Methods, architectures, devices and systems for data driven channel state information (CSI) prediction

Abstract

Processes, methods, architectures, devices, systems, apparatuses, and computer program products relating to data-driven channel state information (CSI) prediction in wireless systems are disclosed. In an embodiment, an apparatus may be configured to: receive a plurality of reference signals transmitted during a time window from a network node; determining a plurality of channel state information (CSI) associated with the plurality of reference signals based on a trained artificial intelligence (AI) model; generating a report including the plurality of CSI; and / or sending a report to the network node.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims the benefit of (i) U.S. Provisional Patent Application No. 63 / 331,286, filed on April 15, 2022, and (ii) U.S. Provisional Patent Application No. 63 / 410,779, filed on September 28, 2022, each of which is incorporated herein by reference. Background Art

[0003] The present disclosure relates generally to the fields of communications, software, and coding, including, for example, methods, architectures, devices, and systems related to data-driven channel state information (CSI) prediction in wireless systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0004] A more detailed understanding may be obtained from the following detailed description given by way of example in conjunction with the accompanying drawings. As with the detailed description, each of the figures in such drawings is an example. Therefore, the figures (figures) and detailed description should not be considered limiting, and other equally effective examples are possible and possible. In addition, the same reference numerals ("labels") in the various figures indicate the same elements, and wherein:

[0005] Figure 1A is a system diagram illustrating an example communication system;

[0006] Figure 1B It shows that it can be Figure 1A A system diagram of an example wireless transmit / receive unit (WTRU) for use within a communication system is shown;

[0007] Figure 1C It shows that it can be Figure 1A A system diagram of an example radio access network (RAN) and an example core network (CN) used within the illustrated communication system;

[0008] Figure 1D It shows that it can be Figure 1A A system diagram of yet another example RAN and yet another example CN used within the communication system shown;

[0009] Figure 2 An example of a CSI measurement setup is shown;

[0010] Figure 3 Codebook-based precoding utilizing feedback information is shown;

[0011] Figure 4 An example of a recurrent neural network (RNN) architecture is shown;

[0012] Figure 5 The signal flow for aperiodic WTRU reporting of predicted CSI samples is shown;

[0013] Figure 6 A timeline for WTRU reporting of predicted CSI samples in a single report is shown;

[0014] Figure 7 A WTRU method for reporting predicted CSI samples in a single report is shown;

[0015] Figure 8 A timeline for WTRU reporting of predicted CSI samples in a single report is shown;

[0016] Fig. 9 A WTRU method for reporting predicted CSI samples in a single report is shown;

[0017] Fig.10 The signal flow for periodic reporting of predicted CSI samples is shown;

[0018] Fig.11 Another signal flow for periodic reporting of predicted CSI samples is shown;

[0019] Fig.12 An example timeline for WTRU reporting is shown;

[0020] Fig.13 The signal flow for aperiodic reporting of predicted CSI samples is shown;

[0021] Fig.14 An example timeline of WTRU reporting for dynamically predicted CSI samples is shown;

[0022] Fig.15 A WTRU is shown reporting a CSI prediction error event;

[0023] Fig.16 An example timeline for a prediction error event is shown;

[0024] Fig.17 An example of a method for CSI prediction for a wireless system is shown; and

[0025] Fig.18 Another example of a method for CSI prediction for a wireless system is shown. DETAILED DESCRIPTION

[0026] In the following detailed description, many specific details are set forth to provide a thorough understanding of the embodiments and / or examples disclosed herein. However, it will be understood that such embodiments and examples can be practiced without some or all of the specific details set forth herein. In other cases, well-known methods, programs, components and circuits are not described in detail to avoid blurring the following description. In addition, the embodiments and examples not specifically described herein can replace the embodiments and other examples explicitly, implicitly and / or inherently described, disclosed or otherwise provided (collectively referred to as "providing") herein to practice or practice in combination with them. Although various embodiments in which equipment, systems, devices, etc. and / or any of its elements perform operations, processes, algorithms, functions, etc. and / or any part thereof are described and / or claimed herein, it should be understood that any embodiment described and / or claimed herein assumes that any equipment, systems, devices, etc. and / or any of its elements are configured to perform any operations, processes, algorithms, functions, etc. and / or any part thereof.

[0027] Example Communication System

[0028] The methods, devices, and systems provided herein are well suited for communications involving wired and wireless networks. Figures 1A to 1D An overview of various types of wireless devices and infrastructure is provided in which various elements of the network can utilize, perform, be arranged according to, and / or be adapted and / or configured for the methods, devices, and systems provided herein.

[0029] Figure 1A is a system diagram illustrating an example communication system 100 in which one or more disclosed embodiments may be implemented. The communication system 100 may be a multiple access system that provides content such as voice, data, video, messaging, broadcast, etc. to multiple wireless users. The communication system 100 may enable multiple wireless users to access such content by sharing system resources (including wireless broadband). For example, the communication system 100 may employ one or more channel access methods such as code division multiple access (CDMA), time division multiple access (TDMA), frequency division multiple access (FDMA), orthogonal FDMA (OFDMA), single carrier FDMA (SC-FDMA), zero tail (ZT) unique word (UW) discrete Fourier transform (DFT) spread OFDM (ZT UW DTS-s OFDM), unique word OFDM (UW-OFDM), resource block filtered OFDM, filter bank multi-carrier (FBMC), etc.

[0030] like Figure 1AAs shown, the communication system 100 may include wireless transmit / receive units (WTRUs) 102a, 102b, 102c, 102d, a radio access network (RAN) 104 / 113, a core network (CN) 106 / 115, a public switched telephone network (PSTN) 108, the Internet 110 and other networks 112, but it will be appreciated that the disclosed embodiments contemplate any number of WTRUs, base stations, networks, and / or network elements. Each of the WTRUs 102a, 102b, 102c, 102d may be any type of device configured to operate and / or communicate in a wireless environment. By way of example, the WTRUs 102a, 102b, 102c, 102d (any of which may be referred to as a “station” and / or “STA”) may be configured to transmit and / or receive wireless signals and may include (or be) a user equipment (UE), a mobile station, a fixed or mobile subscriber unit, a subscription-based unit, a pager, a cellular phone, a personal digital assistant (PDA), a smart phone, a laptop, a netbook, a personal computer, a wireless sensor, a hotspot or Mi-Fi device, an Internet of Things (IoT) device, a watch or other wearable device, a head-mounted display (HMD), a vehicle, a drone, medical devices and applications (e.g., remote surgery), industrial devices and applications (e.g., robots and / or other wireless devices operating in the context of an industrial and / or automated process chain), a consumer electronic device, a device operating on a commercial and / or industrial wireless network, etc. Any of the WTRUs 102a, 102b, 102c, 102d may be interchangeably referred to as a UE.

[0031] The communication system 100 may also include a base station 114a and / or a base station 114b. Each of the base stations 114a, 114b may be any type of device configured to wirelessly interface with at least one of the WTRUs 102a, 102b, 102c, 102d, for example, to facilitate access to one or more communication networks, such as the CN 106 / 115, the Internet 110, and / or the network 112. By way of example, the base stations 114a, 114b may be a base transceiver station (BTS), a Node B (NB), an eNode-B (eNB), a master Node B (HNB), a master eNode-B (HeNB), a gNode-B (gNB), a NR Node B (NR NB), a site controller, an access point (AP), a wireless router, and the like. While the base stations 114a, 114b are each depicted as a single element, it will be appreciated that the base stations 114a, 114b may include any number of interconnected base stations and / or network elements.

[0032] The base station 114a may be part of the RAN 104 / 113, which may also include other base stations and / or network elements (not shown), such as a base station controller (BSC), a radio network controller (RNC), a relay node, etc. The base station 114a and / or the base station 114b may be configured to transmit and / or receive wireless signals on one or more carrier frequencies, which may be referred to as a cell (not shown). These frequencies may be in a licensed spectrum, an unlicensed spectrum, or a combination of a licensed spectrum and an unlicensed spectrum. A cell may provide coverage of wireless services to a specific geographic area that may be relatively fixed or may vary over time. The cell may also be divided into cell sectors. For example, a cell associated with the base station 114a may be divided into three sectors. Therefore, in an embodiment, the base station 114a may include three transceivers, i.e., one for each sector of the cell. In an embodiment, the base station 114a may employ multiple-input multiple-output (MIMO) technology, and may utilize multiple transceivers for each or any sector of the cell. For example, beamforming may be used to transmit and / or receive signals in a desired spatial direction.

[0033] The base stations 114a, 114b may communicate with one or more of the WTRUs 102a, 102b, 102c, 102d over an air interface 116, which may be any suitable wireless communication link (e.g., radio frequency (RF), microwave, centimeter wave, micrometer wave, infrared (IR), ultraviolet (UV), visible light, etc.). The air interface 116 may be established using any suitable radio access technology (RAT).

[0034] More specifically, as described above, the communication system 100 may be a multiple access system and may employ one or more channel access schemes such as CDMA, TDMA, FDMA, OFDMA, SC-FDMA, etc. For example, the base station 114a in the RAN 104 / 113 and the WTRUs 102a, 102b, 102c may implement a radio technology such as Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access (UTRA) which may use Wideband CDMA (WCDMA) to establish the air interface 116. WCDMA may include communication protocols such as High Speed ​​Packet Access (HSPA) and / or Evolved HSPA (HSPA+). HSPA may include High Speed ​​Downlink Packet Access (HSDPA) and / or High Speed ​​Uplink Packet Access (HSUPA).

[0035] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement a radio technology such as Evolved UMTS Terrestrial Radio Access (E-UTRA) which may establish the air interface 116 using Long Term Evolution (LTE) and / or LTE-Advanced (LTE-A) and / or LTE-Advanced Pro (LTE-APro).

[0036] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement a radio technology such as New Radio (NR) to establish NR radio access over the air interface 116.

[0037] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement multiple radio access technologies. For example, the base station 114a and the WTRUs 102a, 102b, 102c may jointly implement LTE radio access and NR radio access, for example using dual connectivity (DC) principles. Thus, the air interface used by the WTRUs 102a, 102b, 102c may be characterized by multiple types of radio access technologies and / or transmissions sent to / from multiple types of base stations (e.g., eNBs and gNBs).

[0038] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement a radio technology such as IEEE 802.11 (i.e., Wireless Fidelity (Wi-Fi), IEEE 802.16 (i.e., Worldwide Interoperability for Microwave Access (WiMAX)), CDMA2000, CDMA2000 1X, CDMA2000 EV-DO, Interim Standard 2000 (IS-2000), Interim Standard 95 (IS-95), Interim Standard 856 (IS-856), Global System for Mobile Communications (GSM), Enhanced Data rates for GSM Evolution (EDGE), GSM EDGE (GERAN), etc.

[0039] Figure 1AThe base station 114b in the example may be, for example, a wireless router, a master Node-B, a master eNode-B, or an access point, and may utilize any suitable RAT to facilitate wireless connectivity in a local area, such as a business location, a home, a vehicle, a campus, an industrial facility, an air corridor (e.g., for use by drones), a road, and the like. In an embodiment, the base station 114b and the WTRUs 102c, 102d may implement a radio technology such as IEEE 802.11 to establish a wireless local area network (WLAN). In an embodiment, the base station 114b and the WTRUs 102c, 102d may implement a radio technology such as IEEE 802.15 to establish a wireless personal area network (WPAN). In an embodiment, the base station 114b and the WTRUs 102c, 102d may utilize a cellular-based RAT (e.g., WCDMA, CDMA2000, GSM, LTE, LTE-a, LTE-a Pro, NR, etc.) to establish any of a small cell, a pico cell, or a femto cell. As Figure 1A As shown, base station 114b may be directly connected to Internet 110. Therefore, base station 114b may not need to access Internet 110 via CN 106 / 115.

[0040] The RAN 104 / 113 may be in communication with the CN 106 / 115, which may be any type of network configured to provide voice, data, applications and / or Voice over Internet Protocol (VoIP) services to one or more of the WTRUs 102a, 102b, 102c, 102d. The data may have different quality of service (QoS) requirements, such as different throughput requirements, latency requirements, fault tolerance requirements, reliability requirements, data throughput requirements, mobility requirements, etc. The CN 106 / 115 may provide call control, billing services, mobile location-based services, prepaid calls, Internet connectivity, video distribution, etc., and / or perform high-level security functions, such as user authentication. Although Figure 1A Not shown, but it will be appreciated that the RAN 104 / 113 and / or the CN 106 / 115 may be in direct or indirect communication with other RANs that employ the same RAT or a different RAT as the RAN 104 / 113. For example, in addition to being connected to the RAN 104 / 113, which may be utilizing an NR radio technology, the CN 106 / 115 may also be in communication with another RAN (not shown) that employs any of GSM, UMTS, CDMA2000, WiMAX, E-UTRA, or Wi-Fi radio technologies.

[0041] The CN 106 / 115 may also serve as a gateway for the WTRUs 102a, 102b, 102c, 102d to access the PSTN 108, the Internet 110, and / or other networks 112. The PSTN 108 may include a circuit-switched telephone network that provides plain old telephone service (POTS). The Internet 110 may include a global system of interconnected computer networks and devices that use common communication protocols such as the Transmission Control Protocol (TCP), the User Datagram Protocol (UDP), and / or the Internet Protocol (IP) in the TCP / IP Internet protocol suite. The networks 112 may include wired and / or wireless communication networks owned and / or operated by other service providers. For example, the networks 112 may include another CN connected to one or more RANs, which may use the same RAT as the RAN 104 / 114 or a different RAT.

[0042] Some or all of the WTRUs 102a, 102b, 102c, 102d in the communication system 100 may include multi-mode capabilities (e.g., the WTRUs 102a, 102b, 102c, 102d may include multiple transceivers for communicating with different wireless networks via different wireless links). Figure 1A The illustrated WTRU 102c may be configured to communicate with the base station 114a, which may employ a cellular-based radio technology, and with the base station 114b, which may employ an IEEE 802 radio technology.

[0043] Figure 1B is a system diagram illustrating an example WTRU 102. Figure 1B As shown, the WTRU 102 may include, among other things, a processor 118, a transceiver 120, a transmit / receive element 122, a speaker / microphone 124, a keypad 126, a display / touchpad 128, non-removable memory 130, removable memory 132, a power source 134, a global positioning system (GPS) chipset 136, and / or other elements / peripherals 138. It will be appreciated that the WTRU 102 may include any sub-combination of the foregoing elements while remaining consistent with an embodiment.

[0044] The processor 118 may be a general purpose processor, a special purpose processor, a conventional processor, a digital signal processor (DSP), a plurality of microprocessors, one or more microprocessors associated with a DSP core, a controller, a microcontroller, an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) circuit, any other type of integrated circuit (IC), a state machine, etc. The processor 118 may perform signal coding, data processing, power control, input / output processing, and / or any other functionality that enables the WTRU 102 to operate in a wireless environment. The processor 118 may be coupled to the transceiver 120, which may be coupled to the transmit / receive element 122. Although Figure 1B The processor 118 and the transceiver 120 are depicted as separate components, but it will be appreciated that the processor 118 and the transceiver 120 may be integrated together, such as in an electronic package or chip.

[0045] The transmit / receive element 122 may be configured to transmit or receive signals to or from a base station (e.g., base station 114a) via an air interface 116. For example, in an embodiment, the transmit / receive element 122 may be an antenna configured to transmit and / or receive RF signals. In an embodiment, the transmit / receive element 122 may be a transmitter / detector configured to transmit and / or receive, for example, IR, UV, or visible light signals. In an embodiment, the transmit / receive element 122 may be configured to transmit and / or receive both RF signals and optical signals. It will be appreciated that the transmit / receive element 122 may be configured to transmit and / or receive any combination of wireless signals.

[0046] Although the transmit / receive element 122 is Figure 1B Although depicted as a single element in the figure, the WTRU 102 may include any number of transmit / receive elements 122. For example, the WTRU 102 may employ MIMO technology. Thus, in an embodiment, the WTRU 102 may include two or more transmit / receive elements 122 (e.g., multiple antennas) for transmitting and receiving wireless signals over the air interface 116.

[0047] The transceiver 120 may be configured to modulate signals to be transmitted by the transmit / receive element 122 and to demodulate signals received by the transmit / receive element 122. As described above, the WTRU 102 may have multi-mode capabilities. Thus, the transceiver 120 may include multiple transceivers for enabling the WTRU 102 to communicate via multiple RATs (e.g., such as NR and IEEE 802.11).

[0048] The processor 118 of the WTRU 102 may be coupled to and may receive user input data from: a speaker / microphone 124, a keypad 126, and / or a display / touchpad 128 (e.g., a liquid crystal display (LCD) display unit or an organic light emitting diode (OLED) display unit). The processor 118 may also output user data to the speaker / microphone 124, the keypad 126, and / or the display / touchpad 128. In addition, the processor 118 may access information from and store data in any type of suitable memory, such as a non-removable memory 130 and / or a removable memory 132. The non-removable memory 130 may include a random access memory (RAM), a read-only memory (ROM), a hard disk, or any other type of memory storage device. The removable memory 132 may include a subscriber identity module (SIM) card, a memory stick, a secure digital (SD) memory card, etc. In other embodiments, the processor 118 may access information from and store data in a memory that is not physically located on the WTRU 102, such as on a server or a home computer (not shown).

[0049] The processor 118 may receive power from the power source 134 and may be configured to distribute the power to and / or control power to other components in the WTRU 102. The power source 134 may be any suitable device for powering the WTRU 102. For example, the power source 134 may include one or more dry cell batteries (e.g., nickel-cadmium (NiCd), nickel-zinc (NiZn), nickel-metal hydride (NiMH), lithium-ion (Li-ion), etc.), solar cells, fuel cells, etc.

[0050] The processor 118 may also be coupled to the GPS chipset 136, which may be configured to provide location information (e.g., longitude and latitude) regarding the current location of the WTRU 102. In addition to or in lieu of the information from the GPS chipset 136, the WTRU 102 may receive location information from a base station (e.g., base stations 114a, 114b) over the air interface 116 and / or determine its location based on the timing of receiving signals from two or more nearby base stations. It will be appreciated that the WTRU 102 may acquire location information by any suitable location-determination method while remaining consistent with an embodiment.

[0051] The processor 118 may also be coupled to other components / peripherals 138, which may include one or more software and / or hardware modules / units that provide additional features, functionality, and / or wired or wireless connectivity. For example, the components / peripherals 138 may include an accelerometer, an electronic compass, a satellite transceiver, a digital camera (e.g., for photos and / or videos), a universal serial bus (USB) port, a vibration device, a television transceiver, a hands-free headset, module, a frequency modulation (FM) radio unit, a digital music player, a media player, a video game player module, an Internet browser, a virtual reality and / or augmented reality (VR / AR) device, an activity tracker, etc. Components / peripherals 138 may include one or more sensors, which may be gyroscopes, accelerometers, Hall effect sensors, magnetometers, orientation sensors, proximity sensors, temperature sensors, time sensors; geolocation sensors; altimeters, light sensors, touch sensors, magnetometers, barometers, gesture sensors, biometric sensors, and / or humidity sensors.

[0052] The WTRU 102 may include a full-duplex radio in which transmission and reception of some or all of the signals (e.g., associated with specific subframes for both uplink (e.g., for transmission) and downlink (e.g., for reception)) may be concurrent and / or simultaneous. The full-duplex radio may include an interference management unit to reduce and or substantially eliminate self-interference via hardware (e.g., choke) or signal processing via a processor (e.g., a separate processor (not shown) or via the processor 118). In an embodiment, the WTRU 102 may include a half-duplex radio in which transmission and reception of some or all of the signals (e.g., associated with specific subframes for both uplink (e.g., for transmission) or downlink (e.g., for reception)) may be concurrent and / or simultaneous.

[0053] Figure 1C 1 is a system diagram illustrating the RAN 104 and the CN 106 in accordance with an embodiment. As described above, the RAN 104 may employ an E-UTRA radio technology to communicate with the WTRUs 102a, 102b, and 102c over the air interface 116. The RAN 104 may also be in communication with the CN 106.

[0054] The RAN 104 may include eNode-Bs 160a, 160b, 160c, though it will be appreciated that the RAN 104 may include any number of eNode-Bs while remaining consistent with an embodiment. The eNode-Bs 160a, 160b, 160c may each include one or more transceivers for communicating with the WTRUs 102a, 102b, 102c over the air interface 116. In an embodiment, the eNode-Bs 160a, 160b, 160c may implement MIMO technology. Thus, for example, the eNode-B 160a may use multiple antennas to transmit wireless signals to, and receive wireless signals from, the WTRU 102a.

[0055] Each of the eNode-Bs 160a, 160b, and 160c may be associated with a particular cell (not shown) and may be configured to handle radio resource management decisions, handover decisions, user scheduling in uplink (UL) and / or downlink (DL), etc. Figure 1C As shown, eNode-Bs 160a, 160b, 160c may communicate with each other via an X2 interface.

[0056] Figure 1C The illustrated CN 106 may include a mobility management entity (MME) 162, a serving gateway (SGW) 164, and a packet data network (PDN) gateway (PGW) 166. While each of the foregoing elements is depicted as part of the CN 106, it will be appreciated that any of these elements may be owned and / or operated by an entity other than the CN operator.

[0057] The MME 162 may be connected to each of the eNode-Bs 160a, 160b, and 160c in the RAN 104 via an S1 interface and may serve as a control node. For example, the MME 162 may be responsible for authenticating users of the WTRUs 102a, 102b, 102c, bearer activation / deactivation, selecting a particular serving gateway during an initial attach of the WTRUs 102a, 102b, 102c, etc. The MME 162 may provide a control plane function for switching between the RAN 104 and other RANs (not shown) that employ other radio technologies, such as GSM and / or WCDMA.

[0058] The SGW 164 may be connected to each of the eNode Bs 160a, 160b, 160c in the RAN 104 via an S1 interface. The SGW 164 may generally route and forward user data packets to and from the WTRUs 102a, 102b, 102c. The SGW 164 may perform other functions, such as anchoring the user plane during inter-eNode-B handovers, triggering paging when DL data is available for the WTRUs 102a, 102b, 102c, managing and storing the context of the WTRUs 102a, 102b, 102c, and the like.

[0059] The SGW 164 may be connected to the PGW 166, which may provide the WTRUs 102a, 102b, 102c with access to packet-switched networks, such as the Internet 110, to facilitate communications between the WTRUs 102a, 102b, 102c and IP-enabled devices.

[0060] The CN 106 may facilitate communications with other networks. For example, the CN 106 may provide the WTRUs 102a, 102b, 102c with access to circuit-switched networks, such as the PSTN 108, to facilitate communications between the WTRUs 102a, 102b, 102c and traditional land-line communications devices. For example, the CN 106 may include or may communicate with an IP gateway (e.g., an IP Multimedia Subsystem (IMS) server) as an interface between the CN 106 and the PSTN 108. In addition, the CN 106 may provide the WTRUs 102a, 102b, 102c with access to other networks 112, which may include other wired and / or wireless networks owned and / or operated by other service providers.

[0061] Although the WTRU Figures 1A to 1D Although depicted as a wireless terminal, it is contemplated that in certain representative embodiments such a terminal may (eg, temporarily or permanently) employ a wired communications interface with a communications network.

[0062] In a representative embodiment, other network 112 may be a WLAN.

[0063] A WLAN in infrastructure basic service set (BSS) mode may have an access point (AP) for the BSS and one or more stations (STA) associated with the AP. The AP may access a distribution system (DS) or another type of wired / wireless network that loads traffic into and / or out of the BSS or has an interface thereto. Traffic originating from outside the BSS to the STA may be reached by the AP and may be delivered to the STA. Traffic from the STA to a destination outside the BSS may be sent to the AP to be delivered to the corresponding destination. Traffic between STAs within the BSS may be sent by the AP, for example, where the source STA may send traffic to the AP, and the AP may deliver the traffic to the destination STA. Traffic between STAs within the BSS may be considered and / or referred to as point-to-point traffic. Point-to-point traffic may be sent between the source STA and the destination STA using a direct link setup (DLS) (e.g., directly sent between them). In certain representative embodiments, the DLS may use 802.11e DLS or 802.11z tunnel DLS (TDLS). A WLAN using an independent BSS (IBSS) mode may not have an AP, and STAs (eg, all STAs) within or using the IBSS may communicate directly with each other. The IBSS communication mode may sometimes be referred to herein as an "ad hoc" communication mode.

[0064] When using the 802.11ac infrastructure mode of operation or a similar mode of operation, the AP can send beacons on a fixed channel, such as a primary channel. The primary channel can be a fixed width (e.g., a 20 MHz wide bandwidth) or a width dynamically set via signaling. The primary channel can be an operating channel of the BSS and can be used by STAs to establish a connection with the AP. In certain representative embodiments, carrier sense multiple access-collision avoidance (CSMA / CA) can be implemented, for example, in an 802.11 system. For CSMA / CA, STAs (e.g., each STA) including the AP can sense the primary channel. If the primary signal is sensed / detected by a particular STA and / or is determined to be busy, the particular STA can back off. One STA (e.g., only one station) can transmit in a given BSS at any given time.

[0065] A high throughput (HT) STA may communicate using a 40 MHz wide channel, for example, via a combination of a primary 20 MHz channel and adjacent or non-adjacent 20 MHz channels to form a 40 MHz wide channel.

[0066] Very high throughput (VHT) STA can support 20MHz, 40MHz, 80MHz and / or 160MHz wide channels. 40MHz and / or 80MHz channels can be formed by combining continuous 20MHz channels. A 160MHz channel can be formed by combining 8 continuous 20MHz channels, or by combining two discontinuous 80MHz channels, which can be referred to as an 80+80 configuration. For the 80+80 configuration, the data can be passed through a fragment parser after channel coding, which can divide the data into two streams. Inverse Fast Fourier Transform (IFFT) processing and time domain processing can be performed on each stream respectively. The stream can be mapped to two 80MHz channels, and the data can be transmitted by a transmitting station. At the receiver of the receiving station, the above-mentioned operation of the 80+80 configuration can be reversed, and the combined data can be sent to a media access control (MAC) layer, an entity, etc.

[0067] 802.11af and 802.11ah support operating modes below 1 GHz. The channel operating bandwidth and carrier are reduced in 802.11af and 802.11ah relative to those channel operating channels and carriers used in 802.11n and 802.11ac. 802.11af supports 5MHz, 10MHz and 20MHz bandwidths in TV white space (TVWS) spectrum, and 802.11ah supports 1MHz, 2MHz, 4MHz, 8MHz and 16MHz bandwidths using non-TVWS spectrum. According to a representative embodiment, 802.11ah can support meter type control / machine type communication (MTC), such as MTC devices in macro coverage. MTC devices may have certain capabilities, for example, limited capabilities, including support for (e.g., only support for) certain and / or limited bandwidths. MTC devices may include batteries with battery life above a threshold (e.g., to maintain very long battery life).

[0068] A WLAN system that can support multiple channels and channel bandwidths (such as 802.11n, 802.11ac, 802.11af, and 802.11ah) includes a channel that can be designated as a primary channel. The primary channel may have a bandwidth equal to the maximum common operating bandwidth supported by all STAs in the BSS. The bandwidth of the primary channel may be set and / or limited by the STA that supports the minimum bandwidth operating mode among all STAs operating in the BSS. In the example of 802.11ah, for STAs (e.g., MTC-type devices) that support (e.g., only support) a 1MHz mode, the primary channel may be 1MHz wide, even if the AP and other STAs in the BSS support 2MHz, 4MHz, 8MHz, 16MHz, and / or other channel bandwidth operating modes. Carrier sensing and / or network allocation vector (NAV) settings may depend on the state of the primary channel. If the primary channel is busy, for example, due to a STA (which only supports a 1MHz operating mode) transmitting to the AP, the entire available band may be considered busy even if most of the band remains idle and may be available.

[0069] In the United States, the available frequency band that can be used by 802.11ah is 902MHz to 928MHz. In South Korea, the available frequency band is 917.5MHz to 923.5MHz. In Japan, the available frequency band is 916.5MHz to 927.5MHz. The total bandwidth available for 802.11ah is 6MHz to 26MHz, depending on the country code.

[0070] Figure 1D1 is a system diagram showing the RAN 113 and the CN 115 according to an embodiment. As described above, the RAN 113 may employ NR radio technology to communicate with the WTRUs 102a, 102b, 102c over the air interface 116. The RAN 113 may also be in communication with the CN 115.

[0071] The RAN 113 may include gNBs 180a, 180b, 180c, though it will be appreciated that the RAN 113 may include any number of gNBs while remaining consistent with an embodiment. The gNBs 180a, 180b, 180c may each include one or more transceivers for communicating with the WTRUs 102a, 102b, 102c over the air interface 116. In an embodiment, the gNBs 180a, 180b, 180c may implement MIMO technology. For example, the gNBs 180a, 180b may utilize beamforming to transmit signals to and / or receive signals from the WTRUs 102a, 102b, 102c. Thus, for example, the gNB 180a may use multiple antennas to transmit wireless signals to and / or receive wireless signals from the WTRU 102a. In an embodiment, the gNBs 180a, 180b, 180c may implement carrier aggregation technology. For example, the gNB 180a may transmit multiple component carriers to the WTRU 102a (not shown). A subset of these component carriers may be located on an unlicensed spectrum, while the remaining component carriers may be located on a licensed spectrum. In an embodiment, the gNBs 180a, 180b, 180c may implement coordinated multi-point (CoMP) technology. For example, the WTRU 102a may receive coordinated transmissions from the gNB 180a and gNB 180b (and / or gNB 180c).

[0072] The WTRUs 102a, 102b, 102c may communicate with the gNBs 180a, 180b, 180c using transmissions associated with scalable parameter sets. For example, the OFDM symbol spacing and / or OFDM subcarrier spacing may vary for different transmissions, different cells, and / or different portions of the wireless transmission spectrum. The WTRUs 102a, 102b, 102c may communicate with the gNBs 180a, 180b, 180c using subframes or transmission time intervals (TTIs) of varying or scalable lengths (e.g., including different numbers of OFDM symbols and / or lasting different lengths of absolute time).

[0073] The gNBs 180a, 180b, 180c may be configured to communicate with the WTRUs 102a, 102b, 102c in a standalone configuration and / or a non-standalone configuration. In a standalone configuration, the WTRUs 102a, 102b, 102c may communicate with the gNBs 180a, 180b, 180c without also accessing other RANs (e.g., such as the eNode Bs 160a, 160b, 160c). In a standalone configuration, the WTRUs 102a, 102b, 102c may use one or more of the gNBs 180a, 180b, 180c as mobility anchors. In a standalone configuration, the WTRUs 102a, 102b, 102c may communicate with the gNBs 180a, 180b, 180c using signals in an unlicensed band. In a non-standalone configuration, the WTRU 102a, 102b, 102c may communicate / connect with the gNB 180a, 180b, 180c while also communicating / connecting with another RAN, such as the eNode-B 160a, 160b, 160c. For example, the WTRU 102a, 102b, 102c may implement the DC principle to communicate with one or more gNBs 180a, 180b, 180c and one or more eNode-Bs 160a, 160b, 160c substantially simultaneously. In a non-standalone configuration, the eNode-B 160a, 160b, 160c may serve as a mobility anchor for the WTRU 102a, 102b, 102c, and the gNB 180a, 180b, 180c may provide additional coverage and / or throughput to serve the WTRU 102a, 102b, 102c.

[0074] Each of the gNBs 180a, 180b, 180c may be associated with a particular cell (not shown) and may be configured to handle radio resource management decisions, handover decisions, user scheduling in UL and / or DL, support for network slicing, dual connectivity, interworking between NR and E-UTRA, routing of user plane data towards a user plane function (UPF) 184a, 184b, routing of control plane information towards an access and mobility management function (AMF) 182a, 182b, etc. Figure 1D As shown, gNBs 180a, 180b, and 180c may communicate with each other via an Xn interface.

[0075] Figure 1DThe illustrated CN 115 may include at least one AMF 182a, 182b, at least one UPF 184a, 184b, at least two session management functions (SMFs) 183a, 183b, and at least one data network (DN) 185a, 185b. Although each of the foregoing elements is depicted as part of the CN 115, it will be appreciated that any of these elements may be owned and / or operated by an entity other than the CN operator.

[0076] The AMF 182a, 182b may be connected to one or more of the gNBs 180a, 180b, 180c in the RAN 113 via the N2 interface and may serve as a control node. For example, the AMF 182a, 182b may be responsible for authenticating users of the WTRU 102a, 102b, 102c, supporting network slicing (e.g., handling different protocol data unit (PDU) sessions with different requirements), selecting a specific SMF 183a, 183b, managing registration areas, terminating NAS signaling, mobility management, etc. The AMF 182a, 182b may use network slicing, for example, to customize CN support for the WTRU 102a, 102b, 102c based on the type of service the WTRU 102a, 102b, 102c is utilizing. For example, different network slices may be established for different use cases, such as services relying on ultra-reliable low latency (URLLC) access, services relying on enhanced massive mobile broadband (eMBB) access, services for MTC access, etc. The AMF 162 may provide a control plane function for switching between the RAN 113 and other RANs (not shown) that employ other radio technologies (such as LTE, LTE-A, LTE-A Pro) and / or non-3GPP access technologies (such as Wi-Fi).

[0077] The SMF 183a, 183b may be connected to the AMF 182a, 182b in the CN 115 via the N11 interface. The SMF 183a, 183b may also be connected to the UPF 184a, 184b in the CN 115 via the N4 interface. The SMF 183a, 183b may select and control the UPF 184a, 184b, and configure the routing of traffic through the UPF 184a, 184b. The SMF 183a, 183b may perform other functions such as managing and allocating UE IP addresses, managing PDU sessions, controlling policy enforcement and QoS, providing downlink data notification, etc. The PDU session type may be IP-based, non-IP-based, Ethernet-based, etc.

[0078] The UPF 184a, 184b may be connected to one or more of the gNBs 180a, 180b, 180c in the RAN 113 via the N3 interface, which may provide the WTRUs 102a, 102b, 102c with access to packet-switched networks, such as the Internet 110, for example, to facilitate communications between the WTRUs 102a, 102b, 102c and IP-enabled devices. The UPF 184, 184b may perform other functions, such as routing and forwarding packets, enforcing user plane policies, supporting multi-homed PDU sessions, handling user plane QoS, buffering downlink packets, providing mobility anchoring, etc.

[0079] The CN 115 may facilitate communications with other networks. For example, the CN 115 may include or may communicate with an IP gateway (e.g., an IP Multimedia Subsystem (IMS) server) as an interface between the CN 115 and the PSTN 108. In addition, the CN 115 may provide the WTRUs 102a, 102b, 102c with access to other networks 112, which may include other wired and / or wireless networks owned and / or operated by other service providers. In an embodiment, the WTRUs 102a, 102b, 102c may be connected to a local data network (DN) 185a, 185b via an N3 interface to the UPF 184a, 184b and an N6 interface between the UPF 184a, 184b and the DN 185a, 185b through the UPF 184a, 184b.

[0080] Given that Figures 1A to 1D and Figures 1A to 1D 102a to 102d, base stations 114a to 114b, eNode-Bs 160a to 160c, MMEs 162, SGWs 164, PGWs 166, gNBs 180a to 180c, AMFs 182a to 182b, UPFs 184a to 184b, SMFs 183a to 183b, DNs 185a to 185b, and / or any other elements / devices described herein. A simulation device may be one or more devices configured to simulate one or more or all of the functions described herein. For example, a simulation device may be used to test other devices and / or simulate network and / or WTRU functions.

[0081] The simulation device can be designed to implement one or more tests of other devices in a laboratory environment and / or an operator network environment. For example, one or more simulation devices can perform one or more or all functions when fully or partially implemented and / or deployed as part of a wired and / or wireless communication network to test other devices within the communication network. One or more simulation devices can perform one or more or all functions when temporarily implemented / deployed as part of a wired and / or wireless communication network. The simulation device can be directly coupled to another device for testing purposes, and / or can use over-the-air wireless communication to perform testing.

[0082] One or more simulation devices can perform one or more (including all) functions when not implemented / deployed as part of a wired and / or wireless communication network. For example, the simulation device can be used for testing scenarios in a test laboratory and / or a wired and / or wireless communication network that is not deployed (e.g., testing) to implement testing of one or more components. One or more simulation devices can be test equipment. The simulation device can use direct RF coupling and / or wireless communication via RF circuits (e.g., which can include one or more antennas) to transmit and / or receive data.

[0083] Methods may be provided to reduce CSI feedback reporting overhead and / or CSI-RS overhead, for example, by using WTRU-based CSI prediction. The WTRU may predict future CSI reports based on current and / or past CSI-RS samples.

[0084] For downlink scheduling and link adaptation methods for both single-user (SU) and multi-user (MU) multiple-input multiple-output (MIMO), accurate knowledge of the channel may be used (e.g., required). This may be achieved, for example, using a DL CSI reference signal (RS) to achieve channel estimation at the WTRU and by feeding back the estimated CSI (e.g., channel quality indicator (CQI); rank indicator (RI); precoding matrix index (PMI); layer indicator (LI)) in a WTRU CSI report. Since 5G NR may support up to 64 antenna ports, there may be a large overhead associated with the DL CSI-RS reference signal and / or the corresponding UL CSI reports. This overhead may increase, for example, as the system bandwidth and number of antennas may increase in beyond fifth generation (B5G) massive MIMO systems.

[0085] CSI prediction can be used to provide CSI reports using a reduced number of CSI-RS signals; traditional (model-based) approaches to CSI prediction may include autoregressive models (AR), but these approaches may be sensitive to loss. In contrast, recent research on data-driven CSI prediction (e.g., using recurrent neural networks, RNNs) has shown promising results.

[0086] While recent research on machine learning (ML) based CSI prediction has shown promising performance of the predictor, it has not addressed how to incorporate ML based CSI prediction in the 3GPP framework to reduce overhead (CSI-RS overhead and / or CSI reporting overhead).

[0087] In the time domain, CSI-RS resources may be configured as periodic, semi-persistent, or aperiodic. Semi-persistent CSI-RS is similar to periodic CSI-RS, except that the resource may be (de)activated by a medium access control element, MAC CE; and the WTRU may report related measurements (e.g., only) when the resource is activated (e.g., when). For aperiodic CSI-RS, the WTRU may be triggered to report the measured CSI-RS on a physical uplink shared channel (PUSCH), for example, by a request in downlink control information (DCI). Periodic reports may be carried on the PUCCH, while semi-persistent reports may be carried on a physical uplink control channel (PUCCH) or PUSCH.

[0088] One or more of the following may be provided: techniques for reducing UL CSI reporting overhead, for example, by signaling predicted CSI for L (>1) time samples in a single reporting opportunity; techniques for using CSI prediction at the WTRU to reduce CSI-RS overhead; techniques for reporting prediction accuracy as a function of the look-ahead window; techniques for the WTRU to determine that retraining of the CSI prediction ML model is required.

[0089] Single report of a batch of L predicted CSIs (single UL grant)

[0090] An exemplary embodiment describes a method performed by a WTRU for reducing CSI overhead by using CSI prediction, the method comprising any of the following actions:

[0091] - The WTRU may receive a look-ahead window size request from the network.

[0092] - The WTRU may receive a signal to the network, for example, of the CSI prediction look-ahead window size “L max” used to construct historical CSI (eg, required) and the number of CSI-RS time samples N:

[0093] o The CSI prediction look-ahead window size may use (eg, depend on) a trained CSI prediction model.

[0094] o The WTRU may report the expected prediction accuracy as a function of the lookahead (for up to L_max lookahead).

[0095] - The WTRU may be configured for CSI prediction with L look-ahead window size (L <= L_max):

[0096] o The WTRU may be configured with a prediction accuracy threshold.

[0097] - The WTRU may receive, for example, N CSI-RS samples for constructing historical CSI data:

[0098] o The WTRU may report legacy CSI, for example, when building historical CSI data.

[0099] - The WTRU may employ a CSI predictor model and / or may obtain L CSI values ​​for look-ahead prediction.

[0100] -The WTRU may send a CSI prediction completion indication to the BS (e.g., eNB, gNB) and / or may request an uplink grant from the network.

[0101] -The WTRU may receive an uplink grant from the network.

[0102] - The WTRU may send L predicted CSI values ​​to the network in a single uplink grant, for example via PUCCH / PUSCH.

[0103] - In one embodiment, the WTRU may receive CSI-RS from the network to track / check the accuracy of the CSI prediction. The WTRU may not send any CSI reports, for example, until the look-ahead window size has passed:

[0104] ○ This can reduce overhead in the uplink.

[0105] ○ In one embodiment, the BS (e.g., eNB, gNB) may transmit periodic CSI-RS.

[0106] WTRU reports CSI prediction error event

[0107] The WTRU may measure the difference between the predicted CSI and the actual CSI for time slot "k" within the look-ahead window, for example, to measure the prediction accuracy. If the difference exceeds a configured threshold, the WTRU may (e.g., only) report a delta from the previously reported CSI for time slot "k" and / or may send a retraining request to a BS (e.g., eNB, gNB). An exemplary embodiment describes a method performed by a WTRU, the method comprising any of the following actions:

[0108] - The WTRU may receive CSI-RS from the network and / or may calculate the error between the predicted CSI and the true CSI.

[0109] - For example, if the prediction error is above a threshold, the WTRU may report to the network.

[0110] - For subsequent look-ahead timeslots, the WTRU may receive a request from the network to send differential CSI values:

[0111] ○ The WTRU may receive a retraining request for CSI prediction from the network:

[0112] ■ The WTRU may receive CSI-RS samples for retraining.

[0113] ■The WTRU may update the prediction model weights.

[0114] ■ For example, if the prediction error is below a threshold within the configured retraining time, the WTRU may send a completed training ACK.

[0115] ■ The WTRU may follow the procedures described in the previous embodiments.

[0116] - The WTRU may calculate the difference between the predicted CSI value and the true CSI value and / or may send the differential CSI to the network.

[0117] - The WTRU may receive data from the network, for example based on the updated CSI value.

[0118] The CSI may include any of the following: a channel quality index (CQI), a rank indicator (RI), a precoding matrix index (PMI), a layer 1 (L1) channel measurement (e.g., a reference signal received power (RSRP), such as L1 reference signal received power (L1-RSRP), or a signal-to-interference-plus-noise ratio (SINR)), a CSI-RS resource indicator (CRI), a synchronization signal (SS) / physical broadcast channel (SS / PBCH) block resource indicator (SSBRI), a layer indicator (LI), and / or any other measurement quantity measured by the WTRU based on a configured reference signal (e.g., a CSI-RS or SS / PBCH block or any other reference signal).

[0119] CSI Reporting Framework

[0120] The WTRU may be configured to report CSI, for example, via an uplink control channel on the PUCCH or as requested by the BS (e.g., eNB, gNB) for an UL PUSCH grant. Depending on the configuration, the CSI-RS may cover the full bandwidth of the bandwidth part (BWP), or only a small portion thereof. Within the CSI-RS bandwidth, the CSI-RS may be configured in every physical resource block (PRB) or every other PRB. In the time domain, the CSI-RS resources may be configured as periodic, semi-persistent, or aperiodic. Semi-persistent CSI-RS may be similar to periodic CSI-RS, except that the resources may be (de)activated by a MAC CE; and the WTRU may report related measurements (e.g., only) when the resources are activated (e.g., when). For aperiodic CSI-RS, the WTRU may be triggered to report the measured CSI-RS on the PUSCH as requested in the DCI. Periodic reports may be carried on the PUCCH, while semi-persistent reports may be carried on the PUCCH or PUSCH. The reported CSI may be used by the scheduler in allocating the best resource blocks, determining the precoding matrix, beams, transmission mode, and selecting the appropriate MCS, possibly based on the time-frequency selectivity of the channel. The reliability, accuracy, and timeliness of WTRU CSI reporting may be critical to meeting URLLC service requirements.

[0121] The WTRU may be configured with a CSI measurement setup, which may include one or more CSI reporting setups, a resource setup, and / or a link between one or more CSI reporting setups and one or more resource setups. Figure 2 Examples of CSI reporting settings, resource settings, and linked configurations are shown.

[0122] In the CSI measurement setting, one or more of the following configuration parameters may be provided:

[0123] N≥1 CSI report settings 211 , M≥1 resource settings 213 , and a CSI measurement setting 215 linking the N CSI report settings 211 with the M resource settings 213 .

[0124] The CSI reporting settings 211 may include any of the following:

[0125] ○ Temporal behavior: aperiodic or periodic / semi-persistent.

[0126] o Frequency granularity, at least for PMI and CQI.

[0127] o CSI report type (e.g., PMI, CQI, RI, CRI, etc.).

[0128] o If PMI is reported, the PMI type (Type I or II) and codebook configuration.

[0129] Resource settings 213 may include any of the following:

[0130] ○ Temporal behavior: aperiodic or periodic / semi-persistent.

[0131] o RS type (eg, for channel measurement or interference measurement).

[0132] ○S≥1 resource sets and each resource set can contain Ks resources.

[0133] The CSI measurement settings 215 may include any of the following:

[0134] ○ A CSI reporting setting.

[0135] ○A resource setting.

[0136] ○ For CQI, refer to the transmission scheme setting.

[0137] ● For CSI reporting of component carriers, any of the following frequency granularities may be supported:

[0138] ○Broadband CSI.

[0139] ○Partial-band CSI.

[0140] ○Sub-band CSI.

[0141] Codebook-based precoding

[0142] Figure 3 The basic concept of codebook based precoding using feedback information is shown. The feedback information may include a PMI which may be referred to as a codeword index in the codebook, as shown.

[0143] like Figure 3 As shown, the codebook may include a set of precoding vectors / matrices for each rank and multiple antenna ports, and each precoding vector / matrix has its own index so that the receiver can inform the transmitter of the preferred precoding vector / matrix index. Compared with non-codebook-based precoding, codebook-based precoding may experience performance degradation due to its limited number of precoding vectors / matrices. Codebook-based precoding can provide lower control signaling / feedback overhead. Table 1 below shows an example of a codebook for 2Tx.

[0144] Table 1: Tx downlink codebook

[0145]

[0146] CSI Processing Standards

[0147] A CSI processing unit (CPU) may be referred to as a minimum CSI processing unit, and a WTRU may support one or more CPUs (e.g., N CPUs). A WTRU with N CPUs may estimate N CSI feedback calculations in parallel, where N may be the WTRU capability. If the WTRU is requested to estimate more than N CSI feedbacks simultaneously, the WTRU may (e.g., only) perform the high priority N CSI feedbacks and may not estimate the remaining feedbacks.

[0148] The start and end of the CPU may be determined based on the CSI reporting type (e.g., aperiodic, periodic, semi-persistent) as follows:

[0149] ● For aperiodic CSI reporting, the CPU is occupied starting from the first OFDM symbol after the physical downlink control channel (PDCCH) trigger until the last OFDM symbol of the PUSCH carrying the CSI report.

[0150] ● For periodic and semi-persistent CSI reporting, the CPU is occupied starting from the first OFDM symbol of one or more associated measurement resources (no earlier than the CSI reference resource) until the last OFDM symbol of the CSI report.

[0151] The amount of CPU occupied may vary based on the CSI measurement type (e.g., beam-based or non-beam-based), as follows:

[0152] Non-beam related reports:

[0153] ○ When there are Ks CSI-RS resources in the CSI-RS resource set used for channel measurement, Ks CPUs.

[0154] Beam-related reports (e.g., "cri-RSRP", "ssb-Index-RSRP", or "none"):

[0155] ○ Since the CSI calculation complexity is low, it is 1 CPU regardless of the number of CSI-RS resources in the CSI-RS resource set used for channel measurement; and

[0156] ○ “None” is used for P3 operation or non-periodic Tracking Reference Signal (TRS) transmission.

[0157] ● For aperiodic CSI reporting with a single CSI-RS resource, 1 CPU is occupied.

[0158] • For reporting CSI for Ks CSI-RS resources, Ks CPUs may be occupied because the WTRU needs to perform CSI measurement for each CSI-RS resource.

[0159] When the number of unoccupied CPUs (N_u) is less than the CPUs required for CSI reporting (N_r), any of the following WTRU behaviors may be used:

[0160] • In case of uplink control information (UCI) on PUSCH without data / hybrid automatic repeat request (HARQ), the WTRU may drop N_r-N_u CSI reports based on priority.

[0161] ● In other cases, the WTRU may report dummy information in the Nr-Nu CSI report based on priority to avoid rate matching processing for PUSCH.

[0162] Artificial Intelligence (AI)

[0163] Artificial intelligence (AI) can be broadly defined as behavior exhibited by machines. Such behavior can, for example, mimic cognitive functions to perceive, reason, adapt, and act.

[0164] Machine Learning (ML)

[0165] Machine learning may refer to a type of algorithm that solves problems based on learning from experience ("data") without being explicitly programmed ("configured rule sets"). Machine learning (ML) can be considered a subset of AI. Different machine learning paradigms can be envisioned based on the nature of the data or feedback available to the learning algorithm. For example, supervised learning methods may involve learning a function that maps inputs to outputs based on labeled training examples, where each training example can be a pair consisting of an input and a corresponding output. For example, unsupervised learning methods may involve detecting patterns in data without pre-existing labels. For example, reinforcement learning methods may involve performing a series of actions in an environment to maximize cumulative rewards. In some solutions, machine learning algorithms can be applied using a combination or interpolation of the above methods. For example, semi-supervised learning methods can use a combination of a small amount of labeled data and a large amount of unlabeled data during training. In this regard, semi-supervised learning is between unsupervised learning (without labeled training data) and supervised learning (with (e.g., only) labeled training data).

[0166] Deep Learning (DL)

[0167] Deep learning refers to a class of machine learning algorithms that use artificial neural networks (specifically, deep neural networks (DNNs)) loosely inspired by biological systems. DNN is a special class of machine learning models inspired by the human brain, in which the input is linearly transformed and passed through a nonlinear activation function multiple times. DNNs are typically composed of multiple layers, each of which consists of a linear transformation and a given nonlinear activation function. DNNs can be trained using training data via a backpropagation algorithm. Recently, DNNs have shown state-of-the-art performance in a variety of fields (e.g., speech, vision, natural language, etc.) and in various machine learning settings (supervised, unsupervised, and semi-supervised). The term AIML-based method / processing can refer to achieving behavior and / or compliance with requirements by learning based on data without explicitly configuring the order of action steps. Such methods can enable learning of complex behaviors that may be difficult to specify and / or implement when using traditional methods.

[0168] CSI prediction based on AI / ML

[0169] RNN has recently become a popular method for AI / ML-based CSI forecasting due to its powerful time series forecasting capabilities. RNN is a neural network consisting of an input layer, an output layer, and one (or more) hidden layers, where the hidden layers use the memory of previous states to predict future samples.

[0170] Figure 4 An example of an RNN architecture is shown in , where the vector of hidden states can be a function of the current input and the previous RNN output, x(t) represents the vector at the RNN input at time t, and y(t) represents the RNN output vector at time t.

[0171] When RNN is used for channel / CSI prediction, the input x may consist of a sequence of N previous consecutive channel estimates (e.g., consisting of). To generate the RNN input, the estimated channel / CSI may be fed into a tapped delay line. Depending on the RNN architecture, the input sequence of N channel estimates may be converted from a matrix to a vector form. The RNN output represents the predicted channel / CSI at time t+L An example of a loss function for training an RNN is in denotes the predicted channel at time t+L, and H(t+L) denotes the desired output of the network (the actual channel at time t+L), and the operator || || F Indicates the Frobenius (Euclidean) norm. The loss function thus defined is used to train the RNN.

[0172] For downlink scheduling and link adaptation purposes for both SU-MIMO and MU-MIMO, accurate knowledge of the channel may be used (e.g., required). This may be achieved using the DL CSI-RS reference signal to enable channel estimation at the WTRU and by feeding back the estimated CSI (e.g., CQI, PMI, RI, LI) in the WTRU CSI report. Since 5G NR may support up to 64 antenna ports, there may be a large overhead associated with the DL CSI-RS reference signal and the corresponding UL CSI report. It is expected that this overhead may increase as the system bandwidth and the number of antennas may increase in B5G massive MIMO systems.

[0173] AI / ML based channel prediction methods have shown potentially promising performance. However, there is currently no mechanism in the 3GPP framework to use these to reduce CSI overhead.

[0174] One or more of the following items may be provided: technology for using AI / ML-based CSI prediction at the WTRU to reduce CSI reporting overhead; technology for using AI / ML-based CSI prediction at the WTRU to reduce CSI-RS overhead; technology for determining at the WTRU that CSI prediction ML model retraining is required; and technology for reporting CSI during online training at the WTRU.

[0175] In one or more embodiments described herein, the term CSI value or predicted CSI value or CSI report may refer to WTRU feedback, including but not limited to any of the following:

[0176] - Implicit channel state information, such as CQI, RI, PMI;

[0177] - Explicit channel state information, e.g., the channel matrix, the covariance matrix, representations of its principal components, coherence time, coherence BW, Doppler spread, or any other statistics derived from the channel matrix;

[0178] - Any other measurement quantity measured by the WTRU based on configured reference signals (e.g., CSI-RS or SS / PBCH blocks or any other reference signal), L1 channel / interference measurement (e.g., RSRP such as L1-RSRP, or SINR), CRI, SSBRI, LI, etc.

[0179] Representative AI / ML-based CSI predictions

[0180] CSI prediction capabilities based on AI / ML

[0181] The WTRU may support AI / ML based CSI prediction, for example, using a recurrent neural network (RNN) or a long short-term memory network (LSTM) AI / ML model, etc. The AI / ML CSI prediction model may use "N" consecutive historical samples of the channel response to determine the predicted CSI. Based on the accumulated CSI history information, the AI / ML CSI model may predict CSI values ​​for up to "L" future time samples (also referred to as a "look-ahead window").

[0182] The "N" historical CSI values ​​may be sampled at a time slot or at multiple (eg, more than 1) periodicities. In one embodiment, the historical CSI values ​​are sampled according to a configured periodicityAndOffset parameter.

[0183] The WTRU's AI / ML based CSI prediction capability may be reported in a radio resource control (RRC) message, for example, as part of a UECapabilityInformation message. The parameters describing the WTRU's CSI prediction capability may include any of the following:

[0184] - AI / ML model type, e.g., RNN, LSTM, etc.

[0185] -AI / ML model ID, which may indicate the model size;

[0186] - length ("N") of the CSI history buffer used for prediction (eg, required);

[0187] -Sampling period of CSI historical information / predicted CSI value;

[0188] - The maximum length of the CSI prediction window (maximum look-ahead window, LAmax); and

[0189] - Training data set information, which may include information on the characteristics of the channel model used to train the AI / ML CSI predictor (e.g., delay spread, coherence bandwidth, coherence time, Doppler, etc.).

[0190] Additionally, the WTRU CSI prediction capability may also include information about the expected prediction accuracy of samples within the (maximum) look-ahead window. For example, a measure of prediction accuracy may be the predicted CSI at time “k” (where “k” is within the look-ahead window, 1≤k≤LA max ) and the actual CSI at time “k”. Other measures of CSI prediction accuracy may include cosine similarity as described above.

[0191] CSI prediction configuration parameters based on AI / ML

[0192] A WTRU that supports CSI prediction may be configured to perform CSI prediction. The WTRU may be configured for periodic, semi-persistent, or aperiodic CSI. The configuration may include any of the following:

[0193] - A target look-ahead window "L" for CSI prediction (less than or equal to the maximum look-ahead window capability LAmax supported by the WTRU, L <LA max )

[0194] - Prediction error metric and / or prediction error threshold: For example, the WTRU may be configured to report NMSE as a prediction accuracy metric and may be configured with a prediction error threshold (eg, NMSE threshold) to detect prediction error events.

[0195] -CSI-RS configuration:

[0196] o For example, the WTRU may be configured for periodic CSI-RS

[0197] ○ In another example, the WTRU may be configured for a set of bursty CSI-RS, e.g., to enable the CSI prediction engine to build a CSI history buffer to perform prediction. If the WTRU is configured with a set of bursty CSI-RS (e.g., at this time), the CSI-RS burst information (such as start, duration, etc.) may be provided to the WTRU

[0198] - The CSI-RS configuration may include a time offset "k" within the look-ahead (prediction) window for transmitting the CSI-RS, and the WTRU may measure the prediction accuracy / prediction error.

[0199] CSI Feedback Report Configuration

[0200] A WTRU that supports CSI prediction may be configured to report CSI feedback. The CSI reporting types may be extended to include traditional CSI reporting and predicted CSI reporting as well as implicit and / or explicit CSI.

[0201] The WTRU may be configured to report predicted CSI, for example, when the prediction error is less than a configured threshold. For example, when the WTRU collects CSI history data to enable prediction, the WTRU may report traditional CSI. In one embodiment, the WTRU may report traditional CSI during retraining of the CSI prediction AI / ML model. The WTRU may indicate whether the reported CSI is traditional or predicted.

[0202] If configured, the WTRU may measure the prediction error metric at time "k" within the look-ahead window and may report it using the CSI feedback report.

[0203] Representative CSI forecasts

[0204] A single report of L predicted CSI values

[0205] WTRU procedure for calculating and reporting L predicted CSI values ​​in a single report; based on periodic CSI-RS transmission

[0206] Aperiodic reporting of L predicted CSI values:

[0207] Figure 5 The signaling process of aperiodic reporting of L predicted CSI values ​​is shown in FIG. In this option, CSI-RS can still be transmitted periodically, while CSI reporting is aperiodic, such as Figure 4 The basic principle with periodic CSI-RS transmission may be to construct an RNN buffer for historical CSI samples, which may be periodically updated using the periodic CSI-RS transmission.

[0208] According to an embodiment, the WTRU may receive a look-ahead window size request from a network (e.g., a network node) in step 501. In step 502, the WTRU may send to the network (e.g., a network node) a CSI prediction look-ahead window size L and a number of CSI-RS time samples N, for example, for constructing historical CSI (e.g., required):

[0209] o The CSI prediction look-ahead window size may use (eg, depend on) a trained CSI prediction model.

[0210] o The WTRU may report the expected prediction accuracy as a function of the lookahead (for up to L_max lookahead).

[0211] For example, if the look-ahead window size L is sufficient, the network (e.g., network node) and / or WTRU may be configured to utilize L look-ahead window size (L<=L_max) for CSI prediction in step 503. The WTRU may receive, for example, N CSI-RS samples for constructing historical CSI data. The WTRU may report legacy CSI, for example, when constructing historical CSI data.

[0212] In step 504, the WTRU, which relies on "N" historical CSI samples calculated using the CSI-RS, may employ an RNN-based CSI prediction model, where the WTRU may predict "L" CSI samples in advance. The WTRU, which predicts CSI for a look-ahead window size L (e.g., thereafter), may, for example, send an acknowledgment (ACK) to the base station (BS) indicating that the L CSI prediction samples are available. In step 505, based on the transmission requirements (e.g., other scheduled users, available resources, etc.), the BS may send an uplink grant to the WTRU for CSI reporting via downlink control information (DCI).

[0213] The WTRU may report the L predicted CSI values, for example, in a single PUSCH, after receiving an uplink grant, for example, via DCI, in step 506. This may significantly reduce the overhead in terms of the number of uplink grants used to utilize the predicted CSI values.

[0214] In step 507, the network (eg, network node) may send an ACK to the WTRU followed by data transmission using the predicted CSI of the L look-ahead time slots.

[0215] In one embodiment, the WTRU may receive a dynamic indication in a DCI of a number of predicted CSI values ​​to be sent in an aperiodic CSI report. The WTRU may be configured to send a minimum of (L, dynamically indicated in the DCI) predicted CSI values ​​in an associated aperiodic CSI report.

[0216] Periodic reporting of L predicted CSI values:

[0217] The WTRU may report L predicted CSI samples on the periodically available PUCCH after predicting the CSI using historical CSI samples for a look-ahead window size L:

[0218] - In one embodiment, when sending periodic reports on PUCCH, the WTRU may be configured to send implicit CSI values ​​(e.g., CQI, PMI, RI, etc.). This may be due to the limited capacity of PUCCH and therefore may not be desirable for larger reporting payloads (such as the full CSI matrix).

[0219] In this option, both CSI-RS and CSI reporting may be periodic.

[0220] Semi-persistent reporting of L predicted CSI values:

[0221] The WTRU may send L predicted CSI samples on periodically assigned PUCCH resources. In semi-persistent reporting, periodic reporting may be activated / deactivated by the MAC CE:

[0222] - Semi-persistent reporting can be used on periodically assigned PUCCH resources or semi-persistently assigned PUSCH:

[0223] ○ PUCCH resources can be used for implicit CSI, i.e., PMI, RI, CQI, LI.

[0224] ○ PUSCH resources can be used for explicit CSI, ie, full CSI matrix.

[0225] Figure 6An example timeline for a single (aperiodic) report of L predicted CSI samples is shown in , where periodic CSI-RS transmission is assumed.

[0226] Figure 7 An example process for reporting L predicted CSI values ​​in a single report is shown in FIG.

[0227] In step 701, the WTRU may be configured for CSI prediction (e.g., with a CSI prediction look-ahead window size L, e.g., for building a CSI history buffer (e.g., required) and a number of CSI-RS time samples N). In step 702, a counter may be initialized to a default value (e.g., "1"). In step 703, the WTRU may receive periodic CSI-RS samples, e.g., for updating the CSI history buffer in step 704. In step 705, the WTRU may determine whether the CSI history buffer is complete. If the CSI history buffer is not complete, then in step 706, the WTRU may send a conventional CSI report. If the CSI history buffer is complete, then in step 707, the counter may be incremented, e.g., with a modulation of the look-ahead window size L. If the counter is equal to zero, then in step 708, the WTRU may send the predicted CSI in a single report and the process may return to step 703. If the counter is not equal to zero, then the process may return to step 703.

[0228] In one or more embodiments, the WTRU may determine the type of predicted CSI (implicit or explicit) based on the UL resources allocated for CSI feedback. For example, when allocated / granted / configured with PUSCH resources or PUCCH resource payloads whose size is below a pre-configured threshold, the WTRU may send implicit CSI values ​​in the CSI report. For example, when allocated / granted / configured with PUSCH resources, or when the payload size of the PUCCH resources is above a pre-configured threshold, the WTRU may send explicit CSI in the report. In some solutions, the WTRU may be pre-configured (e.g., as part of the CSI reporting configuration) for the type of predicted CSI to be reported (e.g., implicit or explicit). The WTRU may determine the number of predicted CSI values ​​to be reported based on the payload size of the allocated / granted / configured PUCCH and / or PUSCH resources.

[0229] WTRU procedure for calculating and reporting L predicted CSI values ​​in a single report; Aperiodic CSI-RS transmission

[0230] To reduce overhead in both uplink and downlink, there may be no periodic CSI-RS transmission.

[0231] The WTRU may report the L CSI values ​​using any of the aforementioned methods after predicting the L CSI values ​​using the CSI prediction model, e.g., based on periodic, semi-persistent, aperiodic reporting. Since the CSI reporting is performed for L slots before the current slot, the BS may not send the CSI-RS until L slots have passed. The BS may use the L predicted CSI values ​​received from the WTRU in a single PUSCH report until the L slot window has passed.

[0232] After L time slots, the network (e.g., network node) may activate CSI-RS transmission using MAC / CE, where the WTRU estimates CSI using the received CSI-RS. The estimated CSI samples may be used to populate the historical CSI samples for CSI prediction. During this process in which the WTRU may fill the historical CSI buffer, the network (e.g., network node) may trigger the WTRU to report legacy CSI, for example, using the same CSI-RS set used for the historical CSI buffer. The CSI estimated using the conventional / legacy method may be sent to the network (e.g., network node).

[0233] If the WTRU's CSI prediction model obtains enough historical samples in the buffer, the WTRU may send a buffer completion flag to the network (e.g., a network node). The network (e.g., a network node) and the WTRU may perform the above method. Any of the following items may be used:

[0234] - The WTRU may receive an uplink grant from the network (e.g., a network node) for a single CSI report; and

[0235] - The WTRU may feed back L predicted CSI values ​​in a single PUSCH.

[0236] This approach may reduce overhead in both UL and / or DL ​​since it relieves the network from transmitting CSI-RS in L time slots.

[0237] Periodic reporting of CSI values:

[0238] The process may also be triggered by RRC for periodic CSI reporting, where the network (e.g., a network node) may periodically send and / or may stop sending CSI-RS, for example, sending CSI-RS for constructing historical CSI values ​​and / or stopping sending CSI-RS until L time slots have passed, such as Figure 8 As shown, where L is the look-ahead window size of the CSI prediction model.

[0239] PUCCH may be used to employ periodic CSI reporting. In this case, the CSI reporting may be implicit, i.e., PMI, RI, LI, CQI.

[0240] Semi-persistent reporting of CSI values:

[0241] This procedure can also be used with semi-persistent reporting, where semi-persistent reporting is activated / deactivated by MAC CE.

[0242] In the semi-persistent CSI report:

[0243] - The predicted CSI value can be reported in a single semi-persistently allocated PUSCH:

[0244] ○ The predicted CSI value can be an explicit CSI matrix or an implicit CSI.

[0245] - The predicted CSI value can be reported in the periodically allocated PUCCH:

[0246] ○ The predicted CSI value may be an implicit CSI.

[0247] Figure 8 An example timeline for single (aperiodic) reporting of L predicted CSI samples is shown in , where no CSI-RS is transmitted during the look-ahead window.

[0248] Fig. 9 A WTRU procedure for reporting L predicted CSI samples in a single report is shown (CSI-RS overhead reduction).

[0249] In step 901, the WTRU may be configured for CSI prediction (e.g., with a CSI prediction look-ahead window size L and a number of CSI-RS time samples N, for example, to build a CSI history buffer (e.g., required). In step 902, the WTRU may determine whether the CSI history buffer is complete. If the CSI history buffer is not complete, then in step 903, the WTRU may continue to receive CSI-RS time samples, build a CSI history buffer and / or report legacy CSI. If the CSI history buffer is complete, then in step 904, the WTRU may determine L predicted CSI, report a single aperiodic report of the L predicted CSI and / or skip the next L-1 CSI reporting opportunities.

[0250] Reporting of a single predicted CSI value

[0251] [WTRU procedure for calculating L predicted CSI values ​​and reporting a single sample]

[0252] Semi-persistent reporting of predicted CSI values:

[0253] Fig.10 The signaling process for semi-persistent reporting of L predicted CSI values ​​is shown in FIG.

[0254] According to an embodiment, the WTRU may receive a look-ahead window size request from the network in step 1001. In step 1002, the WTRU may send to the network (e.g., a network node) a CSI prediction look-ahead window size L and a number of CSI-RS time samples N, for example, for constructing historical CSI (e.g., required):

[0255] - The CSI prediction look-ahead window size may use (eg depend on) a trained CSI prediction model.

[0256] - The WTRU may report the expected prediction accuracy as a function of the lookahead (for up to L_max lookahead).

[0257] For example, if the look-ahead window size L is sufficient, then in step 1003, the network (e.g., network node) and / or WTRU may be configured to utilize L look-ahead window size (L<=L_max) for CSI prediction. The WTRU may receive, for example, N CSI-RS samples for constructing historical CSI data. The WTRU may report legacy CSI, for example, when constructing historical CSI data.

[0258] A WTRU that relies on "N" historical CSI samples calculated using CSI-RS may employ an RNN-based CSI prediction model where the WTRU may predict "L" CSI samples in advance. After predicting the CSI for the look-ahead window size L, the WTRU may send an ACK indicating that L CSI predicted samples for the next L transmission opportunities are available, for example, to the BS in step 1004.

[0259] In step 1005, based on transmission requirements (e.g., other scheduled users, available resources, etc.), the network node / BS may trigger the WTRU to periodically transmit the predicted CSI, where in step 1006, the WTRU may (e.g., only) report the predicted CSI value corresponding to the next transmission opportunity.

[0260] - The WTRU may report the predicted CSI value for the next transmission opportunity on the periodically allocated PUCCH.

[0261] ○ The predicted CSI value may be an implicit CSI.

[0262] - The WTRU may report the predicted CSI value for the next transmission opportunity on the semi-persistently available PUSCH resources.

[0263] ○ The predicted CSI value may be the explicit CSI.

[0264] In step 1007, the network (eg, a network node) may send data using the predicted CSI.

[0265] In steps 1008 and 1009, the WTRU may (e.g., continue) reporting the predicted CSI for the next transmit opportunity in each subsequent PUCCH / PUSCH, e.g., until the WTRU has reported L predicted CSI values ​​for L transmit opportunities, such as Fig.10 As shown:

[0266] - The WTRU may report L predicted CSI values ​​on L PUCCH / PUSCHs, ie, in each PUCCH / PUSCH, the WTRU may report (eg, only) the predicted CSI value related to the instantaneous transmission opportunity.

[0267] - Unlike a single report of predicted CSI where L predicted CSI values ​​are reported in a single PUCCH / PUSCH, this approach may consider reporting the predicted CSI in each subsequent PUCCH / PUSCH where the network (eg, a network node) may request the WTRU to report the CSI.

[0268] - This procedure can be used when the size of PUCCH / PUSCH is limited.

[0269] As discussed above, CSI-RS can still be transmitted periodically, while CSI reporting can be semi-persistent, such as Fig.10 The basic principle with periodic CSI-RS transmission may be to construct an RNN buffer for historical CSI samples, which may be periodically updated using the periodic CSI-RS transmission.

[0270] Periodic reporting of L predicted CSI values:

[0271] The WTRU may report predicted CSI samples associated with an immediate transmission opportunity on the periodically available PUCCH after predicting the CSI using historical CSI samples for a look-ahead window size L.

[0272] - In periodic reporting on PUCCH, the predicted CSI values ​​may be implicit, i.e., PMI, RI, CQI, LI. This is because the capacity of PUCCH is limited and thus it may not be feasible for larger reporting payloads (such as the full CSI matrix).

[0273] In this option, both CSI-RS and CSI reporting may be periodic.

[0274] Aperiodic reporting of L predicted CSI values:

[0275] After the WTRU predicts the CSI for the look-ahead window size L, the WTRU may send an ACK to the network node (e.g., BS) indicating that L CSI prediction samples for the next L transmission opportunities are available. Based on the transmission requirements (e.g., other scheduled users, available resources, etc.), the network node (e.g., BS) may trigger the WTRU with a DCI of the predicted CSI associated with a specific time slot from the L predicted CSI values.

[0276] The WTRU may report the predicted CSI value corresponding to the requested timeslot, for example, using the PUSCH.

[0277] Fig.10 The signal flow for periodic reporting of predicted CSI for any (eg, each) CSI reporting opportunity (eg, periodic predicted CSI reporting) is shown in FIG.

[0278] Look-ahead windows: Adaptive framework

[0279] The WTRU may use an adaptive look-ahead window framework to report the next predicted CSI samples. In this context, after L time slots have passed since the WTRU reported the predicted CSI, the WTRU may send a new look-ahead window size and a new predicted CSI sample size.

[0280] According to an embodiment, the WTRU may be configured to use a different look-ahead window size and / or a different number of future samples each time the predicted CSI is reported. The WTRU may decide to switch to a smaller or larger "L" value based on a specific event. For example, the WTRU may evaluate the prediction accuracy of the samples obtained from the latest "N" historical CSI buffers, and then decide to increase or decrease the look-ahead window size and the number of predicted CSI samples. According to an embodiment, the WTRU may rely on a pre-configured threshold to change "L", and then report the difference in window size "ΔL" (ΔL may be a positive or negative number) and the predicted "L+ΔL" CSI samples to the network (e.g., a network node).

[0281] WTRU procedures with periodic CSI-RS:

[0282] According to an embodiment, adaptive L and predicted CSI samples may be applied in the case where the WTRU keeps receiving CSI-RS during the look-ahead window.

[0283] A WTRU that relies on "N" historical CSI samples calculated using CSI-RS may employ an RNN-based CSI prediction model where the WTRU may predict "L" CSI samples in advance. After the WTRU predicts the CSI for the look-ahead window size L, the WTRU may send an acknowledgement (ACK) to the network node (e.g., BS) indicating that L CSI prediction samples are available. Based on the transmission requirements (e.g., other scheduled users, available resources, etc.), the network (e.g., BS) may send an uplink grant to the WTRU for CSI reporting, e.g., via downlink control information (DCI).

[0284] Based on historical CSI samples calculated using the CSI-RS and the accuracy of previous predictions, the WTRU may calculate a new value for L.

[0285] The WTRU, after receiving an uplink grant via DCI, may report the L predicted CSI values ​​together with the new value of L, for example, in a single PUSCH. The WTRU may report ΔL=L-Lnew to reduce the overhead of uplink signaling.

[0286] Before sending the next predicted CSI samples, the network node (eg, BS) may allocate uplink resources for reporting L'=L+ΔL CSI samples. In the next CSI reporting period, the WTRU may report L' CSI samples, eg, together with an update to L'.

[0287] Fig.11 The signaling process of non-periodic reporting of L predicted CSI values ​​and updates to the L values ​​is shown in FIG.

[0288] According to an embodiment, the WTRU may receive a look-ahead window size request from a network (e.g., a network node) in step 1101. In step 1102, the WTRU may transmit to the network (e.g., a network node) a CSI prediction look-ahead window size L and a number of CSI-RS time samples N, for example, for constructing historical CSI (e.g., required):

[0289] - The CSI prediction look-ahead window size may use (eg depend on) a trained CSI prediction model.

[0290] - The WTRU may report the expected prediction accuracy as a function of the lookahead (for up to L_max lookahead).

[0291] For example, if the look-ahead window size L is sufficient, the network (e.g., network node) and / or WTRU may be configured to utilize L look-ahead window size (L<=L_max) for CSI prediction in step 1103. The WTRU may receive, for example, N CSI-RS samples for constructing historical CSI data. The WTRU may report legacy CSI, for example, when constructing historical CSI data.

[0292] The WTRU, which relies on "N" historical CSI samples calculated using CSI-RS, adopts an RNN-based CSI prediction model, where the WTRU may predict "L" CSI samples in advance. After the WTRU predicts the CSI for the look-ahead window size L, in step 1104, the WTRU may send an acknowledgment (ACK) to the network node (e.g., BS) indicating that L CSI prediction samples are available.

[0293] In step 1105, based on the transmission requirements (eg, other scheduled users, available resources, etc.), the network (eg, BS) may send an uplink grant to the WTRU for CSI reporting via downlink control information (DCI).

[0294] In step 1106, the WTRU may report L predicted CSI values, for example, in a single PUCCH / PUSCH, after receiving an uplink grant via DCI.

[0295] In step 1107, the network (eg, network node) may send an ACK to the WTRU followed by data transmission using the predicted CSI of the L look-ahead time slots.

[0296] In the next CSI reporting period, the WTRU may report the L predicted CSI values ​​in a single PUSCH, eg, together with the new L value, after receiving the uplink grant via DCI in step 1108 .

[0297] In step 1109, the WTRU may report ΔL=L-Lnew to the network node to reduce the uplink signaling overhead.

[0298] In step 1110, the network node may update the value of L and reconfigure the WTRU to receive CSI-RS samples, for example, for constructing historical CSI data.

[0299] In step 1111, the WTRU may report new L predicted CSI values, for example in a single PUCCH / PUSCH, after receiving an uplink grant via DCI.

[0300] Fig.12An example timeline for a single (non-periodic) report of L predicted CSI samples is shown in , which shows that the window size “L1” has been updated to “L2=L1+ΔL” in the second period using ΔL, so the number of predicted CSI samples has changed.

[0301] WTRU procedures without CSI-RS:

[0302] According to an embodiment, the network node (e.g., BS) may not send any CSI-RS during the look-ahead window, which is activated immediately after the look-ahead window has passed. In this case, after the "L" window has passed, the network (e.g., network node) resumes CSI-RS transmission and the WTRU may report legacy CSI using the received CSI-RS when filling the historical CSI buffer. Depending on the newly received CSI-RS, the WTRU may calculate "N" historical CSI samples and may predict the CSI samples for the next look-ahead window. The WTRU may decide to update "L" as any of the following actions:

[0303] - After the window "L" has elapsed, the WTRU starts building a new historical CSI buffer to obtain predicted CSI samples.

[0304] - Based on the calculated historical CSI samples and the accuracy of the previous prediction, a new L value is calculated.

[0305] The WTRU reports L predicted CSI values ​​along with a new value of L in a single PUSCH after receiving an uplink grant via DCI. The WTRU may report ΔL=L-Lnew to reduce the overhead of uplink signaling.

[0306] Before sending the next predicted CSI samples, the network node (eg, BS) allocates uplink resources for reporting L'=L+ΔL CSI samples. In the next CSI reporting period, the WTRU reports L' CSI samples along with an update to L'.

[0307] Fig.13 The signaling process of non-periodic reporting of L predicted CSI values ​​and updates to the L values ​​is shown in FIG.

[0308] According to an embodiment, in step 1301, the WTRU may receive a look-ahead window size request from a network (eg, a network node).

[0309] In step 1302, the WTRU may send to the network (e.g., a network node), for example, a CSI prediction look-ahead window size L and a number of CSI-RS time samples N used to construct historical CSI (e.g., required):

[0310] o The CSI prediction look-ahead window size may use (eg, depend on) a trained CSI prediction model.

[0311] o The WTRU may report the expected prediction accuracy as a function of the lookahead (for up to L_max lookahead).

[0312] For example, if the look-ahead window size L is sufficient, the network (e.g., network node) and / or WTRU may be configured to utilize L look-ahead window size (L <= L_max) for CSI prediction in step 1303. The network node (e.g., BS) may not transmit any CSI-RS during the look-ahead window, which is activated immediately after the look-ahead window has passed. In this case, after the "L" window has passed, the network (e.g., network node) may resume CSI-RS transmission, and the WTRU may use the received CSI-RS to report legacy CSI when filling the historical CSI buffer.

[0313] The WTRU, which relies on "N" historical CSI samples calculated using CSI-RS, adopts an RNN-based CSI prediction model, where the WTRU may predict "L" CSI samples in advance. After the WTRU predicts the CSI for the look-ahead window size L, in step 1304, the WTRU may send an acknowledgment (ACK) to the network node (e.g., BS) indicating that L CSI prediction samples are available.

[0314] In step 1305, based on transmission requirements (eg, other scheduled users, available resources, etc.), the network (eg, BS) may send a request to the WTRU for CSI reporting via downlink control information (DCI).

[0315] In step 1306, the WTRU may report L predicted CSI values, for example, in a single PUSCH, after receiving the request via the DCI.

[0316] In step 1307, the network (eg, a network node) may send data to the WTRU using the predicted CSI of the L look-ahead time slots.

[0317] The WTRU may decide to update “L” as any of the following actions:

[0318] - After the window "L" has elapsed, the WTRU starts building a new historical CSI buffer to obtain predicted CSI samples.

[0319] - Based on the calculated historical CSI samples and the accuracy of the previous prediction, a new L value is calculated.

[0320] In step 1308, the network node may request a CSI report, for example via a DCI.

[0321] In step 1309, the WTRU may report ΔL=L-Lnew to reduce the uplink signaling overhead.

[0322] In step 1310, the network node may update the value of L and reconfigure the WTRU to receive CSI-RS samples, for example, for constructing historical CSI data.

[0323] In step 1311, the WTRU may report new L predicted CSI values, for example, in a single PUCCH / PUSCH, after receiving an uplink grant via DCI.

[0324] Fig.14 An example timeline for a single report of L predicted CSI samples is shown in , which shows that the window size “ L1 ” has been updated to “ L2 = L1 + ΔL” in the second cycle using ΔL based on the newly calculated historical CSI samples.

[0325] Representative CSI prediction performance metrics

[0326] WTRU Measurements for CSI Prediction Performance

[0327] [WTRU performance metrics during the CSI prediction phase]

[0328] The WTRU may perform additional channel measurements, such as channel coherence time, channel coherence bandwidth, SNR, Doppler spread, etc. A change in the measured channel conditions may trigger the WTRU to evaluate the performance of the CSI prediction during the prediction phase. In an embodiment, if the WTRU measures a change in the channel coherence time, it may send an indication to the network node / BS (e.g., eNB, gNB) to report the change. The WTRU may be configured to report the channel coherence time periodically and / or when prompted by the network node / BS (e.g., eNB, gNB) (e.g., via DCI) and / or when a corresponding pre-configured threshold is exceeded. An increase in the channel coherence time may mean that the channel changes from a fast fading channel to a slow fading channel. Therefore, the WTRU may increase the size of the look-ahead window to accommodate a larger number of time slots for prediction. In an embodiment, a small value of the coherence time (i.e., below a pre-configured threshold set by the WTRU or BS (e.g., eNB, gNB)) may indicate a fast fading channel, thereby implicitly indicating to the WTRU that additional metrics (e.g., SNR) may need to be measured. The WTRU may report the additional measurements to the BS (e.g., eNB, gNB) separately or by including the additional measurements as part of the CSI feedback report (e.g., CQI, SNR, etc.).

[0329] The ACK / NACK statistics measured by the WTRU may indicate the performance of the ML-based decoder for CSI prediction. For example, if the WTRU sends several consecutive NACKs to the BS (e.g., eNB, gNB), the BS (e.g., eNB, gNBs) may send a request to the WTRU to re-evaluate the performance of the CSI prediction model. The number of consecutive NACKs that will trigger a re-evaluation of the CSI prediction model may be configured by the BS (e.g., eNB, gNB). The BS (e.g., eNB, gNB) may send a request to train / retrain the ML model at the WTRU.

[0330] The WTRU may decide to measure and track ACK / NACK statistics within a time window. If the number / percentage of NACK responses recorded over this window exceeds a pre-configured threshold, the WTRU may re-evaluate the performance of the CSI prediction, for example by calculating NMSE or cosine similarity.

[0331] CSI prediction error phase during CSI test / calibration phase (sending aperiodic test CSI-RS signal)

[0332] The WTRU may use the legacy CHEST reporting framework as a reference to evaluate the output of the ML model and / or calibrate / recalibrate the neural network. The WTRU may calculate the difference / deviation / error between the output of the CSI prediction model and the results of the legacy CHEST reporting framework. The difference / deviation / error may be calculated by any of the following:

[0333] (i) NMSE

[0334] The normalized mean square error may be used as a performance evaluation of the ML model, whereby the accuracy of the ML model may be inversely proportional to the NMSE value calculated at the WTRU. The WTRU may quantify the normalized MSE (NMSE) as shown in the following equation:

[0335] where H: CSI channel matrix from conventional channel estimation; and Output of the ML-enabled decoder.

[0336] (ii) Cosine similarity

[0337] The cosine similarity measures the similarity between the reference channel matrix and the output of the ML decoder. The WTRU may calculate the cosine similarity p as shown in the following equation:

[0338] in The channel vector reconstructed at the nth subcarrier at the output of the ML decoder.

[0339] NMSE or cosine similarity may be used to quantify the recovery performance. The quantized result of the difference / bias / error that may be calculated by the WTRU may be evaluated against a pre-configured threshold. In an embodiment, if the NMSE calculated by the WTRU < threshold T1, the WTRU may report to the BS (e.g., eNB, gNB) that the performance of the CSI model predictor is sufficient and / or the WTRU may not trigger a remeasurement / recalculation of the NMSE, for example, within a certain time period.

[0340] Similarly, if in an embodiment, the cosine similarity p calculated by the WTRU is above a preconfigured threshold, the WTRU may report to the BS (e.g., eNB, gNB) that the performance of the CSI model predictor is good, and the WTRU may not trigger a recalculation of p for a specific subcarrier within a specific time period. Conversely, if the cosine similarity p calculated by the WTRU is below a specific threshold, the WTRU may report the value of the cosine similarity to the BS (e.g., eNB, gNB), which may send a request to retrain the model, or the WTRU may trigger a remeasurement of the cosine similarity. The aforementioned threshold may, for example, be preconfigured by the WTRU and / or indicated to / approved by the BS (e.g., eNB, gNB). The threshold may (e.g., alternatively) be configured by the BS (e.g., eNB, gNB) and / or shared with the WTRU during initial configuration (e.g., during RRC).

[0341] The WTRU may perform additional channel measurements, such as channel coherence time, channel coherence bandwidth, SNR, Doppler spread, etc. A change in the measured channel conditions may trigger a change in the thresholds. In an embodiment, if the WTRU measures a decrease in the channel coherence time, it may report the change to the BS (e.g., eNB, gNB). The BS (e.g., eNB, gNB) may trigger a change in the pre-configured thresholds to accommodate dynamic changes in channel conditions.

[0342] The measure of NMSE or cosine similarity can be a function of the prediction time in the look-ahead window. For example, the error / bias / difference calculated at time L+1 may be smaller than the error / bias / difference calculated at time L+n (where n>>1). Therefore, the threshold can also be a function of the time in the look-ahead window.

[0343] There may be multiple thresholds (e.g., T1, T2, T3, ..., TN) configured by the BS (e.g., eNB, gNB) for measuring a performance metric. For example, the BS (e.g., eNB, gNB) may configure one or more thresholds that, when exceeded, may trigger the WTRU to calculate the NMSE between the conventional channel estimate and the output of the ML decoder. Any (e.g., each) threshold may be associated with a particular parameter and / or the WTRU may decide which threshold to use based on its measurement of the parameter. In an embodiment, one threshold (e.g., T1) may correspond to a certain SNR range, such that if the SNR is outside of that range, the WTRU may have to use a different threshold (e.g., T2) corresponding to the newly measured SNR. An error / bias / difference (e.g., NMSE or cosine similarity) exceeding a final threshold TN may trigger the WTRU to retrain the ML prediction model.

[0344] Triggering retraining of AI / ML CSI prediction models

[0345] For example, the WTRU may start a counter / timer when (e.g., each time) training of the CSI prediction model is completed. The expiration of the counter / timer may trigger the WTRU to retrain the model. The length of time set by the timer may be measured / recorded in any of the following units: time slot, symbol duration, SFN, and seconds / milliseconds. The counter may be measured in number of symbols. The length of the timer / counter may be pre-configured by the WTRU and indicated to the BS (e.g., eNB, gNB), and vice versa. The BS (e.g., eNB, gNB) may send a message to the WTRU requesting a change in the length of the counter / timer. In an embodiment, the BS (e.g., eNB, gNB) may record poor uplink channel conditions from the CSI report from the WTRU. The BS (e.g., eNB, gNB) may send a request to the WTRU to reduce the length of the timer / counter trigger.

[0346] For example, at the start of a session, the BS (e.g., eNB, gNB) may send a request to a WTRU supporting ML to report its time domain CSI prediction capabilities. In response, the WTRU may report the length of the look-ahead window (LA) and / or the length of the maximum look-ahead window (LAmax), for example, based on the number of time slots. The BS (e.g., eNB, gNB) may have a target length of CSI predictability expected from a WTRU supporting ML. In the event that the LA or LAmax may be less than the target number of time slots for prediction, the BS (e.g., eNB, gNB) may trigger online training / retraining of the CSI prediction model at the WTRU.

[0347] In the event that the error calculation as described above may exceed a pre-configured threshold, the WTRU may trigger retraining of the ML model. For example, if NMSE>threshold T1 and / or if cosine similarity<threshold T2, the WTRU may trigger training / retraining of the ML model. The BS (e.g., eNB, gNB) may also have thresholds corresponding to performance metrics of WTRUs supporting ML. If the WTRU reports the calculated NMSE and / or cosine similarity to the BS (e.g., eNB, gNB), and the error performance metric is lower than the corresponding threshold at the BS (e.g., eNB, gNB), the BS (e.g., eNB, gNBs) may send an indication to the WTRU to trigger training / retraining of the CSI prediction model.

[0348] The WTRU may perform additional channel measurements, such as channel coherence time, channel coherence bandwidth, SNR, Doppler spread, BLER, etc. Changes in measured channel conditions may trigger training / retraining of the ML model at the WTRU. In an embodiment, if the WTRU records / measures changes in the channel coherence time such that the channel coherence time is less than the length of the look-ahead window, the WTRU may need to trigger training / retraining of the CSI prediction model and send an indication to the BS (e.g., eNB, gNB) to notify the BS (e.g., eNB, gNB) of the training / retraining of the ML model and / or any changes to the look-ahead window due to changes in channel conditions.

[0349] The WTRU may report changes in channel coherence time to the BS (e.g., eNB, gNB). Knowing the size of the look-ahead window, the BS (e.g., eNB, gNB) may send a message to the WTRU to trigger training / retraining of the CSI prediction model. The WTRU may be configured to report the channel coherence time to the BS (e.g., eNB, gNB) periodically or when prompted by the BS (e.g., eNB, gNB) via an indication sent to the WTRU (e.g., in a DCI). There may also be a semi-periodic configuration where the WTRU utilizes a periodicity set by the BS (e.g., eNB, gNB) and reports the channel coherence time to the BS (e.g., eNB, gNB) when prompted by the BS (e.g., eNB, gNB) and / or when the WTRU measures a large change in the channel coherence time. In an embodiment, a channel coherence time threshold may be configured at the WTRU. Exceeding the channel coherence time threshold may trigger reporting the coherence time to the BS (e.g., eNB, gNB). Thresholds for other channel measurements may also be configured. In an embodiment, if the SNR measured by the WTRU is lower than a corresponding pre-configured threshold and / or the BLER is higher than a corresponding pre-configured threshold, the WTRU may trigger training / retraining of the CSI prediction model.

[0350] Representative update predicted CSI (upon detection of a prediction error event)

[0351] RS configuration for prediction and prediction error detection

[0352] The WTRU may be configured with a first set of RS (e.g., CSI-RS) on which channel estimation and prediction is performed for up to L time slots. The first set of RS may have a high density and a short periodicity. The first set of RS may be bursty or semi-persistent. For example, the first set of RS may be received by the WTRU in a time period (i.e., a burst), and after the time period or the burst ends, the WTRU may no longer expect to transmit RS until a future burst.

[0353] The WTRU may be configured with a second set of RSs on which channel estimation is performed and compared with a predicted (e.g., previously predicted) CSI report. The second set of RSs may be configured to be periodic. The second set of RSs may have a longer periodicity than the first set of RSs. In an embodiment, the WTRU may only expect to receive the second set of RSs outside of a burst of the first set of RSs.

[0354] In an embodiment, the second set of RSs may be a subset of the first set of RSs. For example, the first set of RSs may include n RSs, each with a different offset and the same or different periodicity. The second set of RSs may be a subset m of the RSs in the first group, where m ≤ n. The start time and duration of the burst of the first set of RSs may be fixed or configured by RRC or DCI or MAC CE. The WTRU may determine the time and duration of the burst of the first set of RSs by any of the following:

[0355] - Semi-static configuration. For example, the start time and duration of the burst may be periodic. The WTRU may receive the configuration via RRC.

[0356] - Dynamic indication. For example, the WTRU may receive a dynamic indication via a DCI or MAC CE indicating an upcoming burst start time and / or duration.

[0357] - The burst start time or duration or end time of the previous burst. For example, if the time since the previous burst is greater than a configurable value, the WTRU may expect a burst of the first set of RS. The time between bursts may be determined based on the number of time slots of the predicted CSI sent by the WTRU.

[0358] -Predict the number or timing of time slots (L).

[0359] - WTRU request. For example, the WTRU may send a request for a burst of the first set of RSs. The WTRU may receive a confirmation to send the burst, for example via a DCI or MAC CE.

[0360] Based on measurements performed on at least one RS in the first set of RSs, the WTRU may determine up to L predicted CSI values. The WTRU may report the L CSI values ​​in a CSI feedback report on the CSI feedback resource. The predicted CSI feedback report may include a complete CSI value for each of the L predicted values, or may include a first complete report for a first reference time slot and differential or incremental CSI values ​​for the other L-1 time slots.

[0361] The WTRU may send a single CSI report or a single set of CSI reports applicable to L predicted time slots. The CSI report may include a CSI value and the number and identity of the L time slots for which the predicted CSI is valid. For example, each CSI value may be associated with a reference time slot. The timing or identity of the time slot for which the predicted value is applicable may be determined by any of the following:

[0362] - A codebook for feedback prediction values. For example, each position in the CSI feedback codebook may be associated with a slot timing or identity.

[0363] - Feedback resources. For example, the timing or identification of at least one associated time slot may be determined by a parameter of the feedback resource used to feed back the prediction value. The parameter may include at least one of the following: timing of the feedback resource, resource type, frequency resource allocation, orthogonal cover code, CS index.

[0364] - The timing and duration and resources of at least one RS in the first set of RSs.

[0365] -Higher level configuration.

[0366] The WTRU may send a CSI report associated with at least one RS in the second set of RSs. For example, the WTRU may report a set of predicted CSI values ​​based on measurements obtained on at least one RS in the first set of RSs. The WTRU may or may additionally report CSI values ​​based on measurements obtained on at least one RS in the second set of RSs. These two types of CSI reports may be reported in different resources with different resource configurations. The CSI report type for each CSI report may be different. The report of the predicted CSI value or the report of the CSI value may include any of the following items: RI, PMI, CQI, CRI, SSBRI, LI, L1-RSRP, coherence time, coherence BW, and Doppler spread.

[0367] For example, a first CSI report predicting CSI values ​​may include a set of RI / PMI / CQI for each of the set of L time slots. A second CSI report may include an updated CQI value and a coherence time. The coherence time may be used to determine the validity of a previously predicted CSI value. In an embodiment, the WTRU may report a correlation coefficient in the second CSI report. The correlation coefficient may be obtained by using a predicted CSI value for a reference time slot and an actual CSI value for a reference time slot.

[0368] Error Detection

[0369] The WTRU may perform CSI measurement on at least one RS in the second set of RSs. At least one resource of one RS in the second set of RSs may be associated with at least one reference time slot for predicting a CSI value.

[0370] The WTRU may compare the CSI measurement on at least one RS in the second set of RSs with a predicted CSI value determined for a reference slot associated with the at least one RS in the second set of RSs. The WTRU may determine a prediction error (e.g., NMSE between the measured value and the predicted value).

[0371] The WTRU may be configured or signaled with a set of error detection thresholds. The WTRU may compare the prediction error of at least one predicted CSI with at least one threshold.

[0372] The WTRU may determine at least one error detection threshold based on any of the following:

[0373] -Configuration. For example, the error detection threshold can be fixed.

[0374] - HARQ-ACK feedback. For example, a threshold may be determined based on a percentage of NACKs for transmissions. The set of transmissions over which the percentage may be determined may be based on a moving window of fixed size.

[0375] - Priority of the transmission. For example, the threshold may depend on the PHY layer priority of at least one associated transmission.

[0376] - BLER requirement. For example, the threshold may be determined according to the required BLER of the associated transmission.

[0377] -The number of predicted CSI values ​​(L).

[0378] - Measured or predicted CSI value. For example, the threshold value may be determined as a percentage difference from the measured or predicted value.

[0379] If the prediction error is greater than a threshold, the WTRU may determine that a prediction error event exists for the associated reference time slot.

[0380] WTRU Behavior When Prediction Error is Detected

[0381] The WTRU may be configured with a set of thresholds, and depending on the threshold that the prediction error is larger than, the WTRU may behave differently.

[0382] If the WTRU determines that the prediction error is greater than the first threshold, the WTRU may add 1 to the counter. The WTRU may be configured with a maximum counter value. The WTRU may be configured with a counter timer. When the counter value is greater than the maximum counter value, the WTRU may determine a prediction error event and may perform one of the actions listed below. When the timer expires, the WTRU may determine a prediction error event and may perform one of the actions listed below. When the timer expires, the WTRU may reset the counter. The WTRU may reset the counter or timer after sending a CSI report or a set of predicted CSI values. When the WTRU increments the counter, the WTRU may restart the timer.

[0383] If the WTRU determines that the prediction error is greater than the second threshold, the WTRU may determine a prediction error event and may perform one of the actions listed below.

[0384] Upon determining or detecting a prediction error event, the WTRU may perform any of the following actions:

[0385] - Report an indication of a prediction error event. For example, the WTRU may report at least one of the value of the prediction error, the number of erroneous slots, the identity of the erroneous slots. The indication may be in the UCI or in the MAC CE.

[0386] - Reports the prediction error for one or more time slots.

[0387] - Report a new set of prediction values. For example, the WTRU may report new prediction values ​​for the associated reference time slot on which the error event was determined. In another example, the WTRU may report new prediction values ​​for a new set of L time slots. In another example, the WTRU may report new prediction values ​​for the remaining time slots in the original set of L time slots.

[0388] - Reporting error correction values. For example, the WTRU may report error correction values ​​that may be used in conjunction with previously sent predicted CSI values ​​to obtain corrected CSI values. The WTRU may report error correction values ​​for one, some, or all remaining time slots of the original set of L time slots for which the WTRU previously reported predicted CSI.

[0389] - A new CSI value for the reference time slot is reported, and all previously reported predicted CSI values ​​for the remaining time slots in the set of original L time slots are cancelled or invalidated.

[0390] - Fallback to non-predictive CSI reporting.

[0391] -Requesting a set of RSs to determine a new set of predicted CSI values. For example, the WTRU may request transmission of at least one RS in a first set of RSs. The WTRU may request an update of at least one parameter of at least one RS in the first set of RSs. For example, the WTRU may request a new burst duration or periodicity.

[0392] -Request a set of RSs to retrain the AI / ML model. For example, the WTRU may request the transmission of at least one RS in the first set of RSs.

[0393] -Request resources to retrain AI / ML models.

[0394] - Request new AI / ML models.

[0395] - Reporting CSI measurements to enable reconfiguration of the first or second set of RSs.

[0396] - Report the new expected value of the prediction set L.

[0397] -Send an indication on the HARQ-ACK transmission.

[0398] Resource selection for indicating detected error events

[0399] The WTRU may be configured with resources on which it may transmit a signal upon determining a prediction error event as described above.

[0400] The WTRU may be configured with a conditional permission to send an error event indication or UCI.

[0401] The WTRU may be configured with a PUCCH on which to send an error event indication or UCI. For example, the WTRU may be configured with a conditional PUCCH that may be used if an error event is detected.

[0402] The WTRU may send an SR to indicate that an error event has occurred. The SR may request resources on which to send a new or updated CSI value or a predicted CSI value. The SR may request the transmission of at least one RS from the first set of RSs.

[0403] The WTRU may send an RRC message indicating the error. The RRC message may indicate the new expected L value.

[0404] Fig.15The signal flow of the process is shown in FIG. In the figure, the WTRU requests at least one RS from the second set of RSs to determine the prediction accuracy. In the figure, the WTRU may report the difference between the predicted CSI value and the actual CSI value in the form of a delta_CSI value. In an embodiment, the figure also shows that the WTRU may be configured to retrain the AI / ML model.

[0405] According to an embodiment, in step 1501, the network (e.g., a network node) may send an ACK to the WTRU, followed by data transmission using the predicted CSI of the L forward time slots. In step 1502, the WTRU may request CSI-RS test samples from the network (e.g., a network node) to check the prediction accuracy. In step 1503, the network (e.g., a network node) may configure CSI-RS test samples for the WTRU and / or send CSI-RS test samples to the WTRU, for example, based on network transmission parameters. In step 1504, the WTRU may calculate the error between the predicted CSI and the true CSI and check whether the error is above a threshold. In step 1505, the WTRU may report the calculated error, for example, if the error is above a threshold. The network (e.g., a network node) may decide whether to receive the CSI difference or retrain the WTRU based on the reported error.

[0406] If the network (e.g., network node) decides to receive CSI difference, then the network (e.g., network node) may configure CSI-RS for the WTRU to obtain CSI difference value for the next look-ahead time slot in step 1506. In step 1507, the WTRU may calculate CSI difference value between predicted CSI and true CSI using CSI-RS and send CSI difference value for the requested time slot in the look-ahead window. In step 1508, the network (e.g., network node) may send data using updated CSI, where updated CSI is obtained based on CSI difference value.

[0407] If, in step 1509, the network (e.g., network node) decides to retrain the WTRU based on the reported error, the network (e.g., network node) may configure the CSI-RS for the WTRU to retrain. In step 1510, the WTRU may recalibrate the CSI prediction model weights. In step 1511, if the error between the predicted CSI and the true CSI is below a threshold within the configured retraining time, the WTRU may send a training completion confirmation.

[0408] Fig.16An example timeline for a WTRU to determine a prediction error event is shown in , assuming periodic CSI-RS transmission. In the figure, the WTRU uses up to 0 CSI-RS samples to determine and report predicted CSI values ​​for time slots 0, 1, 2, ..., L. The WTRU may continue to receive CSI-RS in time slots 1, 2, .... Such CSI-RS may be from a second set of RS. At time k, the WTRU may determine that a prediction error event has occurred due to an error greater than a threshold. In this case, the WTRU may report the actual CSI value for time slot k. The WTRU may also revert to reporting the actual CSI values ​​for the remaining time slots up to time slot L. In addition, the WTRU may request retraining and may indicate this in the CSI report.

[0409] Fig.17 An example of a method 1700 implemented by the WTRU 102 for CSI prediction for a wireless system is shown.

[0410] According to an embodiment, the WTRU 102 may be configured to receive a plurality of reference signals from a network node (eg, a BS), wherein the plurality of reference signals are transmitted during a time window (1710).

[0411] According to an embodiment, the WTRU 102 may be configured to determine a plurality of CSIs associated with a plurality of reference signals based on a trained AI / ML model ( 1720 ).

[0412] According to an embodiment, the WTRU 102 may be configured to generate a report including a plurality of CSIs (1730).

[0413] According to an embodiment, the WTRU 102 may be configured to send a report including a plurality of CSIs to a network node (1740).

[0414] According to an embodiment, the report is sent after the end time of the time window.

[0415] According to an embodiment, the WTRU 102 may be configured to send information to a network node indicating that a plurality of CSIs have been determined.

[0416] According to an embodiment, the WTRU 102 may be configured to send a report including multiple CSIs in a single transmission to a network node.

[0417] According to an embodiment, the report is sent on the Physical Uplink Shared Channel (PUSCH).

[0418] According to an embodiment, the WTRU 102 may be configured to receive an uplink grant from a network node via downlink control information (DCI).

[0419] According to an embodiment, the WTRU 102 may be configured to send the size of the time window (eg, as a time length) and / or the number of the plurality of reference signals to the network node.

[0420] Fig.18 Another example of a method 1800 implemented by the WTRU 102 for CSI prediction for a wireless system is shown.

[0421] According to an embodiment, the WTRU 102 may be configured to receive configuration information from a network node, the configuration information indicating: a first time period for receiving and measuring CSI by the WTRU and a size (e.g., as a time length) of a second time period for predicting CSI by the WTRU, wherein the size of the second time period is less than or equal to a maximum size of the second time period, and wherein the second time period is after the first time period (1810).

[0422] According to an embodiment, the WTRU 102 may be configured to receive a plurality of CSI-RS from a network node during a first time period (1820).

[0423] According to an embodiment, the WTRU 102 may be configured to measure multiple CSIs based on the received multiple CSI-RSs (1830).

[0424] According to an embodiment, the WTRU 102 may be configured to determine an updated size of a second time period, wherein the updated size of the second time period is based on measurements performed on at least one of the received multiple CSI-RSs, and wherein the updated size of the second time period is less than or equal to a maximum size of the second time period (1840).

[0425] According to an embodiment, the WTRU 102 may be configured to send an updated size of the second time period and a plurality of predicted CSIs for the first time period to a network node, wherein the plurality of CSIs may be used to generate the plurality of predicted CSIs (1850).

[0426] According to an embodiment, after the first time period expires, any one of the following actions may be periodically repeated: receiving a second plurality of CSI-RSs from the network node during a third time period; measuring a second plurality of CSIs based on the second plurality of CSI-RSs; determining an updated size of a fourth time period, wherein the updated size of the fourth time period may be based on measurements performed on at least one CSI-RS of the second plurality of CSI-RSs, and wherein the updated size of the fourth time period may be less than or equal to a maximum size of the second time period; and sending the updated size of the fourth time period and the second plurality of predicted CSIs of the second time period to the network node, wherein the second plurality of CSIs may be used to generate a second plurality of predicted CSIs.

[0427] According to an embodiment, multiple predicted CSIs may be sent in a single transmission.

[0428] According to an embodiment, the WTRU may be configured to send information to a network node indicating that generation of the predicted CSI is complete.

[0429] According to an embodiment, the WTRU may be configured to: send a request for an uplink grant to a network node; receive an uplink grant from the network node; and send a report including a plurality of predicted CSIs to the network node using the uplink grant.

[0430] According to an embodiment, the determination of the updated size of the second time period is based on an uplink grant.

[0431] According to an embodiment, the WTRU may be configured to: receive a request message from a network node for obtaining the WTRU's capability to perform CSI prediction; and send a response message to the network node, the response message including information indicating a maximum size of the second time period.

[0432] According to an embodiment, the WTRU may be configured to: determine, for at least one of a plurality of received CSI-RSs, a difference between a predicted CSI generated using at least one CSI and a CSI measurement based on at least one CSI-RS; and send information indicating the difference to a network node.

[0433] According to an embodiment, a plurality of predicted CSIs are generated using a trained CSI prediction AI / ML model.

[0434] According to an embodiment, the maximum size of the second time period is based on the performance of the trained CSI prediction AI / ML model.

[0435] According to an embodiment, the WTRU may be configured to send a request to a network node to update and / or retrain a CSI prediction AI / ML model.

[0436] in conclusion

[0437] Although features and elements are provided above in specific combinations, it will be understood by those skilled in the art that each feature or element can be used alone or in any combination with other features and elements. The present disclosure is not limited in terms of the specific embodiments described in the present application, which are intended to be illustrations of various aspects. Without departing from its spirit and scope, many modifications and changes can be made, as will be apparent to those skilled in the art. Any element, action or instruction used in the description of the present application should not be interpreted as being critical or necessary to the present invention unless explicitly provided as such. In addition to those listed herein, functionally equivalent methods and devices within the scope of the present disclosure are apparent to those skilled in the art from the foregoing description. Such modifications and changes are intended to fall within the scope of the appended claims. The present disclosure is limited only by the terms of the appended claims and the full scope of equivalents given by such claims. It should be understood that the present disclosure is not limited to specific methods or systems herein.

[0438] For simplicity, the foregoing embodiments are discussed with respect to terminology and structure of devices with infrared capabilities (i.e., infrared transmitters and receivers). However, the embodiments discussed are not limited to these systems, but can be applied to other systems using other forms of electromagnetic waves or non-electromagnetic waves (such as sound waves).

[0439] It will also be understood that the terms used herein are used only for the purpose of describing specific embodiments and are not intended to be limiting. As used herein, the term "video" or the term "image" may mean any of a snapshot, a single image, and / or a plurality of images displayed over a certain time basis. As another example, when referred to herein, the term "user equipment" and its abbreviation "UE", the term "remote" and / or the term "head-mounted display" or its abbreviation "HMD" may mean or include (i) a wireless transmit and / or receive unit (WTRU); (ii) any of many embodiments of a WTRU; (iii) a device with wireless capabilities and / or wired capabilities (e.g., wearable) that is configured with some or all of the structure and functionality of a WTRU; (iii) a device with wireless capabilities and / or wired capabilities that is configured with less than all of the structure and functionality of a WTRU; or (iv) a similar device. References herein to Figures 1A to 1D Details of an example WTRU are provided, which may be representative of any WTRU set forth herein. As another example, various disclosed embodiments herein are described above and below as utilizing a head mounted display. Those skilled in the art will recognize that devices other than a head mounted display may be utilized, and some or all of the present disclosure and various disclosed embodiments may be modified accordingly without undue experimentation. Examples of such other devices may include drones or other devices configured to stream information to provide an adapted reality experience.

[0440] In addition, the methods provided herein may be implemented in a computer program, software, or firmware that is incorporated into a computer-readable medium for execution by a computer or processor. Examples of computer-readable media include electronic signals (transmitted via a wired or wireless connection) and computer-readable storage media. Examples of non-transitory computer-readable storage media include, but are not limited to, read-only memory (ROM), random access memory (RAM), registers, cache memory, semiconductor memory devices, magnetic media such as internal hard disks and removable disks, magneto-optical media, and optical media such as CD-ROM disks and digital versatile disks (DVDs). A processor associated with the software may be used to implement a radio frequency transceiver for a WTRU, UE, terminal, base station, RNC, or any host computer.

[0441] Variations of the methods, devices, and systems provided above are possible without departing from the scope of the present invention. In view of the various embodiments that may be applied, it should be understood that the embodiments shown are merely examples and should not be considered to limit the scope of the appended claims. For example, the embodiments provided herein include handheld devices that may include or be used with any suitable voltage source (such as a battery, etc.) that provides any suitable voltage.

[0442] In addition, in the embodiments provided above, processing platforms, computing systems, controllers, and other devices including processors are mentioned. These devices may include at least one central processing unit ("CPU") and memory. According to the practice of those skilled in the art of computer programming, references to actions and symbolic representations of operations or instructions may be performed by various CPUs and memories. Such actions and operations or instructions may be referred to as "execution," "computer execution," or "CPU execution."

[0443] Those of ordinary skill in the art will appreciate that the actions and symbolic representations of operations or instructions include manipulation of electrical signals by the CPU. The electrical system represents data bits, which may cause the final conversion or reduction of electrical signals and maintain the data bits in memory locations in the storage system, thereby reconfiguring or otherwise changing the operation of the CPU and other processing of signals. The memory locations where the data bits are maintained are physical locations having specific electrical, magnetic, optical, or organic properties that correspond to or represent the data bits. It should be understood that the embodiments are not limited to the above-mentioned platforms or CPUs, and other platforms and CPUs may support the provided methods.

[0444] The data bits may also be maintained on a computer-readable medium, including a magnetic disk, an optical disk, and any other volatile (e.g., random access memory (RAM)) or non-volatile (e.g., read-only memory (ROM)) mass storage system readable by a CPU. The computer-readable medium may include cooperating or interconnected computer-readable media that reside only on a processing system or distributed among multiple interconnected processing systems that may be local or remote to the processing system. It should be understood that the embodiments are not limited to the above-mentioned memories, and other platforms and memories may support the provided methods.

[0445] In an illustrative embodiment, any operations, processes, etc. described herein may be implemented as computer-readable instructions stored on a computer-readable medium. The computer-readable instructions may be executed by a processor of a mobile unit, a network element, and / or any other computing device.

[0446] There is little difference between hardware and software implementations of various aspects of the system. The use of hardware or software is usually (but not always, as in some cases, the choice of hardware or software may become important) a design choice that represents a cost-efficiency trade-off. There may be various vehicles (e.g., hardware, software, and / or firmware) with which the processes and / or systems and / or other technologies described herein can be implemented, and the preferred vehicle may change with the context in which the processes and / or systems and / or other technologies are deployed. For example, if the implementer determines that speed and accuracy are most important, then the implementer may select a primary hardware and / or firmware vehicle. If flexibility is most important, then the implementer may select a primary software implementation. Alternatively, the implementer may select some combination of hardware, software, and / or firmware.

[0447] The foregoing detailed description has been described various embodiments of the apparatus and / or process by using block diagrams, flow charts and / or examples. Insofar as such block diagrams, flow charts and / or examples include one or more functions and / or operations, it will be understood by those skilled in the art that each function and / or operation within such block diagrams, flow charts or examples can be implemented individually and / or collectively by a wide range of hardware, software, firmware or indeed any combination thereof. In an embodiment, several parts of the subject matter described herein may be implemented via an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), a digital signal processor (DSP) and / or other integrated formats. However, those skilled in the art will recognize that all or part of some aspects of the embodiments disclosed herein may be equivalently implemented in an integrated circuit, as one or more computer programs running on one or more computers (e.g., as one or more programs running on one or more computer systems), as one or more programs running on one or more processors (e.g., as one or more programs running on one or more microprocessors), as firmware or almost as any combination thereof, and according to the present disclosure, designing circuit systems and / or writing codes for software and / or firmware will be completely within the skill range of those skilled in the art. In addition, those skilled in the art will appreciate that the mechanisms of the subject matter described herein can be distributed as a program product in a variety of forms, and that the illustrative examples of the subject matter described herein apply regardless of the particular type of signal-bearing medium used to actually carry out the distribution. Examples of signal-bearing media include, but are not limited to, the following: recordable media such as floppy disks, hard drives, CDs, DVDs, digital tapes, computer memory, etc.; and transmission media such as digital and / or analog communication media (e.g., fiber optic cables, waveguides, wired communication links, wireless communication links, etc.).

[0448] Those skilled in the art will recognize that it is common in the art to describe devices and / or processes in the manner set forth herein, and thereafter use engineering practices to integrate such described devices and / or processes into data processing systems. That is, at least a portion of the devices and / or processes described herein can be integrated into a data processing system by a reasonable amount of experimentation. Those skilled in the art will recognize that a typical data processing system can typically include a system unit housing, a video display device, a memory such as volatile and non-volatile memory, a processor such as a microprocessor and a digital signal processor, a computing entity such as an operating system, a driver, a graphical user interface, and an application, one or more interactive devices such as a touch pad or screen, and / or a control system including a feedback loop and a control motor (e.g., feedback for sensing position and / or velocity; a control motor for moving and / or adjusting components and / or quantities). A typical data processing system can be implemented using any suitable commercially available components, such as components typically found in data computing / communication and / or network computing / communication systems.

[0449] The subject matter described herein sometimes illustrates different parts that are included in different other parts or connected with different other parts.It should be understood that the architecture of such description is only an example, and many other architectures that realize the same function can actually be implemented.In a conceptual sense, any arrangement of parts for realizing the same function is effectively "associated" so that the desired function can be realized.Therefore, any two parts that are combined to realize a specific function in this article can be regarded as "associated" with each other so that no matter how the architecture or intermediate parts realize the desired function.Similarly, any two parts that are so associated can also be regarded as "operably connected" or "operably coupled" to realize the desired function, and any two parts that can be so associated can also be regarded as "operably coupled" to realize the desired function.The specific example of operable coupling includes (but is not limited to) parts that can be matched physically and / or physically interact, and / or parts that can be wirelessly interacted and / or wirelessly interacted, and / or parts that can be logically interacted and / or parts that can be logically interacted.

[0450] With respect to the use of substantially any plural and / or singular terms herein, those skilled in the art can translate from the plural to the singular and / or from the singular to the plural where appropriate to the context and / or application. For clarity, the various singular / plural arrangements may be expressly set forth herein.

[0451] Those skilled in the art will understand that, in general, the terms used herein and particularly in the appended claims (e.g., the bodies of the appended claims) are generally intended to be "open" terms (e.g., the term "including" should be interpreted as "including but not limited to," the term "having" should be interpreted as "having at least," the term "includes" should be interpreted as "including but not limited to," etc.). Those skilled in the art will further understand that if a specific number of an introduced claim statement is intended, such intent will be expressly stated in the claim, and in the absence of such a statement, such intent is not present. For example, where only one item is intended, the term "single" or similar language may be used. To aid understanding, the following appended claims and / or the description herein may include the use of the introductory phrases "at least one" and "one or more" to introduce multiple claim statements. However, the use of such phrases should not be interpreted as implying that a claim recitation introduced by the indefinite article "a" or "an" will limit any particular claim including such introduced claim recitation to embodiments including only one such recitation, even if the same claim includes the introductory phrases "one or more" or "at least one" and an indefinite article such as "a" or "an" (e.g., "a" and / or "an" should be interpreted as meaning "at least one" or "one or more"). The same is true for the use of definite articles to introduce claim recitations. In addition, even if a specific number of introduced claim recitations is explicitly recited, one skilled in the art will recognize that such recitation should be interpreted as meaning at least the recited number (e.g., merely reciting "two recitations" without other modifiers means at least two recitations or two or more recitations). Furthermore, in those cases where a convention similar to “at least one of A, B, and C, etc.” is used, generally, such construction is intended to represent the convention that one skilled in the art would understand (e.g., “a system having at least one of A, B, and C” would include, but is not limited to, systems having only A, only B, only C, both A and B, both A and C, both B and C, and / or both A, B, and C, etc.). In those cases where a convention similar to “at least one of A, B, or C, etc.” is used, generally, such meaning is intended in the sense that one skilled in the art would understand the convention (e.g., “a system having at least one of A, B, or C” would include, but is not limited to, systems having only A, only B, only C, both A and B, both A and C, both B and C, and / or both A, B, and C, etc.). One skilled in the art would further understand that any transitional word and / or phrase (whether in the specification, claims, or drawings) that actually gives two or more alternatives should be understood to contemplate the possibility of including one of the terms, any one of the terms, or both of the terms.For example, the phrase "A or B" will be understood to include the possibility of "A" or "B" or "A and B." In addition, the term "any" as used herein followed by a list of multiple items and / or categories of items is intended to include "any," "any combination," "any multiple," and / or "any combination of multiples," either alone or in combination with other items and / or other categories of items. Furthermore, the term "set," as used herein, is intended to include any number of items, including zero. Additionally, the term "number," as used herein, is intended to include any number, including zero. And the term "plurality," as used herein, is intended to be synonymous with "multiple."

[0452] In addition, where features or aspects of the disclosure are described in terms of Markush groups, those skilled in the art will recognize that the disclosure is also thereby described in terms of any individual member or subgroup of members of the Markush group.

[0453] As will be understood by those skilled in the art, for any and all purposes, such as in providing a written description, all ranges disclosed herein also encompass any and all possible sub-ranges and combinations of sub-ranges thereof. Any listed range can be easily identified as fully describing and capable of decomposing the same range into at least equal halves, one-third, one-quarter, one-fifth, one-tenth, etc. As a non-limiting example, each range discussed herein can be easily decomposed into a lower third, a middle third, and an upper third, etc. As will be understood by those skilled in the art, all languages ​​such as "at most", "at least", "greater than", "less than", etc. include the enumerated numbers, and refer to the ranges that can be subsequently subdivided into sub-ranges as discussed above. Finally, as will be understood by those skilled in the art, the range includes each individual member. Therefore, for example, a group with 1 to 3 units refers to a group with 1, 2 or 3 units. Similarly, a group with 1 to 5 units refers to a group with 1, 2, 3, 4 or 5 units, and so on.

[0454] Furthermore, the claims should not be read as limited to the order or elements provided unless otherwise stated. In addition, the use of the term "means for..." in any claim is intended to invoke 35 U.S.C. § 112, 6 or means-plus-function claim format, and any claim that does not use the term "means for..." does not have this intention.

Claims

1. A method implemented by a wireless transmit / receive unit (WTRU), the method comprising: Receive configuration information from a network node, the configuration information indicating: a first time period for receiving and measuring channel state information (CSI) by the WTRU, and predicting, by the WTRU, a size of a second time period for CSI, wherein the size of the second time period is less than or equal to a maximum size of the second time period, and wherein the second time period is after the first time period; receiving a plurality of CSI reference signals (CSI-RS) from the network node during the first time period; measuring a plurality of CSIs based on the plurality of CSI-RS; determining an updated size of the second time period, wherein the updated size of the second time period is based on a measurement performed on at least one CSI-RS of the received plurality of CSI-RSs, and wherein the updated size of the second time period is less than or equal to the maximum size of the second time period; as well as The updated size of the second time period and a plurality of predicted CSIs of the first time period are sent to the network node, wherein the plurality of predicted CSIs are generated using the plurality of CSIs.

2. The method according to claim 1, comprising: After the first time period expires, the following steps are periodically repeated: receiving a second plurality of CSI-RSs from the network node during a third time period; measuring a second plurality of CSIs based on the second plurality of CSI-RSs; determining an updated size of a fourth time period, wherein the updated size of the fourth time period is based on measurements performed on at least one CSI-RS of the second plurality of CSI-RSs, and wherein the updated size of the fourth time period is less than or equal to the maximum size of the second time period; as well as The updated size of the fourth time period and a second plurality of predicted CSIs for the second time period are sent to the network node, wherein the second plurality of predicted CSIs are generated using the second plurality of CSIs.

3. The method according to any one of claims 1 to 2, wherein: The multiple predicted CSIs are sent in a single transmission.

4. The method according to any one of claims 1 to 3, comprising: Sending information indicating completion of generating the predicted CSI to the network node.

5. The method according to any one of claims 1 to 4, comprising: sending a request for an uplink grant to the network node; receiving an uplink grant from the network node; as well as A report including the plurality of predicted CSIs is sent to the network node using the uplink grant.

6. The method according to claim 5, wherein: Determining the updated size of the second time period is also based on the uplink grant.

7. The method according to any one of claims 1 to 6, comprising: receiving, from the network node, a request message for obtaining the WTRU's ability to perform CSI prediction; as well as A response message is sent to the network node, the response message including information indicating the maximum size of the second time period.

8. The method according to any one of claims 1 to 7, comprising: determining, for at least one CSI-RS among the received plurality of CSI-RSs, a difference between predicted CSI generated using the at least one CSI and a CSI measurement based on the at least one CSI-RS; as well as Information indicative of the difference is sent to the network node.

9. The method according to any one of claims 1 to 8, wherein: The plurality of predicted CSIs are generated using a trained CSI prediction artificial intelligence (AI) / machine learning (ML) model.

10. The method according to claim 9, wherein: The maximum size of the second time period is based on the performance of the trained CSI prediction AI / ML model.

11. The method according to any one of claims 9 to 10, further comprising: Sending a request to the network node to update and / or retrain the CSI prediction AI / ML model.

12. A wireless transmit / receive unit (WTRU) comprising a circuit system including a transmitter, a receiver, a processor, and a memory, the WTRU being configured to: Receive configuration information from a network node, the configuration information indicating: a first time period for receiving and measuring channel state information (CSI), and predicting, by the WTRU, a size of a second time period for CSI, wherein the size of the second time period is less than or equal to a maximum size of the second time period, and wherein the second time period is after the first time period; receiving a plurality of CSI reference signals (CSI-RS) from the network node during the first time period; measuring a plurality of CSIs based on the plurality of CSI-RS; determining an updated size of the second time period, wherein the updated size of the second time period is based on a measurement performed on at least one CSI-RS of the plurality of CSI-RSs, and wherein the updated size of the second time period is less than or equal to the maximum size of the second time period; as well as The updated size of the second time period and a plurality of predicted CSIs of the first time period are sent to the network node, wherein the predicted CSI is generated using the plurality of CSIs.

13. The WTRU of claim 12, wherein the WTRU is configured to: After the first time period expires, the following steps are periodically repeated: receiving a second plurality of CSI-RSs from the network node during a third time period; measuring a second plurality of CSIs based on the second plurality of CSI-RSs; determining an updated size of a fourth time period, wherein the updated size of the fourth time period is based on a measurement performed on at least one of the CSI-RSs in the second plurality of CSI-RSs, and wherein the updated size of the fourth time period is less than or equal to the maximum size of the second time period; as well as The updated size of the fourth time period and a second plurality of predicted CSIs for the second time period are sent to the network node, wherein the second plurality of predicted CSIs are generated using the second plurality of CSIs.

14. The WTRU of any one of claims 12 to 14, wherein: The multiple predicted CSIs are sent in a single transmission.

15. The WTRU according to any one of claims 12 to 14, the WTRU being configured to: Sending information indicating completion of generating the predicted CSI to the network node.

16. The WTRU according to any one of claims 12 to 15, wherein the WTRU is configured to: sending a request for an uplink grant to the network node; receiving an uplink grant from the network node; and A report including the plurality of predicted CSIs is sent to the network node using the uplink grant.

17. The WTRU of claim 16 wherein: Determination of the updated size of the second time period is also based on the uplink grant.

18. The WTRU according to any one of claims 12 to 17, wherein the WTRU is configured to: receiving a request message from the network node for obtaining the WTRU's ability to perform CSI prediction; and A response message is sent to the network node, the response message including information indicating the maximum size of the second time period.

19. The WTRU according to any one of claims 12 to 18, wherein the WTRU is configured to: determining, for at least one CSI-RS among the received plurality of CSI-RSs, a difference between predicted CSI generated using the at least one CSI and a CSI measurement based on the at least one CSI-RS; and Information indicative of the difference is sent to the network node.

20. The WTRU of any one of claims 12 to 19, wherein: The plurality of predicted CSIs are generated using a trained CSI prediction artificial intelligence (AI) / machine learning (ML) model.

21. The WTRU of claim 20 wherein: The maximum size of the second time period is based on the performance of the trained CSI prediction AI / ML model.

22. The WTRU according to any one of claims 20 to 21, wherein the WTRU is configured to send a request to the network node to update and / or retrain the CSI prediction AI / ML model.

Images