation point probabilities for a plurality of constellation points; receiving, by the second node from a first node of the wireless network, probabilistic shaped constellation information indicative of a strict subset of the constellation point probabilities; determining, by the second node based on the symmetry property and the probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities, the probabilistic shaped constellation including the plurality of constellation point probabilities; and transmitting and / or receiving, by the second node, a signal based on the probabilistic shaped constellation.

[0193] Example B32. The method of example B31, wherein the strict subset of the constellation point probabilities indicate only a portion and less than all of the constellation point probabilities of the probabilistic shaped constellation, and wherein the determining the probabilistic shaped constellation including the plurality of constellation point probabilities comprises determining, by the second node, based on the symmetry property and the strict subset of the constellation point probabilities, a remaining portion of the constellation point probabilities of the probabilistic shaped constellation, such that all constellation point probabilities of the probabilistic shaped constellation are known by the second node. ]

[0194] Example B33. The method of any of examples B31-B32, wherein the symmetry property comprises at least one of the following: a symmetry about an X-axis of the probabilistic shaped constellation; a symmetry about a Y-axis of the probabilistic shaped constellation; a symmetry about both the X-axis and the Y-axis of the probabilistic shaped constellation; a symmetry about a real-axis of the probabilistic shaped constellation; a symmetry about an imaginary-axis of the probabilistic shaped constellation; a symmetry about both the real-axis and the imaginary axis of the probabilistic shaped constellation; a quadrant symmetry of the probabilistic shaped constellation; a symmetry about a predefined axis in a transformed space; or a symmetry about a predefined axis in a transformed space, the transformed space being defined by a kernel function.

[0195] Example B34. The method of any of examples B31-B33, further comprising: transmitting and / or receiving, by the second node to the first node, a message configuring one or more parameters for sharing of the probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities.

[0196] Example B35. The method of any of examples B31-B34, further comprising: receiving, by the second node from the first node, geometric shape information indicative of a geometric shape of the probabilistic shaped constellation; or transmitting, by the second node to the first node, geometric shape information indicative of a geometric shape of the probabilistic shaped constellation.

[0197] Example B36. The method of any of examples B31-B35, wherein the receiving the probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities comprises receiving at least one of the following: full values for the strict subset of the constellation point probabilities; delta or difference values for the strict subset of the constellation point probabilities indicating a difference of constellation point probabilities with respect to a reference or previous constellation; or one or more parameters of a known or agreed upon probability distribution of the strict subset of the constellation point probabilities.

[0198] Example B37. The method of any of examples B31-B36, wherein the receiving the probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities comprises receiving at least one of the following: quantized constellation point probabilities for the strict subset of the constellation point probabilities; or floating point constellation point probabilities for the strict subset of the constellation point probabilities.

[0199] Example B38. An apparatus comprising: means for performing any of the methods of examples B20-B37.

[0200] Example B39. An apparatus comprising: a non-transitory computer-readable storage medium comprising instructions stored thereon that, when executed by at least one processor, are configured to cause a computing system to perform any of the methods of examples B20-B37.

[0201] Example Cl. An apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: determine, by a first node of a wireless network, constellation point probabilities for a plurality of constellation points of a first probabilistic shaped constellation; determine, by the first node, a transformation function for deriving the first probabilistic shaped constellation from a reference constellation; transmit, by the first node to a second node of the wireless network, an indication of the transformation function; and transmit and / or receive, by the first node, a signal based on the first probabilistic shaped constellation.

[0202] Example C2. The apparatus of example Cl, wherein the apparatus is further caused to: determine, by the first node, constellation point probabilities of a plurality of constellation points of the reference constellation, wherein the constellation point probabilities of the plurality of constellation points of the first probabilistic shaped constellation can be derived based on the transformation function and respective constellation points of the reference constellation.

[0203] Example C3. The apparatus of any of examples C1-C2, wherein the apparatus caused to determine constellation point probabilities for the plurality of constellation points of the first probabilistic shaped constellation comprises the apparatus caused to: determine, by the first node based on channel measurement information, the constellation point probabilities for the plurality of constellation points of the first probabilistic shaped constellation.

[0204] Example C4. The apparatus of example C3, wherein the apparatus is further caused to determine the channel measurement information of a channel.

[0205] Example C5. The apparatus of example C4, wherein the apparatus caused to determine channel measurement information comprises the apparatus caused to perform at least one of: measuring the channel to obtain the channel measurement information; or receiving the channel measurement information from the second node.

[0206] Example C6. The apparatus of any of examples C1-C5, wherein the apparatus caused to determine the transformation function for deriving the first probabilistic shaped constellation from the reference constellation comprises the apparatus caused to: determine a geometric shape and a probabilistic shape of the first probabilistic shaped constellation, wherein the probabilistic shape of the first probabilistic shaped constellation comprises the constellation point probabilities of the first probabilistic shaped constellation; determine a geometric shape and a probabilistic shape of the reference constellation; and determine the transformation function based on the geometric shape and the probabilistic shape of the first probabilistic shaped constellation, with respect to the geometric shape and the probabilistic shape of the reference constellation.

[0207] Example C7. The apparatus of any of examples C1-C6, wherein the apparatus caused to determine the transformation function for deriving the first probabilistic shaped constellation from the reference constellation comprises the apparatus caused to: determine constellation point probabilities of a plurality of constellation points of the reference constellation, wherein the reference constellation and the first probabilistic shaped constellation have a same geometric shape; and determine the transformation function based on constellation point probabilities of the plurality of constellation points of the first probabilistic shaped constellation with respect to constellation point probabilities of respective constellation points of the reference constellation.

[0208] Example C8. The apparatus of any of examples C1-C7, wherein the apparatus caused to determine the transformation function for deriving the first probabilistic shaped constellation from the reference constellation is performed by a machine learning model.

[0209] Example C9. The apparatus of any of examples C1-C8, wherein the apparatus is further caused to: transmit and / or receive, by the first node, a message configuring one or more parameters for sharing of the transformation function.

[0210] Example CIO. The apparatus of any of examples C1-C9 wherein the apparatus caused to transmit the indication of the transformation function comprises the apparatus caused to: transmit an index to a lookup table of a plurality of transformation functions, wherein the index points to or indicates the transformation function of the plurality of transformation functions.

[0211] Example Cl 1. An apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: determine, by a second node of a wireless network, constellation point probabilities of a plurality of constellation points of a reference constellation; receive, by the second node from a first node of the wireless network, an indication of a transformation function for deriving a first probabilistic shaped constellation from the reference constellation; determine, by the second node, constellation point probabilities of a plurality of constellation points of the first probabilistic shaped constellation based on the constellation point probabilities of the plurality of constellation points of the reference constellation and the transformation function; and transmit and / or receive, by the second node, a signal based on the first probabilistic shaped constellation.

[0212] Example C12. The apparatus of example Cl 1 wherein the apparatus caused to receive the indication of the transformation function comprises the apparatus caused to: receive an index to a lookup table of a plurality of transformation functions, wherein the index points to or indicates the transformation function of the plurality of transformation functions.

[0213] Example C13. The apparatus of any of examples Cl 1-Cl 2, wherein: the first node comprises a user equipment (UE), and the second node comprises a network node or gNB; or the second node comprises a user equipment (UE), and the first node comprises a network node or gNB.

[0214] Example C14. A method comprising: determining, by a first node of a wireless network, constellation point probabilities for a plurality of constellation points of a first probabilistic shaped constellation; determining, by the first node, a transformation function for deriving the first probabilistic shaped constellation from a reference constellation; transmitting, by the first node to a second node of the wireless network, an indication of the transformation function; and transmitting and / or receiving, by the first node, a signal based on the first probabilistic shaped constellation.

[0215] Example C15. The method of example C14, further comprising: determining, by the first node, constellation point probabilities of a plurality of constellation points of the reference constellation, wherein the constellation point probabilities of the plurality of constellation points of the first probabilistic shaped constellation can be derived based on the transformation function and respective constellation points of the reference constellation.

[0216] Example C16. The method of any of examples C14-C15, wherein the determining constellation point probabilities for the plurality of constellation points of the first probabilistic shaped constellation comprises: determining, by the first node based on channel measurement information, the constellation point probabilities for the plurality of constellation points of the first probabilistic shaped constellation.

[0217] Example Cl 7. The method of example Cl 6, further comprising determining the channel measurement information of a channel.

[0218] Example C18. The method of example C17, wherein the determining channel measurement information comprises at least one of: measuring the channel to obtain the channel measurement information; or receiving the channel measurement information from the second node.

[0219] Example C19. The method of any of examples C14-C18, wherein the determining the transformation function for deriving the first probabilistic shaped constellation from the reference constellation comprises: determining a geometric shape and a probabilistic shape of the first probabilistic shaped constellation, wherein the probabilistic shape of the first probabilistic shaped constellation comprises the constellation point probabilities of the first probabilistic shaped constellation; determining a geometric shape and a probabilistic shape of the reference constellation; and determining the transformation function based on the geometric shape and the probabilistic shape of the first probabilistic shaped constellation, with respect to the geometric shape and the probabilistic shape of the reference constellation.

[0220] Example C20. The method of any of examples C14-C19, wherein the determining the transformation function for deriving the first probabilistic shaped constellation from the reference constellation comprises: determining constellation point probabilities of a plurality of constellation points of the reference constellation, wherein the reference constellation and the first probabilistic shaped constellation have a same geometric shape; and determining the transformation function based on constellation point probabilities of the plurality of constellation points of the first probabilistic shaped constellation with respect to constellation point probabilities of respective constellation points of the reference constellation.

[0221] Example C21. The method of any of examples C14-C20, wherein the determining the transformation function for deriving the first probabilistic shaped constellation from the reference constellation is performed by a machine learning model.

[0222] Example C22. The method of any of examples C14-C21, further comprising: transmitting and / or receiving, by the first node, a message configuring one or more parameters for sharing of the transformation function.

[0223] Example C23. The method of any of examples C14-C22 wherein the transmitting the indication of the transformation function comprises: transmitting an index to a lookup table of a plurality of transformation functions, wherein the index points to or indicates the transformation function of the plurality of transformation functions.

[0224] Example C24. A method comprising: determining, by a second node of a wireless network, constellation point probabilities of a plurality of constellation points of a reference constellation; receiving, by the second node from a first node of the wireless network, an indication of a transformation function for deriving a first probabilistic shaped constellation from the reference probabilistic shaped constellation; determining, by the second first node, constellation point probabilities of a plurality of constellation points of the first probabilistic shaped constellation based on the constellation point probabilities of the plurality of constellation points of the reference probabilistic shaped constellation and the transformation function; and transmitting and / or receiving, by the second node, a signal based on the first probabilistic shaped constellation.

[0225] Example C25. The method of example C24 wherein the receiving the indication of the transformation function comprises: receiving an index to a lookup table of a plurality of transformation functions, wherein the index points to or indicates the transformation function of the plurality of transformation functions.

[0226] Example C26. An apparatus comprising: means for performing any of the methods of examples C14-C25.

[0227] Example C27. An apparatus comprising: a non-transitory computer-readable storage medium comprising instructions stored thereon that, when executed by at least one processor, are configured to cause a computing system to perform any of the methods of examples C14-C25.

[0228]

[0229] FIG. 18 is a block diagram of a wireless station or node (e.g., UE, user device, AP, BS, eNB, gNB, RAN node, network node, TRP, or other node) 1800 according to an example embodiment. The wireless station 1800 may include, for example, one or more (e.g., two as shown in FIG. 18) RF (radio frequency) or wireless transceivers 1802A, 1802B, where each wireless transceiver includes a transmitter to transmit signals and a receiver to receive signals. The wireless station also includes a processor or control unit / entity (controller) 1804 to execute instructions or software and control transmission and receptions of signals, and a memory 1806 to store data and / or instructions.

[0230] Processor 1804 may also make decisions or determinations, generate frames, packets or messages for transmission, decode received frames or messages for further processing, and other tasks or functions described herein. Processor 1804, which may be a baseband processor, for example, may generate messages, packets, frames or other signals for transmission via wireless transceiver 1802 (1802A or 1802B). Processor 1804 may control transmission of signals or messages over a wireless network, and may control the reception of signals or messages, etc., via a wireless network (e.g., after being down-converted by wireless transceiver 1802, for example). Processor 1804 may be programmable and capable of executing software or other instructions stored in memory or on other computer media to perform the various tasks and functions described above, such as one or more of the tasks or methods described above. Processor 1804 may be (or may include), for example, hardware, programmable logic, a programmable processor that executes software or firmware, and / or any combination of these. Using other terminology, processor 1804 and transceiver 1802 together may be considered as a wireless transmitter / receiver system, for example.

[0231] In addition, referring to FIG. 18, a controller (or processor) 1808 may execute software and instructions, and may provide overall control for the station 1800, and may provide control for other systems not shown in FIG. 18, such as controlling input / output devices (e.g., display, keypad), and / or may execute software for one or more applications that may be provided on wireless station 1800, such as, for example, an email program, audio / video applications, a word processor, a Voice over IP application, or other application or software.

[0232] In addition, a storage medium may be provided that includes stored instructions, which when executed by a controller or processor may result in the processor 1804, or other controller or processor, performing one or more of the functions or tasks described above.

[0233] According to another example embodiment, RF or wireless transceiver(s) 1802A / 1802B may receive signals or data and / or transmit or send signals or data. Processor 1804 (and possibly transceivers 1802A / 1802B) may control the RF or wireless transceiver 1802A or 1802B to receive, send, broadcast or transmit signals or data.

[0234] Example embodiments are provided or described for each of the example methods, including: An apparatus (e.g., 1800, FIG. 18) including means (e.g., processor 1804, RF transceivers 1802A and / or 1802B, and / or memory 1806, in FIG. 18) for carrying out any of the methods; a non-transitory computer-readable storage medium (e.g., memory 1806, FIG. 18) comprising instructions stored thereon that, when executed by at least one processor (processor 1804, FIG. 18), are configured to cause a computing system (e.g., 1800, FIG. 18) to perform any of the example methods; and an apparatus (e.g., 1800, FIG. 18) including at least one processor (e.g., processor 1804, FIG. 18), and at least one memory (e.g., memory 1806, FIG. 18) including computer program code, the at least one memory (1806) and the computer program code configured to, with the at least one processor (1804), cause the apparatus (e.g., 1800) at least to perform any of the example methods.

[0235] Embodiments of the various techniques described herein may be implemented in digital electronic circuitry, or in computer hardware, firmware, software, or in combinations of them. Embodiments may be implemented as a computer program product, i.e., a computer program tangibly embodied in an information carrier, e.g., in a machine-readable storage device or in a propagated signal, for execution by, or to control the operation of, a data processing apparatus, e.g., a programmable processor, a computer, or multiple computers. Embodiments may also be provided on a computer readable medium or computer readable storage medium, which may be a non-transitory medium. Embodiments of the various techniques may also include embodiments provided via transitory signals or media, and / or programs and / or software embodiments that are downloadable via the Internet or other network(s), either wired networks and / or wireless networks. In addition, embodiments may be provided via machine type communications (MTC), and also via an Internet of Things (IOT).

[0236] As used in this application, the term ‘circuitry’ or “circuit” refers to all of the following: (a) hardware-only circuit implementations, such as implementations in only analog and / or digital circuitry, and (b) combinations of circuits and soft-ware (and / or firmware), such as (as applicable): (i) a combination of processor(s) or (ii) portions of processor(s) / software including digital signal processor(s), software, and memory(ies) that work together to cause an apparatus to perform various functions, and (c) circuits, such as a microprocessor(s) or a portion of a microprocessor! s), that require software or firmware for operation, even if the software or firmware is not physically present. This definition of ‘circuitry’ applies to all uses of this term in this application. As a further example, as used in this application, the term ‘circuitry’ would also cover an implementation of merely a processor (or multiple processors) or a portion of a processor and its (or their) accompanying software and / or firmware. The term ‘circuitry’ would also cover, for example and if applicable to the particular element, a baseband integrated circuit or applications processor integrated circuit for a mobile phone or a similar integrated circuit in a server, a cellular network device, or another network device.

[0237] The computer program may be in source code form, object code form, or in some intermediate form, and it may be stored in some sort of carrier, distribution medium, or computer readable medium, which may be any entity or device capable of carrying the program. Such carriers include a record medium, computer memory, read-only memory, photoelectrical and / or electrical carrier signal, telecommunications signal, and software distribution package, for example. Depending on the processing power needed, the computer program may be executed in a single electronic digital computer, or it may be distributed amongst a number of computers.

[0238] Furthermore, embodiments of the various techniques described herein may use a cyber-physical system (CPS) (a system of collaborating computational elements controlling physical entities). CPS may enable the embodiment and exploitation of massive amounts of interconnected ICT devices (sensors, actuators, processors microcontrollers,...) embedded in physical objects at different locations. Mobile cyber physical systems, in which the physical system in question has inherent mobility, are a subcategory of cyber-physical systems. Examples of mobile physical systems include mobile robotics and electronics transported by humans or animals. The rise in popularity of smartphones has increased interest in the area of mobile cyberphysical systems. Therefore, various embodiments of techniques described herein may be provided via one or more of these technologies.

[0239] A computer program, such as the computer program(s) described above, can be written in any form of programming language, including compiled or interpreted languages, and can be deployed in any form, including as a standalone program or as a module, component, subroutine, or other unit or part of it suitable for use in a computing environment. A computer program can be deployed to be executed on one computer or on multiple computers at one site or distributed across multiple sites and interconnected by a communication network.

[0240] Method steps may be performed by one or more programmable processors executing a computer program or computer program portions to perform functions by operating on input data and generating output. Method steps also may be performed by, and an apparatus may be implemented as, special purpose logic circuitry, e.g., an FPGA (field programmable gate array) or an ASIC (application specific integrated circuit).

[0241] Processors suitable for the execution of a computer program include, by way of example, both general and special purpose microprocessors, and any one or more processors of any kind of digital computer, chip or chipset. Generally, a processor will receive instructions and data from a read-only memory or a random access memory or both. Elements of a computer may include at least one processor for executing instructions and one or more memory devices for storing instructions and data. Generally, a computer also may include, or be operatively coupled to receive data from or transfer data to, or both, one or more mass storage devices for storing data, e.g., magnetic, magnetooptical disks, or optical disks. Information carriers suitable for embodying computer program instructions and data include all forms of non-volatile memory, including by way of example semiconductor memory devices, e.g., EPROM, EEPROM, and flash memory devices; magnetic disks, e.g., internal hard disks or removable disks; magneto-optical disks; and CD-ROM and DVD-ROM disks. The processor and the memory may be supplemented by, or incorporated in, special purpose logic circuitry.

[0242] To provide for interaction with a user, embodiments may be implemented on a computer having a display device, e.g., a cathode ray tube (CRT) or liquid crystal display (LCD) monitor, for displaying information to the user and a user interface, such as a keyboard and a pointing device, e.g., a mouse or a trackball, by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback, e.g., visual feedback, auditory feedback, or tactile feedback; and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0243] Embodiments may be implemented in a computing system that includes a backend component, e.g., as a data server, or that includes a middleware component, e.g., an application server, or that includes a frontend component, e.g., a client computer having a graphical user interface or a Web browser through which a user can interact with an embodiment, or any combination of such backend, middleware, or frontend components. Components may be interconnected by any form or medium of digital data communication, e.g., a communication network. Examples of communication networks include a local area network (LAN) and a wide area network (WAN), e.g., the Internet.

[0244] While certain features of the described embodiments have been illustrated as described herein, many modifications, substitutions, changes and equivalents will now occur to those skilled in the art. It is, therefore, to be understood that the appended claims are intended to cover all such modifications and changes as fall within the true spirit of the various embodiments.

Claims

1. An apparatus comprising:at least one processor; andat least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to:determine, by a first node of a wireless network, constellation point probabilities for a plurality of constellation points of a probabilistic shaped constellation;determine a symmetry property for the probabilistic shaped constellation;determine a strict subset of the constellation point probabilities based on the symmetry property;transmit, by the first node to a second node of the wireless network, probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities; andtransmit and / or receive, by the first node, a signal based on the probabilistic shaped constellation.

2. The apparatus of claim 1, wherein the apparatus is further caused to:transmit, by the first node to the second node, probabilistic shaped constellation symmetry information indicative of the symmetry property for the probabilistic shaped constellation.

3. The apparatus of any of claims 1-2, wherein the apparatus is further caused to: determine, by the first node, channel measurement information of a channel; and determine, by the first node, the symmetry property based on the channel measurement information.

4. The apparatus of claim 3, wherein the apparatus caused to determine channel measurement information comprises the apparatus caused to perform at least one of: measuring the channel to obtain the channel measurement information; or receiving the channel measurement information from the second node.

5. The apparatus of any of claims 1-4, wherein the symmetry property comprises at least one of the following:a symmetry about an X-axis of the probabilistic shaped constellation;a symmetry about a Y-axis of the probabilistic shaped constellation;a symmetry about both the X-axis and the Y-axis of the probabilistic shaped constellation;a symmetry about a real-axis of the probabilistic shaped constellation;a symmetry about an imaginary-axis of the probabilistic shaped constellation;a symmetry about both the real-axis and the imaginary axis of the probabilistic shaped constellation;a quadrant symmetry of the probabilistic shaped constellation;a symmetry about a predefined axis in a transformed space; ora symmetry about a predefined axis in a transformed space, the transformed space being defined by a kernel function.

6. The apparatus of any of claims 1-5, wherein the apparatus is further caused to:transmit and / or receive, by the first node, a message configuring one or more parameters for sharing of the probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities.

7. The apparatus of any of claims 1-6, wherein the apparatus is further caused to:receive, by the first node from the second node, geometric shape information indicative of a geometric shape of the probabilistic shaped constellation; ortransmit, by the first node to the second node, geometric shape information indicative of a geometric shape of the probabilistic shaped constellation.

8. The apparatus of any of claims 1-7, wherein the apparatus caused to transmit the probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities comprises the apparatus caused to transmit at least one of the following:full values for the strict subset of the constellation point probabilities;delta or difference values for the strict subset of the constellation point probabilities indicating a difference of constellation point probabilities with respect to a reference or previous constellation; orone or more parameters of a known or agreed upon probability distribution for constellation points of the strict subset.

9. The apparatus of any of claims 1-8, wherein the apparatus caused to transmit the probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities comprises the apparatus caused to transmit at least one of the following:quantized constellation point probabilities for the strict subset of the constellation point probabilities; orfloating point constellation point probabilities for the strict subset of the constellation point probabilities.

10. The apparatus of claim 9, wherein the apparatus is further caused to:receive, by the first node from the second node, a message configuring one or more parameters of the quantized constellation point probabilities or the floating point constellation point probabilities for at least the strict subset of the constellation point probabilities.

11. The apparatus of any of claims 1-10, wherein the apparatus caused to transmit the probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities comprises the apparatus caused to:transmit an index to a lookup table of a plurality of strict subsets of constellation point probabilities, wherein the index points to or indicates the strict subset of the constellation point probabilities of the plurality of strict subsets.

12. An apparatus comprising:at least one processor; andat least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to:determine, by a second node of a wireless network, a symmetry property for a probabilistic shaped constellation, wherein the probabilistic shaped constellation includes constellation point probabilities for a plurality of constellation points;receive, by the second node from a first node of the wireless network, probabilistic shaped constellation information indicative of a strict subset of the constellation point probabilities;determine, by the second node based on the symmetry property and the probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities, the probabilistic shaped constellation including the plurality of constellation point probabilities; andtransmit and / or receive, by the second node, a signal based on the probabilistic shaped constellation.

13. The apparatus of claim 12, wherein the strict subset of the constellation point probabilities indicate only a portion and less than all of the constellation point probabilities of the probabilistic shaped constellation,and wherein the apparatus caused to determine the probabilistic shaped constellation including the plurality of constellation point probabilities comprises the apparatus caused to determine, by the second node, based on the symmetry property and the strict subset of the constellation point probabilities, a remaining portion of the constellation point probabilities of the probabilistic shaped constellation, such that all constellation point probabilities of the probabilistic shaped constellation are known by the second node.

14. The apparatus of any of claims 12-13, wherein the symmetry property comprises at least one of the following:a symmetry about an X-axis of the probabilistic shaped constellation;a symmetry about a Y-axis of the probabilistic shaped constellation;a symmetry about both the X-axis and the Y-axis of the probabilistic shaped constellation;a symmetry about a real-axis of the probabilistic shaped constellation;a symmetry about an imaginary-axis of the probabilistic shaped constellation;a symmetry about both the real-axis and the imaginary axis of the probabilistic shaped constellation;a quadrant symmetry of the probabilistic shaped constellation;a symmetry about a predefined axis in a transformed space; ora symmetry about a predefined axis in a transformed space, the transformed space being defined by a kernel function.

15. The apparatus of any of claims 12-14, wherein the apparatus is further caused to: transmit and / or receive, by the second node to the first node, a message configuring one or more parameters for sharing of the probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities.

16. The apparatus of any of claims 12-15, wherein the apparatus is further caused to: receive, by the second node from the first node, geometric shape information indicative of a geometric shape of the probabilistic shaped constellation; ortransmit, by the second node to the first node, geometric shape information indicative of a geometric shape of the probabilistic shaped constellation.

17. The apparatus of any of claims 12-16, wherein the apparatus caused to receive the probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities comprises the apparatus caused to receive at least one of the following:full values for the strict subset of the constellation point probabilities;delta or difference values for the strict subset of the constellation point probabilities indicating a difference of constellation point probabilities with respect to a reference or previous constellation; orone or more parameters of a known or agreed upon probability distribution of the strict subset of the constellation point probabilities.

18. The apparatus of any of claims 12-17, wherein the apparatus caused to receive the probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities comprises the apparatus caused to transmit at least one of the following:quantized constellation point probabilities for the strict subset of the constellation point probabilities; orfloating point constellation point probabilities for the strict subset of the constellation point probabilities.

19. The apparatus of any of claims 1-18, wherein:the first node comprises a user equipment (UE), and the second node comprises a network node or gNB; orthe second node comprises a user equipment (UE), and the first node comprises a network node or gNB.

20. A method comprising:determining, by a first node of a wireless network, constellation point probabilities for a plurality of constellation points of a probabilistic shaped constellation;determining a symmetry property for the probabilistic shaped constellation;determining a strict subset of the constellation point probabilities based on the symmetry property;transmitting, by the first node to a second node of the wireless network, probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities; andtransmitting and / or receiving, by the first node, a signal based on the probabilistic shaped constellation.

21. The method of claim 20, further comprising:transmitting, by the first node to the second node, probabilistic shaped constellation symmetry information indicative of the symmetry property for the probabilistic shaped constellation.

22. The method of any of claims 20-21, further comprising:determining, by the first node, channel measurement information of a channel; anddetermining, by the first node, the symmetry property based on the channel measurement information.

23. A method comprising:determining, by a second node of a wireless network, a symmetry property for a probabilistic shaped constellation, wherein the probabilistic shaped constellation includes constellation point probabilities for a plurality of constellation points;receiving, by the second node from a first node of the wireless network, probabilistic shaped constellation information indicative of a strict subset of the constellation point probabilities;determining, by the second node based on the symmetry property and the probabilistic shaped constellation information indicative of the strict subset of the constellation point probabilities, the probabilistic shaped constellation including the plurality of constellation point probabilities; andtransmitting and / or receiving, by the second node, a signal based on the probabilistic shaped constellation.

24. The method of claim 23, wherein the strict subset of the constellation point probabilities indicate only a portion and less than all of the constellation point probabilities of the probabilistic shaped constellation,and wherein the determining the probabilistic shaped constellation including the plurality of constellation point probabilities comprises determining, by the second node, based on the symmetry property and the strict subset of the constellation point probabilities, a remaining portion of the constellation point probabilities of the probabilistic shaped constellation, such that all constellation point probabilities of the probabilistic shaped constellation are known by the second node.

Images