MMWAVE Cell Discovery in Ultra-Dense Networks

Abstract

A wireless transmit / receive unit (WTRU) may perform cell selection and / or beam association as described herein. The WTRU may use context information, such as location, to enable cell selection and / or beam association. The WTRU may be configured with resources for reporting the WTRU context information. In response to the context information, the WTRU may receive assistance information associated with one or more cells to enable cell selection and / or beam association. For example, the WTRU may receive a defined subset of measurement resources in response to a transmission of a location on the resources. The WTRU may determine a base station (BS) and / or a beam pair (BP) based on the assistance information. The WTRU may perform transmission to a BS using at least one beam of the BP.

Description

[Technical Field]

[0001] (CROSS-REFERENCE TO RELATED APPLICATIONS) This application claims priority to U.S. Provisional Patent Application No. 63 / 314,782, filed in the United States on February 28, 2022, and U.S. Provisional Patent Application No. 63 / 421,456, filed in the United States on November 1, 2022, the entire contents of which are incorporated herein by reference. [Background technology]

[0002] Millimeter wave (MMWAVE) cell discovery in emerging mobile networks may have relatively high signal directionality. Exhaustive periodic beam sweeping (e.g., which may have relatively high latency) may be used. Hierarchical beam sweeping may be used to reduce latency. Additionally and / or alternatively, artificial intelligence (AI) may be used to reduce latency.

[0003] To address the capacity crunch problem faced by existing networks, emerging networks may use frequency spectrum within the MMWAVE range. However, MMWAVE may have a relatively short coverage range due to path loss that occurs at MMWAVE frequencies. To compensate for this, MMWAVE systems may rely on directional antennas, which may make cell discovery more difficult compared to using more traditional omnidirectional antennas. Furthermore, MMWAVE signals may be susceptible to environmental variations that result in blockages. For these reasons, successful MMWAVE base station (BS) discovery may depend on proper beam alignment between a wireless transmit / receive unit (WTRU) and an MMWAVE BS, which refers to the process of finding the best beamforming direction between the WTRU and the BS for transmission and reception during initial access to establish an MMWAVE link before data can be transmitted. Summary of the Invention

[0004] A wireless transmit / receive unit (WTRU) may perform cell selection and / or beam association as described herein. The WTRU may perform cell reselection and / or beam association in one or more phases. For example, the WTRU may perform cell reselection and / or beam association using a two-phase procedure as described herein. The WTRU may use context information, such as the WTRU's location, to enable the first phase of cell selection and / or beam association. The WTRU may refine the cell selection and / or beam association during the second phase of the procedure.

[0005] Systems, methods, and apparatuses for performing cell selection and / or beam association are described herein. In an example, a WTRU may receive system information about one or more cells (e.g., a set of cells). The WTRU may be configured with resources for reporting WTRU context information, such as the WTRU's location (e.g., via System Information (SI), Radio Resource Control (RRC), Medium Access Control (MAC) Control Element (CE), and / or Downlink Control Information (DCI)). The resources may be indicated in the system information. Additionally or alternatively, the resources may be configured by the RRC (e.g., to enable mobility to different cells). The WTRU may be configured to determine and / or report the context information. The WTRU may transmit the determined context information (e.g., regarding the resources). The WTRU may receive a defined subset of measurement resources associated with one or more cells to enable cell selection and / or beam association based on the context information. For example, the WTRU may receive a defined subset of measurement resources in response to a location transmission on the resources. The WTRU may determine a cell and / or beam pair (BP) of a base station (BS) based on measurements performed on the defined subset of measurement resources. The WTRU may perform a first transmission to the BS using one or more of the beams (e.g., uplink (UL)) of the BP.

[0006] The WTRU may be configured to improve beam pairing quality. The WTRU may be able to determine and / or indicate whether fine-tuning is enabled (e.g., as a function of WTRU service requirements). In an example, the WTRU may report one or more first measurements and / or report one or more service requirements. For example, the WTRU may report one or more first measurement results to the BS (e.g., via one or more of the BP's beams). For example, the WTRU may report one or more service requirements to the BS (e.g., via one or more of the first BP's beams). The WTRU may receive a second defined subset of measurement resources associated with the BS (e.g., in response to the one or more first measurements and / or the service requirements). The WTRU may determine a second BP having a beamwidth narrower than the beamwidth of the first BP (e.g., based on a second measurement performed on the second defined subset of measurement resources). The WTRU may perform a second transmission to the BS using one or more of the second BP's beams (e.g., an UL transmission).

[0007] Hierarchical low-latency, low-power initial access may be used. One or more coverage quality indicators (e.g., reference signal received power (RSRP)) and / or WTRU location obtained (e.g., via Minimization of Drive Test (MDT) traces) may be used by the AI. A first of two or more phases may use AI techniques to predict WTRU-base station (BS) association with a relatively wide beam. The first phase may provide a single wide beam and / or an ordered list of candidates to the remaining phases, which may use different techniques (e.g., conventional beam sweeping) to sort the candidates and / or transition to a narrower beam if user demand necessitates.

[0008] The WTRU may report its location to enable AI-based cell detection. For example, the WTRU may implement one or more methods, receive one or more resources, and / or receive one or more triggers to report its location. The WTRU may perform AI-based cell detection in response to measurements and / or broadcasted information. The WTRU may receive a configuration for a cell / beam before accessing a cell. The WTRU may use a DL beam pair for UL transmission. The WTRU may report a preferred cell, beam, and / or beam pair. [Brief explanation of the drawings]

[0009] [Figure 1A] FIG. 1A is a system diagram illustrating an example communication system in which one or more disclosed embodiments may be implemented. [Figure 1B] FIG. 1B is a system diagram illustrating an exemplary wireless transmit / receive unit (WTRU) that may be used within the communication system illustrated in FIG. 1A, according to one embodiment. [Figure 1C] FIG. 1C is a system diagram illustrating an example radio access network (RAN) and an example core network (CN) that may be used within the communication system illustrated in FIG. 1A, according to one embodiment. [Figure 1D] FIG. 1D is a system diagram illustrating a further exemplary RAN and a further exemplary CN that may be used within the communication system illustrated in FIG. 1A, according to one embodiment. [Figure 1E] FIG. 1E is a schematic, illustrative diagram of an exemplary system environment for training and applying artificial intelligence (AI) / machine learning (ML) models. [Figure 2] FIG. 2 illustrates an example network topology showing base station (BS) locations, array orientations, sweep directions, and sample WTRU distributions. [Figure 3] FIG. 3 illustrates exemplary simulation parameters. [Figure 4] FIG. 4 illustrates an example process that may be implemented to perform cell selection and / or beam association using AI / ML. [Figure 5] FIG. 5 illustrates exemplary accurate and inaccurate predictions using the k-nearest neighbor (KNN) algorithm. [Figure 6] FIG. 6 illustrates an exemplary deep neural network (DNN) architecture, where ReLU (rectified linear unit) activation may be used for layers dense_1 and dense_2, the output layer may have a sigmoid activation, the loss function used may be a sparse categorical entropy function, and the optimizer may be an Adam optimization function. [Figure 7] FIG. 7 illustrates an exemplary average precision of the ML algorithm. [Figure 8] FIG. 8 illustrates exemplary receiver operating characteristics (ROC) for a KNN classifier for one or more classes. [Figure 9] FIG. 9 illustrates an exemplary impact of ML-based prediction on RSRP. [Figure 10A] FIG. 10A illustrates a system flow diagram depicting an example of a communication procedure for determining a configuration for cell selection and / or beam association (e.g., beam pair). [Figure 10B] FIG. 10B illustrates a system flow diagram depicting an example of a communication procedure for improving configuration for cell selection and / or beam association (e.g., beam pairing). DETAILED DESCRIPTION OF THE INVENTION

[0010] 1A is a diagram illustrating an example communication system 100 in which one or more disclosed embodiments may be implemented. Communication system 100 may be a multiple-access system that provides content, such as voice, data, video, messaging, broadcasts, etc., to multiple wireless users. Communication system 100 may enable multiple wireless users to access such content through sharing of system resources, including wireless bandwidth. For example, the communication system 100 may use 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 unique-word DFT-Spread OFDM (ZT UW DTS-s OFDM), unique word OFDM (UW-OFDM), resource block filtered OFDM, filter bank multicarrier (FBMC), etc.

[0011] 1A, communications system 100 may include wireless transmit / receive units (WTRUs) 102a, 102b, 102c, 102d, RANs 104 / 113, CNs 106 / 115, public switched telephone network (PSTN) 108, the Internet 110, and other networks 112, although it will be understood that the disclosed embodiments contemplate any number of WTRUs, base stations, networks, and / or network elements. Each of 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 user equipment (UE), mobile stations, fixed or mobile subscriber units, subscription-based units, pagers, mobile phones, personal digital assistants (PDAs), smartphones, laptops, netbooks, personal computers, wireless sensors, hotspots or Mi-Fi devices, Internet of Things (ioT) devices, watches or other wearable, head-mounted displays (HMDs), vehicles, drones, medical devices and applications (e.g., for remote surgery), industrial devices and applications (e.g., robots and / or other wireless devices operating in industrial and / or automated processing chain contexts), consumer electronics devices, devices operating on commercial and / or industrial wireless networks, etc. Any of the WTRUs 102a, 102b, 102c, and 102d may be referred to interchangeably as a UE.

[0012] The communications 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 to facilitate access to one or more communications networks, such as the CN 106 / 115, the Internet 110, and / or other networks 112. By way of example, the base stations 114a, 114b may be a base station transceiver station (BTS), a Node B, an eNodeB, a Home Node B, a Home eNodeB, a gNB, an NR Node B, a site controller, an access point (AP), a wireless router, etc. Although the base stations 114a, 114b are each depicted as a single element, it will be understood that the base stations 114a, 114b may include any number of interconnected base stations and / or network elements.

[0013] 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 base station 114b may be configured to transmit and / or receive radio signals on one or more carrier frequencies, which may be referred to as a cell (not shown). These frequencies may be licensed spectrum, unlicensed spectrum, or a combination of licensed and unlicensed spectrum. A cell may provide wireless service coverage for a particular geographic area, which may be relatively fixed or may change over time. A cell may be further divided into cell sectors. For example, the cell associated with the base station 114a may be divided into three sectors. Thus, in one embodiment, the base station 114a may include three transceivers, i.e., one transceiver for each sector of the cell. In one embodiment, the base station 114a may employ multiple-input multiple output (MIMO) technology and may utilize multiple transceivers per sector of the cell, for example, using beamforming to transmit and / or receive signals in desired spatial directions.

[0014] 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).

[0015] More specifically, as noted above, the communications system 100 may be a multiple-access system, but may use one or more channel access schemes, such as CDMA, TDMA, FDMA, OFDMA, SC-FDMA, etc. For example, the base station 114 a and the WTRUs 102 a, 102 b, 102 c in the RAN 104 / 113 may implement a radio technology such as Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access (UTRA), which may establish the air interface 115 / 116 / 117 using wideband CDMA (WCDMA). WCDMA may include communications protocols such as High-Speed ​​Packet Access (HSPA) and / or Evolved HSPA (HSPA+). HSPA may include High-Speed ​​Downlink (DL) Packet Access (HSDPA) and / or High-Speed ​​Uplink Packet Access (HSUPA).

[0016] In one 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-A Pro).

[0017] In one embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement a radio technology such as New Radio (NR) radio access, which may establish the air interface 116 using NR technology.

[0018] In one 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, e.g., using dual connectivity (DC) principles. Thus, the air interface utilized 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).

[0019] In other embodiments, the base station 114a and the WTRUs 102a, 102b, 102c may implement a wireless technology such as IEEE 802.11 (i.e., Wireless Fidelity, WiFi), 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), or the like.

[0020] 1A may be, for example, a wireless router, a Home NodeB, a Home eNodeB, or an access point and may utilize any suitable RAT to facilitate wireless connectivity in a local area such as a business, a home, a vehicle, a campus, an industrial facility, an air corridor (e.g., for use by drones), a road, etc. In one 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 one 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 yet another 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 a picocell or femtocell. 1A, the base station 114b may have a direct connection to the Internet 110. Therefore, the base station 114b may not need to access the Internet 110 through the CN 106 / 115.

[0021] The RAN 104 / 113 may communicate with the CN 106 / 115, which may be any type of network configured to provide voice, data, application, and / or voice over internet protocol (VoIP) services to one or more of the WTRUs 102a, 102b, 102c, 102d. The data may have various quality of service (QoS) requirements, such as different throughput, latency, error tolerance, reliability, data throughput, and mobility requirements. The CN 106 / 115 may provide call control, billing services, mobile location-based services, prepaid calling, Internet connectivity, video distribution, and / or perform high-level security functions such as user authentication. Although not shown in FIG. 1A , it will be understood that the RAN 104 / 113 and / or the CN 106 / 115 may communicate directly or indirectly with other RANs employing the same RAT as the RAN 104 / 113 or a different RAT. For example, in addition to being connected to the RAN 104 / 113, which may utilize NR radio technology, the CN 106 / 115 may also communicate with another RAN (not shown) using GSM, UMTS, CDMA2000, WiMAX, E-UTRA, or WiFi radio technology.

[0022] 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 providing 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) of the TCP / IP Internet protocol suite. The network 112 may include wired and / or wireless communication networks owned and / or operated by other service providers. For example, the network 112 may include another CN connected to one or more RANs, which may use the same RAT as the RAN 104 / 113 or a different RAT.

[0023] Some or all of the WTRUs 102a, 102b, 102c, 102d in the communications 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 over different wireless links.) For example, the WTRU 102c shown in FIG. 1A may be configured to communicate with a base station 114a, which may employ a cellular-based wireless technology, and a base station 114b, which may employ an IEEE 802.2 wireless technology.

[0024] 1B is a system diagram illustrating an example WTRU 102. As shown in FIG. 1B, 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 peripherals 138. It will be understood that the WTRU 102 may include any sub-combination of the foregoing elements while remaining consistent with an embodiment.

[0025] The processor 118 may be a general-purpose processor, a special-purpose processor, a conventional processor, a digital signal processor (DSP), multiple 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. While FIG. 1B depicts the processor 118 and the transceiver 120 as separate components, it will be understood that the processor 118 and the transceiver 120 may be integrated together in an electronic package or chip.

[0026] The transmit / receive element 122 may be configured to transmit or receive signals to or from a base station (e.g., base station 114a) over the air interface 116. For example, in one embodiment, the transmit / receive element 122 may be an antenna configured to transmit and / or receive RF signals. In one embodiment, the transmit / receive element 122 may be an emitter / detector configured to transmit and / or receive IR, UV, or visible light signals, for example. In yet another embodiment, the transmit / receive element 122 may be configured to transmit and / or receive both RF and light signals. It will be understood that the transmit / receive element 122 may be configured to transmit and / or receive any combination of wireless signals.

[0027] 1B as a single element, the WTRU 102 may include any number of transmit / receive elements 122. More specifically, the WTRU 102 may employ MIMO technology. Thus, in one 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.

[0028] The transceiver 120 may be configured to modulate signals transmitted by the transmit / receive element 122 and demodulate signals received by the transmit / receive element 122. As noted above, the WTRU 102 may have multi-mode capabilities. Thus, the transceiver 120 may include multiple transceivers to enable the WTRU 102 to communicate via multiple RATs, such as, for example, NR and IEEE 802.11.

[0029] The processor 118 of the WTRU 102 may be coupled to and may receive user-entered 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. Additionally, the processor 118 may access information from and store data in any type of suitable memory, such as non-removable memory 130 and / or removable memory 132. The non-removable memory 130 may include random-access memory (RAM), 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 memory that is not physically located on the WTRU 102, such as on a server or home computer (not shown).

[0030] The processor 118 may receive power from the power source 134 and may be configured to distribute and / or control the power to other components in the WTRU 102. The power source 134 may be any suitable device for providing power to the WTRU 102. For example, the power source 134 may include one or more dry batteries (e.g., nickel-cadmium (NiCd), nickel-zinc (NiZn), nickel metal hydride (NiMH), lithium-ion (Li-ion), etc.), solar cells, fuel cells, etc.

[0031] The processor 118 may also be coupled to a 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 instead of, information from the GPS chipset 136, the WTRU 102 may receive location information from base stations (e.g., base stations 114a, 114b) over the air interface 116 and / or determine its location based on the timing of signals received from two or more nearby base stations. It will be appreciated that the WTRU 102 may obtain location information by way of any suitable location-determination method while remaining consistent with an embodiment.

[0032] The processor 118 may further be coupled to other peripherals 138, which may include one or more software and / or hardware modules that provide additional features, functionality, and / or wired or wireless connectivity. For example, the peripherals 138 may include an accelerometer, an electronic compass, a satellite transceiver, a digital camera (for photos and / or videos), a universal serial bus (USB) port, a vibration device, a television transceiver, a hands-free headset, a Bluetooth module, a frequency modulated (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. The peripheral device 138 may include one or more sensors, which may be one or more of a gyroscope, an accelerometer, a Hall effect sensor, a magnetometer, a direction sensor, a proximity sensor, a temperature sensor, a time sensor, a geolocation sensor, an altimeter, a light sensor, a touch sensor, a magnetometer, a barometer, a gesture sensor, a biometric sensor, and / or a humidity sensor.

[0033] The WTRU 102 may include a full-duplex radio where transmission and reception of some or all of the signals associated with a particular subframe (e.g., for both the UL (e.g., for transmission) and downlink (e.g., for reception)) may be parallel and / or simultaneous. The full-duplex radio may include an interference management unit 139 for reducing and or substantially eliminating self-interference through either hardware (e.g., chokes) or signal processing via a processor (e.g., via a separate processor (not shown) or processor 118). In one embodiment, the WTRU 102 may include a half-duplex radio for transmission and reception of either some or all of the signals (e.g., associated with a particular subframe for either the UL (e.g., for transmission) or downlink (e.g., for reception)).

[0034] 1C is a system diagram illustrating the RAN 104 and the CN 106, according to one embodiment. As mentioned above, the RAN 104 may employ E-UTRA radio technology to communicate with the WTRUs 102a, 102b, 102c over the air interface 116. The RAN 104 may also communicate with the CN 106.

[0035] The RAN 104 may include eNodeBs 160a, 160b, and 160c, although it will be understood that the RAN 104 may include any number of eNodeBs while remaining consistent with an embodiment. The eNodeBs 160a, 160b, and 160c may each include one or more transceivers for communicating with the WTRUs 102a, 102b, and 102c over the air interface 116. In an embodiment, the eNodeBs 160a, 160b, and 160c may implement MIMO technology. Thus, the eNodeB 160a may, for example, use multiple antennas to transmit wireless signals to and / or receive wireless signals from the WTRU 102a.

[0036] Each of the eNodeBs 160a, 160b, 160c may be associated with a particular cell (not shown) and may be configured to handle radio resource management decisions, handover decisions, scheduling of users in the UL and / or DL, etc. As shown in FIG. 1C, the eNodeBs 160a, 160b, 160c may communicate with one another via an X2 interface.

[0037] 1C may include a mobility management entity (MME) 162, a serving gateway (SGW) 164, and a packet data network (PDN) gateway (or PGW) 166. Although each of the foregoing elements is depicted as part of the CN 106, it will be understood that any of these elements may be owned and / or operated by an entity other than the CN operator.

[0038] The MME 162 may be connected to each of the eNodeBs 162a, 162b, 162c in the RAN 104 via an S1 interface and may function as a control node. For example, the MME 162 may be responsible for authenticating users of the WTRUs 102a, 102b, 102c, activating / deactivating bearers, selecting a particular serving gateway during 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.

[0039] The SGW 164 may be connected to each of the eNodeBs 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-eNodeB handover, triggering paging when DL data is available to the WTRUs 102a, 102b, 102c, and managing and storing the context of the WTRUs 102a, 102b, 102c.

[0040] The SGW 164 may be connected to a PGW 166, which may provide the WTRUs 102a, 102b, 102c with access to packet-switched networks, such as the Internet 110, to facilitate communication between the WTRUs 102a, 102b, 102c and IP-enabled devices.

[0041] 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 landline communications devices. For example, the CN 106 may include or communicate with an IP gateway (e.g., an IP multimedia subsystem (IMS) server) that serves 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.

[0042] Although the WTRU is illustrated in FIGS. 1A-1D as a wireless terminal, it is contemplated that in certain representative embodiments, such a terminal may use a wired communication interface (e.g., temporarily or permanently) with the communication network.

[0043] In a representative embodiment, the other network 112 may be a WLAN.

[0044] A WLAN in infrastructure basic service set (BSS) mode may have an access point (AP) of the BSS and one or more stations (STAs) associated with the AP. The AP may have access or interface to a distribution system (DS) or another type of wired / wireless network that carries traffic into and / or out of the BSS. Traffic originating outside the BSS to a STA may arrive through the AP and be sent to the STA. Traffic originating at a STA and destined for a destination outside the BSS may be sent to the AP to be sent to the respective destination. Traffic between STAs within a BSS may be sent through the AP, for example, where the source STA may send traffic to the AP, and the AP may send traffic to the destination STA. Traffic between STAs within a BSS may be considered and / or referred to as peer-to-peer traffic. Peer-to-peer traffic may be sent between (e.g., directly between) a source STA and a destination STA using a direct link setup (DLS). In certain representative embodiments, the DLS may use 802.11e DLS or 802.11z tunneled DLS (TDLS). A WLAN using an Independent BSS (IBSS) mode may not have an AP, and STAs within or using the IBSS (e.g., all of the STAs) may communicate directly with each other. The IBSS mode of communication may be referred to herein as an "ad hoc" communication mode.

[0045] When using the 802.11ac infrastructure mode of operation or a similar mode of operation, an AP may transmit beacons on a fixed channel, such as a primary channel. The primary channel may be a fixed width (e.g., a 20 MHz wide bandwidth) or a width that is dynamically configured via signaling. The primary channel may be the operating channel of the BSS, but may also be used by STAs to establish a connection with the AP. In certain representative embodiments, for example, in an 802.11 system, Carrier Sense Multiple Access with Collision Avoidance (CSMA / CA) may be implemented. With CSMA / CA, STAs (e.g., all STAs), including the AP, may sense the primary channel. If the primary channel is sensed / detected and / or determined to be busy by a particular STA, the particular STA may back off. One STA (e.g., only one station) may transmit in a given BSS at any given time.

[0046] High Throughput (HT) STAs may use 40 MHz wide channels for communication, which may be formed, for example, through a combination of a primary 20 MHz channel and adjacent or non-adjacent 20 MHz channels.

[0047] A Very High Throughput (VHT) STA may support channels with widths of 20 MHz, 40 MHz, 80 MHz, and / or 160 MHz. A 40 MHz and / or 80 MHz channel may be formed by combining adjacent 20 MHz channels. A 160 MHz channel may be formed by combining eight contiguous 20 MHz channels or by combining two non-adjacent 80 MHz channels, which may be referred to as an 80+80 configuration. For the 80+80 configuration, after channel encoding, the data may pass through a segment parser that may separate the data into two streams. Inverse Fast Fourier Transform (IFFT) processing and time-domain processing may be performed separately on each stream. The streams may be mapped to two 80 MHz channels, and the data may be transmitted by the transmitting STA. At the receiver of the receiving STA, the operations described above for the 80+80 configuration may be reversed, and the combined data may be sent to Medium Access Control (MAC).

[0048] Sub-1 GHz operating modes are supported by 802.11af and 802.11ah. Channel operating bandwidths and carriers are reduced in 802.11af and 802.11ah compared to those used in 802.11n and 802.11ac. 802.11af supports 5 MHz, 10 MHz, and 20 MHz bandwidths in the TV White Space (TVWS) spectrum, while 802.11ah supports 1 MHz, 2 MHz, 4 MHz, 8 MHz, and 16 MHz bandwidths using non-TVWS spectrum. According to representative embodiments, 802.11ah may support meter-type control / machine-type communications, such as MTC devices within macro coverage areas. MTC devices may have limited capabilities, including support for (e.g., only) certain and / or limited bandwidths. MTC devices may include batteries with above-threshold battery life (e.g., to maintain very long battery life).

[0049] WLAN systems that can support multiple channels and channel bandwidths, such as 802.11n, 802.11ac, 802.11af, and 802.11ah, include a channel that can be designated as a primary channel. The primary channel can have a bandwidth equal to the maximum common operating bandwidth supported by all STAs in the BSS. The bandwidth of the primary channel can be configured and / or limited by the STAs among all STAs operating in the BSS that support the minimum bandwidth operating mode. In an 802.11ah embodiment, the primary channel can be 1 MHz wide for STAs (e.g., MTC-type devices) that support (e.g., only) the 1 MHz mode, even if the AP and other STAs in the BSS support 2 MHz, 4 MHz, 8 MHz, 16 MHz, and / or other channel bandwidth operating modes. Carrier sensing and / or Network Allocation Vector (NAV) configuration can depend on the status of the primary channel. For example, if the primary channel is active due to a STA (that only supports 1 MHz mode of operation) transmitting to the AP, the entire available frequency band may be considered active, even though most of the frequency band may remain inactive and available.

[0050] 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.

[0051] 1D is a system diagram illustrating the RAN 113 and the CN 115, according to one embodiment. As noted 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 communicate with the CN 115.

[0052] The RAN 113 may include gNBs 180a, 180b, and 180c, although it will be understood that the RAN 113 may include any number of gNBs while remaining consistent with an embodiment. The gNBs 180a, 180b, and 180c may each include one or more transceivers for communicating with the WTRUs 102a, 102b, and 102c over the air interface 116. In an embodiment, the gNBs 180a, 180b, and 180c may implement MIMO technology. For example, the gNB 180a, 180b may transmit signals to and / or receive signals from the gNBs 180a, 180b, and 180c using beamforming. Thus, the gNB 180a may transmit and / or receive wireless signals to and / or from the WTRU 102a using, for example, multiple antennas. In one 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 on unlicensed spectrum, while the remaining component carriers may be on licensed spectrum. In one embodiment, the gNBs 180a, 180b, 180c may implement Coordinated Multi-Point (CoMP) technology. For example, the WTRU 102a may receive coordinated transmissions from the gNBs 180a and 180b (and / or 180c).

[0053] The WTRUs 102a, 102b, 102c may communicate with the gNBs 180a, 180b, 180c using transmissions associated with scalable numerology. 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 different or scalable lengths (e.g., including different numbers of OFDM symbols and / or lasting different lengths of absolute time).

[0054] 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 accessing another RAN (e.g., eNodeBs 160a, 160b, 160c, etc.). In a standalone configuration, the WTRUs 102a, 102b, 102c may utilize one or more of the gNBs 180a, 180b, 180c as mobility anchor points. In a standalone configuration, the WTRUs 102a, 102b, 102c may communicate with the gNBs 180a, 180b, 180c using signals in unlicensed bands. In a non-standalone configuration, the WTRUs 102a, 102b, 102c may communicate with and connect to gNBs 180a, 180b, 180c while also communicating with and connecting to another RAN, such as eNodeBs 160a, 160b, 160c. For example, the WTRUs 102a, 102b, 102c may implement DC principles to communicate with one or more gNBs 180a, 180b, 180c and one or more eNodeBs 160a, 160b, 160c substantially simultaneously. In a non-standalone configuration, the eNodeBs 160a, 160b, 160c may act as mobility anchors for the WTRUs 102a, 102b, 102c, and the gNBs 180a, 180b, 180c may provide additional coverage and / or throughput for serving the WTRUs 102a, 102b, 102c.

[0055] 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, scheduling of users in the UL and / or DL, support for network slicing, dual connectivity, interworking between NR and E-UTRA, routing of user plane data to User Plane Functions (UPFs) 184a, 184b, routing of control plane information to Access and Mobility Management Functions (AMFs) 182a, 182b, etc. As shown in FIG. 1D , the gNBs 180a, 180b, 180c may communicate with each other via an Xn interface.

[0056] 1D may include at least one AMF 182a, 182b, at least one UPF 184a, 184b, at least one Session Management Function (SMF) 183a, 183b, and possibly a Data Network (DN) 185a, 185b. While each of the foregoing elements is depicted as part of the CN 115, it will be understood that any of these elements may be owned and / or operated by an entity other than the CN operator.

[0057] The AMF 182a, 182b may be connected to one or more of the gNBs 180a, 180b, 180c in the RAN 113 via an N2 interface and may function as a control node. For example, the AMF 182a, 182b may be responsible for authenticating users of the WTRUs 102a, 102b, 102c, supporting network slicing (e.g., handling different PDU sessions with different requirements), selecting a particular SMF 183a, 183b, managing registration areas, terminating NAS signaling, mobility management, etc. Network slicing may be used by the AMF 182a, 182b to customize the CN support of the WTRUs 102a, 102b, 102c based on the type of service utilizing the WTRUs 102a, 102b, 102c. 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 machine type communication (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 WiFi.

[0058] The SMFs 183a and 183b may be connected to the AMFs 182a and 182b in the CN 115 via an N11 interface. The SMFs 183a and 183b may also be connected to the UPFs 184a and 184b in the CN 115 via an N4 interface. The SMFs 183a and 183b may select and control the UPFs 184a and 184b and configure the routing of traffic through the UPFs 184a and 184b. The SMFs 183a and 183b may perform other functions, such as managing and allocating UE IP addresses, managing PDU sessions, controlling policy enforcement and QoS, and providing downlink data notification. PDU session types may be IP-based, non-IP-based, Ethernet-based, etc.

[0059] The UPFs 184a, 184b may be connected to one or more of the gNBs 180a, 180b, 180c in the RAN 113 via an N3 interface, 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. The UPFs 184, 184b may perform other functions such as routing and forwarding packets, enforcing user plane policy, supporting multi-homed PDU sessions, handling user plane QoS, buffering downlink packets, providing mobility anchoring, etc.

[0060] The CN 115 may facilitate communication with other networks. For example, the CN 115 may include or communicate with an IP gateway (e.g., an IP Multimedia Subsystem (IMS) server) that acts 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 one embodiment, the WTRUs 102a, 102b, 102c may be connected to local data networks (DNs) 185a, 185b through the UPFs 184a, 184b via an N3 interface to the UPFs 184a, 184b and an N6 interface between the UPFs 184a, 184b and the DNs 185a, 185b.

[0061] 1A-1D and the corresponding descriptions thereof, one or more or all of the functions described herein with respect to one or more of the WTRUs 102a-d, base stations 114a-b, eNode-Bs 160a-c, MME 162, SGW 164, PGW 166, gNBs 180a-c, AMFs 182a-ab, UPFs 184a-b, SMFs 183a-b, DNs 185a-b, and / or any other devices described herein may be performed by one or more emulation devices (not shown). The emulation devices may be one or more devices configured to emulate one or more or all of the functions described herein. For example, the emulation devices may be used to test other devices and / or simulate network and / or WTRU functions.

[0062] The emulation devices may be designed to implement one or more tests of other devices in a lab environment and / or an operator network environment. For example, one or more emulation devices may perform one or more or all functions while fully or partially implemented and / or deployed as part of a wired and / or wireless communication network to test other devices in the communication network. One or more emulation devices may perform one or more or all functions while temporarily implemented / deployed as part of a wired and / or wireless communication network. The emulation devices may be directly coupled to another device for testing purposes and / or may perform the tests using terrestrial wireless communication.

[0063] One or more emulation devices may perform one or more functions, inclusive, while not being implemented / deployed as part of a wired and / or wireless communication network. For example, the emulation devices may be utilized in test scenarios in a test lab and / or in an undeployed (e.g., test) wired and / or wireless communication network to implement testing of one or more components. One or more emulation devices may be test equipment. Direct RF coupling and / or wireless communication via RF circuitry (which may include, e.g., one or more antennas) may be used by the emulation devices to transmit and / or receive data.

[0064] The systems, methods, and / or apparatus described herein may implement artificial intelligence (AI) and / or machine learning (ML). For example, one or more devices in the communications system 100 may implement AI / ML. One or more of the WTRUs 102a, 102b, 102c, 102d, the RAN 104 / 113, and / or the CN 106 / 115 may implement AI / ML. Additionally, other WTRUs, base stations, and / or network elements may implement AI / ML.

[0065] AI / ML may implement one or more algorithms configured to learn from data received as input. AI / ML may implement supervised learning or unsupervised learning. When implementing supervised learning, the AI / ML may receive training data as input, and the AI / ML's parameters may be trained toward a specific target output. The training data may be labeled to teach the AI / ML to learn from labeled data and test the accuracy of the AI / ML for implementation on unlabeled input data during generation. Supervised learning may be implemented for various types of AI / ML algorithms, including algorithms implementing linear regression, logistic regression, neural networks, decision trees, Bayesian logic, random forests, and / or support vector machines (SVMs). Supervised learning may be routinely utilized and / or implemented for classification and / or regression algorithms. Classification algorithms may be used to classify data into classes and / or categories. Exemplary classification algorithms may include a logistic regression algorithm, a naive Bayes algorithm, a k-nearest neighbor (KNN) algorithm, a decision tree algorithm, and / or a support vector machine. Regression algorithms may include a linear regression algorithm, a ridge regression algorithm, a neural network regression algorithm, a decision tree regression algorithm, a random forest algorithm, a KNN regression model, a support vector machine (SVM), a Gaussian regression algorithm, and / or a polynomial regression algorithm.

[0066] AI / ML may implement deep learning-based models. Neural networks (NNs) and / or deep neural networks (DNNs) may be common examples of AI / ML models that can be trained using supervised training. Various examples of NNs include perceptrons, multilayer perceptrons (MLPs), feedforward NNs, fully connected NNs, convolutional neural networks (CNNs), recurrent NNs (RNNs), long-short-term memory (LSTM) NNs, and / or residual NNs (ResNets). A perceptron is a NN that includes a function that multiplies the NN's input by learned weight coefficients to generate an output value. A feedforward NN is a NN that receives input at one or more nodes in an input layer and passes directional information through one or more hidden layers to one or more nodes in an output layer. In a feedforward NN, one or more nodes in a given layer may be connected to one or more nodes in another layer. A fully connected NN is a NN that includes an input layer, one or more hidden layers, and an output layer. In a fully connected NN, each node in a layer is connected to each node in another layer of the NN. An MLP is a fully connected class of feedforward NN. A CNN is a NN with one or more convolutional layers configured to perform convolutions. Various types of NNs may have elements that include one or more CNNs or convolutional layers, such as generative adversarial networks (GANs), conditional generative adversarial networks (CGANs), and / or cycle-consistent generative adversarial networks (CycleGANs). An RNN is inherently recursive because nodes include feedback connections and an internal hidden state (e.g., memory) that allows outputs from a node in the NN to influence subsequent inputs to the same node.An LSTM NN can be similar to an RNN in that nodes have feedback connections and an internal hidden state (e.g., memory). However, an LSTM NN can include additional gates to enable the LSTM NN to learn longer-term dependencies between sequences of data. A ResNet is an NN that can include skip connections to skip one or more layers of the NN.

[0067] FIG. 1E is a schematic, illustrative diagram of an exemplary system environment 101 for training and applying an AI / ML model implementing a NN 109a. However, other types of AI / ML models may be similarly trained and / or implemented. The NN 109a may be trained to determine and / or update parameters (e.g., hyperparameters) of the NN 109a. The raw data 103a may be generated from one or more sources. For example, the raw data 103a may include a set of information, such as image data, a set of text, or a set of network information related to a communication network, and / or other types of data. The raw data 103a may be preprocessed at 105a to generate training data 107. The preprocessing may include formatting or other types of processing to generate the training data 107 in a format for input to the NN 109a.

[0068] The NN 109a may include one or more layers 111a. The one or more layers 111a may include one or more input layers for receiving training data 107, one or more hidden layers, and / or one or more output layers for generating outputs 121. Each layer 111a may include one or more nodes that can be trained as described herein. The training data 107 may be in one or more formats, such as an image format, a tensor format (e.g., including a multidimensional array), etc.

[0069] During the training process 123, training data 107 may be input to the NN 109a and used to learn parameters. The parameters may include weights and / or biases of the NN 109a. The NN 109a may also include hyperparameters. The hyperparameters may include, for example, the number of epochs, the batch size, the number of layers, and / or the number of nodes in each layer. Parameters and hyperparameters may be used interchangeably. The parameters and / or hyperparameters may be adjusted during the training process. Training may be performed by initializing the parameters and / or hyperparameters of the NN 109a, accessing the training data 107, generating and inputting the training data 107 into the NN 109a, calculating a loss from the output of the neural network 109a to a target output 115 via a loss function 113 to update the parameters and / or hyperparameters (e.g., via gradient descent and associated backpropagation), and / or repeating the training process until a termination condition is achieved. The termination condition may be achieved when the output of the neural network 109a is within a predefined threshold of the target output 115.

[0070] Loss function 113 may be implemented using backpropagation-based gradient update and / or gradient descent techniques, such as stochastic gradient descent (SGD), synchronous SGD, asynchronous SGD, batch gradient descent, and / or mini-batch gradient descent. An optimizer may be implemented along with loss function 113. The optimizer may be implemented to update parameters and / or hyperparameters of neural network 109a.

[0071] After the training process 123 is completed, the trained parameters and / or hyperparameters 117 may be implemented by the neural network 109b in an operational or production process 125. During the operational or production process 125, the neural network 109b may receive input data 119 and generate output 121 using the trained parameters and / or hyperparameters 117. The input data 119 may be preprocessed from raw data 103b at 105b. For example, the raw data 103b may include similar types of data as the raw data 103a, which may be preprocessed similarly to the training data 107 used as input during the training process 123. The preprocessing may include formatting or other types of processing to generate the input data 119 in a format for input to the NN 109b. The output 121 may be within a predefined threshold of the target output 115 used during the training process 123. The output 121 may be one or more images, tensors, or other formatted outputs. Neural network 109b may include one or more layers 111b having a similar configuration to layer 111a after a training process 123. During an operational or production process 125, parameters and / or hyperparameters may be refined or optimized by being updated based on output 121.

[0072] In contrast to supervised learning in AI / ML as described herein, AI / ML may be used to implement unsupervised learning. AI / ML may receive training data as input and learn from the data without being trained toward a specific target output. For example, during unsupervised learning, AI / ML may receive unlabeled training data and determine patterns and / or similarities in the training data without being trained toward a specific target output. Unsupervised learning may be implemented to perform clustering, anomaly detection, and / or association of different types of input data. AI / ML may implement a hierarchical clustering algorithm, a k-means clustering algorithm, anomaly detection algorithm, a principal component analysis algorithm, and / or a priori algorithms.

[0073] As described herein, AI / ML may be implemented on one or more devices. For example, AI / ML may be implemented in whole or in part on one or more devices, such as one or more WTRUs, one or more base stations, and / or one or more other network entities, such as a network server. An example of a network in which AI / ML may be distributed may include a federated network. A federated network may include a distributed group of devices, each including an AI / ML module. AI / ML may be implemented for collaborative learning, in which the AI / ML module is trained across multiple devices. In another example, AI / ML may be trained at a centralized location or device, and one or more portions of the AI / ML module may be distributed to non-centralized locations. For example, updated parameters or hyperparameters may be sent to one or more devices to update the AI / ML module implemented thereon. Federated learning enables multiple actors to build a common, robust machine learning model without sharing data, thus addressing critical issues such as data privacy, data security, data access rights, and / or access to disparate data. Its applications may be widespread across several industries, including defense, telecommunications, IoT, and / or pharmaceuticals. A key open question at this time may be how inferior a model trained through federated data is to a model where the data is pooled. Another open question may relate to the trustworthiness of edge devices and / or the influence of malicious actors on the trained model.

[0074] The AI / ML described herein may be implemented as described herein using software and / or hardware. The AI / ML may be stored as computer-executable instructions on a computer-readable medium accessible by a processor to perform as described herein. Exemplary AI / ML environments and / or libraries may include TENSORFLOW, TORCH, PYTORCH, MATLAB, GOOGLE CLOUD AI and AUTOML, AMAZON SAGEMAKER, AZURE MACHINE LEARNING STUDIO, and / or ORACLE MACHINE LEARNING.

[0075] Cell discovery in millimeter wave (MMWAVE) networks may include legacy systems (e.g., legacy cell discovery). A legacy system may include a WTRU performing one or more permutations to acquire information on the WTRU operating in a given MMWAVE band. For example, the WTRU may sweep one or more (e.g., several) beams / beam pairs to determine the optimal cell / beam. Context information-based techniques / methods may be employed to reduce the complexity / latency associated with cell discovery in MMWAVE networks. Context information-based techniques / methods may be based on additional information. For example, the context information may include the WTRU position and / or location. Context information-based techniques may help reduce the complexity / latency. A hierarchical method may include a base station (BS) performing an exhaustive search across one or more wide beams. The hierarchical method may include evolving (e.g., iteratively evolving) to narrower beams.

[0076] Described herein are systems, methods, and apparatuses for performing low-latency cell discovery (e.g., in a beam-based environment). The systems, methods, and apparatuses may improve beam / cell selection complexity / latency by combining hierarchical search methods with AI / machine learning (ML). Described herein are embodiments for performing cell selection and / or beam association using two phases. The two-phase cell selection / beam association may include obtaining various coverage quality indicators (e.g., Reference Signal Received Power (RSRP) and / or WTRU location) (e.g., via a Minimization of Drive Test (MDT) trace). The various coverage quality indicators may be used by the BS (e.g., via the AI / ML portion of the two-phase cell selection / beam association). The first phase of the two-phase cell selection / beam association may use context information to reduce beam pairing latency. The first phase may provide either a single wide beam and / or an ordered list of candidates to the remaining phase or phases. One or more remaining phases may use different techniques (e.g., beam sweeping) to sort candidates and / or transition to narrower beams (e.g., in response to user demand).

[0077] The WTRU may use its location and / or other context information to enable the first phase of two-phase cell selection / beam association. The WTRU may report its location and / or other context information to enable the BS to perform cell search (e.g., including a method, resource, and / or trigger for reporting the location). The context information may include service requirements (e.g., reliability requirements, latency requirements, data type, amount of data to transmit, etc.), which may be reported. The report may include sending an indication of the WTRU's location and / or other context information. The indication may be explicit to explicitly identify the WTRU's location and / or other context information. The indication may implicitly indicate the WTRU's location and / or other context information. The indication may be explicit and / or implicit. The WTRU may receive assistance information from the BS in response to the location information and / or other information to enable configuration for the cell / beam (e.g., before accessing the cell). The assistance information may include an indication of a BS (e.g., a cell or set of cells) and / or at least one beam of a beam pair (BP). In one example, the assistance information may include a defined subset of measurement resources for one or more cells of the BS and / or at least one beam of a beam pair to enable cell selection and / or beam association.

[0078] The WTRU may update its cell selection and / or beam association. The updated cell selection and / or beam association may be performed in a second phase to allow refinement of a previously identified cell / beam pair. For example, the WTRU may update its cell selection / beam association to improve beam pairing quality in response to one or more service requirements of the WTRU. The WTRU may report the measurements and / or service requirements to the BS. The reporting may include sending an indication of information indicative of one or more measurements and / or one or more service requirements. The indication may be explicit, to explicitly indicate one or more measurements and / or one or more service requirements. The indication may be implicit, to implicitly indicate one or more measurements and / or one or more service requirements. The indication may be both explicit and implicit. The WTRU may receive a defined subset of measurement resources for performing cell selection and / or beam association (e.g., in response to the measurements and / or service requirements). The defined subset of measurement resources may enable the WTRU to determine an updated beam pair (e.g., narrower) compared to the original cell / beam pair. Although a two-phase cell selection / beam association procedure may be described herein, cell selection and / or beam association may be implemented in one or more phases. For example, the cell selection / beam association procedure may include a first phase of cell selection / beam association described herein. In another example, one or more portions of the first phase and / or second phase of the cell selection / beam association procedure may be implemented in a single phase or multiple phases.

[0079] There may be one or more techniques described herein that address cell discovery in MMWAVE networks. The techniques may implement AI / ML using one or more of naive non-ML techniques, ML-based techniques, and non-ML techniques that utilize context information (e.g., based on measurements of one or more possible cells and / or beams and / or beam pairs). The context information may include user position and / or location, channel gain, user spatial distribution, angles of arrival and departure, past multipath fingerprints, radar signals, sub-6 GHz band information in a control data plane split architecture, and / or antenna configuration. The terms WTRU position and WTRU location may be used interchangeably herein.

[0080] One or more naive non-ML techniques may be used. These techniques may be used to search for the optimal beam pair. For example, a sequential search pattern technique may be used. The sequential search pattern may rely on an exhaustive search through many beam pair combinations between the WTRU and the base station (BS) to find the optimal beam pair with the highest reference signal received power (RSRP). Alternatively, or additionally, a linear rotation pattern may be used. The linear rotation pattern may be an exhaustive search method that sweeps many beam pairs in either a counterclockwise or clockwise direction. Another technique may be a random starting point method in which the BS begins the sweeping process by randomly selecting one direction. This technique may then continue by using a sequential sweep method from the randomly selected starting point, or by randomly selecting from the remaining directions until one or more (e.g., all) directions have been swept. While these techniques may be simple and / or require minimal external information, one or more of these techniques may perform an exhaustive sweep without incorporating any intelligence and / or additional information, resulting in slow cell discovery.

[0081] One or more data-driven machine learning (ML)-based techniques may be used. These techniques may include one or more approaches utilizing recurrent neural networks (RNNs) in which call detail record (CDR) data may be used to predict optimal beam pairs. In some approaches, pseudo-omni-antennas (e.g., rather than directional antennas) may be used at the BS, and each square grid (e.g., bin) in the coverage area may be considered a sector. In other approaches, random forest (RF) and multilayer perceptron ML algorithms may be used to predict optimal BS and WTRU beam pairs using GPS coordinates or other locations of the user, and these algorithms may be comparable to one or more contextual information methods, such as naive methods that select nearby BSs and beams given the WTRU's location, and inverse fingerprinting techniques. Ray-tracing software (e.g., Wireless InSite) may be used to simulate urban outdoor environments.

[0082] As described herein, deep learning-based methods can be used. Omnidirectional sounding signals from multiple BSs can be used to train a deep learning model to predict the optimal beam. In one example, a prototype validation of the proposed deep learning can be performed. However, this approach may use sub-6 GHz for the MMWAVE channel by assuming that both channels have strong spatiotemporal correlation under certain conditions. Deep learning-based solutions in switched-beam multi-user (MU)-MIMO systems can be used. Deep learning-based beam selection strategies using user location and / or orientation information can be implemented. Several support vector machine (SVM)-based algorithms can exist to address optimal beam prediction in MMWAVE networks. SVM can be combined with an iterative sequential minimal optimization algorithm. SVM can be comparable to k-nearest neighbors and multi-layer perceptrons that use angle-of-arrival information.

[0083] Beam training can be formulated in a multi-armed bandit framework to select optimal beam pairs, which can be comparable to exhaustive search methods. Machine learning tools such as random forest classifiers combined with situational awareness can be used to learn beam information (e.g., power, optimal beam index, etc.) from past observations in vehicular networks.

[0084] One or more context information-based non-ML techniques may be used. Non-ML techniques may be used that rely on using some additional context information to improve the exhaustive search method. This additional information may be user position and / or location, channel gain, user spatial distribution, angles of arrival and departure, past multipath fingerprints, radar signals, sub-6 GHz band information in a control-data plane split architecture, and / or antenna configuration. The context information-based non-ML techniques may include analytical solutions (e.g., because analytical solutions typically rely on predefined assumptions). To improve the pure random search algorithm, a greedy search technique called discovery greedy search may be used. The serving MMWAVE BS may know information about the user's location from the C-plane of the macro BS to calculate the optimal beamwidth and / or pointing direction to reach it. However, if the serving MMWAVE BS does not detect the user (e.g., due to positioning inaccuracy), the MMWAVE BS may start scanning over various directions while maintaining the same beamwidth. If the user is still not found, the MMWAVE BS may resume the circular sweep with a reduced beam width and repeatedly scan a larger set of pointing directions. This approach may be comparable to an enhanced discovery procedure. In the presence of positioning inaccuracies, the BS may rely on n circular sectors to scan the surrounding environment. Within the first scanned sector, i.e., the sector pointing to the user position, the BS may begin to search for beam directions adjacent to the user position, alternating between clockwise and counterclockwise directions, using a fixed beam width to cover the sector.

[0085] Enhanced discovery may provide a trade-off between competing methods. For example, performing discovery by scanning a first large azimuth angle and then extending range by narrowing the beam may provide a trade-off compared to performing discovery by searching a first narrow azimuth angle until maximum range is reached and then changing the pointing direction. A control and data separation architecture may be used by deriving and optimizing network coverage probability to evaluate beam misalignment issues. A method that considers only system throughput may be used (e.g., not considering frequent beam handoff issues). The sum rate in a switched-beam-based MIMO system operating in the MMWAVE frequency band may be maximized. Location information from a train control system in high-speed train communications for beam alignment may be considered. A joint consideration of beamwidth selection and scheduling may be implemented to maximize effective network throughput. Using sub-6 GHz out-of-band information to assist MMWAVE beam steering, compressed beam selection may be formulated as a weighted sparse signal recovery problem, and weighting information from sub-6 GHz channels may be obtained. The training overhead of beam selection can be reduced by exploiting the spatial clustering of multipaths in the channel.

[0086] Signal processing-based methods may be used. These methods may include Kalman filter-based methods for tracking angle-of-arrival and angle-of-departure information, and / or extended Kalman filter-based methods that use a joint minimum mean square error (MMSE) beamforming and extended Kalman filter tracking strategy to minimize beamforming angle misalignment. The extended Kalman filter estimation technique may be combined with a conditional beam switching scheme. However, this technique may assume that the device can switch the beam pattern to any arbitrary direction when tracking is lost, which may not be possible with analog beamforming (e.g., the number of unique beam patterns is limited by the number of antenna elements in the beamforming array). Another signal processing technique that may be used is a particle filter-based method in which the BS tracks the WTRU based on a particle filter and adaptively widens or narrows the beamwidth via partial activation of the antenna array.

[0087] A compressed sensing approach may be used, in which a compressed beacon is transmitted to estimate the spatial frequency associated with the emission direction of the dominant ray from the base station and the associated complex gain. However, the compressed beacon may be omnidirectional in nature and may not benefit from the signal-to-noise ratio (SNR) and spatial reuse benefits of beamforming obtained during data transmission. The compressed sensing approach may be comparable to an approach that utilizes knowledge of previous angle of departure (AoD) / angle of arrival (AoA) estimates to asymmetrically scan the beam space by projecting a pseudo-random sequence onto the beam space. One or more approaches may be used to select optimal beam pairs using past multipath fingerprints. In one example, the position and / or location of the WTRU may be used to query a multipath fingerprint database from the BS, which provides prior knowledge of potential pointing directions for beam alignment. One or more types of fingerprinting databases may be used. For example, the first type may have the top M beam pairs ranked according to RSRP level, and the second type may store the average RSRP for each beam pair. The first approach to selecting the optimal beam may be heuristic, while the other may minimize the misalignment probability by maximizing the received power of the optimal selected beam pair. However, since this method relies on a historical database, some paths may not exist in the database due to obstructions.

[0088] A hierarchical search method can be used to reduce latency compared to an exhaustive search method. For example, the BS can first perform an exhaustive sequential search over wider beams and then iteratively progress to narrower beams. A hierarchical search method can be combined with AI / ML.

[0089] Achieving initial access using directional transmission and reception may involve high latency and / or high processing power. For example, an initial robust and reliable link may be found by simply performing a wide beam sweep, which may require a relatively long time and / or high processing power. Methods may be disclosed herein that may reduce both the latency and processing power required for directional transmission and reception systems.

[0090] AI-assisted initial access schemes may be used to reduce latency and / or processing power utilized in directional transmit and receive based systems. As used herein, the terms "low latency initial access," "low latency cell detection," "low latency cell discovery," and / or "low latency measurement" may be used interchangeably.

[0091] An AI-assisted low-latency initial access algorithm may be used. For example, AI / ML may be used to learn the optimal beam / beam pair and / or optimal cell / BS from wider beams (rather than using an exhaustive search to search across wider beams, as may be performed in a hierarchical search method). A narrow beam may be used to fine-tune the optimal beam pair predicted by the exhaustive search. Using AI / ML to learn the optimal beam pair and using an exhaustive search to fine-tune the predicted optimal beam pair may reduce latency compared to using an exhaustive search for both and may take into account user requirements to select whether fine-tuning is needed.

[0092] Learning optimal beam pairs and BSs using AI / ML may utilize fewer resources because the search space may be reduced when wider beams are used compared to narrower beams. Furthermore, in emerging ultra-dense network scenarios, BS density may be much greater than in macrocells, resulting in a large number of cell identification / identifier (ID) options or BS classes for WTRU association. Therefore, training on wider beams may also help narrow down the number of additional classes resulting from multiple beam pairs, since fewer wider beams may cover the same coverage area compared to narrower beams. Training on wider beams (e.g., compared to training on narrow beams) may reduce the probability of overfitting during the model training phase. Developing ML models on wider beams rather than narrower beams may result in greater tolerance to errors due to cellular environment characteristics, such as shadowing and multipath or inaccurate user positioning.

[0093] A system model may be used, and data collection may be performed. Historical Minimized Drive Test (MDT)-based reports from MMWAVE base stations may be used to train the ML algorithm. The MDT reports may include network coverage-related key performance indicators (e.g., RSRP) measured at the WTRU. These reports may be tagged with the WTRU's geographic location information (e.g., WTRU position, WTRU location, etc.) and then transmitted to the WTRU's serving base station. Synthetic data generated through a 3GPP-compliant simulator may be used to investigate the techniques disclosed herein. For example, a 3GPP-defined indoor scenario of a 5G indoor office may be used. Scenario parameters for channel modeling implemented in the simulator may include, among others, parameters related to delay spread, angle of arrival and departure angle spread, shadow fading, k-factor, cross-correlation, number of clusters, and / or rays per cluster. These parameters may be defined for both LoS and NLoS paths.

[0094] FIG. 2 illustrates an example network topology image 200 showing base station (BS) locations, array orientations, sweep directions, and sample WTRU distributions for channel modeling implemented by a simulator. In this example, a total of 15,000 WTRUs may be dropped within the simulation area. Five-fold cross-validation may be used to avoid overfitting. There may be six BSs within the simulation area, each with four arrays rotated around the z-axis by 0, 90, 180, and / or 270 degrees, resulting in a total of 24 BSs. Each array may consist of 2×1 antenna elements, which may result in a wide beamwidth of approximately 60 degrees. The antenna element pattern may be 3GPP-defined using a 3D Gaussian element generation method, 65-degree azimuth and elevation 3-dB beamwidths, 8 dB maximum gain, 25 dB front-to-back and sidelobe ratios, and a 12-degree tilt angle. The WTRUs may have omnidirectional antennas. The RSRP steering angle can take values ​​of 0 and 45 in the azimuth direction, which means that for every BS, beam sweeping is performed in these two directions. As shown in Figure 2, there can be a total of two beam pairs for each of the 24 BSs.

[0095] The remaining simulation parameters may be those parameters as shown in Figure 3. Figure 3 includes a table 300 that includes system parameters 302 and corresponding values ​​304 that are implemented in the simulation.

[0096] The two-phase cell selection and / or beam association process may be implemented using an AI-assisted framework as described herein. For example, the framework may include AI-aided cell discovery in emerging networks (AIDEN) that implements AI / ML. The AIDEN framework may collect MMWAVE user-historical drive test minimization (MDT) traces that include coverage quality indicators (e.g., RSRP and / or location). The AIDEN framework may include using AI techniques on wider beams and transitioning to narrower beams to further fine-tune the optimal beam pair predicted in the first phase (e.g., taking into account user requirements). AIDEN may be more robust to overfitting during the model training phase and / or provide greater tolerance for errors arising from the propagation characteristics of the environment compared to other AI-based search methods (e.g., that may use AI on narrower beams and use a larger search space). Additionally or alternatively, AIDEN may avoid phase 1 latency while also maintaining accuracy comparable to hierarchical search-based methods.

[0097] 4 illustrates an example process 400 that may be implemented for performing cell selection and / or beam association using AI / ML. For example, process 400 may be implemented utilizing the AIDEN framework. One or more portions of process 400 may be implemented in a network entity, such as a BS or a network server in communication with a BS, to implement AI / ML for cell selection and / or beam association. Additionally, although one or more portions of process 400 may be described as being implemented by a BS or another network entity, one or more portions of process 400 may be implemented by another device on the network, such as a WTRU, another BS, or another network server.

[0098] As shown in FIG. 4, process 400 may include a training phase 402 and / or an operational phase 404 (e.g., also referred to as a production phase). During the training phase 402, a training dataset may be constructed, and during the operational phase 404, an AI / ML model may be implemented. As shown in FIG. 4, historical reports from MMWAVE cells consisting of WTRU GPS locations and RSRPs of nearby cells may be logged at 406. The historical reports may be used as raw datasets that may be preprocessed as described herein. An optimal cell / BS and an optimal beam / beam pair may be labeled for each WTRU location in the training data at 408. In the simulation, cell association and beam pair association may be made based on the highest RSRP. The labeled dataset may be preprocessed at 410 to generate data in a format for input into ML. Using the labeled preprocessed dataset, an associated cell ID and beam pair map may be created for each WTRU location at 412. Each user location may be labeled with a 2-tuple (associated cell ID, associated beam pair). Further preprocessing of the training data may be performed (e.g., depending on the capabilities of the ML algorithm). The training phase 402 may include training performed by inputting (e.g., at 406) one or more WTRU locations and / or one or more RSRP values. The training phase may include determining cell / gNB and / or beam associations via an AL / ML model and / or comparing the gNB or beam associations with optimal cell / gNB and / or optimal beam associations (e.g., obtained via an exhaustive search). The training phase may include a cost function. The cost function may include minimizing a (e.g., total) cost when performing the comparison.For example, minimizing cost may include minimizing the difference between the RSRP value measured by the WTRU of a signal transmitted from the strongest (e.g., best) beam selected by the AI / ML and the strongest (e.g., best) beam optimally determined (e.g., via an exhaustive search) selected by the AI / ML.

[0099] For AI / ML algorithms that do not directly support multi-class, multi-output classification, multi-class, single-label classification can be used (e.g., using the label powerset method), where a unique integer is assigned to each 2-tuple of (associated cell ID, associated beam pair). In this way, one multi-class classifier is trained on one or more (e.g., all) unique label combinations found in the training data.

[0100] Outliers in the training data (e.g., WTRUs far away from the particular BS associated with that BS) may be filtered out based on a distance threshold between the WTRU and the BS that defines the range of the BS. An outlier may be defined as a WTRU-BS distance value with an interquartile range greater than 1.5 above the upper quartile (75 percent) or below the lower quartile (25 percent).

[0101] 4, given a WTRU location 416 (e.g., x and y geographic coordinates, a Global Navigation Satellite System (GNSS) or GPS location, and / or another geolocation of the WTRU) as input, one or more AI / ML algorithms 414 may be used to predict an optimal beam pair at 418 and / or predict an optimal cell / BS at 420. The optimal BS and / or optimal beam pair (BP) may be output at 422. One or more of the AI / ML models may be trained (e.g., during the training phase 402 and prior to the operation phase 404 procedures described herein) to take into account the input location coordinates (e.g., possibly along with other inputs such as service requirements, WTRU identification information, interference, etc.). One or more AI / ML models may be trained to output one or more sets of cells, gNB Tx beams, WTRU Rx beams, beam pairs, gNB Rx beams, and / or WTRU Tx beams. Training may be performed with one or more (e.g., multiple) WTRU reporting locations (e.g., and / or any of the inputs described herein). Training may include performing a (e.g., exhaustive) cell / beam search to determine the strongest cell / beam. Training data using wide beams may be used to train several ML algorithms, including support vector machines (SVMs), k-nearest neighbors (KNNs), random forests (RFs), and / or deep neural networks (DNNs). KNNs may be chosen because they are easy to implement, fast, and require hyperparameter tuning of only three variables. KNNs classify new data points based on a similarity measure of historical data points. KNNs may not cope well with a large number of input variables and may require uniform features. Two input variables (eg, WTRU x and y coordinates) may be used, which may be on a homogeneous scale (eg, meters).KNN's sensitivity to outliers and noise can be addressed through data preprocessing (e.g., as described herein). SVM can be chosen because classification decisions are made by understanding the decision boundary / hyperplane. For example, the margin or boundary separating the classes can be visualized (e.g., as shown in Figure 5). Data nonlinearity can be addressed (e.g., via kernel tricks).

[0102] SVMs can be memory-intensive because they may need to store one or more (e.g., all) support vectors, which grow with the training dataset size. RFs can be a collection of decision trees, and the majority vote of the forests can be selected as the predicted output. Compared to decision trees, RFs can be less susceptible to overfitting and can yield more robust solutions. Compared to KNNs, random forests can support automatic feature interactions and can be (e.g., typically) faster. Compared to SVMs (e.g., using kernels to solve nonlinear problems), each decision tree in a random forest can derive a hypercuboid in the input space to solve such problems. Furthermore, decision trees can address collinearity better than SVMs.

[0103] While DNNs may be able to directly support multi-class, multi-output classification tasks, these tasks often have nonlinear activation functions, and computing the gradients of these functions can be computationally expensive during backpropagation. While DNNs can be used (e.g., directly) to predict two output variables (e.g., optimal BS and optimal beam pair), different strategies can be adopted to utilize KNN, SVM, and / or RF. In the case of KNN, 24 classes for BSs and two classes of beam pairs for each BS can be transformed into 48 unique classes. SVMs are inherently binary classification algorithms and may require modification for both multi-output and multi-class classification tasks. Multi-class classifications can be subdivided into multiple binary classifications via one-versus-one and one-versus-all methods, and these binary classifications can be additional hyperparameter options used to tune the SVM model. In the case of decision trees, one classifier can be fitted for each output.

[0104] The operational stage 404 shown in FIG. 4 may include a second phase. In the second phase, the predicted beam / beam pair may be fine-tuned at 424 to generate an optimal beam / beam pair and / or cell / BS 426. The second phase may be performed based on requested user service demand at 428. For example, if the user request demand is determined to be higher at 428, a narrower beam may be determined. If the user request demand is determined to be low, a wide beam may be used. Depending on the requested user demand at 428, one or more narrow beams may be used. Exhaustive beam sweeping may be performed, for example, roughly limited within the beamwidth of the beam predicted from the first phase. This may further refine the predicted beam from the first phase, as shown in FIG. 4. The second phase may refine the cell / beam determined by AI / ML. The AI / ML model may return a beam with a wide beamwidth. The second phase (e.g., a refinement step) may include determining beams with narrow beamwidths. The second phase may use one or more AI / ML models.

[0105] As used herein, the term "beam" or "beam pair" may refer to any of an uplink (UL)-transmit (Tx) beam, a downlink (DL)-Tx beam, a UL-receive (Rx) beam, and / or a DL-Rx beam. The term "beam" or "beam pair" may refer to one or more of a DL-Tx beam (e.g., a beam used by a gNB in ​​DL transmission), a DL-Rx beam (e.g., a beam used by a WTRU in DL reception), a UL-Tx beam (e.g., a beam used by a WTRU in UL transmission), a UL-Rx beam (e.g., a beam used by a gNB in ​​UL reception), a DL Tx-Rx beam pair (e.g., a beam used by a WTRU and a gNB for DL ​​transmission), and a UL Tx-Rx beam pair (e.g., a beam used by a WTRU and a gNB for UL transmission). It may be assumed that a UL Tx-Rx beam pair may use the same beam as a DL Tx-Rx beam pair. In such a case, the UL Tx beam at the WTRU may be the same as the DL Rx beam at the WTRU (e.g., both beams use the same spatial filtering), and the UL Rx beam at the gNB may be the same as the DL Tx beam at the gNB (e.g., both beams use the same spatial filtering).

[0106] The determined beam pair in one direction (e.g., DL) may be used by the WTRU to transmit in the UL. For example, the WTRU may determine the UL Tx beam to be the same as the determined DL Rx beam, and the WTRU may determine the UL transmission resource according to the DL Tx beam used by the gNB.

[0107] The WTRU location report may include coordinates indicating a given position and / or location of the WTRU. The WTRU location report may be configured with a given granularity. For example, the WTRU may be configured with one or more areas, and the WTRU may determine its location as being within a given area. The WTRU may report the area or area index to the gNB. The report may include sending an indication of information indicative of the WTRU location, as described herein. The indication may be explicit, to explicitly indicate the WTRU location. The indication may be implicit, to implicitly indicate the WTRU's location. The indication may be both explicit and implicit.

[0108] The WTRU may determine its location relative to one or more cells or DL-Tx beams and / or beam pairs. The WTRU may report its relative location, for example, along with the DL-Tx beam or beam pair or reference signal (RS) index to which the relative location of the WTRU is applicable.

[0109] The WTRU location report may include one or more positions and / or locations of the WTRU, including coordinates, an area or area index, and / or one or more measurements performed on one or more signals (e.g., signals configured to enable WTRU location determination).

[0110] Signaling may be implemented to support cell discovery. The signaling to support cell discovery may be used to determine the Rx beam on the pair and / or use the UL beam corresponding to the beam pair. The WTRU may report its location to the network, for example, to enable AI-assisted cell discovery. In one example, the WTRU may detect a first cell and DL-Tx beam combination, for example, from a subset of all possible cell and DL-Tx beam combinations. The WTRU may detect the first cell and DL-Tx beam combination by receiving DL transmissions from the first cell and DL-Tx beam combination. The WTRU may determine UL resources to transmit its location from the first cell's DL transmission and DL-Tx beam combination. For example, the WTRU may detect a broadcasted transmission that provides resources for transmitting its location. For example, the transmission may include system information (SI) indicating one or more resources for transmitting its location.

[0111] The WTRU may report its location along with a temporary identification tag. For example, the WTRU may report its location using a preamble. The WTRU may report its location by transmitting a signal in a resource. Parameters of such a signal transmission may indicate the WTRU's location and / or a WTRU ID. The WTRU may report other context information. For example, other context information may be implemented here (e.g., antenna configuration, etc.). The WTRU's location may be indicated by one or more of the resource (e.g., time or frequency) on which the WTRU transmits the signal, the signal structure, the associated preamble, and / or the signal content.

[0112] The location of a WTRU may be indicated by the resources from which the WTRU transmits signals. For example, the WTRU may be configured with a mapping between signal resources and geographic regions (e.g., indicated via a broadcast transmission). The time of the resources may be defined in terms of symbols or slots. The frequency of the resources may be defined in terms of Physical Resource Blocks (PRBs) or subcarriers or Bandwidth Parts (BWPs).

[0113] The location of the WTRU may be indicated by the signal structure, for example, the WTRU may select a transmission sequence depending on its location.

[0114] The location of the WTRU may be indicated by an associated preamble. For example, a WTRU may be configured with one or more sets of preambles or PRACH occasions, where a (e.g., each) set may be associated with a different WTRU location (e.g., or a different WTRU location area). The WTRU may select a preamble or PRACH occasion associated with the location or area in which the WTRU is located.

[0115] The location of the WTRU may be indicated by the content of the signal. For example, the WTRU may encode its location into the signal. The encoding may be done via scrambling of a set of bits (e.g., CRC bits).

[0116] A WTRU may report its location to a serving cell. A WTRU may be triggered to report its location when one or more of the following occur: The WTRU location changes by more than a threshold amount. The WTRU is triggered to report L3 measurements. The WTRU is triggered for a conditional handover (HO). The RSRP is below a threshold. The serving cell RSRP is less than the neighbor cell RSRP value plus an offset. The WTRU's transmission requirements change. The WTRU's best Rx beam changes. The WTRU's best UL panel changes. The WTRU detects a new cell or DL-Tx beam or a combination thereof. The WTRU determines N or more NACKs for DL ​​transmissions (e.g., within a predetermined time period). A configurable, periodic, or predetermined trigger event occurs. The WTRU's velocity changes by more than a threshold amount and / or the WTRU determines that it has failed to access the channel more than N times (e.g., within a predetermined period).

[0117] The WTRU may be triggered to report its location when it detects a new cell or DL-Tx beam or a combination thereof. For example, if the WTRU detects a new cell and / or DL-Tx beam with an RSRP greater than a threshold, the WTRU may report its location.

[0118] The WTRU may be configured to perform neighbor cell discovery / measurements based on low-latency cell detection using the assistance information. The WTRU may be configured with one or more neighbor cells for which low-latency cell detection may be enabled. For example, the WTRU may be configured to trigger a location report to the network when measurements are triggered for at least one neighbor for which low-latency cell detection is enabled. The WTRU may receive assistance information from a gNB. For example, the WTRU may receive assistance information from a gNB as described herein (e.g., in response to transmission of the WTRU's location and / or other context information). The WTRU may determine the assistance information (e.g., in response to the WTRU's location and / or other context information described herein). The functionality for determining the assistance information may include AI / ML. The functionality for determining the assistance information may include the WTRU being configured with an association between one or more locations and one or more sets of assistance information (e.g., via broadcasted SI and / or via radio resource control (RRC)). The assistance information may include a defined subset of measurement resources for at least one beam in a cell and / or beam pair based on the location of the WTRU. For example, the assistance information may include one or more of: one or more measurement objects, a set of resources for monitoring discovery signals or synchronization signal blocks (SSBs), and / or a mini-measurement gap configuration (e.g., the gap may be shorter in duration compared to a regular / legacy measurement gap).

[0119] The assistance information that the WTRU receives from the gNB may include one or more measurement objects. For example, the WTRU may be configured with a prioritized list of one or more neighboring cells and / or frequencies. The WTRU may prioritize these neighbors for performing measurements and / or reporting.

[0120] The assistance information that the WTRU receives from the gNB may include a set of resources for monitoring discovery signals or SSBs. For example, the set of resources may be configured as an SMTC window specific to low latency cell detection. For example, the WTRU may be configured with information such as an SSB index (e.g., or any implicit / explicit beam identification) that is expected to be received within the SMTC window.

[0121] The assistance information that the WTRU receives from the gNB may include a mini-measurement gap configuration. For example, the WTRU may be configured to monitor discovery signals and / or SSBs from neighboring cells within this mini-measurement gap configuration. The WTRU may apply the mini-measurement gap configuration as an alternative to the regular measurement gap configuration. The WTRU may apply the mini-measurement gap configuration for measurements in addition to the regular measurement gap configuration.

[0122] The assistance information may be signaled via a radio resource control (RRC) message and / or a MAC control element (CE). The medium access control (MAC) control element may activate or deactivate a preconfigured measurement configuration. The WTRU may be configured to use the assistance information to perform neighbor cell discovery and / or measurements (e.g., measurement resources). The WTRU may be configured to report neighbor cell measurements to a gNB. The WTRU may be configured to report cell discovery (e.g., including one or more associated measurements) to a gNB. The WTRU may be configured to report neighbor cell measurements via preconfigured UL resources. The reporting may include sending an indication of information indicating the neighbor cell measurements. The indication may be explicit to explicitly indicate the neighbor cell measurements. The indication may be implicit to implicitly indicate the neighbor cell measurements. The indication may be both implicit and explicit. The preconfigured UL resources may be determined as an offset from the timing of the assistance information, configured as part of the assistance information, or implicitly determined based on the content of the assistance information.

[0123] WTRU center cell discovery may be performed. The WTRU may be provided with an association of the WTRU location and resources for transmitting signals or associated cells or DL-Tx beams. The WTRU may transmit signals on resources determined by its location and / or service requirements. The WTRU may monitor for responses. The resources on which the WTRU monitors for responses may be determined by the WTRU location and / or service requirements.

[0124] The granularity of the received association between the WTRU location and the resources for transmitting a signal, or the granularity of the received association with the associated cell or DL-Tx beam, may be such that the WTRU may need to interpolate to determine the appropriate resources of the cell or DL-Tx beam. The WTRU may use AI / ML to perform the interpolation. In an example, there may be an association with a location and a resource for transmitting a signal. The association may have a particular granularity. If the WTRU is located between two locations (e.g., two locations where associated transmission resources exist), the WTRU may input its location into the AI / ML model (e.g., possibly along with other inputs), and / or the output may provide the transmission resources.

[0125] The WTRU may determine a preferred cell (e.g., of a BS) or beam or beam pair. For example, the WTRU may determine a preferred cell (e.g., of a BS) or beam or beam pair based on its location. The WTRU may report the preferred cell (e.g., of a BS) or beam or beam pair to a gNB. Reporting may include sending an indication of information indicating the preferred cell (e.g., of a BS) or beam or beam pair. The indication may be explicit, to explicitly indicate the preferred cell (e.g., of a BS) or beam or beam pair. The indication may be implicit, to implicitly indicate the preferred cell (e.g., of a BS) or beam or beam pair. The indication may be both explicit and implicit. The WTRU may be configured with resources for reporting the preferred cell (e.g., of a BS) or beam or beam pair to at least one gNB. The WTRU may report the preferred cell (e.g., of a BS) or beam or beam pair on the same resources received for reporting location information. The WTRU may report a preferred cell (e.g., of a BS) or beam or beam pair on one or more different resources. The WTRU may report a preferred cell (e.g., of a BS) or beam or beam pair on resources specifically configured for reporting location information. The WTRU may be configured with multiple resources for transmitting signals. The WTRU may select resources depending on the preferred cell (e.g., of a BS) or beam or beam pair. For example, the WTRU may be configured with one or more sets of reporting resources. The one or more sets of reporting resources may be associated with one or more preferred cells (e.g., of a BS) and / or beams and / or beam pairs. The WTRU may transmit an UL signal on the resources. The UL signal may include information or measurements about one or more cells or beams or beam pairs (e.g., including at least the preferred cells or beams or beam pairs of the BS).

[0126] Upon transmitting the BS's preferred cell or beam or beam pair indication, the WTRU may monitor for an acknowledgement from the gNB, which may be received via one or more of a Random Access Response (RAR), a scheduling grant, an RRC (re)configuration, a DL RS, or a downlink control information (DCI).

[0127] The WTRU may indicate its service requirements to the network. This may indicate to the network whether it can be served by a narrow beam or a wide beam. The WTRU may be shown the cell and DL-Tx wide beam (e.g., determined by an AI-ML method) and may immediately begin operation. In an example, the WTRU may be shown the cell and DL-Tx wide beam and may be triggered to perform refined beam selection, for example, to narrow the serving DL-Tx beam.

[0128] The WTRU may indicate one or more of its service requirements (e.g., data volume, reliability requirement, latency requirement, data type) to the gNB. The service requirements may include one or more thresholds (e.g., latency threshold, RSRP threshold, etc.). The gNB may use the WTRU's one or more service requirements to determine an appropriate beam for serving the WTRU. The service requirements may indicate the WTRU's serving cell DL-Tx beam requirement (e.g., narrow beam or wide beam). The WTRU may indicate its service requirements via signaling before completion of cell discovery. For example, the WTRU may encode its service requirements using a scheme similar to the location reporting methods described herein. Alternatively, the WTRU may indicate its service requirements via signaling after completion of coarse cell discovery. For example, once coarse cell discovery is complete, the WTRU may be provided with resources upon which the WTRU may transmit its service requirements. For example, such a transmission may use scheduling request (SR)-like operations whereby the WTRU is configured with one or more, possibly periodic, resources on which the WTRU may indicate changes (e.g., updates) to one or more service requirements. The transmission may use SR-like operations whereby the WTRU is configured with one or more (e.g., possibly periodic) resources on which the WTRU may indicate a new set of service requirements.

[0129] Once coarse cell discovery is complete, the WTRU may receive a transmission to enable finer beam selection. The WTRU may perform fine beam selection if it determines that fine beam selection is appropriate for its service requirements. The WTRU may skip fine beam selection and / or indicate to the network that fine beam selection is not required. Beam refinement may be performed via an exhaustive search. To implement an exhaustive search, the WTRU may be configured with a set of resources (e.g., a set of reference signals) for measuring one or more beams in the set of beams. For example, the set of resources may include a set of reference signals for measuring each of the possible finer beams. The WTRU may report an appropriate value within the wider or narrower beam. The appropriate value may include one or more measurements, as described herein. Additionally or alternatively, the WTRU may use other means (e.g., AI / ML-based) to receive a transmission to enable finer beam selection.

[0130] The WTRU may receive an indication from the network that it is associated with a cell and / or DL-Tx beam. For example, the WTRU may monitor DL ​​transmissions from the network (e.g., after providing its location to the network). The WTRU may monitor a set of discovery signals or SSBs. The set of discovery signals or SSBs to be monitored by the WTRU may be determined depending on the location that the WTRU has provided to the network and / or depending on the ID that the WTRU has provided to the network. The WTRU may ignore any other discovery signals or SSBs that are not associated with its reported location or ID.

[0131] A WTRU reporting a first WTRU location may be configured to monitor a first set of resources on which it may expect at least one discovery signal or SSB. Upon receiving at least one discovery signal or SSB, the WTRU may proceed with random access. The WTRU may perform random access using the determined cell, beam, and / or beam pair. The WTRU may attempt to decode the discovery signal or SSB using its reported ID or location (or location ID or tag). For example, the SSB may be scrambled with the WTRU ID or location tag. The WTRU may select an SSB with the WTRU's location or ID appropriately descrambled.

[0132] The WTRU may decode an information block that may include a set of resources associated with the WTRU location. The WTRU may perform random access to the resources indicated in the information block associated with its location.

[0133] The WTRU may be configured with measurement resources (e.g., associated with the WTRU's location). For example, after transmitting its location, the WTRU may be configured with a set of measurement resources. The WTRU may perform and / or report measurements for at least one cell or beam or beam pair. The measurements may include one or more of: RSRP, Received Signal Strength Indicator (RSSI), Reference Signal Received Quality (RSRQ), Signal to interference and noise ratio (SINR), Rank Indicator (RI), Channel Quality Indicator (CQI), Precoding Matrix Indicator (PMI), Layer Indicator (LI), CRI, Doppler shift, Doppler spread, Angle of Arrival (AoA), Angle of Departure (AoD), delay spread, and / or average delay. The WTRU may report measurements using resources associated with at least one measurement resource. The WTRU may report measurements using resources associated with the measurement resource that provides the best measurement (e.g., highest RSRP, or SINR, or RSRQ). The WTRU may perform transmissions (e.g., to report measurements) using a cell or beam or beam pair selected by the results of measurements performed on the configured measurement resources. The reporting may include sending an indication of information indicating one or more measurement resources. The indication may be explicit, to explicitly indicate one or more measurement resources. The indication may be implicit, to implicitly indicate one or more measurement resources. The indication may be both explicit and implicit.

[0134] The WTRU may determine the set of cells, beams, and / or measurement resources depending on its location and / or broadcast information, e.g., system information block (SIB). The WTRU may be configured with an association between the location and SIB information and the set of cells, beams, and / or measurement resources (e.g., via SI, or RRC, or MAC CE, or DCI). The WTRU may perform measurements on the set of cells and / or beams and / or measurement resources and may report the measurements to the gNB along with an identifier for the set of cells and / or beams and / or measurement resources.

[0135] The WTRU may receive an indication of a cell or DL-Tx beam with which it may associate. Upon receiving the indication of the best cell or DL-Tx beam, the WTRU may perform random access (RA) to that cell. The cell or DL-Tx beam indication may include a reference signal (RS) configuration associated with the cell / beam. The WTRU may perform measurements on the RS. The WTRU may receive resources for performing an RA or first transmission to the indicated cell / beam. In such an RA or first transmission, the WTRU may report measurements performed on the associated RS.

[0136] If the measurements obtained by the WTRU are below a threshold and / or another measurement (e.g., measurement), the WTRU may reject the cell / beam combination and / or decide to perform legacy cell discovery. In one example, the WTRU may simultaneously perform enhanced cell discovery (e.g., by indicating the WTRU's location to the network) and / or legacy cell discovery (e.g., by detecting a discovery signal or SSB). The WTRU may receive an indication of a cell / DL-Tx beam combination from the network. The WTRU may perform measurements on the indicated cell / DL-Tx beam combination. The WTRU may report measurements of the indicated cell / DL-Tx beam combination, possibly in combination with measurements obtained for discovery signals or SSBs detected by the WTRU. This may allow the BS or other network entity to refine its cell discovery algorithm to provide better cell association results. In examples where the cell discovery algorithm includes an AI / ML algorithm, the cell discovery algorithm may be refined to provide better cell association results. If the measurements (e.g., RSRP, RSSI, RSRQ, SINR, RI, CQI, PMI, LI, CRI, Doppler shift, Doppler spread, Angle of Arrival (AoA), Angle of Departure (AoD), delay spread, average delay, etc.) of the indicated cell / DL-Tx beam combination are less than the WTRU-discovered cell / DL-Tx beam plus an offset, the WTRU may ignore the indicated cell / DL-Tx beam and proceed to access the WTRU-discovered cell / DL-Tx beam. The WTRU may indicate to the WTRU-discovered cell that it has ignored the network-determined cell / DL-Tx beam. The WTRU may provide measurements on the network-determined cell / DL-Tx beam to the WTRU-discovered cell.

[0137] AI / ML parameters (e.g., weights, biases, and / or other hyperparameters) may be refined by updating the parameters as described herein. Hyperparameter tuning of the AI / ML model may be performed through Bayesian optimization. For example, tuning of an AI / ML model used in the first phase of the procedure to determine cells / beams from location, service requirements, and / or other contextual information may include hyperparameters that may be refined by tuning through Bayesian optimization. The resulting optimal hyperparameters may be as follows: for KNN, number of neighbors = 1, distance metric = Euclidean, distance weight = inverse squared; for SVM, kernel function = Gaussian, kernel scale = 1.5255, box constraint level = 3.4541, multiclass method = 1 vs. all; for RF, number of trees = 65, maximum tree depth = 50, maximum features for best split = 2, bootstrap = true, out-of-bag score = true.

[0138] An AI-aided cell discovery framework for ultra-dense emerging networks (AIDEN) with high BS density may be implemented as disclosed herein. Compared to hierarchical search algorithms (e.g., which may utilize an exhaustive search to search for optimal cells and beam pairs using wide and narrow beams), AIDEN may use AI in the search phase with wide beams. AIDEN may be implemented with or without an exhaustive search in the first phase of cell reselection and / or beam association to reduce latency. Narrow beams may then be used to further fine-tune the predicted beams from the AI ​​(e.g., depending on user requirements). AIDEN may be trained on wider beams (e.g., only wider beams), which may make AIDEN robust to overfitting and outliers and may reduce the number of BS classes in ultra-dense network scenarios.

[0139] 6 illustrates an example of a DNN architecture 600 and hyperparameters that may be configured for the DNN architecture. The DNN architecture 600 may be implemented by AI / ML operating on one or more devices as described herein. For example, one or more portions of the DNN architecture 600 may be implemented on a network entity, such as a BS or a network server in communication with a BS, to implement AI / ML for cell selection and / or beam association. Additionally, although one or more portions of the DNN architecture 600 may be described as being implemented by a BS or another network entity, one or more portions of the DNN architecture 600 may be implemented by another device on the network, such as a WTRU, another BS, or another network server.

[0140] As shown in FIG. 6, the DNN architecture 600 may receive input 602 at an input layer 604. The input 602 may include location information and / or other context information, as described herein. The input layer 604 may receive input 606. The input 606 may have a tensor configuration of [(none, 2)]. The input layer 604 may generate output 608. The output 608 may be passed to a dense layer 612. The dense layer 612 may receive the output 608 from the input layer 604 as an input. The dense layer 612 may generate output 610. The output 610 from the dense layer 612 may be passed to a dense layer 614. The dense layer 614 may receive the output 610 from the dense layer 612 as an input. The dense layer 614 may generate output 616. The dense layer may provide the output 616 to one or more output layers.

[0141] 6, the DNN architecture 600 may include an output layer 618 and / or an output layer 620. The output layer 618 may be a dense layer that receives the output 616 of the dense layer 614 as an input. The output layer 618 may provide an output 622. The output 622 may include an identifier of a base station and / or a cell (or set of cells) that may be provided to the WTRU in response to the location. The output layer 620 may be a dense layer that receives the output 616 of the dense layer 614 as an input. The output layer 620 may provide an output 624. The output 624 may include a set of resources that may be provided to the WTRU in response to the location.

[0142] A five-fold cross-validation strategy may be implemented to minimize overfitting during the model training phase. The five-fold cross-validation average accuracy of the aforementioned models may be as shown in Figure 7. For RF and DNN, which predict two explicit outputs (unlike SVM and KNN, for example, where multiple output labels are converted to a single output), the accuracy reported in Figure 7 may be a close match (e.g., subset accuracy), which may indicate the proportion of samples in which each of the sample's labels is correctly classified. KNN may perform best in terms of accuracy because the number of features in the data is small compared to the training data. SVM may generally perform better than KNN, for example, when there are large features and less training data. DNN performance may be inferior to SVM. Well-defined boundaries may exist, but are nonlinear (e.g., as can be visualized from the results shown in Figure 5). These boundaries drawn by neural networks may be somewhat arbitrary, as they may depend on several factors that are random, such as weight initialization.

[0143] SVMs can delineate optimal boundaries in a more structured manner by using support vector points. Datasets with two input features may not require DNN-type architectures to extract hidden features from the many input features. However, maximum accuracy may be limited by the large number of classes (e.g., 48). Figure 8 shows the receiver operating characteristics (ROC) of KNN, the best-performing AI / ML algorithm. Multiclass predictions can be reduced to multiple sets of binary predictions by considering one positive class at a time and treating all others as negative. The minimum area under the ROC curve (AUC) can be 0.90, while the maximum can be 1.00. The macro-averaged AUC was 0.977, which is close to the ideal 1.00, indicating that ML techniques can be used to reduce latency during Phase 1 of AI / ML algorithms such as AIDEN (e.g., even when the number of classes is relatively large).

[0144] Referring again to FIG. 5, the graph shown in FIG. 5 illustrates example WTRU locations with accurate predicted classes and example WTRU locations with inaccurately predicted classes. As shown in FIG. 5, the inaccurately predicted points may be primarily on the cell edge. One way to measure or evaluate the impact of accurate prediction may be to investigate how much the key performance indicators (e.g., RSRP, SINR, throughput) corresponding to the target class label differ from the predicted class label. FIG. 9 shows the distribution of the difference between the RSRP of WTRUs corresponding to the predicted BS and beam pair and the RSRP corresponding to the target / actual BS and beam pair for unseen test data of a sample of 1000 WTRUs. As shown in FIG. 9, 80% of the WTRUs may have an RSRP difference of 0 (e.g., accurate prediction of the optimal BS and beam pair), 2.7% of the WTRUs may have less than a 5 dB difference in RSRP due to misclassification, and there may be no WTRUs with a difference of more than 10 dB.

[0145] One or more of the embodiments disclosed herein may reduce latency compared to an exhaustive search. Predictions at the cell edge may be improved. Phase 1 of the AI / ML (e.g., AIDEN) framework may be skipped (e.g., for time-critical use cases). The AI / ML (e.g., AIDEN) framework may be applied to NLoS paths and when obstructions are present in the environment (e.g., because MMWAVE propagation is susceptible to obstructions). This framework may be applied to WTRUs with directional antenna arrays, which may result in more beam pairs and therefore more classes for AI / ML algorithm training. The reported WTRU location may be inaccurate due to location errors (e.g., GPS positioning errors) or to protect user privacy. Location errors (e.g., GPS positioning errors) may be compensated for in the AI / ML (e.g., AIDEN) framework.

[0146] MDT-based data may be sparse, for example, in scenarios with low WTRU density or in small cells where there may be fewer users compared to macro cells. Techniques for data enrichment may be incorporated into existing frameworks to obtain a sufficient amount of training data. Accuracy may be limited by the large number of classes (e.g., 48 classes). AI / ML techniques may be developed that can handle classification of a large number of classes compared to the available data. The AI / ML (e.g., AIDEN) framework may be tested in other 3GPP-defined environmental scenarios where multiple frequency bands operate simultaneously. The AI / ML (e.g., AIDEN) framework may be extended to scenarios with WTRU transition mobility (e.g., instead of initial cell discovery).

[0147] 10A illustrates a system flow diagram depicting an example of a communication procedure 1000 for cell selection and / or beam association. The communication procedure 1000 may be performed between one or more network entities. For example, the communication procedure 1000 may be performed between one or more WTRUs and one or more network entities (e.g., gNBs, BSs, network servers, etc.). If the network entity is a gNB, the gNB may communicate with other network entities, such as a network server, to provide information to the WTRUs, as described herein.

[0148] At 1006, for example, the WTRU 1002 may receive system information (e.g., SIB) from the network entity 1004. The system information may include one or more resources for reporting the location of the WTRU 1002. The system information may include one or more resources for the WTRU to communicate its location to the network entity 1004. The system information may include an indication of one or more channels or subchannels. The WTRU 1002 may determine UL resources for transmitting the WTRU's location from the DL transmission 1006 and DL-Tx beam combinations for which the system information is provided. The WTRU 1002 may detect a broadcasted transmission that provides resources for transmitting its location.

[0149] At 1008, the WTRU may determine context information to be reported to the network entity 1004. For example, the WTRU may determine its location mobility (e.g., speed or direction), antenna configuration, and / or service requirements. The WTRU 1002 may determine its location based on received system information (e.g., the system information received at 1006). The WTRU 1002 may determine its location relative to one or more cells or DL-Tx beams and / or beam pairs as described herein. The WTRU's location may include geographic location information, geographic coordinates (e.g., x and / or y geographic coordinates), GNSS location, GPS location / coordinates, measurements performed on one or more signals (e.g., signals configured to enable WTRU location determination), and / or location information and / or area index for being within a given area (e.g., for a gNB). The WTRU may generate a location report to transmit the WTRU's location as described herein. For example, the WTRU 1002 may be configured with one or more areas. The WTRU 1002 may determine its location to be within an area. The WTRU 1002 may send the area and / or area index to the network entity 1004.

[0150] At 1010, the WTRU may transmit the context information determined at 1008. For example, the WTRU 1002 may transmit its location to the network entity 1004 on one or more resources received from the network entity 1004. The WTRU 1002 may be triggered to report its location. The WTRU 1002 may be triggered to report its location when the WTRU 1002 detects a new cell or DL-Tx beam or a combination thereof, as described herein. The WTRU 1002 may transmit its location in a location report. The location report may include one or more of coordinates, an area or area index, and / or measurements performed on one or more signals (e.g., signals configured to enable location determination of the WTRU 1002). The one or more measurements in the location report may be based on measurements on resources from one or more neighboring cells and / or the serving cell. The WTRU 1002 may report its location by transmitting a signal on a resource as described herein.

[0151] At 1012, the network entity 1004 may determine assistance information to be sent to the WTRU 1002 based on the context information it received from the WTRU 1002. For example, the network entity may determine a preferred cell (or set of cells) of the BS and / or at least one beam of a beam pair associated with a base station based on the WTRU's location. The cell and / or at least one beam may be determined to be the best cell and / or at least one beam based on the WTRU's location. The assistance information may indicate a base station and / or cell (or set of cells) determined from the WTRU's location. The assistance information may also, or alternatively, indicate at least one beam of a beam pair determined from the WTRU's location. The at least one beam may be a DL-Tx beam with which the WTRU 1002 may be associated.

[0152] The assistance information may include a defined subset of measurement resources for at least one beam in a cell and / or beam pair based on the location of the WTRU 1002. For example, the assistance information may include one or more measurement objects, a set of resources for monitoring discovery signals or synchronization signal blocks (SSBs), and / or a mini-measurement gap configuration. The subset of measurement resources may include a reference signal (RS) configuration associated with the cell / beam. The subset of measurement resources may include other measurement resources as described herein.

[0153] The network entity 1004 may use AI / ML to identify a cell (or set of cells) of the BS and / or at least one beam in a beam pair based on the location of the WTRU 1002. The network entity 1004 may use AI / ML to define a subset of measurement resources to be transmitted to the WTRU 1002. In other embodiments, the subset of measurement resources, cell, and / or at least one beam in a beam pair may be pre-defined based on the location of the WTRU.

[0154] At 1014, the WTRU 1002 may receive assistance information. At 1016, the WTRU 1002 may determine, based on the assistance information, a cell of a BS and / or at least one beam of a beam pair to associate with for transmission. For example, the WTRU 1002 may identify a BS (one or more cells) and / or at least one beam of a beam pair from the assistance information. The WTRU 1002 may perform measurements on one or more measurement resources indicated in the assistance information to identify the BS (one or more cells) and / or at least one beam of a beam pair, as described herein. The one or more measurements may include an exhaustive sweep. The measurements may include one or more of RSRP, RSSI, RSRQ, SINR, RI, CQI, PMI, LI, CRI, Doppler shift, Doppler spread, angle of arrival of AoA, angle of departure of AoD, delay spread, and / or average delay. At 1018, the WTRU 1002 may perform communication to the BS on the cell (or multiple cells) using at least one beam of the beam pair. For example, the WTRU 1002 may perform random access (RA) or first transmission on the cell (or multiple cells) to the BS using at least one beam of the beam pair. The WTRU 1002 may transmit on an UL-Tx beam corresponding to the identified serving DL-Tx beam of the BS.

[0155] 10B depicts a flowchart illustrating an example of a communication procedure 1050 for updating the configuration of cells and / or beams (e.g., beam pairs) utilized by one or more WTRUs 1002. One or more portions of the procedure 1050 may be performed by one or more WTRUs 1002 and / or one or more network entities 1054. The network entities 1054 may be the same as or different from the network entities 1004 shown in FIG. 10A. For example, the one or more network entities 1054 may include a gNB, a BS, a network server, and / or another network entity. If the network entity is a gNB, the gNB may communicate with other network entities, such as a network server, to provide information to the WTRUs, as described herein.

[0156] Procedure 1050 may be performed as a second phase of procedure 1000. However, procedures 1000, 1050, and / or one or more portions thereof may be performed independently.

[0157] As shown in FIG. 10B , the WTRU 1002 may perform refined beam selection. In one example, the WTRU 1002 may be configured to and / or may perform communications on a cell and a DL-Tx wide beam and may be triggered to perform refined beam selection to narrow the serving DL-Tx beam. The trigger may include a change in one or more service requirements. The trigger may be based on one or more measurements, such as, for example, interference. The trigger may be based on the performance of one or more transmissions (e.g., if the block error ratio (BLER) is higher than required). In another example, the WTRU 1002 may be configured to and / or may perform communications on a cell and a DL-Tx narrow beam and may be triggered to perform refined beam selection to widen the serving DL-Tx beam (e.g., based on mobility within the cell, as described herein, etc.).

[0158] At 1056, the WTRU 1002 may transmit / report measurements and / or service requirements to a network entity 1054 (e.g., BS, gNB, etc.). The measurements may include one or more of RSRP, RSSI, RSRQ, SINR, RI, CQI, PMI, LI, CRI, Doppler shift, Doppler spread, Angle of Arrival (AoA), Angle of Departure (AoD), delay spread, and / or average delay. As described herein, the network entity 1054 may be the BS of the cell identified during the procedure 1000 shown in FIG. 10A or may be another network entity. The WTRU 1002 may transmit the one or more measurements and / or service requirements via one or more of the beams of the beam pair for communicating with the network entity 1054. For example, the WTRU 1002 may transmit the one or more measurements and / or service requirements via its UL-Tx beam that corresponds to the DL-Tx beam of the network entity 1054. The WTRU 1002 may indicate its service requirements to the network 1004 as described herein. The WTRU 1002 may indicate to the network entity 1054 whether the WTRU 1002 can be served by a narrow beam or a wide beam. The WTRU 1002 may be configured to communicate via a cell and a DL-Tx wide beam (e.g., as determined by the procedure 1000 or a portion thereof) and / or may initiate operation based on the configuration. The WTRU 1002 may be triggered to perform refined beam selection, for example, to narrow the serving DL-Tx beam when the WTRU 1002 is capable.

[0159] At 1058, the network entity 1004 may send information for updating the beam configuration to the WTRU 1002. For example, the information for updating the beam configuration may include a defined subset of measurement resources that may be used by the WTRU 1004 when performing an exhaustive search to identify narrower beams from which DL information may be received on DL-Tx beams from the network entity 1054. The defined subset of resources may include a cell identifier and / or a set of reference signals for measuring each of the possible finer beams during the exhaustive search. In another example, the network entity 1054 may determine one of the cell and / or updated beam / beam pair based on the reported measurements and / or service requirements and explicitly indicate the cell and / or updated beam / beam pair in the communication 1058 to the WTRU 1002. For example, the network entity 1054 may implement AI / ML and / or another refinement algorithm to determine the cell and / or refined beam / beam pair based on the measurements or service requirements. In another example, cells and / or beams / beam pairs may be predefined in information stored in the network entity 1054 based on the range of measurements to be reported.

[0160] At 1060, the WTRU 1002 may determine an updated beam / beam pair based on the information received from the network entity 1054. The updated beam / beam pair may be narrower than the previous beam / beam pair. The updated beam / beam pair may be explicit in the information, or the WTRU 1002 may perform measurements to determine the updated beam / beam pair at 1060 based on the received information. For example, the WTRU 1002 may perform measurements on a set of reference signals received in the information from the network entity 1054 during the exhaustive search. The WTRU 1002 may also determine an updated cell for conducting communication based on the information received from the network entity 1054.

[0161] At 1062, the WTRU 1002 may report at least one of the performed measurements, the cell, and / or the updated beam / beam pair to the network entity 1054. The WTRU 1002 may be configured with resources for reporting the cell and / or the updated beam / beam pair to the network entity 1054 as described herein. The WTRU 1002 may report an appropriate value within a wider or narrower beam. The appropriate value may include one or more measurements as described herein. At 1064, the WTRU 1002 may perform communication with the network entity 1054 using the updated beam configuration.

[0162] The processes and techniques described herein may be applied to other wireless technologies and to other services.

[0163] The WTRU may refer to a physical device identity or subscription-related identity, e.g., a user identity such as MSISDN, SIP URI, etc., and the WTRU may refer to application-based identity, e.g., a username that may be used per application.

[0164] The processes described above may be implemented in a computer program, software, and / or firmware embodied in a computer-readable medium for execution by a computer and / or processor. Examples of computer-readable media include, but are not limited to, electronic signals (transmitted via wired and / or wireless connections) and / or computer-readable storage media. Examples of 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, but not limited to, internal hard disks and removable disks, magneto-optical media, and / or optical media such as CD-ROM disks and / or digital versatile disks (DVDs). A processor in association with software may be used to implement a radio frequency transceiver for use in a WTRU, UE, terminal, base station, RNC, and / or any host computer.

Claims

1. 1. A method implemented by a wireless transmit / receive unit (WTRU), the method comprising: receiving an indication of resources for reporting the location of the WTRU; transmitting an indication of the location using the resource; and receiving, in response to the transmission of the location, an indication of a first subset of a plurality of measurement resources to enable beam association on a first subset of a plurality of beam pairs (BPs); determining a first beam pair (BP) of the first subset of the plurality of BPs based on a first measurement performed on the first subset of the plurality of measurement resources; reporting the first measurement and at least one service requirement via the first BP to trigger a refinement of the beam association; receiving, in response to reporting the first measurement and the at least one service requirement, an indication of a second subset of the plurality of measurement resources to enable refined beam association on a second subset of the plurality of BPs; determining a second BP of the second subset of the plurality of BPs based on second measurements performed on the second subset of the plurality of measurement resources; transmitting the second BP; A method comprising:

2. The method of claim 1 , wherein the second BP has a beam width narrower than a beam width of the first BP.

3. 3. The method of claim 2, further comprising: in response to the second measurements performed on the second subset of the plurality of measurement resources, reporting one or more of the first measurements or one or more of the second measurements to a base station (BS) for reception on a downlink (DL) transmission beam of the second BP that is narrower than a DL transmission beam of the first BP.

4. 4. The method of claim 3, further comprising: performing a search based on the second subset of the plurality of measurement resources to refine the first BP or to determine the narrower DL transmit beam of the second BP.

5. The method of claim 2 , wherein the first BP is a wide beam BP and the second BP is a narrow beam BP.

6. 2. The method of claim 1, wherein the first subset of the plurality of measurements comprises one or more measurement objects, a set of resources to monitor for discovery signals or synchronization signal blocks (SSBs), or a mini-measurement gap configuration.

7. The method of claim 1 , wherein the indication of the first subset of the plurality of measurement resources is received via a Radio Resource Control (RRC) message or a Medium Access Control (MAC) control element.

8. performing neighbor cell discovery using the first subset of the plurality of measurement resources; reporting neighbor cell measurement resources or the neighbor cell discovery via uplink (UL) resources; The method of claim 1 further comprising:

9. determining at least one preferred beam of a preferred cell or BP; reporting at least one beam of the preferred cell or BP; The method of claim 1 further comprising:

10. 2. The method of claim 1, further comprising: determining to trigger refinement of the first subset of the plurality of BPs based on the at least one service requirement, wherein the at least one service requirement comprises at least one of a data volume, a reliability requirement, a latency requirement, or a data type.

11. 2. The method of claim 1, wherein each BP of the plurality of BPs is associated with a corresponding base station (BS), the first BP is associated with a first BS, and the second BP is associated with the first BS.

12. 2. The method of claim 1, wherein each BP of the plurality of BPs is associated with a corresponding base station (BS), the first BP is associated with a first BS, and the second BP is associated with a second BS different from the first BS.

13. 1. A wireless transmit / receive unit (WTRU), comprising: a processor, the processor comprising: receiving an indication of resources for reporting the location of the WTRU; transmitting an indication of the location using the resource; and receiving, in response to the transmission of the location, an indication of a first subset of a plurality of measurement resources to enable beam association on a first subset of a plurality of beam pairs (BPs); determining a first beam pair (BP) of the first subset of the plurality of BPs based on a first measurement performed on the first subset of the plurality of measurement resources; reporting the first measurement and at least one service requirement via the first BP to trigger a refinement of the beam association; receiving, in response to reporting the first measurement and the at least one service requirement, an indication of a second subset of the plurality of measurement resources to enable refined beam association on a second subset of the plurality of BPs; determining a second BP of the second subset of the plurality of BPs based on second measurements performed on the second subset of the plurality of measurement resources; transmitting the second BP; The WTRU is configured to perform the following:

14. The WTRU of claim 13 , wherein the second BP has a beam width narrower than a beam width of the first BP.

15. the processor:

15. The WTRU of claim 14, further configured to, in response to the second measurements performed on the second subset of the plurality of measurement resources, report one or more of the first measurements or one or more of the second measurements to a base station (BS) for reception on a downlink (DL) transmission beam of the second BP that is narrower than a DL transmission beam of the first BP.

16. the processor:

16. The WTRU of claim 15, further configured to perform a search based on the second subset of the plurality of measurement resources to refine the first BP or to determine the narrower DL transmission beam of the second BP.

17. the processor: determining at least one preferred beam of the preferred cell or BP; The WTRU of claim 13 , further configured to report at least one preferred beam of the preferred cell or BP.

18. 14. The WTRU of claim 13, wherein the processor is further configured to trigger refinement of the first subset of the plurality of BPs based on the at least one service requirement, the at least one service requirement including at least one of a data volume, a reliability requirement, a latency requirement, or a data type.

19. 14. The WTRU of claim 13, wherein each BP of the plurality of BPs is associated with a corresponding base station (BS), the first BP being associated with a first BS, and the second BP being associated with the first BS.

20. 14. The WTRU of claim 13, wherein each BP of the plurality of BPs is associated with a corresponding base station (BS), the first BP is associated with a first BS, and the second BP is associated with a second BS different from the first BS.

Images