AI / ML based radio link failure prediction

Abstract

A method of AI-based compression model performance monitoring performed by a UE. The method includes encoding a UE capability report for transmission to a BS, decoding configuration information received from the BS, the configuration information used to train one or more AI-based models for predicting radio link failure (RLF), encoding a notification message for transmission to the BS, the notification message indicating one or more conditions and availability of one or more AI-based models for use by the UE to the BS, decoding an activation instruction from the gNB, activating the one or more AI-based models for predicting RLF based on the activation instruction, predicting RLF using the one or more AI-based models based on a block error rate of a prediction reference signal or classifying a risk level of RLF based on a plurality of inputs, and transmitting an RLF prediction report to the gNB based on the prediction.

Description

Technical Field

[0001] Embodiments of the present invention relate to wireless communication, including apparatus, systems, and methods for user equipment (UE) side performance monitoring for predicting radio link failures (RLF) based on artificial intelligence (AI) in cellular communication networks.

[0002] Related technical descriptions The use of wireless communication systems is growing rapidly. In recent years, wireless devices such as smartphones and tablets have become increasingly sophisticated. In addition to supporting telephone calls, many mobile devices now offer access to the Internet, email, text messaging, and navigation using the Global Positioning System (GPS), and are capable of operating complex applications that utilize these functionalities.

[0003] Long Term Evolution (LTE) has become the technology of choice for most wireless network operators worldwide, providing mobile broadband data and high-speed internet access to their subscriber base. LTE was first proposed in 2004 and standardized for the first time in 2008. Since then, with the exponential growth in the use of wireless communication systems, the demand from wireless network operators to support higher capacity for a higher density of mobile broadband users has also increased. In 2015, research into new radio access technologies began, and in 2017, the first version of 5G New Radio (5G NR) was standardized.

[0004] 5G-NR (also known as NR for short) offers higher capacity for higher density mobile broadband users compared to LTE, while also supporting ultra-reliable and massive machine-type communication between devices, as well as lower latency and / or lower battery consumption. Additionally, NR allows for more flexible UE scheduling compared to current LTE. Therefore, ongoing development of 5G-NR is underway to take advantage of the potentially higher throughput at higher frequencies. Summary of the Invention

[0005] The implementation relates to wireless communication, and more specifically to apparatus, systems, and methods for a user equipment (UE) device, the UE device including one or more processors coupled to a memory, the one or more processors being configured to: encode a UE capability report for transmission to a base station (e.g., base station (base station)); decode configuration information received from the base station for training one or more artificial intelligence (AI)-based models for predicting radio link failures (RLFs); encode a notification message for transmission to the base station, the notification message informing the base station of one or more conditions and availability of the one or more AI-based models for use by the UE; decode an activation instruction from the base station; activate the one or more AI-based models for predicting radio link failures (RLFs) based on the activation instruction; predict the RLF using the one or more AI-based models based on a predicted block error rate (BLER) of one or more reference signals or based on a risk level classification of the RLF based on multiple inputs; and transmit an RLF prediction report to the base station based on the prediction.

[0006] Other embodiments relate to an apparatus for a base station (e.g., a base station (base station)) including one or more processors coupled to a memory, the one or more processors being configured to: decode a UE capability report received from a user equipment (UE); encode configuration information for transmission to the UE, the configuration information being used to train one or more artificial intelligence (AI)-based models for predicting radio link failures (RLFs); decode a notification message received from the UE, the notification message instructing the base station to indicate one or more conditions and availability of the one or more AI-based models for use by the UE; encode an activation instruction for transmission to the UE, the activation instruction being instructed to the UE to activate the one or more AI-based models for predicting radio link failures (RLFs) based on the activation instruction, and to predict the RLF using the one or more AI-based models based on a predicted block error rate (BLER) of one or more reference signals or based on a risk level classification of the RLF based on multiple inputs; and decode an RLF prediction report received from the UE based on the prediction.

[0007] The technologies described herein can be implemented in and / or used with a variety of different types of devices, including but not limited to unmanned aerial vehicles (UAVs), unmanned controllers (UACs), base stations, access points, cellular phones, tablet computers, wearable computing devices, portable media players, and any of a variety of other computing devices.

[0008] The present invention is intended to provide a brief overview of some of the subjects described in this document. Therefore, it should be understood that the above features are merely illustrative and should not be construed as narrowing the scope or substance of the subjects described herein in any way. Other features, aspects, and advantages of the subjects described herein will become apparent from the following detailed description, drawings, and claims. Attached Figure Description

[0009] A better understanding of the subject matter can be obtained by considering the following detailed description of various embodiments in conjunction with the accompanying drawings, in which: Figure 1A Example wireless communication systems according to some implementation schemes are illustrated.

[0010] Figure 1B Examples of base stations and access points communicating with user equipment (UE) devices according to some implementation schemes are illustrated.

[0011] Figure 2 Example block diagrams of base stations according to some implementation schemes are shown.

[0012] Figure 3 Example block diagrams of servers according to some implementation schemes are shown.

[0013] Figure 4 Example block diagrams of a UE according to some implementation schemes are shown.

[0014] Figure 5 Example block diagrams of cellular communication circuits according to some implementation schemes are shown.

[0015] Figure 6 Examples of baseband processor architectures for UEs according to some implementation schemes are illustrated.

[0016] Figure 7 Example block diagrams illustrating the interface of a baseband circuit according to some implementation schemes are shown.

[0017] Figure 8 Examples of control plane protocol stacks based on some implementation schemes are shown.

[0018] Figure 9A and Figure 9B An example diagram illustrates the execution of AI / ML-based radio link failure (RLF) prediction according to some implementation schemes and the reporting of the prediction output to the network.

[0019] Figure 10 An example timing diagram signaling between a user equipment (UE) and a base station (e.g., a base station (base station)) for providing artificial intelligence (AI)-based radio link failure (RLF) prediction is illustrated according to some implementation schemes.

[0020] Figure 11A and Figure 11B An example diagram illustrates how a base station, according to some implementation schemes, uses the UE's BLER prediction to determine whether to hand over the UE to another cell before a radio link failure occurs.

[0021] Figure 12A and Figure 12B An example diagram illustrates the use of an artificial intelligence (AI) model at the UE to predict radio link failures based on multiple input parameters related to the radio link condition, according to some implementation schemes.

[0022] Figure 13 An example flowchart illustrating a method for providing artificial intelligence (AI)-based radio link failure (RLF) prediction at the user equipment (UE) according to some implementation schemes is shown.

[0023] Figure 14 An example flowchart illustrates a method for predicting radio link failures (RLF) at a base station for assisting user equipment (UE) according to some implementation schemes.

[0024] Although the features described herein may be subject to various modifications and alternatives, specific embodiments thereof are shown by way of example in the accompanying drawings and described in detail herein. However, it should be understood that the drawings and their detailed description are not intended to limit one to the specific forms disclosed, but rather to cover all modifications, equivalents, and alternatives falling within the substance and scope of the subject matter as defined by the appended claims. Detailed Implementation

[0025] the term The following is a glossary of terms used in this disclosure: Memory media—any of various types of nontransitory memory devices or storage devices. The term "memory media" is intended to include mounting media, such as CD-ROMs, floppy disks, or magnetic tape devices; computer system memory or random access memory, such as DRAM, DDR RAM, SRAM, EDO RAM, Rambus RAM, etc.; non-volatile memory, such as flash memory; magnetic media, such as hard disk drives or optical storage devices; registers or other similar types of memory elements, etc. Memory media may also include other types of nontransitory memory or combinations thereof. Furthermore, memory media may reside in a first computer system executing a program, or may reside in a different second computer system connected to the first computer system via a network such as the Internet. In the latter example, the second computer system may provide program instructions to the first computer for execution. The term "memory media" may include two or more memory media residing in different locations in different computer systems connected via, for example, a network. Memory media may store program instructions (e.g., embodied in a computer program) that can be executed by one or more processors.

[0026] Carrier media—such as memory media as described above, and physical transmission media such as buses, networks, and / or other physical transmission media that transmit signals such as electrical signals, electromagnetic signals, or digital signals.

[0027] Programmable hardware elements encompass a variety of hardware devices, which consist of multiple programmable functional blocks connected via programmable interconnects. Examples include FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), FPOAs (Field-Programmable Object Arrays), and CPLDs (Complex PLDs). Programmable functional blocks can range from fine-grained (combinational logic or lookup tables) to coarse-grained (arithmetic logic units or processor cores). Programmable hardware elements may also be referred to as "reconfigurable logic units."

[0028] Computer system (or computer) — any of the various types of computing or processing systems, including personal computer systems (PCs), mainframe computer systems, workstations, network appliances, internet-connected appliances, personal digital assistants (PDAs), television systems, grid computing systems, or other devices or combinations thereof. In general, the term "computer system" can be broadly defined to encompass any device (or combination of devices) having at least one processor that executes instructions from a memory medium.

[0029] User equipment (UE) (or “UE device”) — any of various types of computer system devices that are mobile or portable and perform wireless communication. Examples of UE devices include mobile phones or smartphones (e.g., iPhone). ™Based on Android ™ Telephones), portable gaming devices (e.g., Nintendo DS) ™ PlayStation Portable ™ Gameboy Advance ™ iPhone ™ ), laptops, wearable devices (e.g., smartwatches, smart glasses), PDAs, portable internet devices, music players, data storage devices, other handheld devices, unmanned aerial vehicles (UAVs) (e.g., drones), UAV controllers (UACs), etc. Generally speaking, the term "UE" or "UE device" can be broadly defined to encompass any electronic device, computing device, and / or telecommunications device (or combination of devices) that is easily transportable by the user and capable of wireless communication.

[0030] Base station—The term “base station” has the full range of its common meaning and includes at least a wireless communication station that is installed in a fixed location and is used for communication as part of a wireless telephone system or radio system.

[0031] A processing element (or processor) is a component or combination of components capable of performing the functions of a device such as a user equipment or cellular network device. A processing element may include, for example: a processor and associated memory, portions or circuitry of individual processor cores, an entire processor core, a processor array, circuitry such as an ASIC (Application-Specific Integrated Circuit), programmable hardware components such as a Field-Programmable Gate Array (FPGA), and any combination thereof.

[0032] A channel is a medium used to transmit information from a transmitter to a receiver. It should be noted that because the characteristics of the term "channel" can vary depending on the wireless protocol, the term "channel" as used herein can be considered to be used in a standard manner consistent with the type of device to which the term is referenced. In some standards, channel width can be variable (e.g., depending on device capabilities, frequency band conditions, etc.). For example, LTE can support scalable channel bandwidths from 1.4 MHz to 20 MHz. 5G NR can support scalable channel bandwidths from 5 MHz to 100 MHz in Frequency Range 1 (FR1) and up to 400 MHz in FR2. In other radio access technologies, WLAN channels can be 22 MHz wide, while Bluetooth channels can be 1 MHz wide. Other protocols and standards may include different definitions of channels. Furthermore, some standards may define and use multiple types of channels, for example, different channels for uplink or downlink and / or different channels for different purposes such as data, control information, etc.

[0033] Frequency band—The term “frequency band” has the full range of its general meaning and includes at least a segment of spectrum (e.g., radio frequency spectrum) in which a channel is used or reserved for the same purpose.

[0034] Automatic—means that an action or operation is performed by a computer system (e.g., software executed by the computer system) or device (e.g., circuits, programmable hardware elements, ASICs, etc.) without requiring direct specification or execution of the action or operation through user input. Therefore, the term "automatically" is the opposite of an operation performed or specified manually by a user, where the user provides input to directly perform the operation. An automatic process can be initiated by user-provided input, but the subsequent actions performed "automatically" are not specified by the user; that is, they are not performed "manually," where the user specifies each action to be performed. For example, a user filling out a form by selecting each field and providing input specifying information (e.g., by typing information, selecting a checkbox, radio selection, etc.) is considered manually filling out the form, even though the computer system will update the form in response to the user's actions. The form can be automatically filled out by a computer system, where the computer system (e.g., software executed on the computer system) analyzes the fields of the form and fills out the form without any user input specifying answers for the fields. As indicated above, the user can invoke the automatic filling of the form but does not participate in the actual filling of the form (e.g., the user does not manually specify answers for the fields, but they are completed automatically). This manual provides various examples of operations that are automatically performed in response to actions taken by the user.

[0035] Approximately—means a value close to the correct or precise value. For example, approximately could mean a value within 1% to 10% of the precise (or expected) value. However, it should be noted that the actual threshold (or tolerance) can be application-dependent. For example, in some implementations, “approximately” could mean within 0.1% of some specified or expected value, while in various other implementations, the threshold could be, for example, 2%, 3%, 5%, etc., depending on the expectations or settings of the specific application.

[0036] Concurrency refers to the parallel execution or implementation of tasks, processes, or programs in a manner that at least partially overlaps. For example, concurrency can be achieved using “strong” or strict parallelism, where tasks are executed in parallel (at least partially) on corresponding computing elements; or using “weak parallelism,” where tasks are executed in an interleaved manner (e.g., by time multiplexing of execution threads).

[0037] Various components can be described as being "configured" to perform one or more tasks. In this context, "configured" is a broad expression generally meaning "having a structure" that performs one or more tasks during operation. Therefore, a component can be configured to perform a task even when it is not currently performing one (e.g., a set of electrical conductors can be configured to electrically connect one module to another, even when the two modules are not connected). In some contexts, "configured" can be a broad expression generally meaning "having a circuit" that performs one or more tasks during operation. Therefore, a component can be configured to perform a task even when it is not currently switched on. Generally, the circuit forming the structure corresponding to "configured" can include hardware circuitry.

[0038] For ease of description, various components may be described as performing one or more tasks. Such descriptions should be interpreted as including the phrase "configured to". Statements describing a component as configured to perform one or more tasks are explicitly intended not to invoke the interpretation of 35 USC § 112(f) for that component.

[0039] The example implementation can be further understood by referring to the following description and related figures, in which the same elements have the same reference numerals. The example implementation relates to UE-side performance monitoring for an artificial intelligence (AI) based channel state information (CSI) compression model.

[0040] Example implementations are described in relation to communication between the base station and the user equipment (UE). However, references to the base station or UE are provided for illustrative purposes only. The example implementations can be used with any electronic component that can establish a connection to the network and is configured with hardware, software, and / or firmware to support UE-side performance monitoring for an AI-based CSI compression model. Therefore, the base station or UE described herein is used to represent any suitable type of electronic component.

[0041] An example implementation is also described regarding a fifth-generation (5G) new radio (NR) network that can be configured to control UE-side performance monitoring. However, the reference to the 5G NR network is provided for illustrative purposes only. The example implementation can be used with any suitable type of network.

[0042] As described by the example implementation, a limitation of existing radio link failure (RLF) determination processes in 5G NR networks is that they take a reactive approach based on independent assessments of reference signal block error rate, random access channel events, and radio link control state. By leveraging artificial intelligence and machine learning (AI / ML) models, multiple radio link factors can be analyzed concurrently to reveal complex correlations indicating impending outages. In one embodiment, a user equipment (UE) including one or more processors coupled to memory can be configured to: encode a UE capability report for transmission to a base station; decode configuration information received from the base station for training one or more artificial intelligence (AI)-based models for predicting radio link failures (RLFs); encode a notification message for transmission to the base station informing the base station of one or more conditions and availability of the one or more AI-based models available to the UE; decode an activation instruction from the base station; activate the one or more AI-based models for predicting radio link failures (RLFs) based on the activation instruction; predict the RLF using the one or more AI-based models based on a predicted block error rate (BLER) of one or more reference signals or based on a risk level classification of the RLF based on multiple inputs; and send an RLF prediction report to the base station based on the prediction.

[0043] Throughout this specification, various information elements (IEs) are referred to by specific names. It should be understood that these names are merely examples, and IEs carrying information mentioned throughout this specification may be referred to by various entities under other names.

[0044] Figure 1A and Figure 1B Communication system Figure 1A A simplified example wireless communication system according to some implementation schemes is illustrated. It should be noted that... Figure 1A The system described herein is merely one example of a possible system, and the features of this disclosure can be implemented in any of the various systems as needed.

[0045] As shown in the figure, the example wireless communication system includes a base station 102A, which communicates with one or more user equipments 106A, 106B to 106N, etc., via a transmission medium. Each user equipment may be referred to herein as a "user equipment" (UE). Therefore, user equipment 106 is referred to as a UE or UE device.

[0046] Base station (BS) 102A may be a transceiver base station (BTS) or a cell site (“cellular base station”), and may include hardware that enables wireless communication with UE 106A to UE 106N.

[0047] The communication area (or coverage area) of a base station may be referred to as a "cell". Base station 102A and UE 106 can be configured to communicate via a transmission medium using any of a variety of Radio Access Technologies (RATs), also known as wireless communication technologies or telecommunications standards, such as GSM, UMTS (associated with air interfaces such as WCDMA or TD-SCDMA), LTE, LTE-Advanced (LTE-A), 5G New Radio (5G NR), HSPA, 3GPP2 CDMA2000 (e.g., 1xRTT, 1xEV-DO, HRPD, eHRPD), etc. Note that if base station 102A is implemented in the context of LTE, also known as Evolved Universal Terrestrial Radio Access Network (E-UTRAN), its alternative location may be referred to as an "eNodeB" or "eNB". Note that if base station 102A is implemented in a 5G NR environment, its alternative location may be referred to as a "gNodeB" or "gNB".

[0048] As shown in the figure, base station 102A can also be configured to communicate with network 100 (e.g., in various possibilities, the core network of a cellular service provider, telecommunications networks such as the Public Switched Telephone Network (PSTN), and / or the Internet). Therefore, base station 102A facilitates communication between user equipments and / or between user equipments and network 100. Specifically, cellular base station 102A can provide UE 106 with various telecommunications capabilities, such as voice, SMS, and / or data services.

[0049] Base station 102A and other similar base stations (such as base stations 102B, ..., 102N) operating according to the same or different cellular communication standards can therefore be provided as a network of cells that can provide continuous or nearly continuous overlapping services to UE 106A to UE 106N and similar devices over a geographical area via one or more cellular communication standards.

[0050] Therefore, although base station 102A can act as such Figure 1A The example illustrates the "serving cells" of UEs 106A to UE 106N, but each UE 106 may also be able to receive signals (and possibly within its communication range) from one or more other cells (which may be provided by base stations 102B to 102N and / or any other base stations), which may be referred to as "neighboring cells." Such cells may also facilitate communication between user equipments and / or between user equipments and network 100. These cells may include "macro" cells, "micro" cells, "pecimen" cells, and / or any other cells of various other granularities providing service area size. For example, in Figure 1ABase stations 102A to 102B illustrated can be macro cells, while base station 102N can be a micro cell. Other configurations are also possible.

[0051] In some implementations, base station 102A may be a next-generation base station, such as a 5G New Radio (5G NR) base station or a “gNB”. In some implementations, the base station may be connected to a legacy evolved packet core (EPC) network and / or to an NR core (NRC) network. Furthermore, the base station cell may include one or more transition and receive points (TRPs). Additionally, a UE capable of operating according to 5G NR may be connected to one or more TRPs within one or more base stations.

[0052] It should be noted that UE 106 may be able to communicate using multiple wireless communication standards. For example, UE 106 may be configured to communicate using wireless networking (e.g., Wi-Fi) and / or peer-to-peer wireless communication protocols (e.g., Bluetooth, Wi-Fi peer-to-peer, etc.) other than at least one cellular communication protocol (e.g., GSM, UMTS (associated with, for example, WCDMA or TD-SCDMA air interfaces), LTE, LTE-A, 5G NR, HSPA, 3GPP2 CDMA2000 (e.g., 1xRTT, 1xEV-DO, HRPD, eHRPD, etc.)). If desired, UE 106 may also be configured, or alternatively, to communicate using one or more Global Navigation Satellite Systems (GNSS, such as GPS or GLONASS), one or more mobile television broadcasting standards (e.g., ATSC-M / H or DVB-H) and / or any other wireless communication protocol. Other combinations of wireless communication standards (including more than two wireless communication standards) are also possible.

[0053] Figure 1B User equipment 106 (e.g., one of devices 106A to 106N) communicating with base station 102 and access point 112 according to some embodiments is illustrated. UE 106 can be a device with cellular and non-cellular communication capabilities (e.g., Bluetooth, Wi-Fi, etc.), such as a mobile phone, handheld device, computer or tablet computer, or virtually any type of wireless device.

[0054] UE 106 may include a processor configured to execute program instructions stored in memory. UE 106 may execute any method implementation of the method implementations described herein by executing such stored instructions. Alternatively or additionally, UE 106 may include programmable hardware elements, such as an FPGA (Field Programmable Gate Array) configured to perform any of the method implementations described herein or any portion thereof.

[0055] UE 106 may include one or more antennas for communicating using one or more wireless communication protocols or technologies. In some embodiments, UE 106 may be configured to communicate using, for example, CDMA2000 (1xRTT / 1xEV-DO / HRPD / eHRPD), LTE / Advanced LTE, or 5G NR using a single shared radio component and / or GSM, LTE, Advanced LTE, or 5G NR using a single shared radio component. The shared radio component may be coupled to a single antenna or to multiple antennas (e.g., for MIMO) for performing wireless communication. Generally, the radio component may include any combination of baseband processor, analog RF signal processing circuitry (e.g., including filters, mixers, oscillators, amplifiers, etc.) or digital processing circuitry (e.g., for digital modulation and other digital processing). Similarly, the radio component may use the aforementioned hardware to implement one or more receive chains and transmit chains. For example, UE 106 may share one or more portions of the receive chain and / or transmit chain among multiple wireless communication technologies (such as those discussed above).

[0056] In some implementations, UE 106 may include independent transmit and / or receive chains (e.g., including independent antennas and other radio components) for each wireless communication protocol configured to communicate therewith. As another possibility, UE 106 may include one or more radio components shared among multiple wireless communication protocols, as well as one or more radio components used exclusively by a single wireless communication protocol. For example, UE 106 may include shared radio components for communicating using LTE or 5G NR (or LTE or 1xRTT, or LTE or GSM), and separate radio components for communicating using each of Wi-Fi and Bluetooth. Other configurations are also possible.

[0057] Figure 2 Block diagram of a base station Figure 2 Example block diagrams of base station 102 according to some implementation schemes are shown. It should be noted that... Figure 2 The base station shown is merely one example of a possible base station. As illustrated, base station 102 may include processor 204, which executes program instructions for base station 102. Processor 204 may also be coupled to memory management unit (MMU) 240 (which may be configured to receive addresses from processor 204 and translate those addresses into locations in memory (e.g., memory 260 and read-only memory (ROM) 250)) or to other circuitry or devices.

[0058] Base station 102 may include at least one network port 270. Network port 270 may be configured to couple to a telephone network and provide access rights as described above in Figures 1a, 1b, and... Figure 2 The telephone network described herein includes multiple devices, such as UE device 106.

[0059] Network port 270 (or an additional network port) may also be configured, or alternatively configured, to be coupled to a cellular network, such as the core network of a cellular service provider. The core network may provide mobility-related services and / or other services to multiple devices, such as UE device 106. In some cases, network port 270 may be coupled to a telephone network via the core network, and / or the core network may provide a telephone network (e.g., in other UE devices served by a cellular service provider).

[0060] In some implementations, base station 102 may be a next-generation base station, such as a 5G New Radio (5G NR) base station, or "gNB". In such implementations, base station 102 may be connected to a legacy evolved packet core (EPC) network and / or to an NR core (NRC) network. Furthermore, base station 102 may be considered a 5G NR cell and may include one or more transition and receive points (TRPs). Additionally, UEs capable of operating according to 5G NR may connect to one or more TRPs within one or more base stations.

[0061] Base station 102 may include at least one antenna 234, and may include multiple antennas. At least one antenna 234 may be configured to operate as a wireless transceiver and may be further configured to communicate with UE device 106 via radio component 230. Antenna 234 communicates with radio component 230 via communication link 232. Communication link 232 may be a receive link, a transmit link, or both. Radio component 230 may be configured to communicate via various wireless communication standards, including but not limited to 5G NR, LTE, LTE-A, GSM, UMTS, CDMA2000, Wi-Fi, etc.

[0062] Base station 102 can be configured to perform wireless communication using multiple wireless communication standards. In some instances, base station 102 may include multiple radio components that enable base station 102 to communicate according to multiple wireless communication technologies. For example, as one possibility, base station 102 may include an LTE radio component for performing communication according to LTE and a 5G NR radio component for performing communication according to 5G NR. In this case, base station 102 may be able to operate as both an LTE base station and a 5G NR base station. As another possibility, base station 102 may include a multimode radio component capable of performing communication according to any of multiple wireless communication technologies (e.g., 5G NR and Wi-Fi, LTE and Wi-Fi, LTE and UMTS, LTE and CDMA2000, UMTS and GSM, etc.).

[0063] As further described herein, BS 102 may include hardware and software components for implementing or supporting specific implementations of the features described herein. The processor 204 of base station 102 may be configured, for example, to implement or support some or all of the methods described herein by executing program instructions stored on a memory medium (e.g., a non-transitory computer-readable memory medium). Alternatively, processor 204 may be configured as a programmable hardware element, such as a FPGA (Field-Programmable Gate Array), or as an ASIC (Application-Specific Integrated Circuit), or a combination thereof. Alternatively (or further), in conjunction with one or more of other components 230, 232, 234, 240, 250, 260, 270, the processor 204 of BS 102 may be configured to implement or support some or all of the features described herein.

[0064] Furthermore, as described herein, processor 204 may comprise one or more processing elements. In other words, one or more processing elements may be included in processor 204. Therefore, processor 204 may include one or more integrated circuits (ICs) configured to perform the functions of processor 204. Additionally, each integrated circuit may include circuitry (e.g., a first circuit, a second circuit, etc.) configured to perform the functions of processor 204.

[0065] Furthermore, as described herein, radio component 230 may comprise one or more processing elements. In other words, one or more processing elements may be included in radio component 230. Therefore, radio component 230 may include one or more integrated circuits (ICs) configured to perform the functions of radio component 230. Additionally, each integrated circuit may include circuitry (e.g., a first circuit, a second circuit, etc.) configured to perform the functions of radio component 230.

[0066] In some implementations, a base station or base station 102 and / or its processor 204 may be able to and configured to: encode a UE capability report for transmission to the base station; decode configuration information received from the base station for training one or more artificial intelligence (AI)-based models for predicting radio link failures (RLFs); encode a notification message for transmission to the base station informing the base station of one or more conditions and availability of the one or more AI-based models available for use by the UE; decode an activation instruction from the base station; activate the one or more AI-based models for predicting radio link failures (RLFs) based on the activation instruction; predict the RLF using the one or more AI-based models based on the predicted block error rate (BLER) of one or more reference signals or based on a risk level classification of the RLF based on multiple inputs; and send an RLF prediction report to the base station based on the prediction.

[0067] Figure 3 Server block diagram Figure 3 Example block diagrams of server 104 according to some implementation schemes are shown. Note that... Figure 3 The server shown is merely one example of a possible server. As illustrated, server 104 may include processor 344 capable of executing program instructions for server 104. Processor 344 may also be coupled to memory management unit (MMU) 374 (which may be configured to receive addresses from processor 344 and translate those addresses into locations in memory (e.g., memory 364 and read-only memory (ROM) 354)) or to other circuitry or devices.

[0068] Server 104 can be configured to provide network access functionality to multiple devices, such as base station 102 and UE device 106, for example, as further described herein.

[0069] In some implementations, server 104 may be part of a radio access network, such as a 5G New Radio (5G NR) access network. In some implementations, server 104 may be connected to a legacy evolved packet core (EPC) network and / or to an NR core (NRC) network.

[0070] As described herein, server 104 may include hardware and software components for implementing or supporting the implementation of the features described herein. Processor 344 of server 104 may be configured, for example, to implement or support some or all of the methods described herein by executing program instructions stored on a memory medium (e.g., a non-transitory computer-readable storage medium). Alternatively, processor 344 may be configured as a programmable hardware element, such as a FPGA (Field-Programmable Gate Array), or as an ASIC (Application-Specific Integrated Circuit), or a combination thereof. Alternatively (or further), in conjunction with one or more of other components 354, 364, and / or 374, processor 344 of server 104 may be configured to implement or support some or all of the features described herein.

[0071] Furthermore, as described herein, processor 344 may comprise one or more processing elements. In other words, one or more processing elements may be included in processor 344. Therefore, processor 344 may include one or more integrated circuits (ICs) configured to perform the functions of processor 344. Additionally, each integrated circuit may include circuitry (e.g., a first circuit, a second circuit, etc.) configured to perform the functions of processor 344.

[0072] Figure 4 User Equipment Block Diagram Figure 4 A simplified block diagram of a communication device 106 according to some implementation schemes is shown. Note that... Figure 4 The block diagram of the communication device is merely one example of possible communication devices. According to implementations, communication device 106 may be a user equipment (UE) device, a mobile device or mobile station, a wireless device or wireless station, a desktop computer or computing device, a mobile computing device (e.g., a laptop computer, notebook computer, or portable computing device), a tablet computer, an unmanned aerial vehicle (UAV), a UAV controller (UAC), and / or a combination of devices, as well as other devices. As shown, communication device 106 may include a set of components 400 configured to perform core functions. For example, this set of components may be implemented as a system-on-a-chip (SOC), which may include portions for various purposes. Alternatively, the set of components 400 may be implemented as individual components or groups of components for various purposes. The set of components 400 may be (e.g., communicatively; directly or indirectly) coupled to various other circuitry of communication device 106.

[0073] For example, communication device 106 may include various types of memory (e.g., including NAND flash memory 410), input / output interfaces such as connector I / F 420 (e.g., for connecting to a computer system; docking station; charging station; input devices such as microphone, camera, keyboard; output devices such as speaker; etc.), a display 460 that may be integrated with or external to communication device 106, and cellular communication circuitry 430 such as for 5G NR, LTE, GSM, etc., and short- to medium-range wireless communication circuitry 429 (e.g., Bluetooth). ™ (and WLAN circuitry). In some embodiments, the communication device 106 may include wired communication circuitry (not shown), such as, for example, a network interface card for Ethernet.

[0074] Cellular communication circuitry 430 may be coupled (e.g., communicatively grounded; directly or indirectly) to one or more antennas, such as antennas 435 and 436 shown. Short-to-medium-range wireless communication circuitry 429 may also be coupled (e.g., communicatively grounded; directly or indirectly) to one or more antennas, such as antennas 437 and 438 shown. Alternatively, short-to-medium-range wireless communication circuitry 429 may be coupled (e.g., communicatively grounded; directly or indirectly) to antennas 435 and 436 in addition to or instead of to these antennas. Short-to-medium-range wireless communication circuitry 429 and / or cellular communication circuitry 430 may include multiple receive chains and / or multiple transmit chains for receiving and / or transmitting multiple spatial streams, such as in a multiple-input multiple-output (MIMO) configuration.

[0075] In some embodiments, as further described below, the cellular communication circuit 430 may include dedicated receive chains (including and / or coupled to (e.g., communicatively; directly or indirectly) dedicated processors and / or radio components) for multiple radio access technologies (RATs) (e.g., a first receive chain for LTE and a second receive chain for 5G NR). Furthermore, in some embodiments, the cellular communication circuit 430 may include a single transmit chain that can be switched between radio components dedicated to a particular RAT. For example, a first radio component may be dedicated to a first RAT, such as LTE, and may communicate with a dedicated receive chain and a transmit chain shared with additional radio components, such as a second radio component that may be dedicated to a second RAT (e.g., 5G NR) and may communicate with a dedicated receive chain and a shared transmit chain.

[0076] The communication device 106 may also include one or more user interface elements and / or be configured for use with one or more user interface elements. The user interface elements may include any of a variety of elements, such as a display 460 (which may be a touch screen display), a keyboard (which may be a separate keyboard or may be implemented as part of the touch screen display), a mouse, a microphone and / or a speaker, one or more cameras, one or more buttons, and / or any of a variety of other elements capable of providing information to the user and / or receiving or interpreting user input.

[0077] The communication device 106 may also include one or more smart cards 445 with SIM (Subscriber Identity Module) functionality, such as one or more UICC (Universal Integrated Circuit Card) cards 445. It should be noted that the term "SIM" or "SIM entity" is intended to include any of various types of SIM implementations or SIM functionality, such as one or more UICC cards 445, one or more eUICCs, one or more eSIMs, removable or embedded, etc. In some embodiments, the UE 106 may include at least two SIMs. Each SIM may execute one or more SIM applications and / or otherwise implement SIM functionality. Thus, each SIM may be a single smart card that can be embedded, for example, soldered to a circuit board in the UE 106, or each SIM 410 may be implemented as a removable smart card. Therefore, a SIM may be one or more removable smart cards (such as UICC cards, sometimes referred to as "SIM cards"), and / or SIM 410 may be one or more embedded cards (such as embedded UICCs (eUICCs), sometimes referred to as "eSIMs" or "eSIM cards"). In some implementations (such as when the SIM includes an eUICC), one or more SIMs within the SIM can implement embedded SIM (eSIM) functionality; in such implementations, a single SIM within the SIM can execute multiple SIM applications. Each SIM may include components such as a processor and / or memory; instructions for performing SIM / eSIM functionality may be stored in memory and executed by the processor. In some implementations, UE 106 may include, as needed, a combination of removable smart cards and fixed / non-removable smart cards (such as one or more eUICC cards implementing eSIM functionality). For example, UE 106 may include two embedded SIMs, two removable SIMs, or a combination of one embedded SIM and one removable SIM. Various other SIM configurations are also envisioned.

[0078] As described above, in some implementations, UE 106 may include two or more SIMs. Including two or more SIMs in UE 106 allows UE 106 to support two different phone numbers and allows UE 106 to communicate on two or more corresponding networks. For example, the first SIM may support a first RAT (such as LTE), and the second SIM 410 may support a second RAT (such as 5G NR). Other specific implementations and RATs are also possible. In some implementations, when UE 106 includes two SIMs, UE 106 may support Dual SIM Dual Standby (DSDA) functionality. DSDA functionality allows UE 106 to connect to two networks simultaneously (and use two different RATs), or allows two connections supported by two different SIMs using the same or different RATs to be maintained simultaneously on the same or different networks. DSDA functionality also allows UE 106 to receive voice calls or data traffic simultaneously on either phone number. In some implementations, voice calls may be packet-switched communications. In other words, voice calls can be received using LTE-based Voice (VoLTE) technology and / or NR-based Voice (VoNR) technology. In some implementations, UE 106 may support Dual SIM Dual Standby (DSDS) functionality. DSDS functionality allows either of the two SIMs in UE 106 to standby awaiting a voice call and / or data connection. In DSDS, when a call / data connection is established on one SIM, the other SIM is no longer active. In some implementations, DSDx functionality (DSDA or DSDS functionality) can be implemented using a single SIM (e.g., eUICC) that performs multiple SIM applications for different carriers and / or RATs.

[0079] As shown in the figure, the SOC 400 may include a processor 402 and a display circuit 404. The processor executes program instructions of the communication device 106, and the display circuit performs graphics processing and provides display signals to the display 460. The processor 402 may also be coupled to a memory management unit (MMU) 440 (which may be configured to receive addresses from the processor 402 and translate those addresses into locations in memory (e.g., memory 406, read-only memory (ROM) 450, NAND flash memory 410)) and / or coupled to other circuitry or devices, such as the display circuit 404, short-to-medium-range wireless communication circuitry 429, cellular communication circuitry 430, connector I / F 420, and / or display 460. The MMU 440 may be configured to perform memory protection and page table translation or setup. In some embodiments, the MMU 440 may be included as part of the processor 402.

[0080] As described herein, communication device 106 may include hardware and software components for implementing the features described above to communicate a scheduling profile for power saving to a network. The processor 402 of communication device 106 may be configured to implement some or all of the features described herein, for example, by executing program instructions stored on a memory medium (e.g., a non-transitory computer-readable storage medium). Alternatively (or further), processor 402 may be configured as a programmable hardware element, such as a FPGA (Field-Programmable Gate Array), or as an ASIC (Application-Specific Integrated Circuit). Alternatively (or further), in conjunction with one or more of other components 400, 404, 406, 410, 420, 429, 430, 440, 445, 450, 460, the processor 402 of communication device 106 may be configured to implement some or all of the features described herein.

[0081] Furthermore, as described herein, processor 402 may include one or more processing elements. Therefore, processor 402 may include one or more integrated circuits (ICs) configured to perform the functions of processor 402. Additionally, each integrated circuit may include circuitry (e.g., a first circuit, a second circuit, etc.) configured to perform the functions of processor 402.

[0082] Furthermore, as described herein, the cellular communication circuit 430 and the short-to-medium-range wireless communication circuit 429 may each include one or more processing elements. In other words, one or more processing elements may be included in the cellular communication circuit 430, and similarly, one or more processing elements may be included in the short-to-medium-range wireless communication circuit 429. Therefore, the cellular communication circuit 430 may include one or more integrated circuits (ICs) configured to perform the functions of the cellular communication circuit 430. Furthermore, each integrated circuit may include circuitry (e.g., a first circuit, a second circuit, etc.) configured to perform the functions of the cellular communication circuit 430. Similarly, the short-to-medium-range wireless communication circuit 429 may include one or more ICs configured to perform the functions of the short-to-medium-range wireless communication circuit 429. Furthermore, each integrated circuit may include circuitry (e.g., a first circuit, a second circuit, etc.) configured to perform the functions of the short-to-medium-range wireless communication circuit 429.

[0083] In some implementations, base station 102 and / or its processor 402 may be configured and / or able to select a dynamic measurement opportunity sharing scheme at the base station for L3 measurement opportunities relative to L1 measurement opportunities, as described herein.

[0084] Figure 5 Block diagram of cellular communication circuit Figure 5 Simplified block diagrams of cellular communication circuits according to some implementation schemes are shown. Note that... Figure 5 The block diagram of the cellular communication circuit is merely one example of a possible cellular communication circuit. According to the implementation, the cellular communication circuit 530 (which may be the cellular communication circuit 430) may be included in a communication device (such as the communication device 106 described above). As noted above, among other devices, the communication device 106 may be a user equipment (UE) device, a mobile device or mobile station, a wireless device or wireless station, a desktop computer or computing device, a mobile computing device (e.g., a laptop computer, notebook computer, or portable computing device), a tablet computer, and / or a combination of these devices.

[0085] The cellular communication circuit 530 can be coupled (e.g., communicatively; directly or indirectly) to one or more antennas, such as ( Figure 4 Antennas 435a-b and 436 are shown in the diagram. In some embodiments, cellular communication circuitry 530 may include dedicated receive chains for various RATs (including and / or coupled to (e.g., communicative ground; directly or indirectly) dedicated processors and / or radio components) (e.g., a first receive chain for LTE and a second receive chain for 5G NR). For example, as... Figure 5 As shown, the cellular communication circuit 530 may include a modem 510 and a modem 520. The modem 510 may be configured for communication according to a first RAT (e.g., such as LTE or LTE-A), and the modem 520 may be configured for communication according to a second RAT (e.g., such as 5G NR).

[0086] As shown, modem 510 may include one or more processors 512 and memory 516 communicating with processors 512. Modem 510 may communicate with radio frequency (RF) front end 535. RF front end 535 may include circuitry for transmitting and receiving radio signals. For example, RF front end 535 may include receiver circuitry (RX) 532 and transmitter circuitry (TX) 534. In some embodiments, receiver circuitry 532 may communicate with downlink (DL) front end 550, which may include circuitry for receiving radio signals via antenna 335a.

[0087] Similarly, modem 520 may include one or more processors 522 and memory 526 communicating with processor 522. Modem 520 may communicate with RF front end 540. RF front end 540 may include circuitry for transmitting and receiving radio signals. For example, RF front end 540 may include receiving circuitry 542 and transmitting circuitry 544. In some embodiments, receiving circuitry 542 may communicate with DL front end 560, which may include circuitry for receiving radio signals via antenna 335b.

[0088] In some implementations, switch 570 may couple transmitting circuitry 534 to uplink (UL) front-end 572. Additionally, switch 570 may couple transmitting circuitry 544 to UL front-end 572. UL front-end 572 may include circuitry for transmitting radio signals via antenna 336. Therefore, when cellular communication circuitry 530 receives an instruction to transmit according to a first RAT (e.g., supported by modem 510), switch 570 may be switched to a first state allowing modem 510 to transmit signals according to the first RAT (e.g., via a transmission chain including transmitting circuitry 534 and UL front-end 572). Similarly, when cellular communication circuitry 530 receives an instruction to transmit according to a second RAT (e.g., supported by modem 520), switch 570 may be switched to a second state allowing modem 520 to transmit signals according to the second RAT (e.g., via a transmission chain including transmitting circuitry 544 and UL front-end 572).

[0089] As described herein, modem 510 may include hardware and software components for implementing the features described above or for UL data used in time-division multiplexing NSA NR operation, as well as various other techniques described herein. Processor 512 may be configured, for example, to implement some or all of the features described herein by executing program instructions stored on a memory medium (e.g., a non-transitory computer-readable storage medium). Alternatively (or additionally), processor 512 may be configured as a programmable hardware element, such as a FPGA (Field-Programmable Gate Array), or as an ASIC (Application-Specific Integrated Circuit). Alternatively (or additionally), in conjunction with one or more of other components 530, 532, 534, 535, 550, 570, 572, 335a, 335b, and 336, processor 512 may be configured to implement some or all of the features described herein.

[0090] Furthermore, as described herein, processor 512 may include one or more processing elements. Therefore, processor 512 may include one or more integrated circuits (ICs) configured to perform the functions of processor 512. Additionally, each integrated circuit may include circuitry (e.g., a first circuit, a second circuit, etc.) configured to perform the functions of processor 512.

[0091] Processor 522 may be configured to implement some or all of the features described herein, for example, by executing program instructions stored on a memory medium (e.g., a non-transitory computer-readable memory medium). Alternatively (or additionally), processor 522 may be configured as a programmable hardware element, such as a FPGA (Field-Programmable Gate Array), or as an ASIC (Application-Specific Integrated Circuit). Alternatively (or additionally), in conjunction with one or more of other components 540, 542, 544, 550, 570, 572, 335a, 335b, and 336, processor 522 may be configured to implement some or all of the features described herein.

[0092] Furthermore, as described herein, processor 522 may include one or more processing elements. Therefore, processor 522 may include one or more integrated circuits (ICs) configured to perform the functions of processor 522. Additionally, each integrated circuit may include circuitry (e.g., a first circuit, a second circuit, etc.) configured to perform the functions of processor 522.

[0093] Figure 6 Block diagram of the baseband processor architecture for UE Figure 6 Example components of device 600 according to some implementation schemes are illustrated. It should be noted that... Figure 6 The device described is merely one example of a possible system, and the features of this disclosure can be implemented in any UE of various types as needed.

[0094] In some embodiments, device 600 may include application circuitry 602, baseband circuitry 604, radio frequency (“RF”) circuitry 606, front-end module (“FEM”) circuitry 608, one or more antennas 610, and power management circuitry (“PMC”) 612 (at least coupled together as shown). Components of the illustrated device 600 may be included in UE 106 or RAN node 102A. In some embodiments, device 600 may include fewer components (e.g., the RAN node may not utilize application circuitry 602, but instead include a processor / controller to process IP data received from the EPC). In some embodiments, device 600 may include additional components such as, for example, memory / storage devices, displays, cameras, sensors, or input / output (I / O) interfaces. In other embodiments, the components described below may be included in more than one device (e.g., the circuitry may be individually included in more than one device for a cloud-RAN (C-RAN) specific implementation).

[0095] Application circuitry 602 may include one or more application processors. For example, application circuitry 602 may include circuitry such as, but not limited to, one or more single-core or multi-core processors. The one or more processors may include any combination of general-purpose processors and special-purpose processors (e.g., graphics processors, application processors, etc.). These processors may be coupled to or may include memory / storage devices and may be configured to execute instructions stored in the memory / storage device to enable various applications or operating systems to run on device 600. In some embodiments, the processor of application circuitry 602 may process IP data packets received from the EPC.

[0096] Baseband circuitry 604 may include circuitry such as, but not limited to, one or more single-core or multi-core processors. Baseband circuitry 604 may include one or more baseband processors or control logic components to process baseband signals received from the receive signal path of RF circuitry 606 and generate baseband signals for the transmit signal path of RF circuitry 606. Baseband processing circuitry 604 may interact with application circuitry 602 to generate and process baseband signals and control the operation of RF circuitry 606. For example, in some embodiments, baseband circuitry 604 may include a third-generation (3G) baseband processor 604A, a fourth-generation (4G) baseband processor 604B, a fifth-generation (5G) baseband processor 604C, or other existing, under development, or future generations of baseband processors 604D (e.g., second-generation (2G), sixth-generation (6G), etc.). Baseband circuitry 604 (e.g., one or more of baseband processors 604A to 604D) may handle various radio control functions to implement communication with one or more radio networks via RF circuitry 606. In other embodiments, some or all of the functionality of the baseband processors 604A to 604D may be included in modules stored in memory 604G and executed via a central processing unit (CPU) 604E. Radio control functions may include, but are not limited to, signal modulation / demodulation, encoding / decoding, and radio frequency shifting. In some embodiments, the modulation / demodulation circuitry of the baseband circuitry 604 may include Fast Fourier Transform (FFT), pre-decoding, or constellation mapping / demapping functionality. In some embodiments, the encoding / decoding circuitry of the baseband circuitry 604 may include convolution, tail-biting convolution, turbo, Viterbi, or low-density parity-check (LDPC) encoder / decoder functionality. Implementations of the modulation / demodulation and encoder / decoder functions are not limited to these examples, and other suitable functionality may be included in other embodiments.

[0097] In some embodiments, the baseband circuitry 604 may include one or more audio digital signal processors (“DSPs”) 604F. The audio DSP 604F may include elements for compression / decompression and echo cancellation, and in other embodiments may include other suitable processing elements. In some embodiments, components of the baseband circuitry may be suitably combined in a single chip, a single chipset, or disposed on the same circuit board. In some embodiments, some or all of the components of the baseband circuitry 604 and the application circuitry 602 may be implemented together, for example, on a system-on-a-chip (SOC).

[0098] In some implementations, baseband circuit 604 can provide communication compatible with one or more radio technologies. For example, in some implementations, baseband circuit 604 can support communication with the Evolved Universal Terrestrial Radio Access Network (EUTRAN) or other Wireless Metropolitan Area Networks (WMAN), Wireless Local Area Networks (WLAN), or Wireless Personal Area Networks (WPAN). Implementations in which baseband circuit 604 is configured to support radio communication with more than one radio protocol may be referred to as multimode baseband circuits.

[0099] RF circuit 606 enables communication with a wireless network via a non-solid medium using modulated electromagnetic radiation. In various embodiments, RF circuit 606 may include switches, filters, amplifiers, etc., to facilitate communication with the wireless network. RF circuit 606 may include a receive signal path that includes circuitry for down-converting the RF signal received from FEM circuit 608 and providing a baseband signal to baseband circuit 604. RF circuit 606 may also include a transmit signal path that includes circuitry for up-converting the baseband signal provided by baseband circuit 604 and providing an RF output signal for transmission to FEM circuit 608.

[0100] In some embodiments, the receive signal path of RF circuit 606 may include mixer circuit 606a, amplifier circuit 606b, and filter circuit 606c. In some embodiments, the transmit signal path of RF circuit 606 may include filter circuit 606c and mixer circuit 606a. RF circuit 606 may also include synthesizer circuit 606d for synthesizing frequencies used by mixer circuit 606a in both the receive and transmit signal paths. In some embodiments, mixer circuit 606a in the receive signal path may be configured to down-convert the RF signal received from FEM circuit 608 based on the synthesized frequency provided by synthesizer circuit 606d. Amplifier circuit 606b may be configured to amplify the down-converted signal, and filter circuit 606c may be a low-pass filter (LPF) or band-pass filter (BPF) configured to remove unwanted signals from the down-converted signal to generate an output baseband signal. The output baseband signal may be provided to baseband circuit 604 for further processing. In some implementations, these output baseband signals may be zero-frequency baseband signals, but this is not necessary. In some implementations, the mixer circuit 606a in the receiving signal path may include a passive mixer, but the scope of the implementations is not limited in this respect.

[0101] In some implementations, the mixer circuit 606a of the transmit signal path may be configured to up-convert the input baseband signal based on the synthesis frequency provided by the synthesizer circuit 606d to generate an RF output signal for the FEM circuit 608. The baseband signal may be provided by the baseband circuit 604 and may be filtered by the filter circuit 606c.

[0102] In some embodiments, the mixer circuit 606a for the receive signal path and the mixer circuit 606a for the transmit signal path may include two or more mixers and may be arranged for quadrature downconversion and quadrature upconversion, respectively. In some embodiments, the mixer circuit 606a for the receive signal path and the mixer circuit 606a for the transmit signal path may include two or more mixers and may be arranged for image rejection (e.g., Hartley image rejection). In some embodiments, the mixer circuit 606a for the receive signal path and the mixer circuit 606a for the transmit signal path may be arranged for direct downconversion and direct upconversion, respectively. In some embodiments, the mixer circuit 606a for the receive signal path and the mixer circuit 606a for the transmit signal path may be configured for superheterodyne operation.

[0103] In some embodiments, the output baseband signal and the input baseband signal may be analog baseband signals, but the scope of the embodiments is not limited in this respect. In some alternative embodiments, the output baseband signal and the input baseband signal may be digital baseband signals. In these alternative embodiments, RF circuit 606 may include analog-to-digital converter (ADC) and digital-to-analog converter (DAC) circuitry, and baseband circuit 604 may include a digital baseband interface for communicating with RF circuit 606.

[0104] In some dual-mode implementations, separate radio IC circuits may be provided to process signals for each spectrum, but the scope of the implementation is not limited in this respect.

[0105] In some implementations, synthesizer circuit 606d may be a fractional-N synthesizer or a fractional-N / N+1 synthesizer, but the scope of implementations is not limited in this respect, as other types of frequency synthesizers may also be suitable. For example, synthesizer circuit 606d may be a Δ-∑ synthesizer, a frequency multiplier, or a synthesizer including a phase-locked loop with a frequency divider.

[0106] Synthesizer circuit 606d can be configured to synthesize an output frequency based on a frequency input and a divider control input for use by mixer circuit 606a of RF circuit 606. In some embodiments, synthesizer circuit 606d may be a fractional N / N+1 synthesizer.

[0107] In some implementations, the frequency input may be provided by a voltage-controlled oscillator (VCO), but this is not necessary. The divider control input may be provided by the baseband circuit 604 or the application processor 602 according to the desired output frequency. In some implementations, the divider control input (e.g., N) may be determined from a lookup table based on the channel indicated by the application processor 602.

[0108] The synthesizer circuit 606d of the RF circuit 606 may include a frequency divider, a delay-locked loop (DLL), a multiplexer, and a phase accumulator. In some embodiments, the frequency divider may be a dual-mode divider (DMD), and the phase accumulator may be a digital phase accumulator (DPA). In some embodiments, the DMD may be configured to divide the input signal by N or N+1 (e.g., based on carry) to provide a fractional division ratio. In some example embodiments, the DLL may include a cascaded, tunable delay element, a phase detector, a charge pump, and a set of D-type flip-flops. In these embodiments, the delay elements may be configured to divide the VCO cycle into Nd equal phase groups, where Nd is the number of delay elements in the delay line. Thus, the DLL provides negative feedback to help ensure that the total delay through the delay line is one VCO cycle.

[0109] In some embodiments, synthesizer circuitry 606d may be configured to generate a carrier frequency as the output frequency, while in other embodiments, the output frequency may be a multiple of the carrier frequency (e.g., twice the carrier frequency, four times the carrier frequency) and used in conjunction with quadrature generator and frequency divider circuitry to generate multiple signals having multiple different phases relative to each other at the carrier frequency. In some embodiments, the output frequency may be the LO frequency (fLO). In some embodiments, RF circuitry 606 may include an IQ / polarity converter.

[0110] FEM circuit 608 may include a receive signal path, which may include circuitry configured to operate on RF signals received from one or more antennas 610, amplify the received signals, and provide an amplified version of the received signals to RF circuit 606 for further processing. FEM circuit 608 may also include a transmit signal path, which may include circuitry configured to amplify transmit signals provided by RF circuit 606 for transmission by one or more of the one or more antennas 610. In various embodiments, amplification via the transmit or receive signal path may be performed only in RF circuit 606, only in FEM 608, or in both RF circuit 606 and FEM 608.

[0111] In some embodiments, FEM circuit 608 may include a TX / RX switch for switching between transmit and receive mode operation. The FEM circuit may include a receive signal path and a transmit signal path. The receive signal path of the FEM circuit may include an LNA for amplifying the received RF signal and providing the amplified received RF signal as an output (e.g., provided to RF circuit 606). The transmit signal path of FEM circuit 608 may include a power amplifier (PA) for amplifying (e.g., provided by RF circuit 606) the input RF signal; and one or more filters for generating an RF signal for subsequent transmission (e.g., through one or more antennas in one or more antennas 610).

[0112] In some implementations, the PMC 612 can manage the power supplied to the baseband circuitry 604. Specifically, the PMC 612 can control power selection, voltage scaling, battery charging, or DC-DC conversion. The PMC 612 is typically included when the device 600 can be powered by a battery, for example, when the device is included in a UE. The PMC 612 can improve power conversion efficiency while providing the desired implementation size and thermal characteristics.

[0113] Although Figure 6A PMC 612 is shown coupled only to the baseband circuit 604; however, in other embodiments, the PMC 612 may be additionally or alternatively coupled to other components such as, but not limited to, the application circuit 602, the RF circuit 606, or the FEM 608, and perform similar power management operations for these other components.

[0114] In some implementations, the PMC 612 can control or otherwise become part of various power-saving mechanisms of the device 600. For example, if the device 600 is in the Radio Resource Control_Connected (RRC_Connected) state, where the device is still connected to the RAN node because it expects to receive traffic immediately, it can enter a state called Discontinuous Receive Mode (DRX) after a period of inactivity. During this state, the device 600 can be powered down for short intervals, thereby saving power.

[0115] If there is no data traffic activity during the extended period, device 600 can transition to the RRC_Idle state, in which the device disconnects from the network and does not perform operations such as channel quality feedback or handover. Device 600 enters a very low power state and performs paging, in which the device periodically wakes up again to listen to the network, and then powers off again. Device 600 may be unable to receive data in this state, and to receive data, it will transition back to the RRC_Connected state.

[0116] An additional power-saving mode renders the device unusable for a period exceeding the paging interval (from seconds to hours). During this time, the device is completely unconnected to the network and may be completely powered off. Any data transmitted during this period will incur significant latency, which is assumed to be acceptable.

[0117] The processor of application circuit 602 and the processor of baseband circuit 604 can be used to execute elements of one or more instances of the protocol stack. For example, the processor of baseband circuit 604 can be used individually or in combination to perform layer 3, layer 2, or layer 1 functions, while the processor of application circuit 604 can utilize data received from these layers (e.g., packet data) and further perform layer 4 functions (e.g., transmit communication protocol (TCP) and user datagram protocol (UDP) layers). As mentioned herein, layer 3 (L3) may include the Radio Resource Control (RRC) layer, which will be described in further detail below. As mentioned herein, layer 2 (L2) may include the Media Access Control (MAC) layer, the Radio Link Control (RLC) layer, and the Packet Data Convergence Protocol (PDCP) layer, which will be described in further detail below. As mentioned herein, layer 1 (L1) may include the physical (PHY) layer of the UE / RAN node, which will be described in further detail below. Therefore, baseband circuit 604 can be used to encode messages for transmission between the UE and the base station, or to decode messages received between the UE and the base station.

[0118] For example, baseband circuitry 604, operating in conjunction with application circuitry 602, radio frequency (RF) circuitry 606, front-end module (FEM) circuitry 608, one or more antennas 610, and power management circuitry (PMC) 612, can be used to receive from a base station an indication for activating AI-based compressed model performance monitoring at the UE; and to decode configuration information received from the base station at the UE for AI-based compressed model performance monitoring. In another embodiment, baseband circuitry 604 can be used to decode channel state information (CSI) received from the base station; to compress the CSI at the UE using an AI-based compressed model to generate a compressed CSI; and to reconstruct the compressed CSI at the UE using an AI-based reconstruction model to generate a reconstructed CSI for AI-based compressed model monitoring. In another embodiment, baseband circuitry 604 can be used to determine a similarity metric between the CSI and the reconstructed CSI and / or to compare the similarity metric with a compressed model threshold; and to send a monitoring report to the base station based on the comparison. These examples are not intended to be limiting. Baseband circuitry can be used as previously described.

[0119] Figure 7 Block diagram of the baseband circuit interface Figure 7 Example interfaces of baseband circuits according to some implementation schemes are illustrated. Note that... Figure 7 The baseband circuit is merely one example of a possible circuit, and the features of this disclosure can be implemented in any system of various types as needed.

[0120] As discussed above, Figure 6The baseband circuit 604 may include processors 604A to 604E and a memory 604G utilized by the processors. Each of the processors 604A to 604E may respectively include a memory interface 704A to 704E for transferring / receiving data to / from the memory 604G.

[0121] Baseband circuit 604 may also include one or more interfaces for communicatively coupling to other circuits / devices, such as memory interface 712 (e.g., an interface for transferring / receiving data to / from a memory external to baseband circuit 604) and application circuit interface 714 (e.g., an interface for transferring / receiving data to / from a memory external to baseband circuit 604). Figure 6 Application circuit 602 is an interface for transmitting / receiving data), and RF circuit interface 716 (e.g., for transmitting / receiving data to / from...). Figure 6 The RF circuit 606 is an interface for transmitting / receiving data, and the wireless hardware connectivity interface 718 is used for transmitting / receiving data to / from near field communication (NFC) components, Bluetooth, etc. ® Components (e.g., Bluetooth) ® Low power consumption, Wi-Fi ® The interface for transmitting / receiving data to / from the PMC 612 (e.g., an interface for transmitting / receiving power or control signals to / from the PMC 612).

[0122] Figure 8 Control plane protocol stack Figure 8 This is an example of a control plane protocol stack according to some implementation schemes. In this implementation scheme, control plane 800 is shown as a communication protocol stack between UE 106a (or alternatively, UE 106b), RAN node 102A (or alternatively, RAN node 102B) and Mobility Management Entity (MME) 621.

[0123] PHY layer 801 can transmit or receive information used by MAC layer 802 through one or more air interfaces. PHY layer 801 can further perform link adaptive or adaptive modulation and decoding (AMC), power control, cell search (e.g., for initial synchronization and handover purposes), and other measurements used by higher layers (such as RRC layer 805). PHY layer 801 can also further perform error detection of the transport channel, forward error correction (FEC) decoding / decoding of the transport channel, modulation / demodulation of the physical channel, interleaving, rate matching, mapping to the physical channel, and multiple-input multiple-output (MIMO) antenna processing.

[0124] The MAC layer 802 can perform mapping between logical channels and transport channels, multiplexing MAC service data units (SDUs) from one or more logical channels onto a transport block (TB) to be delivered to the PHY via the transport channel, demultiplexing MAC SDUs from a transport block (TB) delivered from the PHY via the transport channel onto one or more logical channels, multiplexing MAC SDUs onto a TB, scheduling information reporting, error correction via Hybrid Automatic Repeat Request (HARQ), and logical channel priority sorting.

[0125] RLC layer 803 can operate in multiple modes, including Transparent Mode (TM), Unacknowledged Mode (UM), and Acknowledged Mode (AM). RLC layer 803 can perform the transmission of upper-layer protocol data units (PDUs), error correction via Automatic Repeat Request (ARQ) for AM data transmission, and the concatenation, segmentation, and reassembly of RLC SDUs for UM and AM data transmission. RLC layer 803 can also re-segment RLC data PDUs for AM data transmission, reorder RLC data PDUs for UM and AM data transmission, detect duplicate data for UM and AM data transmission, discard RLC SDUs for UM and AM data transmission, detect protocol errors for AM data transmission, and perform RLC re-establishment.

[0126] The PDCP layer 804 can perform IP data header compression and decompression, maintain PDCP sequence numbers (SNs), perform sequential delivery of upper-layer PDUs when re-establishing the lower layer, eliminate duplication of lower-layer SDUs when re-establishing the lower layer for radio bearers mapped on RLC AM, encrypt and decrypt control plane data, perform integrity protection and integrity verification on control plane data, control timer-based data discarding, and perform security operations (e.g., encryption, decryption, integrity protection, integrity verification, etc.).

[0127] The main services and functions of RRC layer 805 may include broadcasting system information (e.g., included in the Master Information Block (MIB) or System Information Block (SIB) associated with the Non-Access Stratum (NAS), broadcasting system information associated with the Access Stratum (AS), paging, establishment, maintenance, and release of RRC connections between the UE and the E-UTRAN (e.g., RRC connection paging, RRC connection establishment, RRC connection modification, and RRC connection release), establishment, configuration, maintenance, and release of point-to-point radio bearers, including security functions for key management, inter-Radio Access Technology (RAT) mobility, and measurement configuration for UE measurement reporting. The MIB and SIB may include one or more Information Elements (IEs), each of which may include a separate data field or data structure.

[0128] UE 601 and RAN node 102A can use the Uu interface (e.g., the LTE-Uu interface) to exchange control plane data via a protocol stack including PHY layer 801, MAC layer 802, RLC layer 803, PDCP layer 804 and RRC layer 805.

[0129] The Non-Access Stratum (NAS) protocol 806 forms the highest layer of the control plane between UE 601 and MME 621. NAS protocol 806 supports the mobility and session management procedures of UE 601 to establish and maintain IP connectivity between UE 601 and P-GW 623.

[0130] The S1 Application Protocol (S1-AP) layer 815 supports the functions of the S1 interface and includes the Basic Procedure (EP). The EP is the interaction unit between RAN node 102A and CN 1020. S1-AP layer services can include two sets: UE-associated services and non-UE-associated services. These services perform functions including, but not limited to: E-UTRAN Radio Access Bearer (E-RAB) management, UE capability indication, mobility, NAS signaling transmission, RAN Information Management (RIM), and configuration delivery.

[0131] The Flow Control Transmission Protocol (SCTP) layer (optionally referred to as the SCTP / IP layer) 814 can, in part, rely on the IP protocol supported by the IP layer 813 to ensure reliable delivery of signaling messages between the RAN node 102A and the MME 621. The L2 layer 812 and the L1 layer 811 can refer to the communication links (e.g., wired or wireless) used by the RAN node and the MME to exchange information.

[0132] RAN node 102A and MME 621 can use the S1-MME interface to exchange control plane data via a protocol stack including L1 layer 811, L2 layer 812, IP layer 813, SCTP layer 814 and S1-AP layer 815.

[0133] Wireless communication systems provide mobility by enabling user equipment (UEs) to move between cells via a process known as handover. Handover occurs when a mobile UE switches from one cell to another neighboring cell. Mechanisms have been established to help ensure a smooth transition between cells. NR supports different types of handover not supported in previous 4G LTE specifications. The basic handover in NR is based on LTE handover mechanisms, in which the network controls UE mobility based on UE measurement reports. These measurement reports typically involve Layer 3 (L3) measurements of neighboring cells and reports from the UE to the eNB.

[0134] It should be noted that 5G NR implements various advanced capabilities compared to LTE, and one existing process that can benefit from leveraging these enhancements of 5G technology is the Radio Link Failure (RLF) mechanism. RLF refers to a situation where radio link quality deteriorates below a certain threshold, causing a communication interruption between the User Equipment (UE) and the serving base station. The current RLF process has some limitations because it only reacts to failures after they have occurred, rather than proactively preventing them. The process also relies on a limited set of reference signal measurements that may not fully capture emerging radio link problems. Additionally, downlink and uplink signals are evaluated independently, even though they are often correlated in indicating radio link conditions.

[0135] These gaps highlight the use cases where advanced algorithms, such as artificial intelligence (AI) and machine learning (ML), combined with coordination between the UE and next-generation NodeBs (base stations), can provide more predictive identification of the risk of impending radio link failures. By intelligently fusing multiple radio link indicators and historical measurements, AI / ML can potentially predict failures in advance, allowing mitigation actions (such as handover) to prevent deterioration, rather than simply reacting to RLF events. As 5G networks continue to evolve, achieving such predictive failure management can further improve reliability mechanisms.

[0136] Figure 9A , Figure 9B AI / ML-based prediction and reporting of radio link failures (RLF). In cellular systems, radio link monitoring involves consistently measuring reference signals to detect when radio link quality degrades below a predetermined threshold. When radio link quality degrades below a predetermined threshold, there is a significant chance of a Radio Link Failure (RLF), in which the radio link between two devices fails to function within expected parameters. When an RLF is declared based on a threshold set by the network, communication can be interrupted until the link can be re-established.

[0137] However, the current RLF process in 5G NR has several key issues, including: the current RLF process is reactive rather than proactive in avoiding faults; it relies on a limited set of reference signals for radio link monitoring, which may not be able to fully capture emerging problems; it uses static triggering conditions that decouple downlink indicators from uplink indicators; and it incurs significant costs, such as re-establishment, when declaring a fault.

[0138] To overcome these challenges, the implementation scheme presented in this paper enables UE-side monitoring and reporting of AI-based CSI compression model performance. This is achieved by providing CSI reconstruction capabilities at the UE using an AI-based reconstruction model that can be used to predict block error rate (BLER). The original CSI before compression can then be compared with the reconstructed CSI at the UE using an intermediate metric such as squared generalized cosine similarity (SGCS). The defined monitoring process allows for the evaluation of compression model quality over periodic windows based on thresholding of the intermediate metric. Network configuration of parameters such as the evaluation monitoring window and thresholds allows for flexible supervision. By defining the CSI reconstruction and intermediate metric monitoring process performed at the UE, problems with the AI ​​compression model can be located and quickly reported to the network. These solutions improve the reliability of AI-based CSI compression deployment.

[0139] Figure 9A and Figure 9B An example diagram illustrates the execution of AI / ML-based radio link failure (RLF) prediction according to some implementation schemes and the reporting of the prediction output to the network. As depicted, Figures 9A to 9B The illustration illustrates how the UE collects various radio link inputs, such as Reference Signal Received Power (RSRP), Reference Signal Received Quality (RSRQ), downlink throughput, and beam index. These inputs are fed into a BLER prediction model, which includes a trained machine learning model that generates predicted future BLER and a confidence level associated with the BLER prediction. The confidence level of the predicted BLER rise over future time and the BLER waveform are depicted as transmitted from the UE to the next-generation NodeB (base station). By predicting potential BLER degradation, the base station can proactively assist the UE to avoid radio link failures, such as by triggering early handover to another cell based on BLER predictions.

[0140] More specifically, in Figure 9A In Figure 910, the primary cell (PCell) serving the user equipment (UE) detects five consecutive out-of-synchronization (OOS) indications, triggering the T310 RLF timer. The secondary cell (SCell) receives a BLER prediction report from the UE, indicating that radio conditions are unlikely to recover on the PCell. Before T310 expires, the SCell transmits a handover (HO) command to the PCell, and / or the network (e.g., a base station) moves the UE to another cell.

[0141] exist Figure 9BIn Figure 920, the PCell serving the UE initially receives 5 OOS indications, initiating the T310 timer, but subsequently receives 2 Synchronization (IS) indications indicating potential recovery. The SCell receives a BLER prediction report allowing network-suppressed handover and stops T310 at the PCell based on radio link recovery. By predicting BLER trends via machine learning, the reliability of mobility processes can be enhanced based on coordination between the UE and the base station across primary and secondary cells.

[0142] Therefore, the implementation described herein uses AI / ML-based block error rate (BLER) forecasting operations implemented in the user equipment (UE) to predict potential degradation of radio link quality, and coordinates with the secondary cell and network to utilize BLER forecasts to make adaptive decisions on mobility processes to prevent radio link failures.

[0143] In one implementation, the UE predicts one or more BLERs indicating the risk of future RLF events, thus providing a proactive approach to the RLF process rather than passively reacting to problems via existing RLF procedures. The predicted BLER level allows for the activation of alternative procedures, such as, for example, proactively using early handover. Reporting the prediction on the secondary cell and adapting the process based on BLER forecasts enables reliable coordination between the UE and the base station to take action prior to RLF.

[0144] Figure 10 Timing diagram of AI / ML-based radio link failure (RLF) prediction and reporting .

[0145] Figure 10 Example timing diagram signaling between user equipment (UE) and base station (base station) for providing artificial intelligence (AI)-based radio link failure (RLF) prediction, according to some implementation schemes, is illustrated. Furthermore, Figure 10 An example illustration of UE 106 communicating with base station 102 (e.g., a base station) is provided. In various embodiments, some of the signaling shown may be executed concurrently in a different order than that shown, or may be omitted. Additional signaling may also be executed as needed. As shown, the signaling may take the form of the following example embodiment. Figure 10 The signaling shown can be used in conjunction with any of the systems, methods, and / or devices. In various embodiments, some of the signaling shown may be executed concurrently in a different order than that shown, or may be omitted. Additional signaling may also be executed as needed. As shown in the figure, the signaling can be implemented in one of the following example embodiments.

[0146] The signaling may begin when a UE (such as UE 106) sends a UE Capability Report (1002) to a base station (e.g., base station 102). The UE Capability Report may indicate support for time prediction of the Block Error Rate (BLER) of a reference signal used for Radio Link Monitoring (RLM), support for prediction of BLER across RLM-RS (e.g., predicting the BLER of an RLM-RS based on BLER measurements of different RLM-RSs, rather than directly measuring each RLM-RS), the maximum number of historical and predicted samples used for BLER prediction, the maximum number of predicted samples, and the maximum number of parallel predictions. It should be noted that the RLM-RS may be a specific reference signal (e.g., CSI-RS, SSB) configured for direct monitoring of radio link quality.

[0147] The signaling may also include a base station (such as base station 102) providing 1004 configuration information to the UE for training one or more artificial intelligence (AI)-based models for predicting radio link failures (RLF). The signaling may also include the UE collecting 1006 data for training the one or more AI-based models. In one implementation, the configuration information may include indications for each type of the one or more AI-based models (e.g., Long Short-Term Memory (LSTM) or Recurrent Neural Network (Rnn)), the prediction window length for BLER prediction, and the number of parallel predictions.

[0148] The signaling may also include the UE communicating data collection 1006 to an offline server 1010 to use the data collected at the UE to train 1008 one or more AI-based models offline.

[0149] The signaling may also include the UE transmitting a 1012 notification message, which instructs the base station on the conditions and availability of one or more AI-based models available to the UE.

[0150] The signaling may include the base station transmitting an activation instruction (e.g., via downlink control information (DCI), media access control channel element (MAC-CE), or radio resource control (RRC) signaling) to the UE to activate one or more AI-based models at the UE for predicting radio link failures (RLFs) based on the activation instruction. The signaling may also include the ability to predict 1016 RLFs using one or more AI-based models based on predicting the block error rate (BLER) of one or more reference signals (e.g., inference from BLER prediction) or based on classifying the risk level of RLFs based on multiple inputs.

[0151] The signaling may include the UE transmitting a pre-RLF indication report (1018) to the base station, which may be based on prediction. The signaling may also include the UE monitoring the performance of one or more AI-based models (1020). Furthermore, the signaling may include the base station monitoring the performance of one or more AI-based models (1022).

[0152] The signaling may include the base station signaling to the UE to notify 1024 AI model lifecycle management (e.g., LCM signaling) to disable, activate, and / or switch one or more AI-based models based on performance monitoring. The signaling may also include the UE disabling and / or switching one or more AI-based models.

[0153] Therefore, as Figure 10 As described, the UE first sends a capability report to the base station indicating supporting features for RLF prediction (including the type of prediction mode, maximum history length, etc.). Following the capability report, the base station transmits configuration information for training an AI-based model tailored to the reported capabilities at the UE. The UE collects data, trains the AI-based model at the UE or remotely, and transmits a notification message to the base station informing them of the available trained AI-based model at the UE and its applicability conditions. Based on this notification, the base station determines the appropriate AI model activation and configuration settings and signals them to the UE. According to the activation and configuration instructions, the UE performs RLF inference via the trained AI-based model, thereby generating RLF predictions indicating potentially upcoming RLF events. The UE can report these early predictions to the base station. Additionally, the UE and / or the base station can monitor the performance of the activated AI model over time based on metrics such as, for example, error rate or system efficiency, and initiate AI model switching or deactivation as needed based on the evaluation results. By utilizing the trained AI-based model and the coordinated signaling between the UE and the base station, radio link conditions can be reliably predicted in advance, and mitigation actions can be proactively applied to avoid communication failures. Furthermore, by not using… Figure 10 The process illustrated herein reduces the likelihood of actual handover failures and can avoid significant overhead at the base station and network.

[0154] It should be noted that the UE can be configured to perform various combinations of alternative schemes for BLER prediction. In some implementations, the UE can be configured by the network to utilize machine learning models to perform various block error rate (BLER) prediction alternatives, including time BLER prediction, cross-reference signal BLER prediction, and hybrid combinations thereof.

[0155] In one example, using time-based BLER prediction, the UE can predict the future BLER value of the same RLM-RS based on past measurements of the configured Radio Link Monitoring RS (RLM-RS) within a configured time window. The number of previous (historical) samples and the number of predicted samples can be set by the network. This supports both explicit RLM-RS configuration and implicit prediction based on the Transmit Configuration Indicator (TCI) status of the active Physical Downlink Control Channel (PDCCH).

[0156] In another example, using cross-RS BLER prediction, the UE can predict the BLER trend of an RLM-RS based on historically measured BLERs of different RLM-RSs or other reference signals (e.g., SSB / CSI-RSs not configured as RLM-RSs). Using predicted future BLER trends based on different RLM-RSs reduces the measurement workload for the UE and helps cover all possible beam spatial directions, mitigating the limitation of a small maximum number of RLM-RSs. This leverages long-term beam / spatial correlations between signals provided by the network.

[0157] In another example, using a hybrid model, the UE can be configured to combine temporal BLER and cross-RS BLER prediction models to improve accuracy. Additional supplementary measurements can further enhance the predictions. For each alternative in the BLER prediction model alternatives, an associated confidence level that can indicate the accuracy of the estimate can be configured and provided to be reported along with each BLER prediction.

[0158] It should also be noted that the UE can be configured to perform BLER prediction at certain times. That is, the UE can perform BLER prediction and reporting in various modes, including continuous, periodic, and event-triggered, to balance performance and power efficiency. Other measurements (e.g., cell layer 3 (L3) measurements, layer 1 (L1) RSRP of RS) can also be used as auxiliary information and / or AI / ML inputs.

[0159] For continuous operation, the UE can begin prediction upon receiving configuration information and continue until the timer expires. In one example, the UE predicts and reports BLER indefinitely after initial configuration until the network-defined timer expires.

[0160] For periodic BLER prediction, the UE is configured with another periodicity for the BLER measurement used for prediction. For example, periodic BLER prediction can occur at regular intervals, also configured by the network.

[0161] For event-triggered prediction, the network specifies trigger conditions to achieve more power-efficient discontinuous operation while still activating the BLER prediction when radio conditions deteriorate. Potential triggers include expiration of the RLF risk timer T, BLER of all or a subset of the radio link monitoring RS (RLM-RS) exceeding a threshold, detection of consecutive out-of-sync indications from the lower layer, and combinations thereof.

[0162] For event-triggered operation, the network specifies trigger conditions to activate the BLER prediction, such as for example: Event 1) when the timer (T) for radio link failure risk is triggered (e.g., T310); Event 2) the BLER of all configured radio link monitoring RS (RLM-RS) exceeds a threshold; Event 3) the BLER of any one or more of the configured set of RSs drops below a threshold; Event 4) the BLER of a subset (M) of the RLM-RS exceeds a threshold (e.g., M < N, where N is a constant, such as N310 defined in the 3GPP specification as the maximum number of consecutive "out-of-sync" indications received from the lower layer for the PCell); and / or Event 5) detection of at least M consecutive out-of-sync (OOS) indications from the lower layer. M can be configured by the lower layer communication.

[0163] It should be noted that Event 1 can also be configured together with Events 2, 3, and 4 (i.e., when the report is triggered when both Event 1 and Event 2 are satisfied or when both Event 1 and Event 3 are satisfied). For Events 3 and 4, the UE can be configured to use only the RSs in the configured set of RLM-RS or another configured set of RSs. Thus, the network can further configure the combined triggers for prediction activation (e.g., Event 1 and Event 2), as well as whether to apply dedicated RLM-RS or other RS sets. By supporting such adaptive BLER prediction activation schemes, the efficiency and reliability of the radio link failure mechanism can be enhanced.

[0164] In addition, it should also be noted that the UE can be configured to report pre-RLF indications (e.g., RLF prediction report). For example, the UE can use various modes including periodic, event-triggered, event-triggered periodic, and combinations thereof to report the BLER prediction and RLF prediction to the network via the primary cell and secondary cells.

[0165] For periodic prediction, the RLF prediction can be sent to the primary cell via radio resource control (RRC) signaling, while for event-triggered reporting when an event (such as for example the BLER threshold) is achieved, the secondary cell uses a new dedicated RRC or medium access control (MAC) control element.

[0166] For event-triggered reports, the UE can report RLF prediction reports based on a first scenario and a second scenario. In the first scenario, when an event (e.g., event 3) occurs, the UE can report the RLF prediction to the primary cell via RRC.

[0167] In the second scenario, when an event (such as, for example, event 1, event 2, event 4, or event 5) occurs, the UE can report the RLF prediction to the available secondary cell via a new MAC control element or RRC, because the primary cell uplink may be compromised.

[0168] For both the first and second scenarios, a common scheduling request (SR) for both scenarios and a separate SR resource depending on the event are used. The SR can also be associated with a reporting event (e.g., event triggering) to indicate the existence of a report.

[0169] It should be noted that if, for example, an RLF prediction report is reported in Scenario 1 and the primary cell is expected to recover, the network can wait for the radio link to recover upon receiving the SR. Furthermore, even if the primary cell uplink fails, transmissions via the secondary cell help ensure reliable reception of the warning.

[0170] For example, the UE can report RLF predictions to one or more secondary cells via a new UL MAC-CE or RRC (e.g., similar to Event 1 or Event 2 reporting). Therefore, supporting adaptive reporting modes and channels helps the network perform timely handover or other remedial actions to avoid communication failures based on predicted BLER trends.

[0171] Figure 11A , Figure 11B AI / ML-based prediction and handover of radio link failures (RLF) Figure 11A and Figure 11B An example diagram illustrates how a base station (such as, for example, base station 106) uses BLER prediction of a UE to determine whether to hand over a UE (such as, for example, UE 106) to another cell before a radio link failure occurs, according to some implementation schemes.

[0172] like Figure 11A The scenario depicted in Figure 1110 illustrates a typical scenario where the primary cell experiences five out-of-synchronization (OOS) indications, triggering an RLF risk timer T310. Since BLER prediction was not utilized, T310 expires, resulting in an RLF declaration before any preventative action occurs. This forces the UE to perform cell selection and complete RRC re-establishment to restore connectivity.

[0173] In contrast, Figure 11BThe lower part of Figure 1112 illustrates an RLF avoidance enhancement implemented by AI-based BLER prediction. Initially, the primary cell serving UE 102 suffers five consecutive out-of-synchronization (OOS) indications, thus meeting the trigger threshold defined for initiating the RLF risk timer T310.

[0174] However, in enhanced mode, UE 102 uses a trained BLER prediction model to forecast upcoming radio link conditions, thereby generating a predicted BLER for the primary cell. The BLER prediction report is transmitted via available secondary cells, indicating to UE 102 that recovery is unlikely based on the predicted BLER (e.g., less than a defined percentage, threshold, or assigned value).

[0175] The secondary cell can receive and analyze BLER prediction reports and proactively take action before a predicted RLF (Recurrent Leakage Failure). For example, the primary or secondary cell (if the primary cell has poor connectivity) can preemptively transmit a handover command (HO) to PCell and / or base station 106 to move UE 102 to an alternative cell. Therefore, the handover prevents T310 from expiring at the primary cell, thus proactively avoiding RLF events and maintaining operational continuity.

[0176] Figure 12A , Figure 12B AI / ML-based prediction and reporting of radio link failures (RLF). Figure 12A and Figure 12B An example illustration is shown of using an artificial intelligence (AI) model at the UE to predict radio link failures based on multiple input parameters related to the radio link condition, according to some implementation schemes.

[0177] In one implementation, the UE may use alternative AI / ML RLF prediction operations to determine the risk classification score and / or confidence level of an upcoming RLF event based on analysis of multiple radio link condition inputs. These inputs may include, for example, random access channel (RACH) attempt metrics; radio link control (RLC) retransmission metrics; and block error rate (BLER) and / or other defined metrics for the reference signal used for radio link monitoring (RLM) (e.g., uplink (UL) / downlink (DL) channel fading, system throughput, and hybrid automatic repeat request discontinuous transmission (HARQDTX) status).

[0178] Alternative AI / ML RLF prediction operations use a model based on user equipment (UE)-side AI to infer RLF risk based on the fusion of existing indicator metrics and multiple supplementary radio link metrics as model inputs. Alternative AI / ML RLF prediction operations may include one or more alternative schemes (e.g., two alternative schemes), including a first alternative scheme that uses three existing RLM, RACH, and RLC metrics, along with uplink-downlink (UL / DL) channel correspondences, as model inputs.

[0179] The second alternative extends this by further incorporating additional metrics, such as HARQ indicators and reference signal power measurements, into the model used for enhanced RLF risk identification. By applying AI / ML techniques to concurrently analyze multiple relevant factors indicating radio link conditions, more accurate and timely predictions of potential impending failures can be achieved compared to older, independent assessments. This enables appropriate preemptive actions to avoid communication loss.

[0180] like Figure 12A As illustrated in Figure 1210A, a first alternative scheme is depicted where an artificial intelligence / machine learning (AI / ML) model for radio link failure (RLF) prediction utilizes existing radio link metrics considered in legacy RLF determination as model inputs (which may also include the time of the inputs, such as, for example, t1, t2, t3, etc.). These include the number of random access channel (RACH) attempts, the number of radio link control (RLC) retransmissions, and the BLER of the reference signal used for radio link monitoring (RLM). Furthermore, the first alternative scheme incorporates UL / DL channel correspondences as another input to capture interconnect link conditions. The AI / ML model can evaluate these inputs within both the current measurement window and historical measurement windows to determine future RLF predictions, such as, for example, a 90% chance of an RLF failure probability score mapped to a future time frame T5 or an 80% chance of an RLF failure probability score mapped to a future time frame T6. Based on the reduced RLF at T6, handover may not be performed.

[0181] like Figure 12BAs illustrated in Figure 1210B, a second alternative scheme is depicted, in which the AI / ML model supplements the input with additional radio link metrics, including consecutive HARQ transmission timeouts (e.g., the number of consecutive discontinuous HARQ transmissions (DTX)) and measured reference signal strength (BFD status). Each input may also include the time of the input, such as, for example, t1, t2, t3, etc. By fusing the extended set of relevant RLF inputs, higher accuracy and predictability of impending radio link failures can be achieved through data-driven machine learning analysis. Similarly, the second alternative scheme may also incorporate UL / DL channel correspondences as another input to capture interconnect link conditions. The AI / ML model can evaluate these inputs within both the current measurement window and historical measurement windows to determine RLF predictions, such as, for example, a 90% chance of an RLF failure probability score mapped to a future time frame T5 or an 80% chance of an RLF failure probability score mapped to a future time frame T6.

[0182] In one implementation, alternative AI / ML RLF prediction operations may include additional metrics and aspects for the AI / ML model used for radio link failure (RLF) prediction. Supplemental metrics that can be incorporated as input into the AI / ML model used for RLF prediction include: 1) HARQ DTX logs: Hybrid Automatic Repeat Request (HARQ) discontinuous transmission (DTX) detection of transmission failures due to receiver failure to acknowledge delivered packets. Continuous DTX events indicate repeat transmission problems; 2) BFD status: Beam Failure Detection (BFD) checks indicate that the UE finds and switches to a new beam, which implies a degraded channel quality; 3) DL and UL throughput: Downlink (DL) and uplink (UL) data stream rates also quantify the increasing radio link impairment; 4) L1 SSB / CSI-RS measurements (RSRP / RSRQ): Layer 1 Reference Signal Received Power (RSRP) and Quality (RSRQ) for synchronization and channel state estimation provide additional air signal metrics; 5) L3 intra-frequency measurements: Layer 3 neighboring cell measurements provide indicators for comparing link conditions.

[0183] Additionally, RLF prediction may include RLF prediction and confidence scores. The AI-based RLF prediction model can be executed in different modes, such as where the network is configured for periodic scheduling, where events configured by the network are triggers, such as event 1 (e.g., T310 RLF timer), event 2 (e.g., when the number of RACHs exceeds a threshold), and / or event 3 (e.g., when the number of RLC retransmissions exceeds a threshold). Furthermore, the AI-based RLF prediction model can be executed and provide periodic reports when the network-defined trigger events occur. The predicted RLF reports can be sent to the primary cell (PCell) or the primary cell of the primary cell or secondary cell group (SpCell) via Radio Resource Control (RRC) signaling on the primary cell, and / or reports utilizing the secondary cell or SCell can be provided using Media Access Control (MAC) control elements or RRC signaling to increase reliability.

[0184] As described in this paper, AI-based models can be monitored by the UE and / or base station. For base station-based monitoring, the specific performance monitoring metrics to be evaluated can be determined based on the specific implementation of the base station. The UE can be configured to provide supplementary information to assist base station tracking, such as timestamps for predicted and actual measurements for time alignment, spatial orientation details, and positional differences compared to predicted movement.

[0185] When model monitoring is UE-based, performance monitoring metrics may include the error between the predicted confidence level, prediction accuracy metric, or prediction block error rate (BLER) measurement and the actual BLER measurement, such as the mean square error (MSE) between the predicted BLER and the observed BLER. To obtain the actual BLER measurement, the UE performs both inference and direct measurement against a small set of reference signals. Alternatively, performance monitoring metrics may include assessments of overall system performance metrics, such as, for example, changes in throughput, the number of radio link failures (RLFs) declared during the configured duration, and other definitions.

[0186] Furthermore, as described herein, the UE can be configured to perform model switching or updates based on UE-initiated triggers or network (NW)-initiated signaling.

[0187] In one implementation, for a UE-initiated handover or update, the UE is configured by the base station (base station) with a metric threshold and corresponding model fallback behavior. For example, the UE can monitor the mean square error (MSE) between the predicted and actual block error rate (BLER), where a threshold of 0.01 is specified by the network. If the MSE exceeds 0.01, the predefined behavior is for the UE to switch back to the regular BLER measurement procedure without relying on the machine learning model. Additionally, if the network is configured with different models associated with different combinations of reference signals for radio link monitoring (RLM-RS), the UE can autonomously switch to an appropriate model that matches the current RLM-RS mode notified via downlink control information (DCI), media access control (MAC) control elements, or radio resource control (RRC) update signaling.

[0188] For network-initiated model switching, the UE can report AI model monitoring metrics via methods such as Unified Air Interface (UAI) signaling or MAC-CE and await explicit model lifecycle management (LCM) commands from the base station. The UE can also use standard procedures based on network indications, regardless of monitoring results. To aid in reliable monitoring and adaptation, the base station can further provide the UE with supplementary auxiliary information. This auxiliary information may include, for example, a geometry map of nearby base station deployments, long-term temporal correlation statistics and / or long-term statistics or inter-beam correlations (e.g., Quasi-co-located (QCL) type D reference).

[0189] Figure 13 : A process for providing an AI-based method for predicting radio link failures (RLF) at the UE. picture .

[0190] Figure 13 An example flowchart illustrates a method for providing AI-based radio link failure (RLF) prediction at the user equipment (UE) according to some implementation schemes.

[0191] Figure 13 The methods shown can be used in conjunction with any of the systems, methods, or apparatuses illustrated in the accompanying drawings, as well as other devices. In various embodiments, some of the method elements shown may be performed concurrently in a different order than that shown, or may be omitted. Additional method elements may also be performed as needed.

[0192] According to the implementation scheme, method 1300 for providing AI-based RLF prediction encodes UE capability reports for transmission to a base station (base station), as shown in box 1302.

[0193] Method 1300 further includes decoding configuration information received from the base station for training one or more artificial intelligence (AI)-based models for predicting radio link failures (RLFs), as shown in box 1304. Method 1300 also includes encoding a notification message for transmission to the base station, the notification message informing the base station of one or more conditions and availability of one or more AI-based models for use by the UE, as shown in box 1306.

[0194] Method 1300 also includes decoding an activation instruction received from the base station, as shown in box 1308. Method 1300 also includes activating one or more AI-based models for predicting radio link failures (RLFs) based on the activation instruction, as shown in box 1310.

[0195] Method 1300 further includes using one or more AI-based models to predict RLF based on the predicted block error rate (BLER) of one or more reference signals or based on classifying the risk level of RLF based on multiple inputs, as shown in box 1312. Method 1300 also includes sending an RLF prediction report to a base station based on the prediction, as shown in box 1314.

[0196] Method 1300 also includes collecting data at the UE for training one or more AI-based models. Method 1300 further includes using the data collected at the UE to train one or more AI-based models. Method 1300 also includes monitoring the performance of one or more AI-based models activated at the UE for predicting RLF. Method 1300 also includes disabling and / or switching one or more AI-based models based on performance monitoring.

[0197] In some implementations, the UE capability report indicates support for time prediction of the block error rate (BLER) of the reference signal used for radio link monitoring (RLM), the maximum number of historical and predicted samples used for BLER prediction, the maximum number of predicted samples, and the maximum number of parallel predictions. Configuration information may include indications for each type of one or more AI-based models, the prediction window length used for BLER prediction, and the number of parallel predictions.

[0198] In some implementations, the notification message indicates which of one or more AI-based models are available for use at the UE and the corresponding model applicability conditions.

[0199] Method 1300 further includes decoding an activation command from the base station via downlink control information, a medium access control-control element, or radio resource control signaling. Method 1300 also includes predicting the BLER of the Radio Link Monitoring Reference Signal (RLM-RS) for radio link monitoring or the transparent control information (TCI) state of the activated Physical Downlink Control Channel (PDCCH) based on multiple prior BLER measurements. In some embodiments, one or more of the multiple prior BLER measurements and the predicted BLER measurements are configured by the base station.

[0200] Method 1300 further includes predicting BLER based on one or more previous BLER measurements of one or more different reference signals. Method 1300 also includes decoding auxiliary information received from a base station, the auxiliary information including long-term beam correlation between a first reference signal and a second reference signal.

[0201] Method 1300 also includes generating a confidence level associated with each predicted BLER. Method 1300 also includes performing BLER predictions for the RLF continuously, periodically, or based on events triggered by network configuration.

[0202] Method 1300 also includes identifying event triggering based on the number of timer expirations or out-of-synchronization (OOS) indications received from the lower layer of the UE.

[0203] In some implementations, the RLF prediction report indicates the BLER prediction error between the predicted BLER measurement and the actual BLER measurement.

[0204] Method 1300 further includes periodically reporting RLF predictions to the primary cell via radio resource control signaling. Method 1300 also includes encoding the RLF prediction report to the secondary cell via medium access control element (MAC-CE) or radio resource control (RRC) signaling when a first event is triggered, wherein the first event includes a reference signal measurement exceeding a predetermined threshold.

[0205] Method 1300 further includes encoding an RLF prediction report for transmission to the secondary cell via a Media Access Control Control Element (MAC-CE) or Radio Resource Control (RRC) signaling when a second event is triggered, wherein the second event includes a timer expiration. Method 1300 also includes sending a scheduling request to the base station when the second event is triggered.

[0206] Method 1300 further includes periodically reporting an RLF prediction report to the secondary cell via a Media Access Control Control Element (MAC-CE) or Radio Resource Control (RRC) signaling when a second event is triggered, wherein the second event includes a timer expiration. Method 1300 also includes encoding the RLF prediction report for transmission to the base station, enabling the base station to determine whether to transmit a handover command back to the UE based on the risk of radio link failure indicated by the RLF prediction.

[0207] Method 1300 further includes decoding a handover command received via a secondary cell based on an RLF prediction indicating a radio link quality level below a quality threshold level on the primary cell. Method 1300 also includes decoding a handover command from a base station based on an RLF prediction indicating a radio link quality level above a quality threshold level.

[0208] Method 1300 also includes using one or more AI-based models to predict RLF using one or more of a plurality of inputs, wherein the plurality of inputs are: the number of random access channel attempts; the number of radio link control retransmissions; a measurement of a reference signal configured for radio link monitoring; and an uplink-downlink correspondence metric.

[0209] Method 1300 further includes using one or more AI-based models to predict RLF using one or more of the following inputs: the number of random access channel attempts; the number of radio link control retransmissions; a measurement of a reference signal configured for radio link monitoring; the number of continuous mixed automatic repeated discontinuous transmissions (HARQ DTX) events; and a measurement of the received power of a non-radio link monitoring reference signal.

[0210] Method 1300 also includes periodically predicting RLF based on periodic configurations received from the network.

[0211] Method 1300 also includes monitoring the performance of one or more AI-based models based on prediction confidence levels, prediction accuracy, BLER measurements, system performance metrics, or combinations thereof. Method 1300 also includes autonomously switching between one or more AI-based models based on changes in performance thresholds or reference signals.

[0212] In some embodiments, an apparatus is disclosed that is configured to cause the user equipment (UE) to perform any operation of method 1300.

[0213] In some embodiments, a computer program product is disclosed that includes computer instructions that, when executed by one or more processors, perform any of the operations described with respect to method 1300.

[0214] Figure 14 Artificial intelligence (AI) based radio link failure (RLF) at base stations to assist user equipment (UE). Flowchart of the prediction method .

[0215] Figure 14 A flowchart illustrating an example of an artificial intelligence (AI)-based method for predicting radio link failures (RLF) at a base station (UE) according to some implementation schemes is provided. Figure 14 The methods shown can be used in conjunction with any of the systems, methods, or apparatuses illustrated in the accompanying drawings, as well as other devices. In various embodiments, some of the method elements shown may be performed concurrently in a different order than that shown, or may be omitted. Additional method elements may also be performed as needed.

[0216] According to the implementation scheme, method 1400 for assisting AI-based RLF prediction encodes UE capability reports for transmission to the UE, as shown in box 1402.

[0217] Method 1400 further includes encoding configuration information for transmission to the UE, the configuration information enabling the UE to train one or more artificial intelligence (AI)-based models for predicting radio link failures (RLF), as shown in box 1404. Method 1400 also includes decoding a notification message received from the UE, the notification message informing the base station of one or more conditions and availability of one or more AI-based models available to the UE, as shown in box 1406.

[0218] Method 1400 also includes encoding an activation instruction for transmission to the UE, enabling the UE to activate one or more AI-based models for predicting radio link failures (RLF) based on the activation instruction, as shown in box 1408.

[0219] Method 1400 also includes using one or more AI-based models to predict RLF based on the UE's prediction of the block error rate (BLER) of one or more reference signals or based on the risk level of RLF based on multiple inputs, and decoding the RLF prediction report from the UE to the base station, as shown in box 1410.

[0220] In some implementations, the UE capability report indicates support for time prediction of the block error rate (BLER) of the reference signal used for radio link monitoring (RLM), the maximum number of historical and predicted samples used for BLER prediction, the maximum number of predicted samples, and the maximum number of parallel predictions. In other implementations, the configuration information includes indications for each type of one or more AI-based models, the prediction window length used for BLER prediction, and the number of parallel predictions.

[0221] In some implementations, the notification message indicates which of one or more AI-based models are available for use at the UE and the corresponding model applicability conditions. In some implementations, the RLF prediction report indicates the BLER prediction error between the predicted BLER measurement and the actual BLER measurement.

[0222] Method 1400 further includes encoding auxiliary information for transmission to the UE, the auxiliary information including long-term beam correlation between the first reference signal and the second reference signal. Method 1400 also includes decoding an RLF prediction report received from the UE, enabling the base station to determine whether to transmit a handover command back to the UE based on the risk of the RLF prediction indicating an RLF.

[0223] In some embodiments, an apparatus is configured to cause a base station (base station) to perform the operations of method 1400. The apparatus of the base station may include one or more processors coupled to a memory, the one or more processors being configured to perform any operation of method 1400.

[0224] In some embodiments, the illustrated embodiments provide a user equipment (UE) including one or more processors coupled to memory and configured to: encode a UE capability report for transmission to a base station; decode configuration information received from the base station for training one or more artificial intelligence (AI)-based models for predicting radio link failures (RLFs); encode a notification message for transmission to the base station informing the base station of one or more conditions and availability of the one or more AI-based models available for use by the UE; decode an activation instruction from the base station; activate the one or more AI-based models for predicting RLFs based on the activation instruction; predict the RLF using the one or more AI-based models based on a predicted block error rate (BLER) of one or more reference signals or based on a risk level classification of the RLF based on multiple inputs; and transmit an RLF prediction report to the base station based on the prediction.

[0225] In some implementations, one or more processors are further configured to collect data at the UE for training one or more AI-based models. In some implementations, one or more processors are further configured to use the data collected at the UE to train one or more AI-based models. In some implementations, one or more processors are further configured to monitor the performance of one or more AI-based models activated at the UE for predicting RLF. In some implementations, one or more processors are further configured to deactivate or switch one or more AI-based models based on performance monitoring.

[0226] In some examples, the UE capability report indicates support for time prediction of the block error rate (BLER) of the reference signal used for radio link monitoring (RLM), the maximum number of historical and predicted samples used for BLER prediction, the maximum number of predicted samples, and the maximum number of parallel predictions. Configuration information may include indications for each type of one or more AI-based models, the prediction window length used for BLER prediction, and the number of parallel predictions. Notification messages may indicate which of the one or more AI-based models are available for use at the UE and the corresponding model applicability conditions.

[0227] In some implementations, one or more processors are further configured to decode activation instructions from a base station via downlink control information, media access control-control elements, or radio resource control signaling. In some implementations, one or more processors are further configured to predict the BLER of the Radio Link Monitoring Reference Signal (RLM-RS) used for radio link monitoring or the Transparent Control Information (TCI) state of the activated Physical Downlink Control Channel (PDCCH) based on multiple previous BLER measurements.

[0228] In some implementations, one or more of a plurality of prior BLER measurements and a predicted BLER measurement are configured by the base station. In some implementations, one or more processors are further configured to predict the BLER based on one or more prior BLER measurements of one or more different reference signals.

[0229] In some implementations, one or more processors are further configured to decode auxiliary information received from a base station, the auxiliary information including long-term beam correlation between a first reference signal and a second reference signal.

[0230] In some implementations, one or more processors are further configured to generate confidence levels associated with each predicted BLER.

[0231] In some implementations, one or more processors are further configured to perform BLER predictions for RLF continuously, periodically, or based on events configured by the network.

[0232] In some implementations, one or more processors are further configured to identify event triggering based on the number of timer expirations or out-of-synchronization (OOS) indications received from the lower layer of the UE.

[0233] In some examples, the RLF prediction report indicates the BLER prediction error between the predicted BLER measurement and the actual BLER measurement.

[0234] In some embodiments, one or more processors are further configured to periodically report RLF predictions to the primary cell via radio resource control signaling. In some embodiments, one or more processors are further configured to encode the RLF prediction report to the secondary cell via medium access control element (MAC-CE) or radio resource control (RRC) signaling when a first event is triggered, wherein the first event includes a reference signal measurement exceeding a predetermined threshold.

[0235] In some implementations, one or more processors are further configured to encode an RLF prediction report to be transmitted to the secondary cell via a Media Access Control Control Element (MAC-CE) or Radio Resource Control (RRC) signaling when a second event is triggered, wherein the second event includes a timer expiration.

[0236] In some implementations, one or more processors are further configured to send a scheduling request to the base station when a second event is triggered. In some implementations, one or more processors are further configured to periodically report RLF prediction reports to the secondary cell via Media Access Control-CE (MAC-CE) or Radio Resource Control (RRC) signaling when a second event is triggered, wherein the second event includes a timer expiration. In some implementations, one or more processors are further configured to encode the RLF prediction reports for transmission to the base station, enabling the base station to determine whether to transmit a handover command back to the UE based on the risk of radio link failure indicated by the RLF predictions.

[0237] In some implementations, one or more processors are further configured to decode handover commands received via a secondary cell based on RLF prediction indicating a radio link quality level below a quality threshold level on the primary cell. In some implementations, one or more processors are further configured to decode handover commands from a base station based on RLF prediction indicating a radio link quality level above a quality threshold level.

[0238] In some implementations, one or more processors are further configured to use one or more AI-based models to predict RLF using one or more of a plurality of inputs, wherein the plurality of inputs are: the number of random access channel attempts; the number of radio link control retransmissions; a measurement of a reference signal configured for radio link monitoring; and an uplink-downlink correspondence metric.

[0239] In some implementations, one or more processors are further configured to use one or more AI-based models to predict RLFs using one or more of a plurality of inputs: the number of random access channel attempts; the number of radio link control retransmissions; measurements of reference signals configured for radio link monitoring; the number of continuous mixed automatic repeated discontinuous transmissions (HARQ DTX) events; and measurements of reference signal received power for non-radio link monitoring reference signals.

[0240] In some implementations, one or more processors are further configured to periodically predict RLF based on periodic configurations received from the network.

[0241] In some implementations, one or more processors are configured to monitor the performance of one or more AI-based models based on prediction confidence levels, prediction accuracy, BLER measurements, system performance metrics, or a combination thereof.

[0242] In some implementations, one or more processors are configured to autonomously switch between one or more AI-based models based on changes in performance thresholds or reference signals.

[0243] In some embodiments, a computer program product is disclosed that includes computer instructions that, when executed by one or more processors, perform any of the operations described with respect to method 1400.

[0244] Embodiments of this disclosure may be implemented in any of a variety of forms. For example, some embodiments may be implemented as computer-implemented methods, computer-readable storage media, or computer systems. Other embodiments may be implemented using one or more custom-designed hardware devices such as ASICs. Other embodiments may be implemented using one or more programmable hardware elements such as FPGAs.

[0245] In some embodiments, a non-transitory computer-readable storage medium may be configured to store program instructions and / or data, wherein, if executed by a computer system, the program instructions cause the computer system to perform a method, such as any method embodiment of the method embodiments described herein, or any combination of method embodiments described herein, or any subset or combination of any such subset of any method embodiments described herein.

[0246] In some implementations, the device (e.g., UE 106) may be configured to include a processor (or a set of processors) and a memory medium, wherein the memory medium stores program instructions, and the processor is configured to read from and execute the program instructions from the memory medium, wherein the program instructions are executable to implement any of the various method implementations described herein (or any combination of the method implementations described herein, or any subset of any of the method implementations described herein, or any combination of such subsets). The device may be implemented in any of the various forms.

[0247] By interpreting each message / signal X received by the user equipment (UE) in the downlink as a message / signal X sent by the base station, and interpreting each message / signal Y sent by the UE in the uplink as a message / signal Y received by the base station, any of the methods described herein for operating the UE can serve as the basis for a corresponding method for operating the base station.

[0248] Although the above embodiments have been described in considerable detail, many variations and modifications will become apparent to those skilled in the art once the above disclosure is fully understood. It is intended that the following claims be construed as encompassing all such variations and modifications.

Claims

1. A method for performing AI-based compression model performance monitoring by user equipment (UE), the method comprising: The UE capability report is encoded for transmission to the base station; The configuration information received from the base station is decoded, and the configuration information is used to train one or more artificial intelligence (AI) based models for predicting radio link failures (RLFs). The notification message is encoded for transmission to the base station, and the notification message indicates to the base station one or more conditions and availability of the one or more AI-based models available for use by the UE; Decode the activation command from the base station; The activation instruction is used to activate one or more AI-based models for predicting radio link failures (RLFs); The one or more AI-based models are used to predict the RLF based on the block error rate (BLER) of predicting one or more reference signals or based on classifying the risk level of the RLF based on multiple inputs; as well as Based on the prediction, an RLF prediction report is sent to the base station.

2. The method of claim 1, further comprising collecting data at the UE for training the one or more AI-based models.

3. The method of claim 1, further comprising using data collected at the UE to train the one or more AI-based models.

4. The method of claim 1, further comprising monitoring the performance of the one or more AI-based models activated at the UE for predicting the RLF.

5. The method of claim 1, further comprising disabling or switching the one or more AI-based models based on the performance monitoring.

6. The method of claim 1, wherein the UE capability report indicates support for time prediction of the block error rate (BLER) of the reference signal for radio link monitoring (RLM), the maximum number of historical samples and predicted samples for BLER prediction, the maximum number of predicted samples, and the maximum number of parallel predictions.

7. The method of claim 1, wherein the configuration information includes an indication of each type of the one or more AI-based models, the prediction window length for BLER prediction, and the number of parallel predictions.

8. The method of claim 1, wherein the notification message indicates those AI-based models among the one or more AI-based models that can be used at the UE and corresponding model applicability conditions.

9. The method of claim 1, further comprising decoding the activation instruction from the base station via downlink control information, a media access control-control element, or radio resource control signaling.

10. The method of claim 1, further comprising predicting the transparent control information (TCI) state of the BLER of the radio link monitoring reference signal (RLM-RS) for radio link monitoring or the activated physical downlink control channel (PDCCH) based on a plurality of prior BLER measurements.

11. The method of claim 10, wherein one or more of the plurality of previous BLER measurements and predicted BLER measurements are configured by the base station.

12. The method of claim 1, further comprising predicting the BLER based on one or more previous BLER measurements of one or more different reference signals.

13. The method according to claim 1, further comprising decoding auxiliary information received from the base station, the auxiliary information including long-term beam correlation between a first reference signal and a second reference signal.

14. The method of claim 1, further comprising generating a confidence level associated with each predicted BLER.

15. The method of claim 1, further comprising performing the BLER prediction of the RLF continuously, periodically, or based on events configured by the network.

16. The method of claim 15, further comprising identifying the event triggering based on the number of timer expirations or out-of-synchronization (OOS) indications received from the lower layer of the UE.

17. The method of claim 1, wherein the RLF prediction report indicates the BLER prediction error between the predicted BLER measurement and the actual BLER measurement.

18. The method of claim 1, further comprising periodically reporting the RLF prediction to the primary cell via radio resource control signaling.

19. The method of claim 1, further comprising encoding the RLF prediction report to transmit it to a secondary cell via a Medium Access Control Control Element (MAC-CE) or Radio Resource Control (RRC) signaling when a first event is triggered, wherein the first event includes a reference signal measurement exceeding a predetermined threshold.

20. The method of claim 1, further comprising encoding the RLF prediction report to transmit it to the secondary cell via a Medium Access Control Element (MAC-CE) or Radio Resource Control (RRC) signaling when a second event is triggered, wherein the second event includes a timer expiration.

21. The method of claim 20, further comprising sending a scheduling request to the base station when the second event is triggered.

22. The method of claim 1, further comprising periodically reporting the RLF prediction report to the secondary cell via a Medium Access Control Element (MAC-CE) or Radio Resource Control (RRC) signaling when a second event is triggered, wherein the second event includes a timer expiration.

23. The method of claim 1, further comprising encoding the RLF prediction report for transmission to the base station, such that the base station can determine whether to transmit a handover command back to the UE based on the risk of radio link failure indicated by the RLF prediction.

24. The method of claim 23, further comprising decoding the handover command received via the secondary cell based on the RLF prediction indicating a radio link quality level below a quality threshold level on the primary cell.

25. The method of claim 24, further comprising decoding a handover command from the base station based on the RLF prediction indicating that the radio link quality level is above a quality threshold level.

26. The method of claim 1, further comprising using one or more of the plurality of inputs to predict the RLF using the one or more AI-based models, wherein the plurality of inputs are: The number of random access channel attempts; The number of radio link control retransmissions; Measurement of a reference signal configured for radio link monitoring; and Uplink-downlink correspondence metric.

27. The method of claim 1, further comprising using one or more of the plurality of inputs to predict the RLF using the one or more AI-based models: The number of random access channel attempts; The number of radio link control retransmissions; Measurement of a reference signal configured for radio link monitoring; The number of consecutive mixed automatic repeating discontinuous transmission (HARQ DTX) events; and Measurement of the reference signal received power for non-radio link monitoring reference signal.

28. The method of claim 1, further comprising periodically predicting the RLF based on periodic configuration received from the network.

29. The method of claim 1, further comprising monitoring the performance of the one or more AI-based models based on prediction confidence level, prediction accuracy, BLER measurement, system performance metric, or a combination thereof.

30. The method of claim 1, further comprising autonomously switching between the one or more AI-based models based on changes in a performance threshold or a reference signal.

31. An apparatus configured to cause a user equipment (UE) to perform any of the methods described according to claims 1 to 30.

32. A baseband processor configured to perform one or more methods according to claims 1 to 30.

33. An apparatus for a user equipment (UE), the apparatus comprising: One or more processors coupled to the memory, said one or more processors being configured to: The UE capability report is encoded for transmission to the base station; The configuration information received from the base station is decoded, and the configuration information is used to train one or more artificial intelligence (AI) based models for predicting radio link failures (RLFs). The notification message is encoded for transmission to the base station, and the notification message indicates to the base station one or more conditions and availability of the one or more AI-based models available for use by the UE; Decode the activation command from the base station; The activation instruction is used to activate one or more AI-based models for predicting radio link failures (RLFs); The one or more AI-based models are used to predict the RLF based on the block error rate (BLER) of predicting one or more reference signals or based on classifying the risk level of the RLF based on multiple inputs; as well as Based on the prediction, an RLF prediction report is sent to the base station.

34. An apparatus for a base station, the apparatus comprising: One or more processors coupled to the memory, said one or more processors being configured to: Decode the UE capability report received from the user equipment (UE); Configuration information is encoded for transmission to the UE, and the configuration information is used to train one or more artificial intelligence (AI)-based models for predicting radio link failures (RLFs). The notification message received from the UE is decoded, and the notification message indicates to the base station one or more conditions and availability of the one or more AI-based models available to the UE; An activation instruction is encoded for transmission to the UE, the activation instruction being instructed to the UE to activate one or more AI-based models for predicting radio link failures (RLFs) based on the activation instruction, and to use the one or more AI-based models to predict the RLFs based on the block error rate (BLER) of one or more reference signals or based on classifying the risk level of the RLFs based on multiple inputs. as well as The RLF prediction report received from the UE is decoded based on the prediction.

35. The apparatus of claim 34, wherein the UE capability report indicates support for time prediction of the block error rate (BLER) of the reference signal for radio link monitoring (RLM), the maximum number of historical samples and predicted samples for BLER prediction, the maximum number of predicted samples, and the maximum number of parallel predictions.

36. The apparatus of claim 34, wherein the configuration information includes an indication of each type of the one or more AI-based models, a prediction window length for BLER prediction, and the number of parallel predictions, and the notification message indicates those AI-based models among the one or more AI-based models that can be used at the UE and the corresponding model applicability conditions.

37. The apparatus of claim 34, wherein the one or more processors are further configured to encode auxiliary information for transmission to the UE, the auxiliary information including long-term beam correlation between a first reference signal and a second reference signal.

38. The apparatus of claim 34, wherein the RLF prediction report indicates the BLER prediction error between the predicted BLER measurement and the actual BLER measurement.

39. The apparatus of claim 34, wherein the one or more processors are further configured to decode the RLF prediction report received from the UE, such that the base station can determine whether to transmit a handover command back to the UE based on the risk of the RLF indicated by the RLF prediction.

40. A computer program product comprising computer instructions that, when executed by one or more processors, perform any of the operations described herein.

Images