WO2022187139A1 - Ric-based machine learning methods for beam compression - Google Patents

Abstract

An apparatus and system for using a machine learning model for uplink beam compression are described. The model determines an excess number of streams for a UE for a target PUSCH decoding error rate. The model is trained in a near-real time (RT) radio access network (RAN) Intelligent Controller (RIC) using a decoding error observed from physical uplink shared channel (PUSCH) cyclic redundancy code (CRC) decoding of PUSCH data from the UE, in addition to the beamforming method and number of excess streams. The model is deployed in a non-RT RIC and the parameters of the deployed model is periodically updated by the near-RT RIC. Input parameters to the deployed model for the UE are provided from a distributed unit, and the output beamforming parameters provided from the deployed model to the distributed unit to provide uplink beam compression.

Description

RIC-BASED MACHINE LEARNING METHODS FOR BEAM COMPRESSION

PRIORITY CLAIM

[0001] This application claims the benefit of priority to United States Provisional Patent Application Serial No. 63/155,245, filed March 1, 2021, which is incorporated herein by reference in its entirety.

TECHNICAL FIELD

[0002] Embodiments pertain to next generation (NG) wireless communications. In particular, some embodiments relate to beam compression in NG networks.

BACKGROUND

[0003] The use and complexity of new radio (NR) wireless systems, which include 5^th generation (5G) networks and are starting to include sixth generation (6G) networks among others, has increased due to both an increase in the types of devices UEs using network resources as well as the amount of data and bandwidth being used by various applications, such as video streaming, operating on these UEs. With the vast increase in number and diversity of communication devices, the corresponding network environment, including routers, switches, bridges, gateways, firewalls, and load balancers, has become increasingly complicated. As expected, a number of issues abound with the advent of any new technology.

BRIEF DESCRIPTION OF THE FIGURES

[0004] In the figures, which are not necessarily drawn to scale, like numerals may describe similar components in different views. Like numerals having different letter suffixes may represent different instances of similar components. The figures illustrate generally, by way of example, but not by way of limitation, various embodiments discussed in the present document. [0005] FIG. 1 A illustrates an architecture of a network, in accordance with some aspects.

[0006] FIG. 1 B illustrates a non-roaming 5G system architecture in accordance with some aspects.

[0007] FIG. 1C illustrates a non-roaming 5G system architecture in accordance with some aspects.

[0008] FIG. 2 illustrates a block diagram of a communication device in accordance with some embodiments.

[0009] FIG. 3 illustrates an Open Radio Access Network (O-RAN) system architecture in accordance with some aspects.

[0010] FIG. 4 illustrates a logical architecture of the O-RAN system of FIG. 3 in accordance with some aspects.

[0011] FIG. 5 illustrates interfaces used for machine language (ML) training and inference in accordance with some aspects.

[0012] FIG. 6 illustrates an ML training process in accordance with some embodiments.

[0013] FIG. 7 illustrates ML model use in accordance with some embodiments.

DETAILED DESCRIPTION

[0014] The following description and the drawings sufficiently illustrate specific embodiments to enable those skilled in the art to practice them. Other embodiments may incorporate structural, logical, electrical, process, and other changes. Portions and features of some embodiments may be included in, or substituted for, those of other embodiments. Embodiments set forth in the claims encompass all available equivalents of those claims.

[0015] FIG. 1 A illustrates an architecture of a network in accordance with some aspects. The network 140 A includes 3 GPP LTE/4G and NG network functions that may be extended to 6G functions. Accordingly, although 5G will be referred to, it is to be understood that this is to extend as able to 6G structures, systems, and functions. A network function can be implemented as a discrete network element on a dedicated hardware, as a software instance running on dedicated hardware, and/or as a virtualized function instantiated on an appropriate platform, e.g., dedicated hardware or a cloud infrastructure.

[0016] The network 140 A is shown to include user equipment (UE) 101 and UE 102. The UEs 101 and 102 are illustrated as smartphones (e.g., handheld touchscreen mobile computing devices connectable to one or more cellular networks) but may also include any mobile or non-mobile computing device, such as portable (laptop) or desktop computers, wireless handsets, drones, or any other computing device including a wired and/or wireless communications interface. The UEs 101 and 102 can be collectively referred to herein as UE 101, and UE 101 can be used to perform one or more of the techniques disclosed herein.

[0017] Any of the radio links described herein (e.g., as used in the network 140 A or any other illustrated network) may operate according to any exemplary radio communication technology and/or standard. Any spectrum management scheme including, for example, dedicated licensed spectrum, unlicensed spectrum, (licensed) shared spectrum (such as Licensed Shared Access (LSA) in 2.3-2.4 GHz, 3.4-3.6 GHz, 3.6-3.8 GHz, and other frequencies and Spectrum Access System (SAS) in 3.55-3.7 GHz and other frequencies). Different Single Carrier or Orthogonal Frequency Domain Multiplexing (OFDM) modes (CP-OFDM, SC-FDMA, SC-OFDM, filter bank-based multicarrier (FBMC), OFDMA, etc.), and in particular 3GPP NR, may be used by allocating the OFDM carrier data bit vectors to the corresponding symbol resources.

[0018] In some aspects, any of the UEs 101 and 102 can comprise an Intemet-of-Things (loT) UE or a Cellular loT (CIoT) UE, which can comprise a network access layer designed for low-power loT applications utilizing short- lived UE connections. In some aspects, any of the UEs 101 and 102 can include a narrowband (NB) loT UE (e.g., such as an enhanced NB-IoT (eNB-IoT) UE and Further Enhanced (FeNB-IoT) UE). An loT UE can utilize technologies such as machine-to-machine (M2M) or machine-type communications (MTC) for exchanging data with an MTC server or device via a public land mobile network (PLMN), Proximity-Based Service (ProSe) or device-to-device (D2D) communication, sensor networks, or loT networks. The M2M or MTC exchange of data may be a machine-initiated exchange of data. An loT network includes interconnecting loT UEs, which may include uniquely identifiable embedded computing devices (within the Internet infrastructure), with short-lived connections. The loT UEs may execute background applications (e.g., keep- alive messages, status updates, etc.) to facilitate the connections of the loT network. In some aspects, any of the UEs 101 and 102 can include enhanced MTC (eMTC) UEs or further enhanced MTC (FeMTC) UEs.

[0019] The UEs 101 and 102 may be configured to connect, e.g., communicatively couple, with a radio access network (RAN) 110. The RAN 110 may be, for example, an Evolved Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access Network (E-UTRAN), a NextGen RAN (NG RAN), or some other type of RAN.

[0020] The UEs 101 and 102 utilize connections 103 and 104, respectively, each of which comprises a physical communications interface or layer (discussed in further detail below); in this example, the connections 103 and 104 are illustrated as an air interface to enable communicative coupling, and can be consistent with cellular communications protocols, such as a Global System for Mobile Communications (GSM) protocol, a code-division multiple access (CDMA) network protocol, a Push-to-Talk (PTT) protocol, a PTT over Cellular (POC) protocol, a Universal Mobile Telecommunications System (UMTS) protocol, a 3GPP Long Term Evolution (LTE) protocol, a 5G protocol, a 6G protocol, and the like.

[0021] In an aspect, the UEs 101 and 102 may further directly exchange communication data via a ProSe interface 105. The ProSe interface 105 may alternatively be referred to as a sidelink (SL) interface comprising one or more logical channels, including but not limited to a Physical Sidelink Control Channel (PSCCH), a Physical Sidelink Shared Channel (PSSCH), a Physical Sidelink Discovery Channel (PSDCH), a Physical Sidelink Broadcast Channel (PSBCH), and a Physical Sidelink Feedback Channel (PSFCH).

[0022] The UE 102 is shown to be configured to access an access point (AP) 106 via connection 107. The connection 107 can comprise a local wireless connection, such as, for example, a connection consistent with any IEEE 802.11 protocol, according to which the AP 106 can comprise a wireless fidelity (WiFi®) router. In this example, the AP 106 is shown to be connected to the Internet without connecting to the core network of the wireless system (described in further detail below).

[0023] The RAN 110 can include one or more access nodes that enable the connections 103 and 104. These access nodes (ANs) can be referred to as base stations (BSs), NodeBs, evolved NodeBs (eNBs), Next Generation NodeBs (gNBs), RAN nodes, and the like, and can comprise ground stations (e.g., terrestrial access points) or satellite stations providing coverage within a geographic area (e.g., a cell). In some aspects, the communication nodes 111 and 112 can be transmi ssion/reception points (TRPs). In instances when the communication nodes 111 and 112 are NodeBs (e.g., eNBs or gNBs), one or more TRPs can function within the communication cell of the NodeBs. The

RAN 110 may include one or more RAN nodes for providing macrocells, e.g., macro RAN node 111, and one or more RAN nodes for providing femtocells or picocells (e.g., cells having smaller coverage areas, smaller user capacity, or higher bandwidth compared to macrocells), e.g., low power (LP) RAN node 112. [0024] Any of the RAN nodes 111 and 112 can terminate the air interface protocol and can be the first point of contact for the UEs 101 and 102. In some aspects, any of the RAN nodes 111 and 112 can fulfill various logical functions for the RAN 110 including, but not limited to, radio network controller (RNC) functions such as radio bearer management, uplink and downlink dynamic radio resource management and data packet scheduling, and mobility management. In an example, any of the nodes 111 and/or 112 can be a gNB, an eNB, or another type of RAN node.

[0025] The RAN 110 is shown to be communicatively coupled to a core network (CN) 120 via an SI interface 113. In aspects, the CN 120 may be an evolved packet core (EPC) network, a NextGen Packet Core (NPC) network, or some other type of CN (e.g., as illustrated in reference to FIGS. 1B-1C). In this aspect, the SI interface 113 is split into two parts: the Sl-U interface 114, which carries traffic data between the RAN nodes 111 and 112 and the serving gateway (S-GW) 122, and the SI -mobility management entity (MME) interface 115, which is a signaling interface between the RAN nodes 111 and 112 and MMEs 121. [0026] In this aspect, the CN 120 comprises the MMEs 121, the S-GW 122, the Packet Data Network (PDN) Gateway (P-GW) 123, and a home subscriber server (HSS) 124. The MMEs 121 may be similar in function to the control plane of legacy Serving General Packet Radio Service (GPRS) Support Nodes (SGSN). The MMEs 121 may manage mobility aspects in access such as gateway selection and tracking area list management. The HSS 124 may comprise a database for network users, including subscription-related information to support the network entities' handling of communication sessions. The CN 120 may comprise one or several HSSs 124, depending on the number of mobile subscribers, on the capacity of the equipment, on the organization of the network, etc. For example, the HSS 124 can provide support for routing/roaming, authentication, authorization, naming/addressing resolution, location dependencies, etc.

[0027] The S-GW 122 may terminate the SI interface 113 towards the RAN 110, and routes data packets between the RAN 110 and the CN 120. In addition, the S-GW 122 may be a local mobility anchor point for inter-RAN node handovers and also may provide an anchor for inter-3GPP mobility. Other responsibilities of the S-GW 122 may include a lawful intercept, charging, and some policy enforcement.

[0028] The P-GW 123 may terminate an SGi interface toward a PDN. The P-GW 123 may route data packets between the CN 120 and external networks such as a network including the application server 184 (alternatively referred to as application function (AF)) via an Internet Protocol (IP) interface 125. The P-GW 123 can also communicate data to other external networks

131 A, which can include the Internet, IP multimedia subsystem (IPS) network, and other networks. Generally, the application server 184 may be an element offering applications that use IP bearer resources with the core network (e.g., UMTS Packet Services (PS) domain, LTE PS data services, etc.). In this aspect, the P-GW 123 is shown to be communicatively coupled to an application server 184 via an IP interface 125. The application server 184 can also be configured to support one or more communication services (e.g., Voice-over-Internet Protocol (VoIP) sessions, PTT sessions, group communication sessions, social networking services, etc.) for the UEs 101 and 102 via the CN 120. [0029] The P-GW 123 may further be a node for policy enforcement and charging data collection. Policy and Charging Rules Function (PCRF) 126 is the policy and charging control element of the CN 120. In a non-roaming scenario, in some aspects, there may be a single PCRF in the Home Public Land Mobile Network (HPLMN) associated with a UE's Internet Protocol Connectivity Access Network (IP-CAN) session. In a roaming scenario with a local breakout of traffic, there may be two PCRFs associated with a UE's IP-CAN session: a Home PCRF (H-PCRF) within an HPLMN and a Visited PCRF (V-PCRF) within a Visited Public Land Mobile Network (VPLMN). The PCRF 126 may be communicatively coupled to the application server 184 via the P-GW 123.

[0030] In some aspects, the communication network 140 A can be an loT network or a 5G or 6G network, including 5G new radio network using communications in the licensed (5GNR) and the unlicensed (5GNR-U) spectrum. One of the current enablers of loT is the narrowband-IoT (NB-IoT). Operation in the unlicensed spectrum may include dual connectivity (DC) operation and the standalone LTE system in the unlicensed spectrum, according to which LTE-based technology solely operates in unlicensed spectrum without the use of an “anchor” in the licensed spectrum, called MulteFire. Further enhanced operation of LTE systems in the licensed as well as unlicensed spectrum is expected in future releases and 5G systems. Such enhanced operations can include techniques for sidelink resource allocation and UE processing behaviors for NR sidelink V2X communications.

[0031] An NG system architecture (or 6G system architecture) can include the RAN 110 and a 5G core network (5GC) 120. The NG-RAN 110 can include a plurality of nodes, such as gNBs and NG-eNBs. The CN 120 (e.g., a 5G core network/SGC) can include an access and mobility function (AMF) and/or a user plane function (UPF). The AMF and the UPF can be communicatively coupled to the gNBs and the NG-eNBs via NG interfaces. More specifically, in some aspects, the gNBs and the NG-eNBs can be connected to the AMF by NG-C interfaces, and to the UPF by NG-U interfaces. The gNBs and the NG-eNBs can be coupled to each other via Xn interfaces. [0032] In some aspects, the NG system architecture can use reference points between various nodes. In some aspects, each of the gNBs and the NG- eNBs can be implemented as a base station, a mobile edge server, a small cell, a home eNB, and so forth. In some aspects, a gNB can be a master node (MN) and NG-eNB can be a secondary node (SN) in a 5G architecture.

[0033] FIG. 1B illustrates a non-roaming 5G system architecture in accordance with some aspects. In particular, FIG. 1B illustrates a 5G system architecture 140B in a reference point representation, which may be extended to a 6G system architecture. More specifically, UE 102 can be in communication with RAN 110 as well as one or more other 5GC network entities. The 5G system architecture 140B includes a plurality of network functions (NFs), such as an AMF 132, session management function (SMF) 136, policy control function (PCF) 148, application function (AF) 150, UPF 134, network slice selection function (NSSF) 142, authentication server function (AUSF) 144, and unified data management (UDM)/home subscriber server (HSS) 146.

[0034] The UPF 134 can provide a connection to a data network (DN) 152, which can include, for example, operator services, Internet access, or third- party services. The AMF 132 can be used to manage access control and mobility and can also include network slice selection functionality. The AMF 132 may provide UE-based authentication, authorization, mobility management, etc., and may be independent of the access technologies. The SMF 136 can be configured to set up and manage various sessions according to network policy. The SMF 136 may thus be responsible for session management and allocation of IP addresses to UEs. The SMF 136 may also select and control the UPF 134 for data transfer. The SMF 136 may be associated with a single session of a UE 101 or multiple sessions of the UE 101. This is to say that the UE 101 may have multiple 5G sessions. Different SMFs may be allocated to each session. The use of different SMFs may permit each session to be individually managed. As a consequence, the functionalities of each session may be independent of each other.

[0035] The UPF 134 can be deployed in one or more configurations according to the desired service type and may be connected with a data network. The PCF 148 can be configured to provide a policy framework using network slicing, mobility management, and roaming (similar to PCRF in a 4G communication system). The UDM can be configured to store subscriber profiles and data (similar to an HSS in a 4G communication system).

[0036] The AF 150 may provide information on the packet flow to the PCF 148 responsible for policy control to support a desired QoS. The PCF 148 may set mobility and session management policies for the UE 101. To this end, the PCF 148 may use the packet flow information to determine the appropriate policies for proper operation of the AMF 132 and SMF 136. The AUSF 144 may store data for UE authentication.

[0037] In some aspects, the 5G system architecture 140B includes an IP multimedia subsystem (IMS) 168B as well as a plurality of IP multimedia core network subsystem entities, such as call session control functions (CSCFs). More specifically, the IMS 168B includes a CSCF, which can act as a proxy CSCF (P-CSCF) 162BE, a serving CSCF (S-CSCF) 164B, an emergency CSCF (E-CSCF) (not illustrated in FIG. 1B), or interrogating CSCF (I-CSCF) 166B. The P-CSCF 162B can be configured to be the first contact point for the UE 102 within the IM subsystem (IMS) 168B. The S-CSCF 164B can be configured to handle the session states in the network, and the E-CSCF can be configured to handle certain aspects of emergency sessions such as routing an emergency request to the correct emergency center or PSAP. The I-CSCF 166B can be configured to function as the contact point within an operator's network for all IMS connections destined to a subscriber of that network operator, or a roaming subscriber currently located within that network operator's service area. In some aspects, the I-CSCF 166B can be connected to another IP multimedia network 170E, e.g. an IMS operated by a different network operator.

[0038] In some aspects, the UDM/HSS 146 can be coupled to an application server 160E, which can include a telephony application server (TAS) or another application server (AS). The AS 160B can be coupled to the IMS 168B via the S-CSCF 164B or the I-CSCF 166B.

[0039] A reference point representation shows that interaction can exist between corresponding NF services. For example, FIG. 1B illustrates the following reference points: N1 (between the UE 102 and the AMF 132), N2 (between the RAN 110 and the AMF 132), N3 (between the RAN 110 and the UPF 134), N4 (between the SMF 136 and the UPF 134), N5 (between the PCF 148 and the AF 150, not shown), N6 (between the UPF 134 and the DN 152), N7 (between the SMF 136 and the PCF 148, not shown), N8 (between the UDM 146 and the AMF 132, not shown), N9 (between two UPFs 134, not shown), N10 (between the UDM 146 and the SMF 136, not shown), N11 (between the AMF 132 and the SMF 136, not shown), N12 (between the AUSF 144 and the AMF 132, not shown), N13 (between the AUSF 144 and the UDM 146, not shown), N14 (between two AMFs 132, not shown), N15 (between the PCF 148 and the AMF 132 in case of a non-roaming scenario, or between the PCF 148 and a visited network and AMF 132 in case of a roaming scenario, not shown), N16 (between two SMFs, not shown), and N22 (between AMF 132 and NSSF 142, not shown). Other reference point representations not shown in FIG. 1B can also be used.

[0040] FIG. 1C illustrates a 5G system architecture 140C and a service- based representation. In addition to the network entities illustrated in FIG. 1 B, system architecture 140C can also include a network exposure function (NEF) 154 and a network repository function (NRF) 156. In some aspects, 5G system architectures can be service-based and interaction between network functions can be represented by corresponding point-to-point reference points Ni or as service-based interfaces.

[0041] In some aspects, as illustrated in FIG. 1C, service-based representations can be used to represent network functions within the control plane that enable other authorized network functions to access their services. In this regard, 5G system architecture 140C can include the following service-based interfaces: Namf 158H (a service-based interface exhibited by the AMF 132), Nsmf 1581 (a service-based interface exhibited by the SMF 136), Nnef 158B (a service-based interface exhibited by the NEF 154), Npcf 158D (a service-based interface exhibited by the PCF 148), aNudm 158E (a service-based interface exhibited by the UDM 146), Naf 158F (a service-based interface exhibited by the AF 150), Nnrf 158C (a service-based interface exhibited by the NRF 156), Nnssf 158A (a service-based interface exhibited by the NSSF 142), Nausf 158G (a service-based interface exhibited by the AUSF 144). Other service-based interfaces (e g., Nudr, N5g-eir, and Nudsf) not shown in FIG. 1C can also be used. [0042] NR-V2X architectures may support high-reliability low latency sidelink communications with a variety of traffic patterns, including periodic and aperiodic communications with random packet arrival time and size. Techniques disclosed herein can be used for supporting high reliability in distributed communication systems with dynamic topologies, including sidelink NR V2X communication systems.

[0043] FIG. 2 illustrates a block diagram of a communication device in accordance with some embodiments. The communication device 200 may be a UE such as a specialized computer, a personal or laptop computer (PC), a tablet PC, or a smart phone, dedicated network equipment such as an eNB, a server running software to configure the server to operate as a network device, a virtual device, or any machine capable of executing instructions (sequential or otherwise) that specify actions to be taken by that machine. For example, the communication device 200 may be implemented as one or more of the devices shown in FIGS. 1 A-1C. Note that communications described herein may be encoded before transmission by the transmitting entity (e.g., UE, gNB) for reception by the receiving entity (e.g., gNB, UE) and decoded after reception by the receiving entity.

[0044] Examples, as described herein, may include, or may operate on, logic or a number of components, modules, or mechanisms. Modules and components are tangible entities (e.g., hardware) capable of performing specified operations and may be configured or arranged in a certain manner. In an example, circuits may be arranged (e.g., internally or with respect to external entities such as other circuits) in a specified manner as a module. In an example, the whole or part of one or more computer systems (e.g., a standalone, client or server computer system) or one or more hardware processors may be configured by firmware or software (e.g., instructions, an application portion, or an application) as a module that operates to perform specified operations. In an example, the software may reside on a machine readable medium. In an example, the software, when executed by the underlying hardware of the module, causes the hardware to perform the specified operations.

[0045] Accordingly, the term “module” (and “component”) is understood to encompass a tangible entity, be that an entity that is physically constructed, specifically configured (e.g., hardwired), or temporarily (e.g., transitorily) configured (e.g., programmed) to operate in a specified manner or to perform part or all of any operation described herein. Considering examples in which modules are temporarily configured, each of the modules need not be instantiated at any one moment in time. For example, where the modules comprise a general-purpose hardware processor configured using software, the general -purpose hardware processor may be configured as respective different modules at different times. Software may accordingly configure a hardware processor, for example, to constitute a particular module at one instance of time and to constitute a different module at a different instance of time.

[0046] The communication device 200 may include a hardware processor (or equivalently processing circuitry) 202 (e.g., a central processing unit (CPU), a GPU, a hardware processor core, or any combination thereof), a main memory 204 and a static memory 206, some or all of which may communicate with each other via an interlink (e.g., bus) 208. The main memory 204 may contain any or all of removable storage and non-removable storage, volatile memory or non-volatile memory. The communication device 200 may further include a display unit 210 such as a video display, an alphanumeric input device 212 (e.g., a keyboard), and a user interface (UI) navigation device 214 (e.g., a mouse). In an example, the display unit 210, input device 212 and UI navigation device 214 may be a touch screen display. The communication device 200 may additionally include a storage device (e.g., drive unit) 216, a signal generation device 218 (e.g., a speaker), a network interface device 220, and one or more sensors, such as a global positioning system (GPS) sensor, compass, accelerometer, or other sensor. The communication device 200 may further include an output controller, such as a serial (e.g., universal serial bus (USB), parallel, or other wired or wireless (e.g., infrared (IR), near field communication (NFC), etc.) connection to communicate or control one or more peripheral devices (e.g., a printer, card reader, etc.).

[0047] The storage device 216 may include a non-transitory machine readable medium 222 (hereinafter simply referred to as machine readable medium) on which is stored one or more sets of data structures or instructions 224 (e.g., software) embodying or utilized by any one or more of the techniques or functions described herein. The instructions 224 may also reside, completely or at least partially, within the main memory 204, within static memory 206, and/or within the hardware processor 202 during execution thereof by the communication device 200. While the machine readable medium 222 is illustrated as a single medium, the term "machine readable medium" may include a single medium or multiple media (e.g., a centralized or distributed database, and/or associated caches and servers) configured to store the one or more instructions 224.

[0048] The term “machine readable medium” may include any medium that is capable of storing, encoding, or carrying instructions for execution by the communication device 200 and that cause the communication device 200 to perform any one or more of the techniques of the present disclosure, or that is capable of storing, encoding or carrying data structures used by or associated with such instructions. Non-limiting machine readable medium examples may include solid-state memories, and optical and magnetic media. Specific examples of machine readable media may include: non-volatile memory, such as semiconductor memory devices (e.g., Electrically Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM)) and flash memory devices; magnetic disks, such as internal hard disks and removable disks; magneto-optical disks; Random Access Memory (RAM); and CD-ROM and DVD-ROM disks.

[0049] The instructions 224 may further be transmitted or received over a communications network using a transmission medium 226 via the network interface device 220 utilizing any one of a number of wireless local area network (WLAN) transfer protocols (e.g., frame relay, internet protocol (IP), transmission control protocol (TCP), user datagram protocol (UDP), hypertext transfer protocol (HTTP), etc.). Example communication networks may include a local area network (LAN), a wide area network (WAN), a packet data network (e.g., the Internet), mobile telephone networks (e.g., cellular networks), Plain Old Telephone (POTS) networks, and wireless data networks. Communications over the networks may include one or more different protocols, such as Institute of Electrical and Electronics Engineers (IEEE) 802.11 family of standards known as Wi-Fi, IEEE 802.16 family of standards known as WiMax, IEEE 802.15.4 family of standards, a Long Term Evolution (LTE) family of standards, a Universal Mobile Telecommunications System (UMTS) family of standards, peer-to-peer (P2P) networks, a next generation (NG)/5^th generation (5G) standards among others. In an example, the network interface device 220 may include one or more physical jacks (e.g., Ethernet, coaxial, or phonejacks) or one or more antennas to connect to the transmission medium 226.

[0050] Note that the term “circuitry” as used herein refers to, is part of, or includes hardware components such as an electronic circuit, a logic circuit, a processor (shared, dedicated, or group) and/or memory (shared, dedicated, or group), an Application Specific Integrated Circuit (ASIC), a field-programmable device (FPD) (e.g., a field-programmable gate array (FPGA), a programmable logic device (PLD), a complex PLD (CPLD), a high-capacity PLD (HCPLD), a structured ASIC, or a programmable SoC), digital signal processors (DSPs), etc., that are configured to provide the described functionality. In some embodiments, the circuitry may execute one or more software or firmware programs to provide at least some of the described functionality. The term “circuitry” may also refer to a combination of one or more hardware elements (or a combination of circuits used in an electrical or electronic system) with the program code used to carry out the functionality of that program code. In these embodiments, the combination of hardware elements and program code may be referred to as a particular type of circuitry.

[0051] The term “processor circuitry” or “processor” as used herein thus refers to, is part of, or includes circuitry capable of sequentially and automatically carrying out a sequence of arithmetic or logical operations, or recording, storing, and/or transferring digital data. The term “processor circuitry” or “processor" may refer to one or more application processors, one or more baseband processors, a physical central processing unit (CPU), a single- or multi-core processor, and/or any other device capable of executing or otherwise operating computer-executable instructions, such as program code, software modules, and/or functional processes.

[0052] Any of the radio links described herein may operate according to any one or more of the following radio communication technologies and/or standards including but not limited to: a Global System for Mobile Communications (GSM) radio communication technology, a General Packet Radio Service (GPRS) radio communication technology, an Enhanced Data Rates for GSM Evolution (EDGE) radio communication technology, and/or a Third Generation Partnership Project (3GPP) radio communication technology, for example Universal Mobile Telecommunications System (UMTS), Freedom of Multimedia Access (FOMA), 3 GPP Long Term Evolution (LTE), 3 GPP Long Term Evolution Advanced (LTE Advanced), Code division multiple access 2000 (CDMA2000), Cellular Digital Packet Data (CDPD), Mobitex, Third Generation (3G), Circuit Switched Data (CSD), High-Speed Circuit-Switched Data (HSCSD), Universal Mobile Telecommunications System (Third Generation) (UMTS (3G)), Wideband Code Division Multiple Access (Universal Mobile Telecommunications System) (W-CDMA (UMTS)), High Speed Packet Access (HSPA), High-Speed Downlink Packet Access (HSDPA), High-Speed Uplink Packet Access (HSUPA), High Speed Packet Access Plus (HSPA+), Universal Mobile Telecommunications System-Time-Division Duplex (UMTS-TDD), Time Division-Code Division Multiple Access (TD-CDMA), Time Division- Synchronous Code Division Multiple Access (TD-CDMA), 3rd Generation Partnership Project Release 8 (Pre-4th Generation) (3 GPP Rel. 8 (Pre-4G)), 3GPP Rel. 9 (3rd Generation Partnership Project Release 9), 3GPP Rel. 10 (3rd Generation Partnership Project Release 10) , 3GPP Rel. 11 (3rd Generation Partnership Project Release 11), 3GPP Rel. 12 (3rd Generation Partnership Project Release 12), 3GPP Rel. 13 (3rd Generation Partnership Project Release 13), 3GPP Rel. 14 (3rd Generation Partnership Project Release 14), 3GPP Rel. 15 (3rd Generation Partnership Project Release 15), 3GPP Rel. 16 (3rd Generation Partnership Project Release 16), 3GPP Rel. 17 (3rd Generation Partnership Project Release 17) and subsequent Releases (such as Rel. 18, Rel. 19, etc.), 3GPP 5G, 5G, 5G New Radio (5GNR), 3GPP 5G New Radio, 3GPP LTE Extra, LTE- Advanced Pro, LTE Licensed- Assisted Access (LAA), MuLTEfire, UMTS Terrestrial Radio Access (UTRA), Evolved UMTS Terrestrial Radio Access (E-UTRA), Long Term Evolution Advanced (4th Generation) (LTE Advanced (4G)), cdmaOne (2G), Code division multiple access 2000 (Third generation) (CDMA2000 (3G)), Evolution-Data Optimized or Evolution-Data Only (EV-DO), Advanced Mobile Phone System (1st Generation) (AMPS (1G)), Total Access Communication System/Extended Total Access Communication System (TACS/ETACS), Digital AMPS (2nd Generation) (D-AMPS (2G)), Push-to-talk (PTT), Mobile Telephone System (MTS), Improved Mobile Telephone System (IMTS), Advanced Mobile Telephone System (AMTS), OLT (Norwegian for Offentlig Landmobil Telefoni, Public Land Mobile Telephony), MTD (Swedish abbreviation for Mobiltelefoni system D, or Mobile telephony system D), Public Automated Land Mobile (Autotel/PALM), ARP (Finnish for Autoradiopuhelin, "car radio phone"), NMT (Nordic Mobile Telephony), High capacity version of NTT (Nippon Telegraph and Telephone) (Hicap), Cellular Digital Packet Data (CDPD), Mobitex, DataTAC, Integrated Digital Enhanced Network (iDEN), Personal Digital Cellular (PDC), Circuit Switched Data (CSD), Personal Handy- phone System (PHS), Wideband Integrated Digital Enhanced Network (WiDEN), iBurst, Unlicensed Mobile Access (UMA), also referred to as also referred to as 3 GPP Generic Access Network, or GAN standard), Zigbee, Bluetooth(r), Wireless Gigabit Alliance (WiGig) standard, mmWave standards in general (wireless systems operating at 10-300 GHz and above such as WiGig, IEEE 802.11 ad, IEEE 802.1 lay, etc.), technologies operating above 300 GHz and THz bands, (3GPP/LTE based or IEEE 802.1 Ip or IEEE 802.11bd and other) Vehicle-to-Vehicle (V2V) and Vehicle-to-X (V2X) and Vehicle-to- Infrastructure (V2I) and Infrastructure-to- Vehicle (12 V) communication technologies, 3GPP cellular V2X, DSRC (Dedicated Short Range Communications) communication systems such as Intelligent-Transport-Systems and others (typically operating in 5850 MHz to 5925 MHz or above (typically up to 5935 MHz following change proposals in CEPT Report 71)), the European ITS-G5 system (i.e. the European flavor of IEEE 802.1 Ip based DSRC, including ITS-G5A (i.e., Operation of ITS-G5 in European ITS frequency bands dedicated to ITS for safety re-lated applications in the frequency range 5,875 GHz to 5,905 GHz), ITS-G5B (i.e., Operation in European ITS frequency bands dedicated to ITS non- safety applications in the frequency range 5,855 GHz to 5,875 GHz), ITS-G5C (i.e., Operation of ITS applications in the frequency range 5,470 GHz to 5,725 GHz)), DSRC in Japan in the 700MHz band (including 715 MHz to 725 MHz), IEEE 802.1 Ibd based systems, etc. [0053] Aspects described herein can be used in the context of any spectrum management scheme including dedicated licensed spectrum, unlicensed spectrum, license exempt spectrum, (licensed) shared spectrum (such as LSA = Licensed Shared Access in 2.3-2.4 GHz, 3.4-3.6 GHz, 3.6-3.8 GHz and further frequencies and SAS = Spectrum Access System / CBRS = Citizen Broadband Radio System in 3.55-3.7 GHz and further frequencies). Applicable spectrum bands include IMT (International Mobile Telecommunications) spectrum as well as other types of spectrum/bands, such as bands with national allocation (including 450 - 470 MHz, 902-928 MHz (note: allocated for example in US (FCC Part 15)), 863-868.6 MHz (note: allocated for example in European Union (ETSI EN 300220)), 915.9-929.7 MHz (note: allocated for example in Japan), 917-923.5 MHz (note: allocated for example in South Korea), 755-779 MHz and 779-787 MHz (note: allocated for example in China), 790 - 960 MHz, 1710 - 2025 MHz, 2110 - 2200 MHz, 2300 - 2400 MHz, 2.4-2.4835 GHz (note: it is an ISM band with global availability and it is used by Wi-Fi technology family (11b/g/n/ax) and also by Bluetooth), 2500 - 2690 MHz, 698-790 MHz, 610 - 790 MHz, 3400 - 3600 MHz, 3400 - 3800 MHz, 3800 - 4200 MHz, 3.55- 3.7 GHz (note: allocated for example in the US for Citizen Broadband Radio Service), 5.15-5.25 GHz and 5.25-5.35 GHz and 5.47-5.725 GHz and 5.725-5.85 GHz bands (note: allocated for example in the US (FCC part 15), consists four U-NII bands in total 500 MHz spectrum), 5.725-5.875 GHz (note: allocated for example in EU (ETSI EN 301 893)), 5.47-5.65 GHz (note: allocated for example in South Korea, 5925-7125 MHz and 5925-6425MHz band (note: under consideration in US and EU, respectively. Next generation Wi-Fi system is expected to include the 6 GHz spectrum as operating band but it is noted that, as of December 2017, Wi-Fi system is not yet allowed in this band. Regulation is expected to be finished in 2019-2020 time frame), IMT-advanced spectrum, IMT-2020 spectrum (expected to include 3600-3800 MHz, 3800 - 4200 MHz, 3.5 GHz bands, 700 MHz bands, bands within the 24.25-86 GHz range, etc.), spectrum made available under FCC's "Spectrum Frontier" 5G initiative (including 27.5 - 28.35 GHz, 29.1 - 29.25 GHz, 31 - 31.3 GHz, 37 - 38.6 GHz, 38.6 - 40 GHz, 42 - 42.5 GHz, 57 - 64 GHz, 71 - 76 GHz, 81 - 86 GHz and 92 - 94 GHz, etc), the ITS (Intelligent Transport Systems) band of 5.9 GHz (typically 5.85-5.925 GHz) and 63-64 GHz, bands currently allocated to WiGig such as WiGig Band 1 (57.24-59.40 GHz), WiGig Band 2 (59.40-61.56 GHz) and WiGig Band 3 (61.56-63.72 GHz) and WiGig Band 4 (63.72-65.88 GHz), 57- 64/66 GHz (note: this band has near-global designation for Multi-Gigabit Wireless Systems (MGWS)/WiGig . In US (FCC part 15) allocates total 14 GHz spectrum, while EU (ETSI EN 302 567 and ETSI EN 301 217-2 for fixed P2P) allocates total 9 GHz spectrum), the 70.2 GHz - 71 GHz band, any band between 65.88 GHz and 71 GHz, bands currently allocated to automotive radar applications such as 76-81 GHz, and future bands including 94-300 GHz and above. Furthermore, the scheme can be used on a secondary basis on bands such as the TV White Space bands (typically below 790 MHz) where in particular the 400 MHz and 700 MHz bands are promising candidates. Besides cellular applications, specific applications for vertical markets may be addressed such as PMSE (Program Making and Special Events), medical, health, surgery, automotive, low-latency, drones, etc. applications.

[0054] Aspects described herein can also implement a hierarchical application of the scheme is possible, e.g., by introducing a hierarchical prioritization of usage for different types of users (e.g., low/medium/high priority, etc.), based on a prioritized access to the spectrum e.g., with highest priority to tier-1 users, followed by tier-2, then tier-3, etc. users, etc.

[0055] Aspects described herein can also be applied to different Single Carrier or OFDM flavors (CP-OFDM, SC-FDMA, SC-OFDM, filter bank-based multicarrier (FBMC), OFDMA, etc.) and in particular 3GPP NR (New Radio) by allocating the OFDM carrier data bit vectors to the corresponding symbol resources.

[0056] Some of the features are defined for the network side, such as APs, eNBs, NR or gNBs - note that this term is typically used in the context of 3GPP 5G and 6G communication systems, etc. Still, a UE may take this role as well and act as an AP, eNB, or gNB; that is some or all features defined for network equipment may be implemented by a UE.

[0057] As above, UEs make use of multiple transmit (Tx) and receive

(Rx) antennas at both the transmitter and receiver to improve communication performance via multiple-input and multiple-output (MIMO) communications. Precoding is used when the same signal is emitted from each of the Tx antennas using channel state information (CSI). In this case, the signal from each Tx antenna is both phase and gain weighted such that the signal power is maximized at the receiver. Spatial multiplexing, on the other hand, splits the signal to be transmitted into multiple streams transmitted from a different Tx antenna. Both single unit MIMO (SU-MIMO), in which a single receiver is used, or multi-unit MIMO (MU-MIMO) in which a multiple transmitters and receivers are used to transmit the same signal.

[0058] In some cases, a UE may have a 64 Rx antenna that receives 64 streams. The UE may be scheduled to transmit a 1 -layer physical uplink shared channel (PUSCH), for example. In this case, it is possible that 4 streams (or 3 excess streams) may be sufficient to achieve a target PUSCH decoding error rate of 10% with proper selection of beamforming parameters. In this case only 4 out of 64 streams are needed to be transported by the fronthaul (FH) allowing a significant compression of the uplink data rate. The FH is the links between the centralized radio controllers (specifically the DU) and the radio heads/units (RU). Thus, a method is disclosed herein for predicting the link quality (PUSCH) packet error rate based on machine learning (ML) given a predetermined number of excess streams. The ML model may be trained based on the actual decoding error observed from PUSCH cyclic redundancy check (CRC) decoding with a selected beamforming method (maximal ratio combining (MRC), zero forcing (ZF), Discrete Fourier Transform (DFT)) and a predetermined number of excess streams from a past time period (or duration). This permits prediction of the excess number of streams and use of a beamforming method for such a UE or a set of UEs in a future time period.

[0059] A decentralized system architecture is shown in FIG. 3. Specifically, FIG. 3 illustrates an O-RAN system architecture in accordance with some aspects. FIG. 3 provides a high-level view of an O-RAN architecture 300. The O-RAN architecture 300 includes four O-RAN defined interfaces - namely, the A1 interface, the 01 interface, the 02 interface, and the Open Fronthaul Management (M)-plane interface - which connect the Service Management and Orchestration (SMO) framework 302 to O-RAN network functions (NFs) 304 and the O-Cloud 306. [0060] The 01 interface is an interface between orchestration & management entities (Orchestration/NMS) and O-RAN managed elements, for operation and management, by which FCAPS management, Software management, File management and other similar functions is achieved. The 02 interface is an interface between the SMO Framework and the O-Cloud. The A1 interface is an interface between Non-Real Time (RT) RAN Intelligent Controller (RIC) and Near-RT RIC to enable policy-driven guidance of Near-RT RIC applications/functions, and support AI/ML workflow.

[0061] The SMO 302 also connects with an external system 310, which provides additional configuration data to the SMO 302. FIG. 3 also illustrates that the A1 interface connects the O-RAN Non-Real Time (RT) RAN Intelligent Controller (RIC) 312 in or at the SMO 302 and the O-RAN Near-RT RIC 314 in or at the O-RAN NFs 304. The O-RAN NFs 304 can be virtualized network functions (VNFs) such as virtual machines (VMs) or containers, sitting above the O-Cloud 306 and/or Physical Network Functions (PNFs) utilizing customized hardware. All O-RAN NFs 304 are expected to support the 01 interface when interfacing with the SMO framework 302. The O-RAN NFs 304 connect to the NG-Core 308 via the NG interface (which is a 3GPP defined interface). The Open Fronthaul M-plane interface between the SMO 302 and the O-RAN Radio Unit (O-RU) 316 supports the O-RU 316 management in the O- RAN hybrid model. The Open Fronthaul M-plane interface is an optional interface to the SMO 302 that is included for backward compatibility purposes and is intended for management of the O-RU 316 in hybrid mode only. The O- RU 316 termination of the 01 interface towards the SMO 302.

[0062] FIG. 4 illustrates a logical architecture of the O-RAN system of FIG. 3 in accordance with some aspects. FIG. 4 shows an O-RAN logical architecture 400 corresponding to the O-RAN architecture 300 of FIG. 3. In FIG. 4, the SMO 402 corresponds to the SMO 302, O-Cloud 406 corresponds to the O-Cloud 306, the Non-RT RIC 412 corresponds to the Non-RT RIC 312, the Near-RT RIC 414 corresponds to the Near-RT RIC 314, and the O-RU 416 corresponds to the O-RU 316 of FIG. 3, respectively. The O-RAN logical architecture 400 includes a radio portion and a management portion. [0063] The management portion/ side of the architectures 400 includes the SMO Framework 402 containing the Non-RT RIC 412 and may include the O-Cloud 406. The O-Cloud 406 is a cloud computing platform including a collection of physical infrastructure nodes to host the relevant O-RAN functions (e.g., the Near-RT RIC 414, O-RAN Central Unit - Control Plane (O-CU-CP)

421, O-RAN Central Unit - User Plane (O-CU-UP) 422, and the O-RAN Distributed Unit (O-DU) 415), supporting software components (e g., OSs, VMMs, container runtime engines, ML engines, etc.), and appropriate management and orchestration functions.

[0064] The radio portion/side of the logical architecture 400 includes the Near-RT RIC 414, the O-RAN Distributed Unit (O-DU) 415, the O-RU 416, the O-CU-CP 421, and the O-CU-UP 422 functions. The radio portion/side of the logical architecture 400 may also include the O-e/gNB 410.

[0065] The O-DU 415 is a logical node hosting radio link control (RLC), medium access control (MAC), and higher physical (PHY) layer entities/ elements (High-PHY layers) based on a lower layer functional split. The O-RU 416 is a logical node hosting lower PHY layer entities/elements (Low-PHY layer) (e.g., Fast Fourier Transform/Inverse Fast Fourier Transform (FFT/iFFT), Physical Random Access Channel (PRACH) extraction, etc.) and RF processing elements based on a lower layer functional split. The O-CU-CP 421 is a logical node hosting the Radio Resource Control (RRC) and the control plane (CP) part of the PDCP protocol. The O-CU-UP 422 is a logical node hosting the user- plane part of the PDCP protocol and the Service Data Adaptation Protocol (SDAP) protocol.

[0066] An E2 interface terminates at a plurality of E2 nodes. The E2 nodes are logical nodes/entities that terminate the E2 interface. For NR/5G access, the E2 nodes include a RAN node, such as the O-CU-CP 421, O-CU-UP

422, O-DU 415, or any combination of elements. For E-UTRA access the E2 nodes include the O-e/gNB 410. As shown in FIG. 4, the E2 interface also connects the O-e/gNB 410 to the Near-RT RIC 414. The protocols over the E2 interface are based exclusively on CP protocols. The E2 functions are grouped into the following categories: (a) Near-RT RIC 414 services (REPORT, INSERT, CONTROL, and POLICY; and (b) Near-RT RIC 414 support functions, which include E2 Interface Management (E2 Setup, E2 Reset, Reporting of General Error Situations, etc.) and Near-RT RIC Service Update (e.g., capability exchange related to the list of E2 Node functions exposed over E2).

[0067] FIG. 4 shows the Uu interface between a UE 401 and O-e/gNB 410 as well as between the UE 401 and O-RAN components. The Uu interface is a 3GPP defined interface, which includes a complete protocol stack from LI to L3 and terminates in the NG-RAN or E-UTRAN. The O-e/gNB 410 is an LTE eNB, a 3G gNB, or ng-eNB that supports the E2 interface. The O-e/gNB 410 may be the same or similar as other RAN nodes discussed previously. The UE 401 may correspond to UEs discussed previously and/or the like. There may be multiple UEs 401 and/or multiple O-e/gNB 410, each of which may be connected to one another via respective Uu interfaces. Although not shown in FIG. 4, the O-e/gNB 410 supports O-DU 415 and O-RU 416 functions with an Open Fronthaul (OF) interface between them.

[0068] The OF interface(s) is/are between O-DU 415 and O-RU 416 functions. The OF interface(s) includes the Control User Synchronization (CUS) Plane and Management (M) Plane. FIG. 3 and FIG. 4 also show that the O-RU 416 terminates the OF M-Plane interface towards the O-DU 415 and optionally towards the SMO 402. The O-RU 416 terminates the OF CUS-Plane interface towards the O-DU 415 and the SMO 402.

[0069] The F1-c interface connects the O-CU-CP 421 with the O-DU

415. As defined by 3GPP, the F1-c interface is between the gNB-CU-CP and gNB-DU nodes. However, for purposes of O-RAN, the F1-c interface is adopted between the O-CU-CP 421 with the O-DU 415 functions while reusing the principles and protocol stack defined by 3GPP and the definition of interoperability profile specifications.

[0070] The F1 -u interface connects the O-CU-UP 422 with the O-DU

415. As defined by 3GPP, the F1-u interface is between the gNB-CU-UP and gNB-DU nodes. However, for purposes of O-RAN, the F1-u interface is adopted between the O-CU-UP 422 with the O-DU 415 functions while reusing the principles and protocol stack defined by 3 GPP and the definition of interoperability profile specifications. [0071] The NG-c interface is defined by 3GPP as an interface between the gNB-CU-CP and the AMF in the 3GC. The NG-c is also referred to as the N2 interface. The NG-u interface is defined by 3GPP, as an interface between the gNB-CU-UP and the UPF in the 3GC. The NG-u interface is referred to as the N3 interface. In O-RAN, NG-c and NG-u protocol stacks defined by 3 GPP are reused and may be adapted for O-RAN purposes.

[0072] The X2-c interface is defined in 3GPP for transmitting control plane information between eNBs or between eNB and en-gNB in EN-DC. The X2-u interface is defined in 3GPP for transmitting user plane information between eNBs or between eNB and en-gNB in EN-DC. In O-RAN, X2-c and X2-u protocol stacks defined by 3GPP are reused and may be adapted for O- RAN purposes.

[0073] The Xn-c interface is defined in 3GPP for transmitting control plane information between gNBs, ng-eNBs, or between an ng-eNB and gNB. The Xn-u interface is defined in 3 GPP for transmitting user plane information between gNBs, ng-eNBs, or between ng-eNB and gNB. In O-RAN, Xn-c and Xn-u protocol stacks defined by 3GPP are reused and may be adapted for O- RAN purposes.

[0074] The E1 interface is defined by 3GPP as being an interface between the gNB-CU-CP (e.g., gNB-CU-CP 3728) and gNB-CU-UP. In O- RAN, El protocol stacks defined by 3GPP are reused and adapted as being an interface between the O-CU-CP 421 and the O-CU-UP 422 functions.

[0075] The O-RAN Non-RT RIC 412 is a logical function within the SMO framework 302, 402 that enables non-real-time control and optimization of RAN elements and resources; AI/machine learning (ML) workflow(s) including model training, inferences, and updates; and policy-based guidance of applications/features in the Near-RT RIC 414.

[0076] The O-RAN Near-RT RIC 414 is a logical function that enables near-real-time control and optimization of RAN elements and resources via fine- grained data collection and actions over the E2 interface. The Near-RT RIC 414 may include one or more AI/ML workflows including model training, inferences, and updates. [0077] The Non-RT RIC 412 can be an ML training host to host the training of one or more ML models. ML training can be performed offline using data collected from the RIC, O-DU 415, and O-RU 416. For supervised learning, Non-RT RIC 412 is part of the SMO 402, and the ML training host and/or ML model host/actor can be part of the Non-RT RIC 412 and/or the Near- RT RIC 414. For unsupervised learning, the ML training host and ML model host/actor can be part of the Non-RT RIC 412 and/or the Near-RT RIC 414. For reinforcement learning, the ML training host and ML model host/actor may be co-located as part of the Non-RT RIC 412 and/or the Near-RT RIC 414. In some implementations, the Non-RT RIC 412 may request or trigger ML model training in the training hosts regardless of where the model is deployed and executed. ML models may be trained and not currently deployed.

[0078] In some embodiments, the Non-RT RIC 412 provides a query- able catalog for an ML designer/developer to publish/install trained ML models (e.g., executable software components). In these implementations, the Non-RT RIC 412 may provide a discovery mechanism if a particular ML model can be executed in a target ML inference host (MF), and what number and type of ML models can be executed in the MF. For example, there may be three types of ML catalogs made discoverable by the Non-RT RIC 412: a design-time catalog (e.g., residing outside the Non-RT RIC 412 and hosted by some other ML platform(s)), a training/deployment-time catalog (e.g., residing inside the Non- RT RIC 412), and a run-time catalog (e.g., residing inside the Non-RT RIC 412). The Non-RT RIC 412 supports necessary capabilities for ML model inference in support of ML assisted solutions running in the Non-RT RIC 412 or some other ML inference host. These capabilities enable executable software to be installed such as VMs, containers, etc. The Non-RT RIC 412 may also include and/or operate one or more ML engines, which are packaged software executable libraries that provide methods, routines, data types, etc., used to run ML models. The Non-RT RIC 412 may also implement policies to switch and activate ML model instances under different operating conditions.

[0079] The Non-RT RIC 412 can access feedback data (e.g., FM and PM statistics) over the 01 interface on ML model performance and perform necessary evaluations. If the ML model fails during runtime, an alarm can be generated as feedback to the Non-RT RIC 412. How well the ML model is performing in terms of prediction accuracy or other operating statistics it produces can also be sent to the Non-RT RIC 412 over 01. The Non-RT RIC 412 can also scale ML model instances running in a target MF over the 01 interface by observing resource utilization in MF. The environment where the ML model instance is running (e.g., the MF) monitors resource utilization of the running ML model. This can be done, for example, using an ORAN-SC component called ResourceMonitor in the Near-RT RIC 414 and/or in the Non- RT RIC 412, which continuously monitors resource utilization. If resources are low or fall below a certain threshold, the runtime environment in the Near-RT RIC 414 and/or the Non-RT RIC 412 provides a scaling mechanism to add more ML instances. The scaling mechanism may include a scaling factor such as a number, percentage, and/or other like data used to scale up/down the number of ML instances. ML model instances running in the target ML inference hosts may be automatically scaled by observing resource utilization in the MF. For example, the Kubernetes® (K8s) runtime environment typically provides an auto-scaling feature.

[0080] The A1 interface is between the Non-RT RIC 412 (within or outside the SMO 402) and the Near-RT RIC 414. The A1 interface supports three types of services, including a Policy Management Service, an Enrichment Information Service, and ML Model Management Service. A1 policies have the following characteristics compared to persistent configuration: A1 policies are not critical to traffic; A1 policies have temporary validity; A1 policies may handle individual UE or dynamically defined groups of UEs; A1 policies act within and take precedence over the configuration; and A1 policies are non- persistent, i.e., do not survive a restart of the Near-RT RIC.

[0081] FIG. 5 illustrates interfaces used for ML training and inference in accordance with some aspects. As shown in FIG. 5, ML training may be performed in the SMO, and, in particular, the non-RT RIC. The trained ML model may then be provided to, and implemented in, the near RT RIC. The ML model may be generated using input parameters related to a UE and may provide output parameters. This permits the high resolution/number of streams that are provided/received by the RU to be reduced for communications with a particular UE, thereby allowing information from/to the UE to be decoded without degradation.

[0082] Input parameters to the ML model

[0083] The input parameters to the ML model may include, among others, elements corresponding to a UE. The input parameters corresponding to a UE include, for example, the UE signature (e.g., the UE identity provided, for example, via RRC communications), the sounding reference signal (SRS) channel quality, the PUSCH channel quality, the PUSCH interference characteristics, an estimate of UE speed, an estimate of the number of scheduled layers for the UE and the total number of co-scheduled layers for the UE, a number of streams before beamforming compression (antenna streams in uncompressed domain), and beam compression method, beamforming parameters. These parameters can be extended to a set of co-scheduled UEs, and the same set or different sets of parameters may be used for each UE.

[0084] The SRS channel quality may be filtered over time, such as by using filtered signal-to-interference and noise ratio (SINR) on the SRS resource elements. This is to say that the weighted average of the SINR is used.

[0085] The PUSCH channel quality may include, for example, the filtered SINR estimated from the PUSCH demodulation reference signals (PUSCH-DMRS) or PUSCH data, as well as the PUSCH modulation order. [0086] The PUSCH interference characteristics may include the diagonal elements of interference covariance matrix estimated from the SRS or the diagonal elements of an interference covariance matrix estimated from the PUSCH when orthogonal beam compression is used.

[0087] The UE speed estimate may be in the form of a Doppler estimate, or a correlation estimate across time. This information can also be obtained from non-RAN based mobility information (e.g., GPS, GNSS) via the A1 interface.

[0088] The beamforming parameters may include, for example, the number of beams, the excess number of streams, and/or whether beamforming includes a UE Tx precoder. [0089] The various signals may be measured or estimated over one or more predetermined time periods. Each time period may be, for example, 10ms to 1 second.

[0090] Output parameters from the ML model

[0091] The output parameters from the ML model includes a number of elements corresponding to the UE. The output parameters may include, for example, the PUSCH quality. The PUSCH quality may be indicated by the packet error rate and/or the block error rate.

[0092] Data/narameters exchanged on the following interfaces:

[0093] Method of beamforming parameter selection for uplink beam compression

[0094] As above, predicting the excess number of streams for a UE for a target PUSCH decoding error rate is a difficult problem, where the excess number of streams is defined as the number of streams in addition to the number of layers scheduled for a UE. Thus, in the above example in which the UE is scheduled to transmit a 1 -layer PUSCH using 64 streams (64 Rx antenna), the use of only 4 streams (or 3 excess streams) may be sufficient to achieve a target PUSCH decoding error rate of 10% with proper selection of beamforming parameters - i.e., use of only 4 out of 64 streams transported by the fronthaul allows a significant compression of the uplink data-rate. This example can be extended from a single UE to a set of co-scheduled UEs.

[0095] In practice, the actual decoding error observed from PUSCH CRC decoding with each of at least one beamforming method (MRC, ZF, DPT) and a number of excess streams from at least one predetermined time period is used to train the ML model. This may permit prediction of the excess number of streams and beamforming method for such a UE or a set of UEs in a future time period. In general, the ML model training corresponds to design space exploration of a model that minimizes the error between given input data and an expected output. Accordingly, ML training can take varying durations dependent, for example, on the volume of the input data, the complexity of the ML model, and the available computing power. Thus, when input data is supplied to the ML model, the output generated may be supplied to the ML model as training feedback.

[0096] The data collection across the 01 interface for ML model training includes A1-A8 and B 1 parameters collected from one or more of the O-DU nodes over a predetermined time period. The input parameters to the deployed ML model in the near-RT RIC is provided from a O-DU node via the E2 interface. The determined beamforming parameters and type A7, A8 corresponding to a target PUSCH quality is based on the ML inference and is informed to the O-DU node from near-RT RIC.

[0097] The ML model may use, for example, an artificial neural network (ANN)-based approach in which various decision nodes are used to simulate a neural network. Each decision node may make decisions based on one or more of the parameters, with the parameters used at at least one node able to be different from the parameters used at at least one other node. The artificial intelligence (AI)/ML process may be used to adjust the number of beams used by the UE. The overall AI/ML process may include both a training mode to train the ML model in the Non RT-RIC and an inference mode to use in the RT-

RIC once the ML model is sufficiently trained. Training can be performed on one or more computing resources of the near RT RIC, which may be a server or a distributed (cloud) network. Training may occur on a first scale, the parameters of an existing ML model may be valid over a second scale that is significantly longer than the first scale (e.g., 5x, 10x, or greater), and the ML model may be valid over a third scale that is significantly longer than the second scale (e.g., 5x, 10x, or greater). For example, the first scale may be seconds or longer (e.g., the scale at which the Non RT-RIC operates), the second scale may be on the order of tens of seconds or longer, and the third scale may be on the order of several minutes or longer. Thus, if the non-RT RIC determines that the ML model is no longer valid, the non-RT RIC may update the near RT RIC with a new (trained) ML model; the non-RT RIC determines that the parameters of the ML model being used are no longer valid (but the ML model is still valid), the non-RT RIC may update the ML model in the near RT RIC with the parameters. Note that the near RT RIC operates on a scale of 10ms, while the DU operates at an OFDM time scale of a few hundred ns.

[0098] FIG. 6 illustrates an ML training process in accordance with some embodiments. The ML model (shown here as ANN 602 is a neural network in which multiple layers exist: the first (input) layer 602a, intermediate (hidden) layers 602b ... 602n-1, and the last (output) layer 602n. Each of the layers 602a... 602n in the ANN 602 contains nodes (neurons) that processes the data in the ANN 602 through a sum and transfer function. The prediction accuracy of the ANN 602 depends on the number of nodes in the hidden layers. As shown, in the process 600, the ANN 602 receives input data, which is processed through the layers 602a... 602n, before an output is generated and fed back as training feedback to the ANN 602 for further changes to the parameters of the ANN 602. [0099] In some embodiments, training may be based on a comparison between the error observed during PUSCH CRC decoding with a specific beamforming method and the number of excess streams during a predetermined time period. In other embodiments, UL signals other than the PUSCH may be used. The UE may be instructed to alter beamforming methods and training may occur for each beamforming method once implemented by the UE. The time period may be the same as or different for the different beamforming methods. [00100] After the ANN 602 is trained (and the accuracy is determined to be acceptable) in the non-RT RIC, the ANN may be transferred to the near RT RIC. Alternatively, the parameters of the trained ANN may be sent to the near RT RIC to update the parameters used in an existing ANN. The non-RT RIC may continue to update the ANN based on continued or intermittent training (e.g., using PUSCH CRC decoding error rate) and supply the near RT RIC with the updated parameters. In some embodiments, the ANN may be a model that is initially generalized.

[00101] FIG. 7 illustrates ML model use in accordance with some embodiments. In the process 700, input data (e.g., the PUSCH CRC decoding error rate) is fed to the ANN which is trained and then deployed. The output of the ANN is monitored, and the performance of the ANN is analyzed to update the data used to train the ANN. The updated data is then used to adjust the ANN. ML models are used rather than using standard signal models to permit adaptation to the antenna environment, which can change over time.

[00102] As above, the ML model receives input data, such as that provided above, from the UE. The data (e.g., averaged over time) is used by the non-RT RIC to determine whether the ML model being used by the near RT RIC remains valid as well as whether the parameters of each ML model are to be updated. The updates of the parameters/replacement of the ML model may occur periodically and/or in response to predetermined events (e.g., a determination that the ML model has failed, or that the parameters of the current ML model are to be adjusted by more than a threshold amount). In some embodiments, the ML model output (e.g., PER information) determined using the ML model for the UE is transmitted to the DU for UL/DL communication with the UE. The DU then generates a beamforming matrix that is valid for a particular time period and sends the beamforming information for the RU to compress/combine the number of streams. In some embodiments, the excess streams (the minimum over the number of MIMO layers) that would otherwise have been used for communication between the RU and UE may be used for communication between the RU and multiple UEs scheduled simultaneously to use the full number of streams.

[00103] Although an embodiment has been described with reference to specific example embodiments, it will be evident that various modifications and changes may be made to these embodiments without departing from the broader scope of the present disclosure. Accordingly, the specification and drawings are to be regarded in an illustrative rather than a restrictive sense. The accompanying drawings that form a part hereof show, by way of illustration, and not of limitation, specific embodiments in which the subject matter may be practiced. The embodiments illustrated are described in sufficient detail to enable those skilled in the art to practice the teachings disclosed herein. Other embodiments may be utilized and derived therefrom, such that structural and logical substitutions and changes may be made without departing from the scope of this disclosure. This Detailed Description, therefore, is not to be taken in a limiting sense, and the scope of various embodiments is defined only by the appended claims, along with the full range of equivalents to which such claims are entitled.

[00104] The subject matter may be referred to herein, individually and/or collectively, by the term “embodiment” merely for convenience and without intending to voluntarily limit the scope of this application to any single inventive concept if more than one is in fact disclosed. Thus, although specific embodiments have been illustrated and described herein, it should be appreciated that any arrangement calculated to achieve the same purpose may be substituted for the specific embodiments shown. This disclosure is intended to cover any and all adaptations or variations of various embodiments. Combinations of the above embodiments, and other embodiments not specifically described herein, will be apparent to those of skill in the art upon reviewing the above description. [00105] In this document, the terms "a" or "an" are used, as is common in patent documents, to include one or more than one, independent of any other instances or usages of "at least one" or "one or more." In this document, the term "or" is used to refer to a nonexclusive or, such that "A or B" includes "A but not B," "B but not A," and "A and B," unless otherwise indicated. In this document, the terms "including" and "in which" are used as the plain-English equivalents of the respective terms "comprising" and "wherein." Also, in the following claims, the terms "including" and "comprising" are open-ended, that is, a system, UE, article, composition, formulation, or process that includes elements in addition to those listed after such a term in a claim are still deemed to fall within the scope of that claim. Moreover, in the following claims, the terms "first," "second," and "third," etc. are used merely as labels, and are not intended to impose numerical requirements on their objects.

[00106] The Abstract of the Disclosure is provided to comply with 37 C.F.R. § 1.72(b), requiring an abstract that will allow the reader to quickly ascertain the nature of the technical disclosure. It is submitted with the understanding that it will not be used to interpret or limit the scope or meaning of the claims. In addition, in the foregoing Detailed Description, it can be seen that various features are grouped together in a single embodiment for the purpose of streamlining the disclosure. This method of disclosure is not to be interpreted as reflecting an intention that the claimed embodiments require more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive subject matter lies in less than all features of a single disclosed embodiment. Thus, the following claims are hereby incorporated into the Detailed Description, with each claim standing on its own as a separate embodiment.

Claims

CLAIMS What is claimed is:

1. An apparatus for a near-real time (RT) radio access network (RAN) Intelligent Controller (RIC), the apparatus comprising: processing circuitry configured to: decode input parameters for a user equipment (UE), the input parameters including target channel characteristics and beamforming parameters for communication with the UE; supply the input parameters to a machine learning (ML) model; obtain, from the ML model in an inference mode, output parameters based on the input parameters, the output parameters including at least one error rate of communications with the UE; and encode the output parameters for transmission to an open RAN distributed unit (O-DU) to reduce a number of beams during communication with the UE; and a memory configured to store the ML model.

2. The apparatus of claim 1, wherein the processing circuitry is further configured to periodically decode updates to parameters of the ML model from a non-RT RIC, the updates based on channel condition feedback for communications with the UE from at least one of the O-DU or a radio unit (O- RU).

3. The apparatus of claim 1, wherein the processing circuitry is further configured to decode, from a non-RT RIC, a new ML model to replace the ML model, the new ML model based on channel condition feedback for communications with the UE from at least one of the O-DU or a radio unit (O- RU).

4. The apparatus of claim 1, wherein the input parameters comprise: UE identification, channel quality information based on at least one of sounding reference signal (SRS) channel quality, physical uplink shared channel (PUSCH) channel quality, or PUSCH interference characteristics, number of scheduled layers and total number of co-scheduled layers for the UE, a number of streams before beamforming compression, and beam compression method.

5. The apparatus of claim 4, wherein the channel quality information is averaged over a predetermined time period.

6. The apparatus of claim 5, wherein at least one of: the SRS channel quality is filtered over time using filtered signal-to- interference and noise ratio (SINR) estimated from SRS resource elements, or the PUSCH channel quality is filtered over time using filtered SINR estimated from PUSCH demodulation reference signals (PUSCH-DMRS) or PUSCH data, as well as PUSCH modulation order.

7. The apparatus of claim 4, wherein the PUSCH interference characteristics include diagonal elements of an interference covariance matrix estimated from SRS or PUSCH when orthogonal beam compression is used.

8. The apparatus of claim 1, wherein the processing circuitry is further configured to use at least some of the input parameters for a set of co-scheduled UEs to reduce a number of beams during communication with each UE of the set of co-scheduled UEs.

9. The apparatus of claim 1, wherein the beamforming parameters include a number of beams for communication with the UE, an excess number of streams used for communication with the UE, and whether beamforming includes a UE transmit precoder.

10. The apparatus of claim 1, wherein the output parameters include at least one of a packet error rate or block error rate, method of beamforming compression, and beamforming parameters.

11. The apparatus of claim 1, wherein the processing circuitry is configured to decode, from a non-RT RIC, UE enrichment data, the UE enrichment data comprising:

UE mobility information of the UE, non-RAN-based location information of the UE, and performance degradation targets for the ML model.

12. The apparatus of claim 1, wherein the at least one error rate is dependent on a beamforming configuration for the UE provided to a radio unit (O-RU) from a non-RT RIC and beamforming parameters for the UE provided to the O- RU from a centralized unit (O-CU).

13. The apparatus of claim 1, wherein: parameters of the ML model are valid for a predetermined time period, and the parameters of the ML model are dependent on a decoding error observed from physical uplink shared channel (PUSCH) cyclic redundancy code (CRC) decoding of PUSCH data from the UE, a beamforming method used to communicate with the UE, and a number of excess streams determined for communication with the UE from a previous predetermined time period.

14. The apparatus of claim 13, wherein the beamforming method is selected from a group of beamforming methods that include maximal ratio combining (MRC), zero forcing (ZF), and Discrete Fourier Transform (DFT).

15. An apparatus for a non-real time (RT) radio access network (RAN) Intelligent Controller (RIC), the apparatus comprising: processing circuitry configured to: decode, from an open RAN distributed unit (O-DU), physical uplink shared channel (PUSCH) link quality information of a user equipment (UE) in communication with a radio unit (O_RU) using beamforming; train a machine learning (ML) model using the PUSCH link quality information; and encode, for transmission to a near RT RIC, parameters of the ML model after training of the ML model for uplink beam compression; and a memory configured to store the ML model.

16. The apparatus of claim 15, wherein the processing circuitry is configured to train the ML model using PUSCH link quality information that is averaged over a first time period, and encode updates of the parameters to the near RT RIC periodically using a second time period, the second time period longer than the first time period.

17. The apparatus of claim 15, wherein the processing circuitry is configured to train the ML model using input parameters that include a decoding error observed from physical uplink shared channel (PUSCH) cyclic redundancy code (CRC) decoding of PUSCH data from a user equipment (UE), a beamforming method used to communicate with the UE, and a number of excess streams determined for communication with the UE from a previous predetermined time period over which the parameters are valid.

18. The apparatus of claim 17, wherein the input parameters further include mobility information and non-RAN-based location information of the UE, and performance degradation targets for the ML model.

19. A non-transitory computer-readable storage medium that stores instructions for execution by one or more processors of a near-real time (RT) radio access network (RAN) Intelligent Controller (RIC), the one or more processors to configure the near-RT RIC to, when the instructions are executed: decode input parameters for a user equipment (UE), the input parameters including target channel characteristics and beamforming parameters for communication with the UE; supply the input parameters to a machine learning (ML) model; obtain, from the ML model in an inference mode, output parameters based on the input parameters, the output parameters including at least one error rate of communications with the UE; and encode the output parameters for transmission to an open RAN distributed unit (O-DU) to reduce a number of beams for beamforming during communication with the UE.

20. The non-transitory computer-readable storage medium of claim 19, wherein: the input parameters further include UE mobility information and non- RAN-based location information of the UE, and performance degradation targets, parameters of the ML model are valid for a predetermined time period, and the parameters of the ML model are dependent on a decoding error observed from physical uplink shared channel (PUSCH) cyclic redundancy code (CRC) decoding of PUSCH data from the UE, a beamforming method used to communicate with the UE, and a number of excess streams determined for communication with the UE from a previous predetermined time period.