Method, apparatus and computer program

Abstract

An apparatus is provided that includes means for receiving measurement data from a user equipment regarding one or more cells of a network, means for determining, based on the measurement data, a prediction including at least one sequence of one or more beams that are predicted to have the highest signal quality for the user equipment at each one or more time instances, and means for transmitting the prediction to the user equipment.

Description

[Technical Field]

[0001] The present application relates to methods, apparatus, systems and computer programs, particularly but not exclusively, to predicting sequences of beams to be used in the future by user equipment. [Background technology]

[0002] A communication system can be considered as a facility that enables communication sessions between two or more entities, such as user terminals, base stations, and / or other nodes, by providing carriers between the various entities involved in the communication paths. A communication system can be provided, for example, by a communication network and one or more compatible communication devices. The communication sessions can include, for example, data communications for transmitting communications such as voice, video, electronic mail (email), text messages, multimedia and / or content data. Non-limiting examples of services provided include two-way or multi-way calls, data communications or multimedia services, and access to data network systems such as the Internet.

[0003] In a wireless communication system, at least a portion of a communication session between at least two stations is conducted over a wireless link. Examples of wireless systems include public land mobile networks (PLMNs), satellite-based communication systems, and different wireless local networks, such as wireless local area networks (WLANs). Some wireless systems can be divided into cells and are therefore often referred to as cellular systems.

[0004] A user can access a communication system using a suitable communication device or terminal. A user's communication device can be referred to as user equipment (UE) or user device. A communication device is provided with suitable signal receiving and transmitting equipment to enable communication, e.g., access to a communication network or direct communication with other users. A communication device can access a carrier provided by a station (e.g., a base station of a cell) and transmit and / or receive communications on the carrier.

[0005] Communication systems and associated devices typically operate according to a given standard or specification that describes what the various entities associated with the system are allowed to do and how they should accomplish it. The communication protocols and / or parameters used for connectivity are typically also defined. One example of a communication system is UTRAN (3G radio). Other examples of communication systems are the Long Term Evolution (LTE) of the Universal Mobile Telecommunications System (UMTS) radio access technology, and so-called 5G or New Radio (NR) networks. NR is being standardized by the 3rd Generation Partnership Project (3GPP). Summary of the Invention

[0006] According to one aspect, an apparatus is provided that includes: means for receiving measurement data from a user equipment regarding one or more cells and / or one or more beams of a network; means for determining, based on the measurement data, a prediction including at least one sequence of one or more beams that are predicted to have the highest signal quality for the user equipment at each one or more time instances; and means for transmitting the prediction to the user equipment.

[0007] The means may be for transmitting an indication to the user equipment that beam sequence prediction is available for the user equipment, and the receiving is performed in response to transmitting the indication that beam sequence prediction is available.

[0008] The prediction may include at least a first sequence of one or more beams that is a sequence of one or more beams predicted to have the highest signal quality for the user equipment at each one or more time instances, and a second sequence of the sequence of one or more beams at each one or more time instances, wherein at least one of the one or more beams differs between the first sequence and the second sequence.

[0009] Transmitting the prediction may include transmitting at least one confidence interval associated with each sequence of the at least one sequence.

[0010] The confidence intervals can be different for different time instances of the sequence.

[0011] Determining the prediction can be performed by a machine learning algorithm or an adaptive algorithm.

[0012] The means can be for receiving an indication from the user equipment that the prediction was inaccurate for at least one of the one or more time instances.

[0013] The indication may include an indication that the prediction was inaccurate by more than the confidence interval.

[0014] The indication may include further measurement data for one or more beams at one or more time instances where the prediction was inaccurate.

[0015] The means may be for performing retraining of the model based on the indication.

[0016] The means may be for determining a new prediction based at least in part on the indication and transmitting the new prediction to the user equipment.

[0017] The means may be for determining that the prediction was accurate.

[0018] Determining that the prediction was accurate may include at least one of receiving an indication from the user equipment that the prediction was accurate or not receiving an indication from the user equipment after a period of time that the prediction was inaccurate.

[0019] Determining that the prediction was accurate may include determining that the prediction was accurate within a confidence interval.

[0020] The indication that the prediction was accurate may further include information regarding the sequence of one or more beams utilized by the user equipment.

[0021] The means may be for, in response to determining that the prediction was accurate, transmitting a signal control element command to the user equipment based on the prediction to trigger a beam or cell switch of the user equipment from a first beam at time interval t to a second beam at time interval t+1.

[0022] According to one aspect, an apparatus is provided, comprising: means for transmitting measurement data relating to one or more cells and / or one or more beams of a network to a network node; and means for receiving from the network node a prediction comprising at least one sequence of one or more beams predicted to have the highest signal quality for the apparatus at each one or more time instances, the prediction being based at least in part on the measurement data.

[0023] The means may be for receiving an indication from the network node that beam sequence prediction is available, and the transmission may be performed in response to receiving an indication that beam sequence prediction is available.

[0024] The at least one sequence may comprise at least a first sequence of one or more beams and a second sequence of one or more beams that are sequences of one or more beams predicted to have the highest signal quality to the user equipment at each one or more time instances, wherein at least one of the one or more beams differs between the first sequence and the second sequence.

[0025] Receiving the prediction may include receiving a confidence interval associated with each sequence of the at least one sequence.

[0026] The confidence intervals can be different for different time instances of the sequence.

[0027] The means may be for acquiring further measurement data for at least one of the one or more beams at at least one of the respective one or more time instances, and determining whether the prediction was accurate based on a comparison between the further measurement data and the prediction.

[0028] The means may be for, in response to determining that the prediction was inaccurate for at least one of the one or more time instances, transmitting an indication to the network node that the prediction was inaccurate for at least one of the one or more time instances.

[0029] The indication may include an indication that the prediction was inaccurate by more than a confidence interval.

[0030] The indication may include further measurement data for at least one of the one or more beams at one of the one or more time instances in which the prediction was inaccurate.

[0031] The means may be for receiving a new prediction from the network node, the new prediction based at least in part on the indication that the prediction was inaccurate.

[0032] The means may be for, in response to determining that the prediction was accurate, transmitting an indication to the network node that the prediction was accurate or refraining from transmitting to the network node an indication that the prediction was inaccurate, the network node being configured to consider the prediction to be accurate if the device does not transmit to the network node within a certain time that the prediction was inaccurate.

[0033] Determining that the prediction was accurate may include determining that the prediction was accurate within a confidence interval.

[0034] The indication that the prediction was accurate may further include information regarding the trajectory taken by the user equipment.

[0035] The means may be for receiving a signal control element command from a network node to trigger a beam switch from a first beam at time interval t to a second beam at time interval t+1, and for performing the beam switch based on the signal control element command.

[0036] The means may be for performing a beam switch from a first beam at time interval t to a second beam at time interval t+1 based on the prediction if the prediction is accurate.

[0037] According to one aspect, there is provided an apparatus comprising at least one processor and at least one memory including computer program code, wherein the at least one memory and the computer program code are configured to cause, using the at least one processor, the apparatus to at least: receive measurement data from a user equipment regarding one or more cells and / or one or more beams of a network; determine, based on the measurement data, a prediction including at least one sequence of one or more beams that are predicted to have the highest signal quality for the user equipment at each one or more time instances; and transmit the prediction to the user equipment.

[0038] The at least one memory and the at least one processor can be configured to cause the device to transmit an indication to a user equipment that a beam sequence prediction is available, and the at least one memory and the at least one processor can be configured to cause the device to receive measurement data in response to transmitting the indication that a beam sequence prediction is available.

[0039] The prediction may include at least a first sequence that is a sequence of one or more beams that are predicted to have the highest signal quality for the user equipment at each one or more time instances, and a second sequence of one or more beams at each one or more time instances, wherein at least one of the one or more beams differs between the first sequence and the second sequence.

[0040] Transmitting the prediction may include transmitting at least one confidence interval associated with each sequence of the at least one sequence.

[0041] The confidence intervals can be different for different time instances of the sequence.

[0042] Determining the prediction can be performed by a machine learning algorithm or an adaptive algorithm.

[0043] The at least one memory and the at least one processor can be configured to cause the apparatus to receive an indication from the user equipment that the prediction was inaccurate for at least one of the one or more time instances.

[0044] The indication may include an indication that the prediction was inaccurate by more than the confidence interval.

[0045] The indication may include further measurement data for one or more beams at one or more time instances where the prediction was inaccurate.

[0046] The at least one memory and the at least one processor may be configured to cause the device to perform retraining of the model based on the indication.

[0047] The at least one memory and the at least one processor may be configured to cause the apparatus to determine a new prediction based at least in part on the indication and transmit the new prediction to the user equipment.

[0048] The at least one memory and the at least one processor can be configured to cause the device to determine that the prediction was accurate.

[0049] The at least one memory and the at least one processor can be configured to cause the device to determine that the prediction was accurate by performing at least one of receiving an indication from the user equipment that the prediction was accurate or not receiving an indication from the user equipment after a period of time that the prediction was inaccurate.

[0050] The at least one memory and the at least one processor may be configured to cause the apparatus to determine that the prediction was accurate by determining that the prediction was accurate within a confidence interval.

[0051] The indication that the prediction was accurate may further include information regarding the sequence of one or more beams utilized by the user equipment.

[0052] The at least one memory and the at least one processor may be configured to, in response to determining that the prediction was accurate, cause the device to transmit a signal control element command to the user equipment that triggers a beam or cell switch of the user equipment from a first beam at time interval t to a second beam at time interval t+1 based on the prediction.

[0053] According to one aspect, an apparatus is provided that includes at least one processor and at least one memory containing computer program code, the at least one memory and the computer program code being configured to cause the apparatus, using the at least one processor, to transmit measurement data regarding one or more cells and / or one or more beams of the network to a network node, and to receive from the network node a prediction including at least one sequence of one or more beams that are predicted to have the highest signal quality for the apparatus at each one or more time instances, the prediction being based at least in part on the measurement data.

[0054] The at least one memory and the at least one processor may be configured to cause the device to receive an indication from the network node that a beam sequence prediction is available, and the at least one memory and the at least one processor may be configured to cause the device to transmit measurement data in response to receiving the indication that a beam sequence prediction is available.

[0055] The at least one sequence may comprise a first sequence of one or more beams that is a sequence of one or more beams predicted to have the highest signal quality to the user equipment at each one or more time instances, and a second sequence of one or more beams, wherein at least one of the one or more beams differs between the first sequence and the second sequence.

[0056] The at least one memory and the at least one processor may be configured to cause the apparatus to receive a prediction by receiving a confidence interval associated with each of the at least one sequence.

[0057] The confidence intervals can be different for different time instances of the sequence.

[0058] The at least one memory and the at least one processor may be configured to cause the apparatus to acquire further measurement data for at least one of the one or more beams at at least one of the respective one or more time instances, and determine whether the prediction was accurate based on a comparison between the further measurement data and the prediction.

[0059] The at least one memory and the at least one processor may be configured to cause the apparatus, in response to indicating that the prediction was inaccurate for at least one of the one or more time instances, to send an indication to a network node that the prediction was inaccurate for at least one of the one or more time instances.

[0060] The indication may include an indication that the prediction was inaccurate by more than the confidence interval.

[0061] The indication may include further measurement data for at least one of the one or more beams at one of the one or more time instances in which the prediction was inaccurate.

[0062] The at least one memory and the at least one processor can be configured to cause the device to receive a new prediction from the network node, the new prediction based at least in part on an indication that the prediction was inaccurate.

[0063] The at least one memory and the at least one processor may be configured to cause the device, in response to determining that the prediction was accurate, to send an indication to the network node that the prediction was accurate or to refrain from sending an indication to the network node that the prediction was inaccurate, and the network node is configured to consider the prediction to be accurate if the device does not send an indication to the network node that the prediction was inaccurate within a certain period of time.

[0064] The at least one memory and the at least one processor may be configured to cause the apparatus to determine that the prediction was accurate by determining that the prediction was accurate within a confidence interval.

[0065] The indication that the prediction was accurate may further include information regarding the trajectory taken by the user equipment.

[0066] The at least one memory and the at least one processor may be configured to cause the device to receive a signal control element command from a network node triggering a beam switch from a first beam at time interval t to a second beam at time interval t+1, and to perform the beam switch based on the signal control element command.

[0067] The at least one memory and the at least one processor can be configured to cause the device to perform a beam switch from a first beam at time interval t to a second beam at time interval t+1 based on the prediction if the prediction is accurate.

[0068] According to one aspect, a method is provided that includes receiving measurement data from a user equipment regarding one or more cells and / or one or more beams of a network, determining a prediction based on the measurement data that includes at least one sequence of one or more beams that are predicted to have the highest signal quality for the user equipment at each one or more time instances, and transmitting the prediction to the user equipment.

[0069] The method may include transmitting an indication to a user equipment that beam sequence prediction is available to the user equipment, and receiving is performed in response to transmitting the indication that beam sequence prediction is available.

[0070] The prediction may include at least a first sequence that is a sequence of one or more beams that are predicted to have the highest signal quality for the user equipment at each one or more time instances, and a second sequence of one or more beams at each one or more time instances, wherein at least one of the one or more beams differs between the first sequence and the second sequence.

[0071] Transmitting the prediction may include transmitting at least one confidence interval associated with each sequence of the at least one sequence.

[0072] The confidence intervals can be different for different time instances of the sequence.

[0073] Determining the prediction can be performed by a machine learning algorithm or an adaptive algorithm.

[0074] The method can include receiving an indication from the user equipment that the prediction was inaccurate for at least one of the one or more time instances.

[0075] The indication may include an indication that the prediction was inaccurate by more than the confidence interval.

[0076] The indication may include further measurement data for one or more beams at one or more time instances where the prediction was inaccurate.

[0077] The method may include performing retraining of the model based on the indication.

[0078] The method can include determining a new prediction based at least in part on the indication and transmitting the new prediction to the user equipment.

[0079] The method can include determining that the prediction was accurate.

[0080] Determining that the prediction was accurate may include at least one of receiving an indication from the user equipment that the prediction was accurate or not receiving an indication from the user equipment that the prediction was inaccurate after a period of time.

[0081] Determining that the prediction was accurate may include determining that the prediction was accurate within a confidence interval.

[0082] The indication that the prediction was accurate may further include information regarding the sequence of one or more beams utilized by the user equipment.

[0083] The method may include, in response to determining that the prediction was accurate, transmitting a signal control element command to the user equipment based on the prediction to trigger a beam or cell switch of the user equipment from a first beam at time interval t to a second beam at time interval t+1.

[0084] According to one aspect, a method is provided that includes transmitting measurement data for one or more cells and / or one or more beams of a network to a network node, and receiving from the network node a prediction that includes at least one sequence of one or more beams that are predicted to have the highest signal quality for a device at each one or more time instances, the prediction being based at least in part on the measurement data.

[0085] The method may include receiving an indication from a network node that beam sequence prediction is available, and the transmission is performed in response to receiving the indication that beam sequence prediction is available.

[0086] The at least one sequence may comprise at least a first sequence of one or more beams, which is a sequence of one or more beams predicted to have the highest signal quality for the user equipment at each one or more time instances, and a second sequence of one or more beams, wherein at least one of the one or more beams differs between the first sequence and the second sequence.

[0087] Receiving the prediction may include receiving a confidence interval associated with each sequence of the at least one sequence.

[0088] The confidence intervals can be different for different time instances of the sequence.

[0089] The method may include obtaining further measurement data for at least one of the one or more beams at at least one of the respective one or more time instances, and determining whether the prediction was accurate based on a comparison between the further measurement data and the prediction.

[0090] The method may include, in response to determining that the prediction was inaccurate for at least one of the one or more time instances, transmitting an indication to the network node that the prediction was inaccurate for at least one of the one or more time instances.

[0091] The indication may include an indication that the prediction was inaccurate by more than a confidence interval.

[0092] The indication may include further measurement data for at least one of the one or more beams at one of the one or more time instances in which the prediction was inaccurate.

[0093] The method can include receiving a new prediction from the network node, the new prediction based at least in part on the indication that the prediction was inaccurate.

[0094] The method may include, in response to determining that the prediction was accurate, transmitting to the network node an indication that the prediction was accurate or refraining from transmitting to the network node an indication that the prediction was inaccurate, the network node being configured to consider the prediction to be accurate if the device does not transmit to the network node within a certain time period an indication that the prediction was inaccurate.

[0095] Determining that the prediction was accurate may include determining that the prediction was accurate within a confidence interval.

[0096] The indication that the prediction was accurate may further include information about the trajectory taken by the user equipment.

[0097] The method may include receiving a signal control element command from a network node that triggers a beam switch from a first beam at time interval t to a second beam at time interval t+1, and performing the beam switch based on the signal control element command.

[0098] The method may include, if the prediction is accurate, performing a beam switch from a first beam at time interval t to a second beam at time interval t+1 based on the prediction.

[0099] According to one aspect, a computer-readable medium is provided that includes program instructions to cause an apparatus to at least receive, from a user equipment, measurement data regarding one or more cells and / or one or more beams of a network; determine, based on the measurement data, a prediction including at least one sequence of one or more beams that are predicted to have the highest signal quality for the user equipment at each one or more time instances; and transmit the prediction to the user equipment.

[0100] The program instructions may be for causing the device to transmit an indication to a user equipment that a beam sequence prediction is available to the user equipment, and the receiving is performed in response to transmitting the indication that a beam sequence prediction is available.

[0101] The prediction may include at least a first sequence that is a sequence of one or more beams that are predicted to have the highest signal quality for the user equipment at each one or more time instances, and a second sequence of one or more beams at each one or more time instances, wherein at least one of the one or more beams differs between the first sequence and the second sequence.

[0102] Transmitting the prediction may include transmitting at least one confidence interval associated with each sequence of the at least one sequence.

[0103] The confidence intervals can be different for different time instances of the sequence.

[0104] Determining the prediction can be performed by a machine learning algorithm or an adaptive algorithm.

[0105] The program instructions can be for causing the apparatus to receive, from the user equipment, an indication that the prediction was inaccurate for at least one of the one or more time instances.

[0106] The indication may include an indication that the prediction was inaccurate by more than the confidence interval.

[0107] The indication may include further measurement data for one or more beams at one or more time instances where the prediction was inaccurate.

[0108] The program instructions may cause the device to retrain the model based on the indication.

[0109] The program instructions can be for causing the device to determine a new prediction based at least in part on the indication and to transmit the new prediction to the user equipment.

[0110] The program instructions may be for causing the device to determine that the prediction was accurate.

[0111] Determining that the prediction was accurate may include at least one of receiving an indication from the user equipment that the prediction was accurate or not receiving an indication from the user equipment after a period of time that the prediction was inaccurate.

[0112] Determining that the prediction was accurate may include determining that the prediction was accurate within a confidence interval.

[0113] The indication that the prediction was accurate may further include information regarding the sequence of one or more beams utilized by the user equipment.

[0114] The program instructions may be for causing the device to, in response to determining that the prediction was accurate, and based on the prediction, send a signal control element command to the user equipment that triggers a beam or cell switch of the user equipment from a first beam at time interval t to a second beam at time interval t+1.

[0115] According to one aspect, a computer-readable medium is provided comprising program instructions for causing a device to at least: transmit measurement data regarding one or more cells and / or one or more beams of a network to a network node; and receive a prediction from the network node including at least one sequence of one or more beams predicted to have the highest signal quality to the device at each one or more time instances, the prediction being based at least in part on the measurement data.

[0116] The program instructions may be for causing the device to receive an indication from a network node that beam sequence prediction is available, and the transmission is performed in response to receiving the indication that beam sequence prediction is available.

[0117] The at least one sequence may comprise a first sequence of one or more beams that is a sequence of one or more beams predicted to have the highest signal quality to the user equipment at each one or more time instances, and a second sequence of one or more beams, wherein at least one of the one or more beams differs between the first sequence and the second sequence.

[0118] Receiving the prediction may include receiving a confidence interval associated with each sequence of the at least one sequence.

[0119] The confidence intervals can be different for different time instances of the sequence.

[0120] The program instructions may cause the apparatus to acquire further measurement data for at least one of the one or more beams at at least one of the respective one or more time instances, and determine whether the prediction was accurate based on a comparison between the further measurement data and the prediction.

[0121] The program instructions may be for causing the apparatus to, in response to determining that the prediction was inaccurate for at least one of the one or more time instances, send an indication to the network node that the prediction was inaccurate for at least one of the one or more time instances.

[0122] The indication may include an indication that the prediction was inaccurate by more than a confidence interval.

[0123] The indication may include further measurement data for at least one of the one or more beams at one of the one or more time instances in which the prediction was inaccurate.

[0124] The program instructions can cause the device to receive a new prediction from the network node, the new prediction based at least in part on an indication that the prediction was inaccurate.

[0125] The program instructions may be for causing the device, in response to determining that the prediction was accurate, to send an indication to the network node that the prediction was accurate or to refrain from sending an indication to the network node that the prediction was inaccurate, the network node being configured to consider the prediction to be accurate if the device does not send an indication to the network node that the prediction was inaccurate within a certain period of time.

[0126] Determining that the prediction was accurate may include determining that the prediction was accurate within a confidence interval.

[0127] The indication that the prediction was accurate may further include information about the trajectory taken by the user equipment.

[0128] The program instructions may cause the device to receive a signal control element command from a network node that triggers a beam switch from a first beam at time interval t to a second beam at time interval t+1, and perform the beam switch based on the signal control element command.

[0129] The program instructions may be for causing the apparatus to perform a beam switch from a first beam at time interval t to a second beam at time interval t+1 based on the predicted value if the predicted value is accurate.

[0130] According to one aspect, there is provided a non-transitory computer readable medium comprising program instructions for causing at least an apparatus to perform a method according to any of the above aspects.

[0131] A number of different embodiments have been described above, and it should be understood that any two or more of the above-described embodiments may be combined to provide further embodiments.

[0132] Embodiments will now be described, by way of example only, with reference to the accompanying drawings, in which: [Brief explanation of the drawings]

[0133] [Figure 1] FIG. 1 illustrates a network system according to some example embodiments. [Figure 2] FIG. 1 illustrates a control device according to some illustrative embodiments. [Figure 3] FIG. 1 illustrates an apparatus according to some exemplary embodiments. [Figure 4] FIG. 10 is an exemplary signaling diagram for L1 / 2 inter-cell mobility. [Figure 5] FIG. 1 is an illustration of an exemplary predicted mobility scenario. [Figure 6] FIG. 1 illustrates a method according to some examples. [Figure 7] FIG. 1 illustrates signal exchange according to some examples. [Figure 8] FIG. 1 illustrates signal exchange according to some examples. [Figure 9] FIG. 1 illustrates signal exchange according to some examples. [Figure 10] FIG. 1 illustrates an exemplary neural network architecture. DETAILED DESCRIPTION OF THE INVENTION

[0134] In the following, certain embodiments will be described with reference to mobile communication devices capable of communicating via a wireless cellular system and a mobile communication system providing services to such mobile communication devices. Before describing the exemplary embodiments in detail, certain general principles of wireless communication systems, their access systems, and mobile communication devices will be briefly described with reference to Figures 1, 2, and 3 to facilitate understanding of the technology underlying the described examples.

[0135] Figure 1 shows a schematic diagram of a 5G system (5GS), which can be composed of a terminal or user equipment (UE), a 5G radio access network (5GRAN) or next-generation radio access network (NG-RAN), a 5G core network (5GC), one or more application functions (AFs), and one or more data networks (DNs).

[0136] The 5G-RAN may comprise one or more gNodeB (GNB) distributed unit functions connected to one or more gNodeB (GNB) or one or more gNodeB (GNB) centralized unit functions. The 5G-RAN may comprise the following entities: Network Slice Selection Function (NSSF), Network Exposure Function (NEF), Network Repository Function (NRF), Policy Control Function (PCF), Unified Data Management (UDM), Application Function (AF), Authentication Server Function (AUSF), Access and Mobility Management Function (AMF), and Session Management Function (SMF).

[0137] FIG. 2 illustrates an example of a control device 200 for controlling the functions of the 5GRAN or 5GC shown in FIG. 1 . The control device may include at least one random access memory (RAM) 211a, at least one read-only memory (ROM) 211b, at least one processor 212, 213, and an input / output interface 214. The at least one processor 212, 213 may be coupled to the RAM 211a and the ROM 211b. The at least one processor 212, 213 may be configured to execute appropriate software code 215. The software code 215 may, for example, enable execution of one or more steps for implementing one or more aspects of the present invention. The software code 215 may be stored in the ROM 211b. The control device 200 may be interconnected with another control device 200 that controls another function of the 5GRAN or 5GC. In some embodiments, each function of the 5GRAN or 5GC includes a control device 200. In alternative embodiments, two or more functions of the 5GRAN or 5GC may share a control device.

[0138] FIG. 3 illustrates an example of a terminal 300, such as the terminal illustrated in FIG. 1. The terminal 300 may be provided by any device capable of transmitting and receiving wireless signals. Non-limiting examples include user equipment, a mobile station (MS) or mobile device such as a mobile phone or what is known as a "smartphone," a computer equipped with a wireless interface card or other wireless interface equipment (e.g., a USB dongle), a personal data assistant (PDA) or tablet equipped with wireless communication capabilities, a machine-type communication (MTC) device, an Internet of Things (IoT) type communication device, or any combination thereof. The terminal 300 may provide, for example, communication of data for communication. The communication may be one or more of voice, electronic mail (email), text message, multimedia, data, machine data, etc.

[0139] The terminal 300 can receive signals via an air or wireless interface 307 via suitable equipment for reception and can transmit signals via suitable equipment for transmitting wireless signals. In Fig. 3, a transceiver is indicated schematically by block 306. The transceiver 306 can be provided, for example, by a radio element and an associated antenna arrangement. The antenna arrangement can be located inside or outside the mobile device.

[0140] The terminal 300 may comprise at least one processor 301, at least one memory ROM 302a, at least one RAM 302b, and other executable components 303 for use in software and hardware-assisted execution of tasks it is designed to perform, including controlling access to and communication with access systems and other communication devices. The at least one processor 301 is coupled to the RAM 302b and the ROM 302a. The at least one processor 301 may be configured to execute appropriate software code 308. The software code 308 may, for example, enable one or more of the present aspects to be performed. The software code 308 may be stored in the ROM 302a.

[0141] The processor, memory and other related controls may be provided on a suitable circuit board and / or within a chipset. This feature is indicated by reference numeral 304. The device may optionally have a user interface such as a keypad 305, a touch-sensitive screen or pad, or a combination thereof. Optionally, one or more of a display, a speaker and a microphone may be provided, depending on the type of device.

[0142] The goal in 3GPP is to provide mobility enhancement via L1 / 2 inter-cell mobility. In contrast to the L3 mobility procedure, where handover between two cells is decided by the RRC layer, L1 / 2 inter-cell mobility is implemented / performed by the MAC layer, which is configured by a Centralized Unit (CU) and terminated in a Distributed Unit (DU).

[0143] 4 shows an example implementation of a signaling diagram for L1 / 2 inter-cell mobility from a serving cell of DU1 to a target cell of DU2, where each DU is connected to a central unit (CU), a so-called inter-DU intra-CU scenario. The same diagram can also be applied in the case of an intra-DU intra-CU cell change where DU1 is the same as DU2, i.e., when the handover is from the serving cell of DU1 to the target cell of DU1 (i.e., when the UE remains in the same DU).

[0144] In step 400, the UE sends a measurement report to DU1. In 402, DU1 forwards the measurement report to the CU. In 404a, the CU sends a UE context setup request to DU1 and in 404b to DU2. In response, in 406a, DU1 sends a UE context setup response to the CU, and in 406b, DU2 sends a UE context setup response to the CU.

[0145] At 408, the CU generates an RRC reconfiguration message comprising the configuration of the provisioning cell for the target DU (i.e., DU2) based on the measurement reporting of the L1 cell change. At 410, the CU sends the RRC reconfiguration to the UE, and the UE confirms that the RRC reconfiguration is complete by sending an RRC reconfiguration complete message to the CU at 412.

[0146] In this way, steps 400 to 412 may represent a preparation stage for L1 / 2 inter-cell mobility, in which the network decides to configure potential target cells (within DU2) for L1 / 2 inter-cell mobility based on measurement reporting received from the UE.

[0147] After confirming the RRC reconfiguration to the network in step 412, the UE begins periodically reporting L1 beam measurements of the serving cell and target candidate cells in 414.

[0148] If it is determined that there is a target candidate cell that has better radio link beam measurements than the serving cell (e.g., L1-RSRP of target beam measurements > L1-RSRP of serving beam measurements + offset (e.g., TTT (Time-to-Trigger) time)), then at 416 the serving cell (i.e., DU1) sends a signaling control element (e.g., MAC CE) or an L1 message to trigger a cell change to the target candidate cell.

[0149] A handover from the serving cell to the target cell is performed by the UE in step 418 .

[0150] One of the advantages of L1 inter-cell mobility compared to baseline and conditional handover is that the UE does not need to perform higher layer (RRC, PDCP) reconfiguration and in some scenarios the UE connects to the target cell without using the Random Access Channel procedure, which can significantly reduce interruptions during handover execution and handover / cell change execution times.

[0151] 3GPP TS 38.214 describes a framework for NR beam measurement reporting. In particular, it defines a framework for channel state information (CSI), where the time and frequency resources available to a UE for reporting CSI are controlled by the gNB. CSI can include a channel quality indicator (CQI), a precoding matrix indicator (PMI), a CSI-RS resource indicator (CRI), a SS / PBCH block resource indicator (SSBRI), a layer indicator (LI), a rank indicator (RI), a L1-RSRP, or a L1-SINR. That is, CSI can include L1 measurements.

[0152] CSI reporting can be controlled using a CSI reporting configuration, and each reporting configuration CSI-ReportConfig can be associated with a single downlink BWP (indicated by a higher layer parameter BWP-Id) given by the associated CSI-ResourceConfig for channel measurements. A CSI-ReportConfig can contain parameters for one CSI reporting band, such as codebook configuration including codebook subset restrictions, time-domain operation, frequency granularity of CQI and PMI, measurement restriction configuration, and CSI-related quantities to be reported by the UE, such as Layer Indicator (LI), L1-RSRP, L1-SINR, CRI, and SSBRI (SSB Resource Indicator).

[0153] The time domain behavior of CSI-ReportConfig can be indicated by the higher layer parameter reportConfigType, which can be set to "periodic", "semiPersistentOnPUCCH", "semiPersistentOnPUSCH", or "periodic". For "periodic" and "semiPersistentOnPUCCH" / "semiPersistentOnPUSCH" CSI reporting, the configured periodicity and slot offset can be applied to the numerology of the UL BWP on which the CSI reporting is configured to be transmitted. The higher layer parameter reportQuantity can indicate the CSI-related quantity, L1-RSRP-related quantity, or L1-SINR-related quantity to report.

[0154] Each CSI-ResourceConfig may include a configuration of a list of S≧1 CSI resource sets (given by the higher layer parameter csi-RS-ResourceSetList), where the list consists of references to either or both of NZP CSI-RS resource sets and SS / PBCH block sets, or the list consists of references to CSI-IM resource sets. Each CSI resource configuration may be located in a DL BWP identified by the higher layer parameter BWP-id, and all CSI resource configurations linked to a CSI reporting configuration have the same DL BWP.

[0155] Several goals were agreed upon in the 3GPP Study Item "Study on Artificial Intelligence (AI) / Machine Learning (ML) for NR Air Interface."

[0156] These include use cases focused on enhancing CSI feedback, e.g., reducing overhead and improving accuracy, prediction and beam management, e.g., beam prediction in the time and / or spatial domain for reduced overhead and latency, improving beam selection accuracy, etc.

[0157] Goals for PHY layer aspects are also included, including providing impact on use cases and UE and gNB collaboration level specific specifications, such as new signaling (e.g., AI / ML UE capabilities), signaling aspects for training and validation data assistance, assistance information, measurements, and feedback.

[0158] Another goal is to identify common and specific characteristics for AI / ML models, terminology, and descriptions for a framework study to identify different levels of collaboration between UE and gNB relevant to selected use cases, e.g., different levels of UE / gNB collaboration targeting separate or joint ML operations.

[0159] Mobility management is a method used in wireless communications to ensure service continuity for UEs during their mobility operations by minimizing call drops, RLF, unnecessary handovers, and ping-pong. Furthermore, for applications characterized by stringent QoS requirements such as reliability and latency, QoE may be sensitive to handover performance, so mobility management is required to avoid handover failures and reduce latency during handover procedures.

[0160] However, in some conventional methods, trial and error based schemes may find it difficult to achieve near zero failure handover.

[0161] In RAN3 #110e, RAN research on enhancing data collection in NR and EN-DC was initiated with the general goal of studying high-level principles for the enablement of AI in the RAN and a functional framework including the inputs and outputs required for AI functions and ML algorithms.

[0162] One use case defined in TR37.817 Section 5.3 "Mobility Optimization" aims to improve UE mobility performance using AI / ML solutions. For example, an ML model deployed in the network can receive radio measurements from the UE, predicted resource status of neighboring RAN nodes, and UE trajectory predictions as inputs. These inputs can be used to predict the handover target node in advance, significantly increasing the chances of a successful UE handover.

[0163] UE trajectory predictions are discussed in 3GPP RAN3. These predictions may include the UE's latitude, longitude, altitude, cell ID, and beam ID for a future time period.

[0164] As mentioned above, inter-cell mTRP transmission and L1-centric inter-cell mobility may rely on L1 beam measurement reports (i.e., CSI measurement reports) of serving and non-serving cells.

[0165] The UE can report both serving and non-serving cells as part of its periodic L1 beam measurement reporting. The reporting periodicity is up to 5 ms, allowing the network to collect measurements more frequently from the UE compared to the minimum reporting periodicity of L3 mobility cell / beam quality reporting (120 ms).

[0166] However, L1 beam reporting increases the signaling overhead in the system as well as the power consumption of the UE.

[0167] The signaling overhead on the air interface caused by L1 beam reporting can be mitigated with the help of trajectory prediction.

[0168] In this disclosure, a UE trajectory refers to a particular path / sequence of a UE through the cells and beams of a wireless network and can be characterized by PCI and SSB beam indicators, which can be further refined by CSI-RS based signaling in the network.

[0169] Predicting the future trajectory of the UE can help reduce the number of target cells required to report measurements.

[0170] However, while it may be difficult to perform accurate UE trajectory prediction for a single UE, it may be possible to generate statistical predictions for UE trajectories based on data collected over time (e.g., multiple beam IDs).

[0171] Figure 5 illustrates the problem when a mobile terminal moves along a road with an intersection. Figure 5 shows the beam radiation patterns of each cell and the UE's position for different time steps.

[0172] The problem is that an incorrect orbit prediction at one time instance will reduce the accuracy of future predictions, as the predictions are processed in a cascading manner where the current prediction result aids the next future beam prediction.

[0173] For example, from Figure 5, the network can predict that a UE on a road with a similar previous trajectory will follow cell 1 to cell 2 90% of the time (i.e., the UE will continue straight down the road) and connect to cell 3 10% of the time (i.e., the UE will turn right at the intersection). Then, at each of the time steps [t, t+1, t+2, t+3, t+4, t+5], the network prediction of the optimal future beam index will be [1, 2, 3, 4, 5, 5], which corresponds to the optimal beam for the UE's path that is predicted to continue straight down the road.

[0174] However, if the UE turns to the right path (as shown in Figure 5), the optimal beam index at different time steps will be [1,2,3,6,7,8], as shown in Figure 5. Since the prediction at time step t+3 is incorrect and the ML model uses the predictions at times t, t+1, t+2, and t+3 to perform prediction at time t+4, the prediction at time t+4 is likely to be incorrect. As a result, future predictions will rely on the incorrect prediction, resulting in poor future prediction accuracy.

[0175] In summary, inter-cell lower layer mobility-based beam measurements may increase signaling overhead in the air interface and may require optimization (reduction) without affecting the beam selection error rate. ML approaches based on UE trajectory prediction can be implemented to reduce signaling overhead, but incorrect predictions can lead to mobility failures (e.g., handover failures when the network instructs the UE to connect to beam 5 of cell 2 at time t+4, but due to the UE trajectory change according to the example in Figure 5, the signal quality of beam 7 of cell 3 is better) and increased service interruption times, leading to additional signaling required to process the connection recovery.

[0176] Please refer to FIG. 6, which shows some example methods.

[0177] At 600, the method includes receiving measurement data from a user equipment regarding one or more cells and / or one or more beams of the network.

[0178] At 602, the method includes determining, based on the measurement data, a prediction including at least one sequence of one or more beams predicted to have the highest signal quality for the user equipment at each one or more time instances.

[0179] At 604, the method includes transmitting the prediction to the user equipment.

[0180] At 606, the method includes transmitting, to a network node, measurement data regarding one or more cells and / or one or more beams of the network.

[0181] At 608, the method includes receiving, from the network node, a prediction including at least one sequence of one or more beams predicted to have the highest signal quality for the device at each one or more time instances, the prediction being based at least in part on the measurement data.

[0182] Some embodiments may provide a solution to predict the proper sequence of future beams while reducing signaling overhead without impacting beam selection error rates and mobility failure rates. Some embodiments utilize a predictive inter-cell beam management method to reduce CSI measurement overhead (L1 beam reporting) and avoid mobility failure by ensuring that the network recognizes changes in UE trajectory within a certain confidence margin, e.g., a mean squared error threshold (depending on the scenario, deployment, and configuration).

[0183] In some examples, the network (e.g., a DU for L1 mobility) may predict the optimal next N beam index / RSRP values ​​in time and share the prediction with the UE.

[0184] The prediction output may include the PCI and SSB-RS / CSI-RS indices of the cell. The network can share the new prediction with the UE based on past measurement reporting (e.g., CSI measurement reporting) received from the UE, and potentially with other UEs identified / selected to be along the same UE trajectory or similar geographic movement path (e.g., based on statistical distribution of historical data).

[0185] In some examples, the UE may evaluate the prediction received from the network and trigger CSI measurement reporting for the L1 beam measurement if the prediction for the current time step does not match the UE's current measurements. In some examples, if the predicted value for the current time step matches the UE's current measurements, no measurement report is sent.

[0186] When the network receives the report from the UE, it can refine its previous estimates of future beams based on the indications from the UE, and then perform inference to generate new predictions based on measurement data from the UE.

[0187] If the network prediction is correct, the UE's beam change is managed by the network using the signaling CE beam switch command of the intra-cell beam management or the signaling CE trigger handover message L1 inter-cell mobility. As long as the network prediction of the optimal beam index / L1-RSRP measurement is correct, the UE can perform the beam change.

[0188] Data collected by the network based on incorrect predictions can be used to facilitate model updating / retraining. Thus, the network can store updated measurement data for later model training. In some instances, the network can initiate model updating / retraining. For example, if the network receives frequent incorrect predictions, the network can trigger an update / retraining.

[0189] In some examples, the network can share with the UE not only the best predicted trajectory in the beam domain, but also other possible trajectories for the UE (e.g., the most likely trajectory determined based on other UEs and historical data). For example, in Figure 5, the network can share with the UE both predicted trajectory options [1, 2, 3, 4, 5, 5] and [1, 2, 3, 6, 7, 8]. In this case, the UE can indicate to the network which predicted trajectory option to follow based on actual measurements.

[0190] See FIG. 7 for some example signal exchanges.

[0191] At 700, when an RRC measurement event is triggered, the UE sends a measurement report including measurement results (eg, L3 measurement results) to a serving cell under DU1.

[0192] At 702, DU1 transfers the measurement results to the CU.

[0193] Based on the measurement results, the CU can configure cells under DU1 and DU2 at 704. For example, the CU can send a UE context setup request to DU1 at 704a and to DU2 at 704b. This can be performed by the CU to activate inter-cell beam management / L1 inter-cell mobility.

[0194] In some examples, the UE context setup request may include a request to learn the ML capabilities of the DU and a request to learn whether the DU can perform predictive beam management / L1 mobility.

[0195] Send a UE context setup response to the CU in 706a DU1 and 706b DU2. Optionally, the UE context setup response may include information indicating predictive beam management / L1 mobility capability if requested in 704a and 704b, respectively.

[0196] In some examples, the information may include information regarding the model's required input data, output type, and prediction window (eg, how many beams can be predicted in advance).

[0197] At 708, based on the received cell's predicted beam management / L1 mobility capabilities, the CU generates an RRC reconfiguration and an indication that predictive mobility is enabled. This indication can be performed in the CSI-ReportConfig IE.

[0198] At 710, the CU sends an RRC reconfiguration message to the UE with an indication that predicted mobility is enabled. The network may further include additional information, for example, regarding synchronization points (or events) at which the UE is forced to send L1 measurement reports to ensure that it maintains synchronization / alignment with the network regarding predicted and measured beams.

[0199] At 712, the UE sends an RRC reconfiguration complete message to the CU indicating that the UE has received the RRC reconfiguration.

[0200] At 714, the UE starts reporting N L1-RSRP measurement results of the serving cell and / or non-serving cells as indicated in the RRC-Reconfiguration. The measurement reports may include, for example, beam measurements of configured cells for inter-cell beam management / L1 inter-cell mobility, which can be used by the network (as a seed) for initial prediction.

[0201] At 716, the serving cell under DU1 performs a prediction based on data collected from the UE. The prediction may be to identify the number of cells or beams through which the UE is expected to pass (i.e., the predicted UE trajectory passes through the identified beams).

[0202] For example, at time step t, the network predicts the next 10 optimal beams with a granularity of 10 ms. The granularity of the prediction at each step can also vary in the granularity of the predicted dwell time for each beam index (e.g., because the UE may not move at a uniform speed across the predicted beams).

[0203] The predicted output may include PCI of the cell and SSB-RS / CSI-RS index and / or RSRP value of each SB-RS / CSI-RS. Further details of the ML model output are provided below.

[0204] At 718, the serving cell under DU1 transmits the predicted power, i.e., the prediction of the next best beam index / RSRP value, to the UE.

[0205] As part of the prediction, the network may also transmit a confidence interval for the prediction, which the UE can use to determine whether the network's prediction is within a tolerance margin based on actual measurements.

[0206] For example, if the confidence interval for the RSRP value prediction at time step t+2 is 1 dB, the UE may not trigger reporting if the predicted RSRP value for a beam index at time t+2 differs by less than 1 dB from the measured RSRP value for the same beam index at time t+2. Furthermore, the UE switches to the beam predicted (or suggested) by the network.

[0207] The following steps may depend on the accuracy of the prediction at the UE based on a comparison of UE measurements and network predictions. Three different cases can be considered. Case 1: Incorrect prediction Case 2: Predictive and network-controlled mobility is appropriate. Case 3: Fair Prediction and UE Controlled Mobility

[0208]

[0047] Referring to Figure 8, an exemplary signaling exchange is shown for Case 1 above, i.e., when the prediction is incorrect. The signaling exchange of Figure 8 may follow step 718 described in connection with Figure 7 above.

[0209] The UE performs one or more beam measurements at 800. The UE may not report beam measurements for configured cells as long as the network predictions match the actual measurements.

[0210] The UE can continue to perform measurements of the serving and non-serving cells, but as long as the actual measurements match the network predictions, the UE may not include L1 beam measurements.

[0211] If the network predicts the future best beam index, L1 reporting can be triggered if the predicted best beam index at time t+X is not equal to the measured best beam index at time t+X.

[0212] For example, referring to the example of Figure 5, the network may predict the best beam prediction index as [1,2,3,4,5,5]. At time t+3, the UE may trigger a report to indicate that the predicted beam was incorrect, as the measured best beam belongs to cell 3 and beam 6 (not cell 2 and beam 4), and include the actual measurement in the report.

[0213] In some examples, if the network predicts the best beam measurement (e.g., L1-RSRP), L1 reporting is triggered if the measured beam measurement is not within the confidence interval of the network prediction (as notified by the network when the measurement configuration parameters were provided).

[0214] The network can share a confidence interval (e.g., 95%) with the prediction. The confidence interval can be different for each beam's prediction depending on the statistics of the data collected by the network for that particular beam.

[0215] In some examples, the UE may send a CSI report including KPIs (eg, CQI, PMI, RI, etc.) even if it does not receive any predictions for these KPIs from the network.

[0216] At 802, the UE determines, based on the previously received prediction and the measurements obtained at 800, that there is a discrepancy between the network prediction and the actual measurements.

[0217] At 804, the UE sends an indication to the network that the prediction was incorrect. The indication can include actual measurements performed by the UE that indicate that the network's prediction at time step t+T was incorrect.

[0218] In some examples, an indication may be sent if the discrepancy between the network's prediction and the actual measurement is greater than the confidence interval of the prediction.

[0219] In some examples, if the network performs a prediction of the signal quality value, the UE can share that a mismatch occurred between [t,t] (e.g., t_err). This can indicate to the network how much the prediction needs to be adjusted to obtain more accurate measurement data. In some examples, if t_err is within the confidence interval of the prediction, the UE can ignore the difference, i.e., the UE does not send an indication at 804.

[0220] In some examples where the network performs prediction of signal quality values, the UE may maintain a history of measurements for each beam equal to the length of past training frames N (e.g., 10). If this signal quality prediction for a beam is incorrect, the UE may share historical beam measurements for [tN,t], where t is the current time step.

[0221] At 806, the network may perform model update / retraining based on the indication received from the UE at 804. That is, the network may take action to improve its ML model in response to the erroneous prediction feedback. In some examples, the network may store the indication, optionally including measurement data, for later model training.

[0222] In some examples, the network may initiate a model update (e.g., switch to a different model) / retraining if it receives consecutive incorrect predictions, e.g., more than a certain number of indications, or more than a certain number of indications within a certain period of time.

[0223] At 808, the network shares the new prediction with the UE based on the received measurements.

[0224] In some examples, the DU can also indicate a beam switch as part of a new prediction if the UE's measurements indicate a beam switch. For example, if the network can predict that the UE is observing [1, 2, 2, 2, 2] as the best beam index, but the actual UE measurements indicate [1, 2, 2, 3, 3] as the best beam sequence observed by the UE, the network can send the UE a new prediction that includes a beam switch to beam 3.

[0225]

[0062] Reference is now made to Figure 9, which illustrates an exemplary signal exchange under Cases 2 or 3 above, i.e., when the prediction is correct. The signal exchange of Figure 9 may follow step 718 described in connection with Figure 7 above.

[0226] Steps 900 to 908 correspond to case 2 above, where network predictions are made appropriately and mobility is controlled by the network. It should be understood that in some instances where steps 900 to 908 are performed, steps 910 to 912 may not be performed.

[0227] At 900, the UE performs one or more beam measurements and, based on the measurements, determines that the prediction was correct at 902. For example, the network may predict that at a particular time, such as time t+40 ms (where t is the prediction time step), the UE will observe a particular beam, such as SSB-RS index 5 of PCI 2, as the strongest beam measurement. Based on the prediction, the UE verifies the prediction by performing beam measurements at the particular time, such as time step t+40 ms, and determining that the particular beam, such as SSB-RS index 5 of PCI 2, is the strongest beam index.

[0228] Optionally, the UE may transmit an indication regarding the status of the prediction, at 904. For example, the UE may transmit an indication of whether the prediction was correct or not.

[0229] In some instances, a one-bit indication can be used to indicate that the network prediction was accurate, allowing the network to trigger a beam switch based on the prediction.

[0230] In some examples, if the network prediction is still within the confidence interval, the UE may transmit information regarding the discrepancy between the network prediction and the UE measurements.

[0231] If multiple trajectories are shared with the UE, the UE may also include information regarding the trajectory to be followed along with the indication.

[0232] At 906, the network determines that the prediction was correct.

[0233] For example, the network may receive 904 an indication that the prediction was correct (e.g., a 1-bit indication, an indication having a length of k bits, where k≧1, an indication providing at least two different values ​​referring to a correct or incorrect prediction, an indication providing a likelihood p that the UE is still on the predicted path, where likelihood p≧thres1 indicates a correct predicted path and thres2 indicates an incorrect predicted path). Alternatively, if the UE is configured to report L1-RSRP beam measurements only if the prediction is incorrect, the network may assume that the prediction at time step t+40 ms was correct, assuming the UE has not indicated that it was incorrect at time step t+40 ms.

[0234] At 908, the serving cell sends a signaling CE (e.g., MAC CE) command to the UE to trigger a beam / cell switch.

[0235] In some examples, the signaling CE command is sent when the network determines that the prediction at time step t is not equal to the prediction at time step t+1 (t!=t+1), i.e., there is a network-determined beam switch event.

[0236] At 910, the UE acknowledges the beam switch.

[0237] In some examples, if the measurements at time t+X do not match the predicted values ​​at time t+X, the UE may reject the beam switch and the UE may notify the network of the actual measurements regarding the current beam.

[0238] Step 912 corresponds to case 3 above, where network predictions are correct and mobility is controlled by the UE. It should be understood that in some instances where step 912 is performed, steps 900 through 910 may not be performed.

[0239] At 912, a beam switch / change is determined by the UE based on the prediction received from the network. That is, the beam switch may be determined by the UE without receiving a signaling CE message from the network for execution. In some examples, the UE may decide to perform a beam switch in response to determining that the actual beam measurements match the network prediction.

[0240] At 914, the UE performs a beam switch operation in response to receiving the signaling CE command at 908 or in response to the UE determining to perform a beam switch at 912.

[0241] For example, the UE may determine whether the predicted beam at time step t+1 belongs to the beam of the preparation / target cell. If the UE determines that the predicted beam at time step t+1 belongs to the beam of the preparation / target cell, it may perform a random access procedure to access the target beam of the preparation / target cell to complete the beam switch.

[0242] At 916, the UE indicates to the network that the beam switch operation was successfully performed. The UE can provide the indication using an L1 / L2 ACK in the uplink of the new beam after successfully decoding the PDCCH in the previous serving beam.

[0243] As mentioned above, in some examples, the network may also share different trajectories with the UE. For example, the network may share the trajectories as a sequence of beam IDs, and thus two trajectories may be indicated as two sequences of beam IDs (e.g., the first trajectory is [1, 2, 3, 4, 5, 5] and the second trajectory is [1, 2, 3, 6, 7, 8]).

[0244] In some examples, the beams and cells indicated in the trajectory may be provisioned by the network, i.e., the network expects the UE to connect to the beam specified by the trajectory.

[0245] In some examples, as long as the UE follows a trajectory included in the trajectory list, the UE does not send reports about its serving or neighboring beam measurements to the network, but the UE can provide channel state information, such as beam precoding information, to the network as needed.

[0246] In some examples, the UE can switch to a new beam according to the trajectory using the means described above, for example, the network can provide signaling CE at a predicted time, or the UE can indicate that the time to switch is imminent via an indicator.

[0247] If the UE wants to select a cell / beam that is not in the orbit list, the UE may start transmitting a complete neighbor beam / cell measurement reporting.

[0248] In some examples, the network can indicate a ranking of the trajectory list. The ranking can indicate that the first trajectory in the list has prepared cells, while the cells of the other trajectories are not prepared. If the UE determines that it is not following the first trajectory, the UE can indicate to the network the corresponding index in the trajectory list to follow.

[0249] For example, in the given example of a first trajectory as [1, 2, 3, 4, 5, 5] and a second trajectory as [1, 2, 3, 6, 7, 8], both trajectories have the first three beams [1, 2, 3,] in common. When the UE recognizes that it will not proceed to 4 after beam / cell 3 but will proceed to 6, the UE indicates to the network that it is "selecting trajectory 2." In response to receiving the indication, the network can prepare cells / beams along the second trajectory for the UE and send an indication to the UE that the cells / beams along trajectory 2 are prepared. After receiving confirmation from the network, the UE can consider the cells of Path 2 to be prepared.

[0250] In some instances, an ML model may not be necessary: ​​the network can obtain a list of trajectories by collecting serving cell / beam sequences from past UEs and rank them according to their frequency of occurrence (e.g., which beam follows after the UE is connected to beam A).

[0251] In some cases, inter-cell HO can also be organized by a pre-configured RACH grant, in which case the network does not need to send signaling CE to trigger the UE change, and the UE initiates the HO (e.g., case 3).

[0252] As explained above, in some examples, an ML framework can be utilized to predict the trajectory of a UE and identify the number of cells or beams that the UE is expected to move in. That is, an ML model in the network can be used to perform prediction of the optimal beam index and cell ID for a given UE to connect to a cell.

[0253] For example, the model may generate the best predicted SSB-RS index and physical cell ID (PCI) output for the base UE at time step t based on past measurements. In some examples, a Long Short-Term Memory (LSTM) network may be applied to predict the future from variable-length sequences. LSTM networks may be preferred for time series prediction due to their ability to learn long-term relationships in data, and by introducing special gates (e.g., forget gates, input gates), they can solve problems related to the vanishing gradient problem in RNNs.

[0254] An example of the neural network architecture of the model is shown in Figure 10.

[0255] Input Matrix JPEG2025528674000002.jpg6150 has D features, i.e. JPEG2025528674000003.jpg6150 (e.g., input type) over T times in the past, where t is the time of prediction and i is the UE id (e.g., C-RNTI).

[0256] The size of the input matrix may depend on the granularity of the input, e.g., 100 ms of time over T (e.g., 1 second may result in 10 stacked input features D), and the number of features, i.e., D.

[0257] In Figure 10, there are two LSTM layers followed by a softmax output layer. It should be understood that in other examples, different configurations can be used. Each LSTM cell takes as input the input JPEG2025528674000004.jpg6150 received, cell status Generates JPEG2025528674000005.jpg6150, a hidden state value that can be used for another LSTM cell. Outputs JPEG2025528674000006.jpg6150.

[0258] The sigmoid activation function σ can be used for the input and output gates of an LSTM cell. The output value of the sigmoid function can be in the range of 0 to 1. The tanh activation is JPEG2025528674000007.jpg6150 and hidden state It can be used for JPEG2025528674000008.jpg6150 and can produce output values ​​in the range of -1 to 1. The output layer can use a softmax or sigmoid activation function to calculate the probability of each label, e.g., the probability that the beam / cell is the best beam / cell at time t+T.

[0259] The input data for the model is the following information: UE measurement reports, e.g., RSRP, RSRQ or SINR measurements -Good prediction from previous time step UE velocity information (e.g., calculated based on observed Doppler shift) UE location information (optionally, if available) Current / predicted resources of serving cell and neighboring cells (optional, if available) The UE measurement reports can help the network understand the channel degradation over time and can be used for initial predictions. As long as the model predictions are correct (verified by the UE), the network may not need to use / send / consider / evaluate the UE measurement reports.

[0260] The correct prediction may include the optimal beam index and PCI. The network can use the previous prediction as the ground truth to predict the future, as long as the model prediction is verified as correct according to the information provided by the UE.

[0261] The UE location information may include the coordinates and velocity of the UE.

[0262] The current / predicted resources of the serving cell and neighboring cells can be used by the model to understand traffic load information on different beams / cells that can affect inter-cell / beam interference, and the best beam index / RSRP observed by the UE.

[0263] The model can perform multi-step predictions, i.e., the model can use predictions in previous steps as input for future predictions.

[0264] Based on the input data, the model can perform at least the following types of predictions: Prediction of best beam index and PCI for a given UE Prediction of RSRP values ​​for configured reference signal indexes of cells

[0265] To predict the best beam index and PCU, the ML model calculates the output vector for prediction at time t+T. This will generate JPEG2025528674000009.jpg6150, where JPEG2025528674000010.jpg6150 is the best SSB-RS index, JPEG2025528674000011.jpg6150 is the physical cell ID of UEi at time t+T. where: JPEG2025528674000012.jpg6150 Note that the output is relative to JPEG2025528674000013.jpg6150, e.g., the beam of PCI. In the case of multi-step prediction, the output is JPEG2025528674000014.jpg6150, where g is the prediction granularity (e.g., 100 ms), and Ng = T. Thus, if T is 1000 ms and g is 100 ms, the ML model can generate 10 predictions representing the optimal beam / cell pair for UEi.

[0266] To predict the RSRP value, the ML model uses the output vector can generate JPEG2025528674000015.jpg6150, where JPEG2025528674000016.jpg6150 is a prediction of the RSRP value of the SSB-RS beam index at t+T of cell IDc. JPEG2025528674000017.jpg6150 is the estimated RSRP measurement for SSB-RS index 0 of cell c observed by UEi at time step t+T. In the case of multi-step prediction, the output is JPEG2025528674000018.jpg6150, where g is the granularity of the prediction (e.g., 100 ms), and Ng=T.

[0267] For training the model, the above input data and UE feedback can be logged over time and collected at the network entity that performs the training. Beam management, including both intra-cell and inter-cell beam management, can be handled by the gNB or gNB-Distributed Unit, and inference can also be performed at the gNB or gNB-DU.

[0268] As an example use case, the scenario in Figure 5 can be assumed, where cell 1 performs a prediction of the best beam index for the UE at time step t as {t:1, t+1:2, t+2:3, t+3:4, t+4:5, t+5:5}.

[0269] The UE continues to move along the street and perform measurements of serving and non-serving cells, but as long as the predictions are correct, the UE does not start reporting.

[0270] At time step t+3, the UE turns right onto the street and measures beam ID6 from cell 3 as the strongest beam. The UE compares the actual measurement with the network prediction at time step t+3, which indicates beam ID4.

[0271] If the network prediction is incorrect, the UE indicates the incorrect prediction to the network along with other beam measurements at time step t+3. Based on the correct measurements received at time step t+3, e.g., {t:1, t+1:2, t+2:3, t+3:6}, the network updates the prediction to take into account the UE's trajectory, predicts the next beam index to be 7 at t+4 and 8 at t+5, and notifies the UE of the new prediction.

[0272] In this way, in some examples, an adaptive inter-cell beam management procedure is provided with reduced CSI measurement overhead. The network can collect feedback on its predictions (receive ground truth from the UE) and retrain the model. This can mean that a network-driven ML approach can be utilized, eliminating the need to implement UE ML capabilities. In the case of multi-step predictions, the network can use only previous correct predictions as input for the next prediction, and the methods described above allow the network to avoid erroneous consecutive predictions that can lead to mobility failures and high interruption times.

[0273] In some cases, an apparatus is provided that includes means for receiving measurement data from a user equipment regarding one or more cells and / or one or more beams of a network; means for determining, based on the measurement data, a prediction including at least one sequence of one or more beams that are predicted to have the highest signal quality for the user equipment at each one or more time instances; and means for transmitting the prediction to the user equipment.

[0274] In some examples, the apparatus may include at least one processor and at least one memory including computer program code, the at least one memory and the computer program code configured to cause the apparatus, using the at least one processor, to at least perform the following: receive measurement data from a user equipment regarding one or more cells and / or one or more beams of the network; determine, based on the measurement data, a prediction including at least one sequence of one or more beams that are predicted to have the highest signal quality for the user equipment at each one or more time instances; and transmit the prediction to the user equipment.

[0275] In some cases, an apparatus is provided that includes means for transmitting measurement data regarding one or more cells and / or one or more beams of the network to a network node, and means for receiving from the network node a prediction including at least one sequence of one or more beams that are predicted to have the highest signal quality for the apparatus at each one or more time instances, wherein the prediction is based at least in part on the measurement data.

[0276] In some examples, the device may include at least one processor and at least one memory including computer program code, the at least one memory and the computer program code configured to cause the device, using the at least one processor, to at least: transmit measurement data related to one or more cells and / or one or more beams of the network to a network node; and receive from the network node a prediction including at least one sequence of one or more beams predicted to have the highest signal quality to the device at each one or more time instances, the prediction being based at least in part on the measurement data.

[0277] It should be understood that the device may comprise or be coupled to other units or modules, such as radio components or radio heads used in or for transmitting and / or receiving. Although the device has been described as one entity, the different modules and memories may be implemented in one or more physical or logical entities.

[0278] It should be noted that although some embodiments have been described in the context of 5G networks, similar principles may be applied in the context of other networks and communication systems. Thus, although particular embodiments have been described above by reference to particular example architectures for wireless networks, technologies, and standards, the embodiments may be applied to any other suitable form of communication system other than those illustrated and described herein.

[0279] Also, although exemplary embodiments have been described above, it should be noted herein that there are several variations and modifications that can be made to the disclosed solution without departing from the scope of the present invention.

[0280] In general, various embodiments may be implemented in hardware or special purpose circuits, software, logic, or any combination thereof. While some aspects of the present disclosure may be implemented in hardware, other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor, or other computing device, although the present disclosure is not limited thereto. Although various aspects of the present disclosure may be illustrated and described as block diagrams, flowcharts, or using some other graphical representation, it is well understood that these blocks, apparatus, systems, techniques, or methods described herein may be implemented in, by way of non-limiting example, hardware, software, firmware, special purpose circuits or logic, general purpose hardware or controller or other computing device, or any combination thereof.

[0281] As used herein, the term "circuit" may refer to one or more or all of the following: (a) hardware-only circuit implementations (e.g., implementations in analog and / or digital circuitry only); (b) a combination of hardware circuitry and software, such as: (i) a combination of analog and / or digital hardware circuitry and software / firmware; and (ii) any portion of software (including digital signal processors), hardware processors with software and memory that operate as a whole to cause a communications device and / or device and / or server and / or network entity to perform the various functions described above; and (c) A hardware circuit and / or processor, e.g., a microprocessor or portion of a microprocessor, that requires software (e.g., firmware) for operation, but where software is not required for operation, may be absent.

[0282] This definition of circuit applies to all uses of the term in this application, including any claims. As a further example, the term "circuit," as used in this application, covers implementations of simply a hardware circuit or processor (or processors), or a portion of a hardware circuit or processor and its (or their) accompanying software and / or firmware. The term circuit also covers, for example, and where applicable to certain claim elements, baseband or processor integrated circuits for mobile devices, or similar integrated circuits in servers, cellular network devices, or other computing or network devices.

[0283] Embodiments of the present disclosure may be implemented by computer software executable by a data processor of a mobile device, such as in a processor entity, or by hardware, or by a combination of software and hardware. Computer software or programs, also referred to as program products, including software routines, applets, and / or macros, may be stored on any device-readable data storage medium and comprise program instructions for performing specific tasks. A computer program product may comprise one or more computer-executable components configured to execute in an embodiment when the program is executed. The one or more computer-executable components may be at least one software code or portion thereof.

[0284] Further in this regard, it should be noted that any block of the logic flow as shown may represent a program step, or interconnected logic circuits, blocks and functions, or a combination of program steps and logic circuits, blocks and functions. Software may be stored on physical media such as memory chips or memory blocks implemented within a processor, magnetic media such as hard disks or floppy disks, and optical media such as DVDs and their data variants, CDs. Physical media is non-transitory.

[0285] The memory may be of any type suitable for the local technology environment and may be implemented using any suitable data storage technology, such as semiconductor-based memory devices, magnetic memory devices and systems, optical memory devices and systems, fixed and removable memory, etc. The data processor may be of any type suitable for the local technology environment and may comprise, by way of non-limiting examples, one or more of a general purpose computer, a special purpose computer, a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), an FPGA, a gate level circuit, and a processor based on a multi-core processor architecture.

[0286] Embodiments of the present disclosure can be implemented in a variety of components, such as integrated circuit modules. The design of integrated circuits is, for the most part, a highly automated process. Complex and powerful software tools are available for converting logic-level designs into semiconductor circuit designs that can be etched onto semiconductor substrates.

[0287] The scope of protection sought for various embodiments of the present disclosure is defined by the independent claims. Where embodiments and features not falling within the scope of the independent claims are described in this specification, they are to be construed as examples useful for understanding various embodiments of the present disclosure.

[0288] The foregoing description provides a complete and informative description of exemplary embodiments of the present disclosure, by way of non-limiting examples. However, various modifications and adaptations may become apparent to those skilled in the relevant art in light of the foregoing description, when read in conjunction with the accompanying drawings and the appended claims. However, all such and similar modifications of the teachings of the present disclosure remain within the scope of the present invention, as defined by the appended claims. Indeed, further embodiments exist that comprise one or more of the embodiments in combination with any of the other embodiments previously described. [Explanation of symbols]

[0289] 700 Measurement Reports 702 Measurement Report 704a UE context setup request 706a UE Context Setup Response 704b UE context setup request 706b UE context setup response 708 RRC reconstruction generation 710 RRC reconfiguration message + predictive mobility enabled 712 RRC reconfiguration completed 714 Measurement Report 716 Predictions 718 Prediction Output

Claims

1. means for receiving, from a user equipment, measurement data relating to one or more cells and / or one or more beams of the network; means for determining, based on the measurement data, a prediction comprising at least one sequence of one or more beams predicted to have the highest signal quality for the user equipment at each one or more time instances; means for transmitting the prediction to the user equipment; An apparatus comprising:

2. 2. The apparatus of claim 1, wherein the prediction comprises at least a first sequence of one or more beams, the first sequence being the sequence of one or more beams predicted to have the highest signal quality to the user equipment at the respective one or more time instances, and a second sequence of one or more beams at the respective one or more time instances, wherein at least one of the one or more beams differs between the first sequence and the second sequence.

3. The means comprises: An apparatus according to any preceding claim, for receiving an indication from the user equipment that a prediction was inaccurate for at least one of the one or more time instances.

4. The means comprises: The apparatus of claim 4 , further comprising: a processor configured to: perform retraining of a model based on the indication;

5. The means is: determining a new prediction based at least in part on said indication; and 5. Apparatus according to claim 3 or 4, for transmitting said new prediction to said user equipment.

6. The means comprises: Apparatus according to any one of claims 1 to 2, for determining that the prediction was accurate.

7. Determining that the prediction was accurate includes: receiving an indication from the user equipment that the prediction was accurate; or not receiving an indication from the user equipment that the prediction was inaccurate after a period of time; 7. The apparatus of claim 6, comprising at least one of:

8. 8. The apparatus of claim 7, wherein the indication that the prediction was accurate further includes information regarding a sequence of one or more beams utilized by the user equipment.

9. The means comprises:

9. The apparatus of claim 6, wherein, in response to determining that the prediction was accurate, the apparatus is configured to transmit a signal control element command to the user equipment to trigger a beam or cell switch of the user equipment from a first beam at time interval t to a second beam at time interval t+1 based on the prediction.

10. 1. An apparatus comprising: means for transmitting measurement data relating to one or more cells and / or one or more beams of the network to a network node; means for receiving from the network node a prediction comprising at least one sequence of one or more beams predicted to have the highest signal quality to the device at a respective one or more time instances, the prediction being based at least in part on the measurement data; and An apparatus comprising:

11. 11. The apparatus of claim 10, wherein the at least one sequence comprises at least a first sequence of one or more beams that is a sequence of one or more beams predicted to have the highest signal quality to the user equipment at the respective one or more time instances, and a second sequence of one or more beams, wherein at least one of the one or more beams differs between the first sequence and the second sequence.

12. The means comprises: acquiring further measurement data for at least one of the one or more beams at at least one of the respective one or more time instances; and determining whether the prediction was accurate based on a comparison between the further measurement data and the prediction; The device according to any one of claims 10 to 11, for

13. The means comprises: in response to determining that the prediction was inaccurate for at least one of the one or more time instances, transmitting an indication to the network node that the prediction was inaccurate for at least one of the one or more time instances; The device according to claim 12, for

14. In response to determining that the prediction was accurate, the means: sending an indication to the network node that the prediction was accurate; or refraining from sending an indication to the network node that the prediction was inaccurate, the network node being configured to assume that the prediction was accurate if the device does not send an indication to the network node that the prediction was inaccurate within a certain time period; The device according to claim 12, for

15. The means comprises: receiving a signal control element command from the network node to trigger a beam switch from a first beam at time interval t to a second beam at time interval t+1; and performing a beam switch based on said signal control element command; 15. The device according to claim 14,

16. The means comprises: performing a beam switch from a first beam at time interval t to a second beam at time interval t+1 based on the prediction if the prediction is accurate; 16. The device according to any one of claims 14 to 15, for

Images