Method and apparatus for repetitive user equipment report transmission

Abstract

A method of repeating user equipment (UE) report transmissions by a user equipment (UE) device connected to a wireless communication network in which the user equipment (UE) device determines a radio channel quality condition of a beam or cell used based on a CQI metric, and if it is determined that the channel quality is poorer, the user equipment (UE) device determines that the channel quality is poorer. If so, a copy of a local model update report is transmitted in the time-frequency domain, where a base station (gNB) configures time-frequency resources in a dedicated manner with an RRC reconfiguration message and / or system information.

Description

Technical Field

[0001] The present application relates generally to wireless communications and, more particularly, to apparatus and methods for improving the reliability of uplink data, such as local model updates transmitted by a mobile device under different radio resource control (RRC) states. Background Art

[0002] Because the transition from the RRC inactive or RRC idle state to the RRC connected state may cause overhead to the user equipment (UE) when only a small amount of data is to be transmitted, the 3rd Generation Partnership Project (3GPP) has introduced techniques for optimizing the transmission of such small packets. In practice, the UE needs to exchange multiple control signals to initiate and maintain a connection with the network. When the payload / effective data size is relatively small compared to the amount of control signals required, establishing a connection becomes a concern for both the network and the UE due to the control signaling overhead.

[0003] Recently, AI / ML (Artificial Intelligence / Machine Learning) has been adopted as a research project of 3GPP and has started technical research to be applied to multiple use cases at PHY / MAC (Physical Layer / Media Access Control Layer) and higher layers of the OSI (Open System Interconnection) model of computer networks. Among AI / ML technologies, Federated Learning (FL) has been included in the 3GPP AI / ML working list. In FL, AI / ML-based local model updates are collected from multiple users (e.g., UE devices) and the global model on the server (e.g., gNodeB (gNB), a 3GPP-compatible implementation of a 5G-NR (New Radio) base station (i.e., a base station for wireless communication)) is updated in an iterative manner for model training / inference.

[0004] The RRC inactive state is introduced to maintain the AS (Access Stratum) context at the base station and the UE, with the goal of reducing energy consumption and the number of messages exchanged between the user equipment and the base station. The AS describes the functional layer between the radio network and the user equipment. The AS is responsible for transmitting data over the wireless connection and managing the radio resources (data link layer).

[0005] However, in a radio access network with gNBs and UEs for performing federated learning, the UEs may encounter intra-cell / inter-cell mobility issues during AI / ML operations (such as model training) due to the mobility of the UEs.

[0006] The 5G NR (New Radio) standard adopts highly directional communication links, using a large number of antenna elements and providing a large number of directional beams for communication. By using highly directional beam forms, gains that compensate for propagation losses can be achieved. However, highly directional links require precise alignment of the beams at the gNB and UE. This requires efficient beam management, especially in cases where the UE and gNB move relative to each other. Therefore, during communication between one gNB and one UE, it may be necessary to switch from one beam to another. This beam switching is called intra-cell mobility or beam-level mobility. On the other hand, inter-cell mobility describes the switching of ongoing communications from one cell to another.

[0007] When there are mobile UEs performing intra-cell / inter-cell movement, the overall global model performance in AI / ML operations may degrade because these mobile UEs may be missed and cause the global model to diverge.

[0008] Especially in the case of beam-level mobility scenarios, it is very important for mobile UEs to provide local model updates to the network side (such as gNB, where the global model is located) in UE report transmission to keep as many UEs as possible participating in model training after pre-selection. In AI / ML global model training with federated learning, UEs providing local model updates may move away from the determined beam direction due to beam-level mobility or may be located at the edge of the beam, and then these UEs may be missed due to poor link quality due to outdated beam directions.

[0009] Therefore, it is very necessary to consider how to manage mobile UEs that provide local model updates in UE report transmissions when the UE experiences beam-level mobility.

[0010] As we all know, 5G NR (New Radio) beam management can keep the best beam pair for a good connection. A beam pair consists of a transmit beam and a corresponding receive beam in a link. To achieve this, the UE measures the received signal power in RRC inactive and RRC connected states. This measurement is usually based on the detected beam strength. Once a new uplink is authorized, the UE reports these measurements to the gNB at preconfigured intervals and receives information about the new beam from the gNB.

[0011] The prior art shows contributions related to the key areas of the chosen taxonomy. The prior art contains various approaches for ML-based applications using federated learning for wireless communications. However, no solution has been proposed yet for the explicit UE mobility scenario. Figure 1 and Figure 2 A stamen diagram of the problem defined above is shown and will be explained in more detail later.

[0012] The purpose of this application is to provide a solution to this defined problem. If these UEs are not managed carefully, the entire global model operation will be affected by missing these UEs during model training and cause performance differences.

[0013] The present invention provides a solution to the described problem by means of the method of claim 1 and / or 8 and the corresponding apparatus according to claim 6, 7 and / or 9, 10 and / or 11. A repetition of local model update reports is proposed, wherein each local model update report of a UE with poor channel quality in beam-level mobility or beam-edge areas is repeated and transmitted at different time intervals via different frequency resources.

[0014] Beneficially, the proposed idea can improve the reliability of local model update reports. Summary of the invention

[0015] In one aspect, a method for repeated user equipment (UE) report transmission by a user equipment device connected to a wireless communication network is proposed. UE report transmission can be defined as transmitting local model updates collected in the UE to a network side having a global model for model training and / or inference of the global model, i.e., transmission from a user equipment (UE) device. The location of the global model can be a base station (gNB) of the wireless communication network or a base station connected to the wireless communication network.

[0016] The proposed method for transmission of user equipment (UE) reports by or from a user equipment (UE) device connected to a wireless communication network comprises: the UE determines the channel quality of the used beam or cell based on a CQI metric and, if it determines that the channel quality is poor, it sends a copy (replica) of a local model update report in the time-frequency domain of a wireless communication, wherein a base station (gNB) of the wireless communication network configures the time-frequency resources in a dedicated manner using an RRC reconfiguration message and / or system information. Wireless communications such as 5G-NR (New Radio) typically operate in more frequency bands controlled by a base station gNB. Determining that the channel quality is poor means that the UE monitors beam reference signals (RS) exchanged in the wireless communication between the UE and the gNB and identifies a potential beam failure when a predetermined failure trigger condition is met. This is known to those skilled in the art, for example in 5G NR communications described in the 3GGP standard. Sending a copy of the local model update report in the time-frequency domain of wireless communication means that the UE selects another communication channel or beam in the wireless communication, which communication channel or beam is still in the time-frequency domain of the wireless communication configured by the base station gNB, that is, repeated reports are transmitted at different time intervals on different frequency resources, but are still within the time-frequency domain of wireless communication.

[0017] The UE knows the time-frequency domain actually used by the gNB based on the periodic RRC reconfiguration and / or system information messages between the UE and the gNB.

[0018] The CQI metric (Channel Quality Indicator) is established and used by the UE in mobile or wireless telecommunications (such as LTE or 5G) to indicate the channel quality to the base station gNB. The CQI reporting value is usually between 0 and 15. CQI is a feedback mechanism used by the user equipment (UE) to inform the serving base station (eNodeB) about the downlink channel quality. The CQI can be calculated at the UE based on the signal-to-noise ratio of the received common pilot. Instead of expressing the CQI as the received signal quality, the CQI is expressed as a recommended transport block size, also taking into account the receiver performance. This technique is well known to the skilled person.

[0019] The proposed solution means that if the original UE report transmission fails due to beam level mobility issues (based on significant movement of the UE), the network side is likely to receive duplicate UE report transmissions.

[0020] According to an advantageous embodiment of the proposed method, the UE determines the radio channel quality condition based on a threshold value configured by the base station gNB, wherein the threshold value is configured via a system information message for synchronization in idle mode (SSB, Synchronization Signal Block) and an RRC reconfiguration message for channel state information in connected mode (CSI-RS, Channel State Information Reference Signal). This information is well defined for 5G NR communications and known to a person skilled in the art, for example.

[0021] According to an advantageous proposal, the method may be characterized in that the User Equipment (UE) device is configured to decide to repeat the local model update transmission when the current channel quality is poor.

[0022] In order to avoid any latency issues when reporting local model updates to the server containing the AI / ML global model, the base station (gNB) configures the CG-period (configured grant) to be very short, i.e. the configured scheduling (period) of the data uplink from the user equipment (UE) device to the base station (gNB). This avoids significant delays (latency) in the model updates, especially when the actual data of the global model is needed. In particular, very short means that the uplink period is shorter than the usual communication process for each transmission initialized by the user equipment (UE) device using, for example, downlink control information (DCI) (including information for scheduling (allocating physical resources) downlink data (PDSCH) and information for scheduling (allocating physical resources) uplink data (PUSCH)).

[0023] According to the preferred proposal, it may be provided that, for a local model update report, if the number of bits in the local update report is small, i.e., it contains only a small amount of payload data, the PUCCH channel of the wireless communication network is used as the channel; and if the local model update information may be large and is part of the RRC signaling, the PUSCH channel of the wireless communication network is used as the channel, wherein the PUCCH channel is a physical uplink control channel that carries uplink control information UCI and can be combined with medium payload data, and the PUSCH channel is a physical uplink shared channel that carries user data and can be combined with uplink control information UCI. Compared with using the PUSCH channel for communication, using the PUCCH channel for communication uses fewer resources, and therefore may be more suitable for transmitting only a small amount of payload bits for the local model update report.

[0024] The invention also relates to an apparatus for repeating UE report transmissions to a base station in a wireless communication network, the apparatus comprising a wireless transceiver, a processor coupled to a memory storing therein computer program instructions (603), the computer program instructions being configured to implement the steps or parts thereof as claimed in any one of claims 1 to 5. According to a preferred embodiment, such an apparatus (as defined in claim 6) may be comprised in a User Equipment (UE) device. The User Equipment (UE) device may be a mobile station, a wireless terminal or the like, such as any of the following (this list is not exhaustive): a mobile or cellular phone or communication device, a wireless modem, a wireless communication device, a handheld device, a laptop, an IoT (Internet of Things) device like a wireless camera, a smart sensor or a smart meter, a vehicle, a Global Positioning System device or any other device configured to communicate over a wireless network.

[0025] In a preferred embodiment, the user equipment (UE) device may be a device adapted to move at a relatively high speed relative to a base station of a wireless communication network in road traffic applications or other applications, ie typically at a relative speed faster than 20 km / h or even faster.

[0026] The present invention also relates to a method for repeated UE report transmissions by a User Equipment (UE) device connected to a wireless communication network, in particular according to or for use in a method as described above and / or in connection with any one of claims 1 to 5, for receiving repeated UE report transmissions, as defined in claim 8. In the transmission, if the UE determines based on a CQI metric that the channel quality of the used beam or cell is poor, it may send a copy of the local model update report in the time-frequency domain, wherein the base station (gNB) configures the time-frequency resources in a dedicated manner using an RRC reconfiguration message and / or system information.

[0027] The present invention also relates to an apparatus for repeated UE report transmission in a wireless communication network, the apparatus comprising a wireless transceiver, a processor coupled to a memory storing computer program instructions therein, the computer program instructions being configured to implement the steps as claimed in claim 8. According to a preferred embodiment, such an apparatus (as defined in claim 9) may be included in a base station (gNB) of a wireless communication system.

[0028] The present invention also relates to a wireless communication system for performing repeated UE report transmissions from a user equipment (UE) device to a base station, wherein the base station (gNB) comprises a processor coupled to a memory in which computer program instructions are stored, and the computer program instructions are configured to implement the steps as claimed in claim 8, wherein the user equipment (UE) device comprises a processor coupled to a memory in which computer program instructions are stored, and the computer program instructions are configured to implement the steps as claimed in claims 1 to 5.

[0029] In some embodiments, the various steps of the method for receiving a small data transmission by a user equipment and / or the method for sending a small data transmission by a base station are determined by instructions of a computer program.

[0030] Therefore, the present disclosure further contemplates computer programs on an information medium, which are suitable for implementation in a user equipment device and a base station, or more generally in a computer, respectively, and which programs respectively include instructions adapted to implement the steps of the wireless communication method disclosed herein, which is supported by the user equipment and performed by the base station, respectively.

[0031] These programs may use any programming language and may be in the form of source code, object code, or an intermediate code between source code and object code, such as partially compiled form or any other desired form.

[0032] On the other hand, a computer-readable information medium is envisaged, the information medium including instructions of a computer program such as mentioned above. The information medium may be any entity or device capable of storing a program. For example, the medium may include a storage device such as a ROM (read-only memory) (e.g., a CD ROM or a microelectronic circuit ROM), an EEPROM (electrically erasable programmable read-only memory), a FLASH memory or any magnetic recording device (e.g., a hard disk drive).

[0033] Furthermore, the information medium may be a transmissible medium such as an electric signal or an optical signal that can be transmitted via an electric or optical cable by radio or by other means.The program according to the embodiment of the present invention may be downloaded from a network.

[0034] Alternatively, the information medium may be an integrated circuit in which the program is embodied, the circuit being arranged to execute or to be used for executing the method in question. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Other advantages and characteristics of the invention will become more apparent on reading the following description, given by way of simple illustrative and non-limiting examples, and the accompanying drawings, in which:

[0036] Figure 1 Describes AI / ML-based federated learning in wireless networks;

[0037] Figure 2 AI / ML model training using beam-level mobility UE is shown;

[0038] Figure 3 shows the duplication of local model update reports;

[0039] Figure 4 The method steps of a base station gNB receiving repeated local model update reports from a UE device are shown;

[0040] Figure 5 The method steps of the base station gNB indicating whether the UE needs to repeat the local model update report (e.g., RRC_CONNECTED) are shown;

[0041] Figure 6 The method steps of a UE device receiving a repeated report indication (e.g., RRC_CONNECTED) are shown;

[0042] Figure 7 The method steps for a UE device to determine to repeatedly transmit a local model update report (eg, RRC_INACTIVE / IDLE) are shown. DETAILED DESCRIPTION

[0043] The specific embodiments described below with reference to the accompanying drawings are intended as descriptions of various configurations and are not intended to represent the only configurations in which the concepts described herein may be practiced. The specific embodiments include specific details to provide a thorough understanding of the various concepts. However, it will be apparent to those skilled in the art that these concepts may be practiced without these specific details. In particular, although terminology from 3GPP 5G NR may be used in this disclosure to illustrate the embodiments herein, this should not be viewed as limiting the scope of the invention.

[0044] Some embodiments contemplated herein will now be described more fully with reference to the accompanying drawings. However, other embodiments are also included within the scope of the subject matter disclosed herein, and the disclosed subject matter should not be construed as being limited to the embodiments set forth herein; rather, these embodiments are provided by way of example to convey the scope of the subject matter to those skilled in the art.

[0045] Generally, all terms used herein should be interpreted according to their ordinary meaning in the relevant technical field, unless different meanings are clearly given and / or different meanings are implied from the context of their use. Unless otherwise clearly stated, all references to one / a kind / the element, device, part, mode, step, etc. should be openly interpreted as referring to at least one instance of an element, device, part, mode, step, etc. The steps of any method disclosed herein do not have to be performed in the exact order disclosed, unless a step is clearly described as being after or before another step and / or it is implied that a step must be after or before another step. Where appropriate, any feature of any embodiment disclosed herein may be applicable to any other embodiment. Similarly, any advantage of any embodiment may be applicable to any other embodiment, and vice versa. According to the following description, other purposes, features and advantages of the attached embodiments will become apparent.

[0046] In some embodiments, a more general term "network node" may be used, which may correspond to any type of radio network node or any network node that communicates with a UE (directly or via another node) and / or communicates with another network node. Examples of network nodes are NodeB, MeNB, ENB, network nodes belonging to MCG or SCG, base stations (BS), multi-standard radio (MSR) radio nodes (such as MSR BS, eNodeB, gNodeB), network controllers, radio network controllers (RNC), base station controllers (BSC), relays, donor node controlled relays, base transceiver stations (BTS), access points (AP), transmission points, transmission nodes, RRUs, RRHs, nodes in distributed antenna systems (DAS), core network nodes (such as mobile switching centers (MSCs), mobile management entities (MMEs), etc.), operations and maintenance (O&M), operations support systems (OSS), self-optimizing networks (SONs), positioning nodes (such as evolved serving mobile positioning centers (E-SMLCs)), minimization of drive tests (MDTs), test equipment (physical nodes or software), etc.

[0047] In some embodiments, the non-limiting term user equipment (UE) or wireless device may be used and may refer to any type of wireless device that communicates with a network node and / or another UE in a cellular or mobile communication system. Examples of UEs are target devices, device-to-device (D2D) UEs, machine-type UEs or UEs capable of machine-to-machine (M2M) communication, PDAs, PADs, tablet computers, mobile terminals, smart phones, laptop embedded devices (LEEs), laptop mounted equipment (LMEs), USB dongles, M1 class UEs, M2 class UEs, ProSe UEs, V2V UEs, V2X UEs, etc.

[0048] In addition, terms such as base station / gNodeB and UE should be considered non-restrictive and in particular do not imply a certain hierarchical relationship between the two; generally, "gNodeB" can be considered as device 1, "UE" can be considered as device 2, and the two devices communicate with each other through a certain radio channel. And in the following, a transmitter or a receiver can be a gNodeB (gNB) or a UE.

[0049] As will be appreciated by those skilled in the art, aspects of the embodiments may be embodied as a system, apparatus, method or program product. Thus, the embodiments may take the form of a complete hardware embodiment, a complete software embodiment (including firmware, resident software, microcode, etc.), or a combination of software and hardware aspects.

[0050] For example, the disclosed embodiments may be implemented as hardware circuits including custom very large scale integrated ("VLSI") circuits or gate arrays, off-the-shelf semiconductors (e.g., logic chips, transistors, or other discrete components). The disclosed embodiments may also be implemented in programmable hardware devices such as field programmable gate arrays, programmable array logic, programmable logic devices, etc. As another example, the disclosed embodiments may include one or more physical or logical blocks of executable code, which may be organized, for example, as objects, procedures, or functions.

[0051] In addition, embodiments may take the form of a program product embodied in one or more computer-readable storage devices storing machine-readable code, computer-readable code, and / or program code (hereinafter referred to as code). The storage device may be tangible, non-transient, and / or non-transmitting. The storage device may not embody signals. In certain embodiments, the storage device only uses signals to access the code.

[0052] Any combination of one or more computer readable media may be utilized. The computer readable medium may be a computer readable storage medium. The computer readable storage medium may be a storage device storing code. The storage device may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, holographic, micromechanical, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing.

[0053] More specific examples of storage devices (a non-exhaustive list) would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory ("RAM"), a read-only memory ("ROM"), an erasable programmable read-only memory ("EPROM" or flash memory), a portable compact disk read-only memory ("CD-ROM"), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer-readable storage medium may be any tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device.

[0054] The code for performing the operation of the embodiment can be any number of rows, and can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Python, Ruby, Java, Smalltalk, C++ and conventional procedural programming languages ​​such as "C" programming language and / or machine languages ​​such as assembly language. The code can be executed completely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or executed completely on a remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network (including local area network ("LAN"), wireless LAN ("WLAN") or wide area network ("WAN")), or can be connected to an external computer (for example, using an Internet service provider ("ISP") through the Internet).

[0055] In addition, the described features, structures or characteristics of the embodiments can be combined in any suitable manner. In the following description, many specific details (such as examples of programming, software modules, user selection, network transactions, database queries, database structures, hardware modules, hardware circuits, hardware chips, etc.) are provided to provide a thorough understanding of the embodiments. However, those skilled in the relevant art will recognize that the embodiments can be practiced without one or more specific details or using other methods, components, materials, etc. In other examples, well-known structures, materials or operations are not shown or described in detail to avoid blurring the various aspects of the embodiments. The reference to "one (one) embodiment", "one (an) embodiment" or similar language throughout the specification means that in at least one embodiment, the specific features, structures or characteristics described in combination with the embodiment are included. Therefore, unless otherwise clearly indicated, the phrases "one (one) embodiment", "one (an) embodiment" and similar language that appear throughout the specification may but do not necessarily refer to the same embodiment, but mean "one or more embodiments, but not all embodiments". Unless otherwise clearly indicated, the terms "including (including and comprising)", "having (having)" and their variants mean "including but not limited to". The enumerated listing of items does not imply that any or all of the items are mutually exclusive, unless expressly specified otherwise. The terms "a" and "an" and "the" also mean "one or more," unless expressly specified otherwise.

[0056] Various aspects of the embodiments are described below with reference to schematic flow charts and / or schematic block diagrams of methods, devices, systems, and program products according to the embodiments. It should be understood that each frame of the schematic flow charts and / or schematic block diagrams and the combination of frames in the schematic flow charts and / or schematic block diagrams can be implemented by code. The code can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to generate a machine, so that instructions executed by the processor of the computer or other programmable data processing device create means for implementing the functions / actions specified in the flow charts and / or block diagrams.

[0057] The code may also be stored in a storage device that can direct a computer, other programmable data processing apparatus, or other device to operate in a specific manner so that the instructions stored in the storage device produce an article of manufacture including instructions for implementing the functions / actions specified in the flowchart and / or block diagram.

[0058] The code may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus, or other device to produce a computer-implemented process, so that the code executed on the computer or other programmable apparatus provides a process for implementing the functions / actions specified in the flowchart and / or block diagram.

[0059] The flowcharts and / or blocks in the accompanying drawings illustrate the architecture, functions and operations of possible implementations of the apparatus, system, method and program product according to various embodiments. In this regard, each block in the flowchart and / or block diagram may represent a module, a fragment, or a code portion, which includes one or more executable instructions for implementing (multiple) specified logical functions.

[0060] It should also be noted that in some alternative implementations, the functions indicated in the blocks may not occur in the order indicated in the drawings. For example, two blocks shown in succession may actually be executed substantially in parallel, or the blocks may sometimes be executed in reverse order depending on the functions involved. Other steps and methods may be conceived that are equivalent in function, logic or effect to one or more blocks or portions thereof in the drawings shown.

[0061] Although various arrow types and line types may be used in the flow chart and / or block diagram, it should be understood that they do not limit the scope of the corresponding embodiment. In fact, some arrows or other connectors may only be used to indicate the logical flow of the depicted embodiment. For example, an arrow may indicate a waiting or monitoring cycle of an unspecified duration between the enumerated steps of the depicted embodiment. It should also be noted that each frame of the block diagram and / or flow chart and the combination of frames in the block diagram and / or flow chart can be implemented by a combination of a dedicated hardware-based system or dedicated hardware and code that performs a specified function or action.

[0062] The description of an element in each figure may refer to an element in a subsequent figure. In all figures, the same reference numerals refer to the same elements, including alternative embodiments of the same elements.

[0063] The specific embodiments described below with reference to the accompanying drawings are intended as descriptions of various configurations and are not intended to represent the only configurations in which the concepts described herein may be practiced. The specific embodiments include specific details to provide a thorough understanding of the various concepts. However, it will be apparent to those skilled in the art that these concepts may be practiced without these specific details. In particular, although terminology from 3GPP 5G NR may be used in this disclosure to illustrate the embodiments herein, this should not be viewed as limiting the scope of the invention.

[0064] Figure 1An exemplary 5G New Radio (NR) wireless communication system including a user equipment device UE and a base station gNB in ​​which various aspects of the present disclosure may be practiced is shown. The wireless network WN may be an LTE network or some other wireless network, such as an LTE, 5G or NR network. The wireless network may include one or more base stations gNB. Depending on the wireless standard implemented, the base station gNB may be referred to as a BS, NB, eNodeB (or eNB), gNodeB (or gNB), access point, etc. The base station gNB provides radio communication coverage for a specific geographical area called a "cell".

[0065] User equipment device UE may refer to any device such as a mobile station, a wireless terminal, etc. In some examples, the user equipment may be a cellular phone, a wireless modem, a wireless communication device, a handheld device, a laptop computer, etc. The user equipment may also be an IoT (Internet of Things) device like a wireless camera, a smart sensor or smart meter, a vehicle, a global positioning system device, or any other device configured to communicate over a wireless network.

[0066] The user equipment device UE is used for artificial intelligence / machine learning AI, including a local model LM contained in a dataset of artificial intelligence / machine learning AI. The user equipment device UE participates in federated learning FL, where AI / ML based local model updates are collected from multiple user equipment UE devices and a global model on a server gNB is updated in an iterative manner for model training / inference.

[0067] The user equipment UC may support various communication modes, such as a connected mode or state (RRC connected), an inactive mode or state (RRC inactive), or an idle mode or state (RRC idle) defined by the 3GPP standard. When operating in the RRC connected mode, the user equipment device UE is active and communicates with the base station. The user equipment device UE may use various commands and messages received from the base station gNB to transition from one communication mode to another. For example, the user equipment device UE may transition from the RRC connected state to the RRC inactive state upon receiving an RRC release message including the suspendConfig parameter.

[0068] When there is no traffic, the user equipment device UE can enter the RRC inactive state without completely releasing radio resources so as to quickly switch back to the RRC connected state when necessary. In this case, the user equipment and the base station can store the context (e.g., access layer (AS) context) for the user equipment so as to apply the stored context when transitioning from the RRC inactive state to the RRC connected state, thereby reducing latency and signaling overhead. Such context may include radio configuration parameters such as uplink grant, RNTI (Radio Network Temporary Identifier), MCS (Modulation and Coding Scheme), etc.

[0069] However, while the user equipment UE is in the RRC inactive state, the radio conditions may change, for example the user equipment may move to another location, and thus the channel quality changes.

[0070] Figure 2 AI / ML global model training using beam-level mobility UE is shown.

[0071] like Figure 2 As mentioned and shown in more detail in FIG, the AI / ML global model GM is trained n times by federated learning FL, and the user equipment device UE provides local model updates for the global model located in the base station gNB in ​​this example. In modern wireless communication networks (such as 3GPP 5G NR), data transmission is carried out via directional beams BM between the base station gNB and the user equipment device. Usually, there are multiple beams BM in different directions connected to the base station gNB. Figure 2 In the example, the columns are represented by indexes 1 to 5.

[0072] User equipment devices UE may move away from the determined beam direction (BM4 in the example shown) due to beam level mobility or may be located at the edge of the beam, and then these equipment UEs may be missed due to outdated beam directions resulting in poor link quality. If these user equipment devices UE are not carefully managed, the entire global model operation will be affected by missing these UEs during model training and cause performance differences.

[0073] During preliminary steps, the user equipment device UE may transition to the RRC inactive state in response to an RRC release message with a suspendConfig parameter. An I-RNTI (Inactive Radio Network Temporary Identifier) ​​may be allocated to the user equipment device UE as part of the suspendConfig parameter within such RRC release message.

[0074] According to the proposal and Figure 3As shown, repetition of local model update reports is proposed, wherein each local model update report of a user equipment device UE with poor channel quality in beam level mobility or beam edge area is repeated and transmitted at different time intervals through different frequency resources (i.e., different beams BM1 and BM2).

[0075] Figures 4 to 7 Different method steps performed by a base station gNB and / or a user equipment device UE are shown. In more detail, Figure 4 The base station gNB receives repeated local model update reports from the user equipment device UE, Figure 5 It shows that the base station gNB indicates to the user equipment device UE whether repeated local model update reports (e.g., RRC_CONNECTED) are required. Figure 6 The user equipment device UE receives a repeat reporting indication (eg, RRC_CONNECTED), and Figure 7 It is shown that the user equipment device UE determines to repeatedly transmit the local model update report (eg, RRC_INACTIVE / IDLE).

[0076] The user equipment device UE (device) includes a processor and a memory, such as a random access memory (RAM). The processor can be controlled by a computer program stored in the memory, the computer program including instructions configured to implement a method for receiving data transmission from a base station gNB in ​​a wireless communication network WN.

[0077] More specifically, the computer program comprises instructions for receiving a paging notification from a base station gNB in ​​an inactive state, the paging notification comprising at least an indication that downlink small data is available for transmission and a priority flag associated with the downlink small data; determining at least one synchronization signal reference signal received power, and when the priority flag indicates low priority downlink data and the at least one synchronization signal reference signal received power is lower than a threshold, postponing downlink data reception until the next paging cycle.

[0078] At initialization, the instructions of the computer program may be loaded into the memory before being executed by the processor. The processor implements the steps of the method according to the instructions of the computer program.

[0079] The user equipment device UE comprises a wireless communication unit, such as a 3G, 4G, 5G, 5G NR, WiFi or WiMax transceiver, for exchanging messages with other devices.

[0080] The user equipment device UE further includes a channel quality sensor. The channel quality sensor can be configured by computer program instructions to measure the signal strength on one or more available SSBs (synchronization signal blocks) and compare the measured value with a preconfigured threshold to determine whether the RSRP of all SSBs is below the threshold.

[0081] According to an embodiment, the user equipment device UE further comprises a scheduler unit. The scheduler unit can be configured by computer program instructions to postpone downlink data reception until the next paging cycle when the priority flag received by the communication unit indicates low priority downlink data and when the channel quality sensor determines that the RSRP of all SSBs measured is lower than the threshold.

[0082] In some embodiments, the user equipment device UE may include a random access module configured to initiate a random access procedure through computer program instructions. The random access procedure may include sending a quality indicator determined by a channel quality sensor to a serving base station through a communication unit. In some examples, the quality indicator is sent as a binary flag that is set to indicate that the RSRP of all SSBs is below a preconfigured threshold (CQI metric).

[0083] According to an embodiment, the communication unit is further configured by computer program instructions to receive downlink data from a base station, the downlink data being transmitted using a low modulation scheme selected by the base station based on the at least one synchronization signal reference signal received power being below a threshold.

[0084] In some embodiments, the user equipment device UE is comprised in a smartphone, a laptop, an IoT (Internet of Things) device or a vehicle.

[0085] In this communication context, and if the global model aggregation based on federated learning FL requires high timeliness, the proposed repeated transmission can also consider the following method steps and variants.

[0086] If the gNB knows based on the measurements that the communication quality is poor, it can configure CG resources in consecutive time slots. Therefore, the UE can send local model update reports in a repeated manner (back-to-back consecutive time slots), or the gNB can configure the periodicity of CG resources in a dense manner to avoid any latency issues (applicable to RRC connected as well as inactive mode).

[0087] According to a specific embodiment of the present invention and as described below, the user equipment device UE may measure the CQI based on the Figure 7) to measure radio quality conditions, e.g. periodically. If the result indicates (compared to a defined threshold) that the channel quality is not bad, i.e., good enough for regular data transmission, no further action is taken and the channel quality measurement is repeated later, e.g., after transmission of the next upcoming user equipment report transmission.

[0088] However, if the channel quality is poor, the user equipment device UE sends repeated local model update reports (user equipment report transmission) to the base station gNB, such as Figure 3 shown.

[0089] Depending on the duplication or local model update, upon receiving a UE report transmission (local model update), the gNB determines whether the transmission is related to a duplicate local model update ( Figure 4 ). If not, the base station gNB waits to receive a new (next) local model update from the user equipment device UE. If yes, the base station gNB decodes in conjunction with the repeated local model update.

[0090] On the other hand, Figure 5 As shown, after the user equipment device UE determines the radio channel quality condition of the beam or cell used based on the CQI metric, it transmits a (channel quality) measurement report to the base station gNB, and after receiving the measurement report, the base station gNB evaluates the radio channel quality condition and triggers whether the user equipment device UE should send repeated user equipment (UE) report transmissions. If so, the base station gNB can send an indication to the user equipment device UE to enable repeated local model update report transmissions as proposed ( Figure 6 ).

[0091] In this context, it may be provided that the base station gNB configures a threshold value to determine whether repeated local model update report transmissions are required. The threshold value is configured, for example, via a system information message for SSB and an RRC reconfiguration message for CSI-RS.

[0092] The user equipment device UE sends a copy of this local model update report in the time-frequency domain, wherein the base station gNB can configure the time-frequency resources for repeated report transmission in a dedicated manner (using RRC reconfiguration message / system information (such as CG)).

[0093] Then, or depending on the RRC mode (connected or inactive / idle), the UE decides to repeat the local model update transmission when the current channel quality is poor based on a threshold configured by the base station gNB.

[0094] In this context, the base station gNB can configure the CG period to be very short if necessary to avoid any latency issues. This enables quasi-continuous transmission of update reports.

[0095] Furthermore, the base station gNB may determine the use of the local model update report channel based on the local model update report size by considering PUCCH and PUSCH.

[0096] Based on the proposed repeated transmission method for mobile user equipment devices UE with beam-level mobility, the AI / ML performance of wireless communications can be greatly improved.

[0097] The methods described in all examples can be combined with all other methods disclosed accordingly.

[0098] This feature is most beneficial for messaging and presence applications in sensors, IoT devices, and even smartphones or vehicles, especially fast-moving user equipment devices.

Claims

1. A method for performing repeated user equipment (UE) report transmission by a user equipment (UE) device connected to a wireless communication network, wherein: The user equipment (UE) device determines the radio channel quality condition of the used beam or cell based on the CQI metric and sends a copy of the local model update report in the time-frequency domain if the channel quality is determined to be poor, wherein the base station (gNB) configures the time-frequency resources in a dedicated manner using RRC reconfiguration messages and / or system information.

2. The method according to claim 1, wherein: The method is characterized in that a radio channel quality condition is determined in the user equipment (UE) device based on a threshold configured by the base station (gNB), wherein the threshold is configured by a system information message (SSB) for synchronization and an RRC reconfiguration message for channel state information (CSI-RS).

3. The method according to claim 1 or 2, wherein: The method is characterized in that when the current channel quality is poor, the user equipment (UE) device decides to repeat the local model update transmission.

4. The method according to claims 1 to 3, wherein: The method is characterized in that the CG period is configured to be very short to avoid any latency issues.

5. The method according to claims 1 to 4, wherein: The method is characterized in that, for a local model update report, if the number of payload bits in the local update report is small, the PUCCH channel of the wireless communication network is used as the channel; and if the local model update information may be large and is part of the RRC signaling, the PUSCH channel of the wireless communication network is used as the channel, wherein the PUCCH channel is a physical uplink control channel that carries uplink control information and can be combined with medium payload data, and the PUSCH channel is a physical uplink shared channel that carries user data and can be combined with uplink control information.

6. An apparatus for performing repeated UE report transmissions to a base station (gNB) in a wireless communication network, the apparatus comprising a wireless transceiver, a processor coupled to a memory storing computer program instructions therein, the computer program instructions being configured to implement the steps of the method as described in any one of claims 1 to 5.

7. A user equipment (UE) device, comprising the apparatus according to claim 6.

8. A method for repeated UE report transmission, in particular according to any one of claims 1 to 5, for receiving the UE report transmission by a base station (gNB) in a wireless communication network, wherein: The time-frequency resources for wireless transmission are configured in a dedicated manner by the base station (gNB) using RRC reconfiguration messages and / or system information.

9. An apparatus for performing repeated UE report transmission in a wireless communication network, the apparatus comprising a wireless transceiver, a processor coupled to a memory storing computer program instructions therein, the instructions being configured to implement the steps of claim 8.

10. A base station, comprising the device according to claim 9.

11. A wireless communication system for performing repeated UE report transmission from a user equipment (UE) device to a base station (gNB), in, The base station (gNB) comprises a processor coupled to a memory having computer program instructions stored therein, the computer program instructions being configured to implement the steps of the method according to claim 8, The user equipment (UE) device comprises a processor coupled to a memory storing computer program instructions therein, the computer program instructions being configured to implement the steps of the method according to claims 1 to 5.

Images