Method and apparatus used in wireless communication

Abstract

Disclosed in the present application are a method and apparatus used in wireless communication. The method comprises: a first node receiving a first RRC message, which comprises a configuration for at least one candidate handover cell; executing both first prediction and second prediction, wherein a result of the first prediction indicates that a condition for performing a handover to a first cell is met within a first time window, and a result of the second prediction indicates that a radio link failure occurs within a second time window; and executing a first action on the basis of a time-domain position relationship between the first time window and the second time window, wherein the at least one candidate handover cell comprises the first cell, and when the start time of the first time window is earlier than the start time of the second time window, the first action is starting to apply a stored configuration for the first cell at a first moment. The present application can effectively support a prediction-based cell handover, thereby avoiding a radio link failure.

Description

A method and apparatus for use in wireless communication

[0001] This application claims priority to Chinese Patent Application No. 202411934345.4, filed on December 25, 2024, entitled "A Method and Apparatus for Wireless Communication", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to methods and apparatus in wireless communication systems, and more particularly to methods and apparatus for mobility management and wireless link management based on AI (Artificial Intelligence) in wireless communication systems. Background Technology

[0003] The application scenarios of future wireless communication systems are becoming increasingly diversified, and different application scenarios place different performance requirements on the system. In order to meet the different performance requirements of various application scenarios, the 3GPP (3rd Generation Partner Project) RAN (Radio Access Network) #72 plenary meeting decided to study New Radio (NR) (or 5G). The 3GPP RAN #75 plenary meeting adopted the WI (Work Item) for New Radio technology and began the standardization work for NR.

[0004] Cell handover provides effective mobility support. The basic requirements for cell handover are to reduce handover latency, minimize the impact on latency-sensitive services, and improve the success rate of cell handover. In order to adapt to diverse application scenarios and meet different needs, 3GPP has been evolving cell handover technology, including but not limited to the introduction of Conditional Handover (CHO) in NR Release 17 and the introduction of L1 / L2-Triggered Mobility (LTM) based mobility enhancement technology in NR Release 18.

[0005] In NR Release 18, research on AI technology was initiated to explore its impact on system performance and design. Compared to measurement-based processing in traditional wireless communication systems, AI-based processing relies heavily on prediction, posing different requirements for system design. AI is also a key candidate technology for future 6G communication. Summary of the Invention

[0006] The inventors discovered through research that, after introducing AI or other predictive functions into wireless communication systems, how to effectively design and optimize cell handover management and wireless link management together is a problem that needs to be solved in the post-5G and 6G era.

[0007] To address the aforementioned problems, this application discloses a solution. Unless otherwise specified, the embodiments and features described in this application can be arbitrarily combined. While this application is initially intended for AI-based prediction system design, it can also be used for system design based on non-AI prediction algorithms, such as DSP (Digital Signal Processing) systems. Furthermore, although this application is initially intended for the joint design of cell handover management and radio link management, it can also be used for joint design of cell handover management and beam management, mobility management design, CSI (Channel Status Information) compression design, and other scenarios. Moreover, adopting a unified solution for different scenarios helps reduce hardware complexity and cost, and reduces standardization work. In particular, the interpretation of terms, nouns, functions, and variables in this application (unless otherwise specified) can be found in the definitions in the 3GPP specification protocols TS38 series, TS37 series, and future 6G standards.

[0008] This application discloses a method used in a first node of wireless communication, comprising:

[0009] Receive a first RRC message, the first RRC message including configuration for at least one handover candidate cell;

[0010] The first prediction and the second prediction are performed respectively. The result of the first prediction is that the handover conditions to the first cell are met within the first time window, and the result of the second prediction is that a radio link failure occurs within the second time window.

[0011] The first action is executed based on the temporal positional relationship between the first time window and the second time window;

[0012] Wherein, the at least one handover candidate cell includes the first cell; the first action is to start applying the stored configuration for the first cell at a first moment, or to send a first report; when the start time of the first time window is earlier than the start time of the second time window, the first action is to start applying the stored configuration for the first cell at the first moment; when the start time of the first time window is later than the start time of the second time window, the first action is to send the first report.

[0013] As an example, the first RRC (Radio Resource Control) message includes configuration parameters for cell handover triggered by the UE (User Equipment).

[0014] As an example, the first prediction is used for cell handover management.

[0015] As an example, the second prediction is used for wireless link management.

[0016] As an example, the first prediction is based on at least one of the measured RSRP (Reference Signal Received Power), RSRQ (Reference Signal Received Quality), or SINR (Signal to Interference & Noise Ratio).

[0017] As an example, the second prediction is based on at least one of the measured RSRP, RSRQ, or SINR.

[0018] As an example, both the first prediction and the second prediction are time-domain predictions, meaning that future predictions are inferred from at least the current measurements.

[0019] As an example, the first prediction and the second prediction are two independent predictions, including: the first prediction and the second prediction are implemented by two different models, or the first prediction and the second prediction are implemented by two different sets of model parameters; or the first prediction and the second prediction have two different associated IDs.

[0020] As an example, in traditional wireless communication systems, measurement and triggering mechanisms are designed for cell handover and radio link failure, respectively, and the two functions operate independently. However, when the cell handover is performed too late, it will cause radio link failure, which will have a significant impact on UE services.

[0021] As an example, predictions typically reflect statistical characteristics, such as the probability of an event occurring. The output based on the prediction is valid within a time window. When a cell handover triggered by the UE is performed, if the determination of whether the cell handover conditions are met is based on the prediction, the UE needs to determine the specific time to perform the cell handover within a time window in which the handover conditions are met.

[0022] As an example, combining the results of the first prediction and the second prediction can provide more information, enabling the first node to flexibly execute the first action.

[0023] As an example, performing the first action by combining the results of the first prediction and the second prediction can improve link reliability, reduce service interruption time, and improve the user experience for UEs.

[0024] As an example, determining the first action based on the temporal positional relationship between the first time window and the second time window can, on the one hand, avoid performing cell handover too late and causing radio link failure; on the other hand, it can send a report in a timely manner so that the network can respond promptly, such as sending a handover command, to avoid radio link failure.

[0025] According to one aspect of this application, the above method is characterized by:

[0026] The first moment is not earlier than the start time of the first time window and not later than the earlier of the end time of the first time window and the start time of the second time window.

[0027] As an example, the above method can perform cell handover in a timely manner, avoiding radio link failure due to late cell handover.

[0028] According to one aspect of this application, the above method is characterized by:

[0029] The first report was sent earlier than the start time of the second time window.

[0030] As an example, the above method can report in a timely manner, thus avoiding wireless link failures.

[0031] According to one aspect of this application, the above method is characterized by:

[0032] The first prediction output is the probability that the handover condition to the first cell is met within a time window; when the probability that the handover condition to the first cell is met within the first time window is greater than a first threshold, it is predicted that the handover condition to the first cell will be met within the first time window.

[0033] As an example, the first prediction is a direct prediction.

[0034] As an example, the direct prediction output is the probability of an event occurring within a future time window; when the probability of occurrence is greater than a threshold, the occurrence of the event is predicted.

[0035] In this application, unless otherwise stated, direct prediction and direct measurement event prediction can be used interchangeably.

[0036] According to one aspect of this application, the above method is characterized by:

[0037] The first prediction includes: predicting at least one of the channel quality of the first cell and the channel quality of the second cell; and predicting that the handover condition to the first cell is met within the first time window when any one of the at least one conditions at the second time point is met.

[0038] Wherein, the first time window is a time window formed by shifting the second time point forward along the time axis by a first time length to shifting the second time point backward along the time axis by the first time length; the at least one condition includes the channel quality of the first cell being better than the channel quality of the second cell by more than a second threshold; the second cell is a serving cell.

[0039] As an example, the first prediction is an indirect prediction.

[0040] As an example, indirect prediction first infers future predicted values ​​based on measured values, and then determines that an event will occur at some point in the future based on at least the latter of the measured values ​​and the predicted values. Since the predicted values ​​are probabilistic, extending the certain point in time to a time window centered on that point in time can improve the rationality and effectiveness of prediction-based system design.

[0041] In this application, unless otherwise stated, indirect prediction and indirect measurement event prediction can be used interchangeably.

[0042] As an example, the first time length is related to the performance of the first prediction.

[0043] According to one aspect of this application, the above method is characterized by:

[0044] The output of the second prediction is the probability of a wireless link failure occurring within a time window; when the probability of a wireless link failure occurring within the second time window is greater than a third threshold, a wireless link failure is predicted to occur within the second time window.

[0045] As an example, the second prediction is a direct prediction.

[0046] According to one aspect of this application, the above method is characterized by:

[0047] The second prediction includes: measuring a first reference signal resource and predicting future wireless link quality based on the measured wireless link quality; and predicting whether a wireless link failure will occur within a first timer duration based on at least the latter of the measured wireless link quality and the predicted wireless link quality.

[0048] As an example, the second prediction is an indirect prediction.

[0049] As an example, the first timer is T310.

[0050] As an example, the above method is backward compatible with existing technologies, can effectively support existing terminals, and can simplify standards.

[0051] According to one aspect of this application, the above method is characterized by:

[0052] If no K consecutive wireless link qualities are higher than the fourth threshold within the duration of the first timer, a wireless link failure is predicted to occur within the second time window.

[0053] The second time window is formed by shifting the expiration time of the first timer forward along the time axis by a second time length to shifting the expiration time of the first timer backward along the time axis by a second time length.

[0054] As an example, K is a positive integer.

[0055] According to one aspect of this application, the above method is characterized by:

[0056] The first report includes at least one of the performance monitoring results of the first prediction and the performance monitoring results of the second prediction; wherein the first prediction and the second prediction are respectively based on AI.

[0057] As an example, the AI ​​includes at least one of AI or ML (Machine Learning).

[0058] This application discloses a first node used for wireless communication, comprising:

[0059] A first transceiver receives a first RRC message, the first RRC message including configuration for at least one handover candidate cell; performs a first prediction and a second prediction respectively, the result of the first prediction being that the handover conditions to the first cell are met within a first time window, and the result of the second prediction being that a radio link failure occurs within a second time window; and performs a first action according to the temporal positional relationship between the first time window and the second time window.

[0060] Wherein, the at least one handover candidate cell includes the first cell; the first action is to start applying the stored configuration for the first cell at a first moment, or to send a first report; when the start time of the first time window is earlier than the start time of the second time window, the first action is to start applying the stored configuration for the first cell at the first moment; when the start time of the first time window is later than the start time of the second time window, the first action is to send the first report.

[0061] This application discloses a method used in a first node of wireless communication, comprising:

[0062] Receive a first RRC message, the first RRC message including configuration for at least one handover candidate cell;

[0063] The first prediction and the second prediction are performed respectively. The result of the first prediction is that the handover conditions to the first cell are met within the first time window, and the result of the second prediction is that a radio link failure occurs within the second time window.

[0064] The stored configuration for the first cell is applied at a first moment; wherein the at least one handover candidate cell includes the first cell; the start time of the first time window is earlier than the start time of the second time window; the first moment is not earlier than the start time of the first time window and not later than the earlier of the end time of the first time window and the start time of the second time window.

[0065] This application discloses a first node used for wireless communication, comprising:

[0066] A first transceiver receives a first RRC message, the first RRC message including configuration for at least one handover candidate cell; performs a first prediction and a second prediction respectively, the result of the first prediction being that the handover conditions to the first cell are met within a first time window, and the result of the second prediction being that a radio link failure occurs within a second time window; and applies the stored configuration for the first cell starting at a first moment.

[0067] Wherein, the at least one handover candidate cell includes the first cell; the start time of the first time window is earlier than the start time of the second time window; the first moment is not earlier than the start time of the first time window, and not later than the earlier of the end time of the first time window and the start time of the second time window.

[0068] This application discloses a terminal, comprising: one or more processors and a memory;

[0069] The memory is coupled to the one or more processors and is used to store computer program code, which includes computer instructions. The one or more processors invoke the computer instructions to cause the terminal to execute the method described above in the first node. Attached Figure Description

[0070] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0071] Figure 1 illustrates a signal transmission flowchart of a first node according to an embodiment of this application;

[0072] Figure 2 illustrates a schematic diagram of a network architecture according to an embodiment of this application;

[0073] Figure 3 illustrates a schematic diagram of the wireless protocol architecture of the user plane and control plane according to an embodiment of this application;

[0074] Figure 4 illustrates a schematic diagram of the hardware modules of a communication device according to an embodiment of this application;

[0075] Figure 5 illustrates a flowchart of wireless signal transmission according to an embodiment of this application;

[0076] Figure 6 illustrates a flowchart of wireless signal transmission according to an embodiment of this application;

[0077] Figure 7 illustrates a signal processing flowchart in a first node according to an embodiment of this application;

[0078] Figure 8 illustrates a schematic diagram of the relationship between a first time window and a second time window at a first moment according to an embodiment of this application;

[0079] Figure 9 illustrates a schematic diagram of the relationship between the first time window and the second time window in sending a first report according to an embodiment of this application;

[0080] Figure 10 illustrates a schematic diagram showing the relationship between the execution of a first prediction, a second moment, a first time window, and a first time length according to an embodiment of this application;

[0081] Figure 11 illustrates a schematic diagram of the relationship between the second prediction, the first timer, the second time window, and the second time length according to an embodiment of this application.

[0082] Figure 12 illustrates a schematic diagram of the relationship between measurement time, measurement, prediction time, and prediction according to an embodiment of this application.

[0083] Figure 13 illustrates a schematic diagram of an AI processing system according to an embodiment of this application;

[0084] Figure 14 illustrates an AI-based schematic diagram according to an embodiment of this application;

[0085] Figure 15 illustrates a structural block diagram of a processing apparatus in a first node according to an embodiment of the present application. Detailed Implementation

[0086] The technical solution of this application will be further described in detail below with reference to the accompanying drawings. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of this application can be arbitrarily combined with each other.

[0087] Example 1

[0088] Example 1 illustrates a signal transmission flowchart of a first node according to an embodiment of this application, as shown in Figure 1.

[0089] In Embodiment 1, the first node 100 receives a first RRC message in step 101, the first RRC message including configuration for at least one handover candidate cell; in step 102, it performs a first prediction and a second prediction respectively, the result of the first prediction being that the handover conditions to the first cell are met within a first time window, and the result of the second prediction being that a radio link failure occurs within a second time window; in step 103, it performs a first action according to the temporal positional relationship between the first time window and the second time window; wherein, the at least one handover candidate cell includes the first cell; the first action is to start applying the stored configuration for the first cell at a first moment, or to send a first report; when the start time of the first time window is earlier than the start time of the second time window, the first action is to start applying the stored configuration for the first cell at the first moment; when the start time of the first time window is later than the start time of the second time window, the first action is to send the first report.

[0090] As an example, a first RRC message is received, the first RRC message including configuration for at least one handover candidate cell.

[0091] As one embodiment, the first transceiver stores the configuration for the at least one handover candidate cell.

[0092] As one embodiment, the first transceiver stores at least some parameters from the configuration for the at least one handover candidate cell.

[0093] As an example, the first RRC message includes at least one condition for conditional reconfiguration to be performed for each of the at least one handover candidate cells.

[0094] As an example, the conditional reconfiguration is performed as follows: a conditional switch is performed.

[0095] As an example, the first RRC message is ConditionalReconfiguration.

[0096] As an example, the first RRC message includes condExecutionCond (conditional execution condition), wherein condExecutionCond includes at least one condition that triggers the conditional reconfiguration to be executed.

[0097] As an example, the first node performs a condition switch when any one of the at least one conditions is met.

[0098] As one embodiment, the condition switching is a layer 3 switching, or the condition switching is a layer 1 switching.

[0099] As an example, the conditional handover is a CHO (Conditional Handover).

[0100] As one example, the layer 3 handover depends on the channel quality of layer 3.

[0101] As an example, the conditional switching is C-LTM (Conditional LTM).

[0102] As an example, the Layer 1 handover depends on the channel quality of Layer 1.

[0103] As an example, the first RRC message includes CondRRCReconfig (CondRRC Reconfiguration).

[0104] As an example, the first RRC message includes RRCReconfiguration.

[0105] As an example, the first RRC message includes ReconfigurationWithSync.

[0106] As an example, the configuration for the at least one handover candidate cell includes at least one of the following: cellGroupId (cell group identifier), RLC (RadioLinkControl) bearer configuration, MAC (Medium Access Control) cell group configuration, and physical cell group configuration for each handover candidate cell included in the at least one handover candidate cell.

[0107] As an example, each of the at least one handover candidate cells is a neighboring cell of the current serving cell, or an Scell ​​(Secondary Cell).

[0108] As an example, the first prediction and the second prediction are performed respectively.

[0109] As an example, at least some of the parameters included in the configuration of the at least one handover candidate cell are used to perform the first prediction.

[0110] As an example, the first prediction is for the at least one handover candidate cell.

[0111] As an example, the first prediction is for the first cell.

[0112] As an example, the first prediction and the second prediction are two independent prediction functions.

[0113] As an example, the activation times of the first prediction and the second prediction are unrelated.

[0114] As an example, the result of the first prediction does not depend on the result of the second prediction; and vice versa.

[0115] As an example, the first prediction is a condition switching prediction.

[0116] As an example, the second prediction is a Radio Link Failure (RLF) prediction.

[0117] As an example, the first prediction and the second prediction are implemented by a first AI model and a second AI model, respectively; wherein the first AI model and the second AI model are two independent models.

[0118] As an example, the function of the first AI model is to predict whether the switching conditions to a community are met.

[0119] As an example, the function of the first AI model is to predict whether the handover conditions to the first cell are met.

[0120] As an example, the input to the first AI model includes at least one condition for which the conditional reconfiguration is performed.

[0121] As an example, the first AI model is activated by the network.

[0122] As an example, the activation time of the first AI model is no earlier than the reception time of the first RRC message.

[0123] As an example, in response to receiving the first RRC message, the first AI model is activated.

[0124] As an example, the first AI model begins to execute the first prediction after it is activated.

[0125] As one example, in response to receiving the first RRC message, the first prediction is initiated.

[0126] As an example, the function of the second AI model is to predict whether a wireless link failure will occur.

[0127] As an example, the second AI model is activated by the network.

[0128] As an example, the second AI model begins to execute the second prediction after it is activated.

[0129] As an example, both the first prediction and the second prediction are implemented using a third AI model.

[0130] As a sub-example of the above embodiment, the result of the first prediction and the result of the second prediction are two results output by the third AI model.

[0131] As an example, the input to the third AI model includes at least one condition for which the conditional reconfiguration is performed.

[0132] As an example, the third AI model is activated by the network.

[0133] As an example, the third AI model is activated and then begins to execute the first prediction and the second prediction.

[0134] As an example, the activation time of the third AI model is no earlier than the reception time of the first RRC message.

[0135] As one example, the input used for the first prediction is at least partially different from the input used for the second prediction.

[0136] As a sub-example of the above embodiments, the input includes channel measurement values.

[0137] As an example, the result of the first prediction is that the handover conditions to the first cell are met within the first time window, and the result of the second prediction is that a radio link failure occurs within the second time window.

[0138] As an example, the duration of the first time window is greater than 0.

[0139] As an example, the duration of the second time window is greater than 0.

[0140] As an example, the at least one handover candidate cell includes the first cell.

[0141] As one embodiment, the first action is performed based on the temporal positional relationship between the first time window and the second time window.

[0142] As an example, the first time window and the second time window do not overlap.

[0143] As one embodiment, the first time window and the second time window at least partially overlap.

[0144] As an example, the first action is to apply the stored configuration for the first cell at a first moment, or to send a first report.

[0145] As one embodiment, the candidates for the first action include: starting to apply the stored configuration for the first cell at a first moment, or sending a first report.

[0146] As an example, the step of starting to apply the stored configuration for the first cell includes: starting to perform the conditional handover to the first cell.

[0147] As an example, the initial application uses the stored configuration for the first cell, which includes RLC bearer configuration, MAC cell group configuration, and physical cell group configuration.

[0148] As one embodiment, the initial application of the stored configuration for the first cell includes: detaching from the source gNB.

[0149] As an example, the first report is an RRC message.

[0150] As an example, the first report is a MAC sublayer message.

[0151] As an example, the first report is a PHY (physical) layer message.

[0152] As an example, the first report includes the result of the second prediction.

[0153] As an example, the first report includes the result of the first prediction.

[0154] As an example, the first report includes at least one of the measurement results for AI and the prediction results based on AI.

[0155] As an example, when the start time of the first time window is earlier than the start time of the second time window, the first action is to start applying the stored configuration for the first cell at the first moment.

[0156] As an example, when the start time of the first time window is equal to the start time of the second time window, the first action is to start applying the stored configuration for the first cell at the first moment.

[0157] As a sub-implementation of the above embodiments, the first moment is the start time of the first time window.

[0158] As an example, when the start time of the first time window is later than the start time of the second time window, the first action is to send the first report.

[0159] As an example, when the start time of the first time window is equal to the start time of the second time window, the first action is to send the first report.

[0160] Example 2

[0161] Example 2 illustrates a network architecture diagram according to an embodiment of this application, as shown in Figure 2.

[0162] Figure 2 illustrates network architecture 200, which is the network architecture of NR 6G, NR 5G, LTE (Long-Term Evolution), and LTE-A (Long-Term Evolution Advanced) systems. The NR 6G, NR 5G, LTE, or LTE-A network architecture 200 may be referred to as 6GS (6G system) / 5GS (5G System) / EPS (Evolved Packet System) 200, or some other suitable terminology. The 6GS / 5GS / EPS 200 may include one or more UEs (User Equipment) 201, NG-RAN (Next Generation Radio Access Network) 202, 6GC (6G core network) / 5GC (5G Core Network) / EPC (Evolved Packet Core) 210, HSS (Home Subscriber Server) / UDM (Unified Data Management) 220, and Internet services 230. The 6GS / 5GS / EPS can interconnect with other access networks, but these entities / interfaces are not shown for simplicity. As shown in the figure, the 6GS / 5GS / EPS provides packet-switched services; however, those skilled in the art will readily understand that the various concepts presented throughout this application can be extended to networks providing circuit-switched services or other cellular networks. The NG-RAN includes NR Node Bs (gNBs) 203 and other gNBs 204. gNBs 203 provide user and control plane protocol termination toward the UE 201. The gNB203 can connect to other gNB204s via the Xn interface (e.g., a backhaul link). The XnAP protocol of the Xn interface is used to transmit control plane messages for the wireless network, and the user plane protocol of the Xn interface is used to transmit user plane data. The gNB203 can also be referred to as a base station, base transceiver station, radio base station, radio transceiver, transceiver function, Basic Service Set (BSS), Extended Service Set (ESS), TRP (Transmission Reception Point), or some other suitable term. In an NTN (Non-Terrestrial Network) network, the gNB203 can be a satellite, an aircraft, or a ground base station relayed via satellite. The gNB203 provides the UE201 with access to the 6GC / 5GC / EPC210.Examples of UE201 include cellular phones, smartphones, Session Initiation Protocol (SIP) phones, laptops, personal digital assistants (PDAs), satellite radios, global positioning systems, multimedia devices, video devices, digital audio players (e.g., MP3 players), cameras, game consoles, drones, aircraft, narrowband IoT devices, machine-type communication devices, land vehicles, automobiles, in-vehicle equipment, in-vehicle communication units, wearable devices, or any other similar functional devices. Those skilled in the art may also refer to UE201 as a mobile station, subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handheld device, user agent, mobile client, client, or any other suitable term. The gNB203 connects to the 6GC / 5GC / EPC210 via the S1 / NG interface. The 6GC / 5GC / EPC210 includes the MME (Mobility Management Entity) / AMF (Authentication Management Field) / SMF (Session Management Function) 211, other MMEs / AMFs / SMFs 214, the S-GW (Service Gateway) / UPF (User Plane Function) 212, and the P-GW (Packet Data Network Gateway) / UPF 213. The MME / AMF / SMF 211 is the control node that handles signaling between the UE201 and the 6GC / 5GC / EPC210. ​​Generally, the MME / AMF / SMF 211 provides bearer and connection management. All user IP (Internet Protocol) packets are transmitted through the S-GW / UPF212, which is itself connected to the P-GW / UPF213. The P-GW provides UE IP address allocation and other functions. The P-GW / UPF213 is connected to Internet service 230. Internet service 230 includes operator-compliant Internet Protocol services, specifically including the Internet, intranet, IMS (IP Multimedia Subsystem), and PS (Packet Switching) services.

[0163] As an example, UE201 corresponds to the first node in this application.

[0164] As an example, gNB203 corresponds to the second node in this application.

[0165] As an example, the first node includes the UE201.

[0166] As one embodiment, the second node includes the gNB203.

[0167] As an example, the UE201 is a user equipment.

[0168] As an example, the UE201 is a terminal.

[0169] As an example, the UE201 is an AI-enabled device.

[0170] As an example, the gNB203 is a macrocell base station.

[0171] As an example, the gNB203 is a microcell base station.

[0172] As an example, the gNB203 is a PicoCell base station.

[0173] As an example, the gNB203 is a femtocell.

[0174] As an example, the gNB203 is a base station device that supports large latency differences.

[0175] As one example, the gNB203 is a flight platform device.

[0176] As an example, the gNB203 is a satellite device.

[0177] As an example, the gNB203 is a base station device that supports large latency differences.

[0178] As an example, the gNB203 is an AI-enabled device.

[0179] As one embodiment, the gNB203 is a test device (e.g., a transceiver device simulating part of the functions of a base station, a signaling tester).

[0180] As an example, the radio link between the UE201 and the gNB203 includes a cellular network link.

[0181] As an example, the radio link from the UE201 to the gNB203 is an uplink, which is used to perform uplink transmissions.

[0182] As an example, the radio link from the gNB203 to the UE201 is a downlink, which is used to perform downlink transmissions.

[0183] As an example, the UE201 and the gNB203 are connected via a Uu interface.

[0184] As an example, the first RRC message is generated in gNB203.

[0185] As an example, the first report is generated by the UE201.

[0186] As an example, the first prediction and the second prediction are performed on the UE201.

[0187] As an example, the first action is performed on the UE201.

[0188] Example 3

[0189] Example 3 illustrates a schematic diagram of the wireless protocol architecture for the user plane and control plane according to an embodiment of this application, as shown in Figure 3. Figure 3 is a schematic diagram illustrating an embodiment of the wireless protocol architecture for the user plane 350 and control plane 300. Figure 3 shows the wireless protocol architecture of the control plane 300 of the UE and gNB using three layers: Layer 1, Layer 2, and Layer 3. Layer 1 (L1 layer) is the lowest layer and implements various PHY (Physical Layer) signal processing functions. The L1 layer will be referred to herein as PHY 301. Layer 2 (L2 layer) 305 is above PHY 301 and is responsible for the link between the UE and gNB through PHY 301. L2 layer 305 includes a MAC (Medium Access Control) sublayer 302, an RLC (Radio Link Control) sublayer 303, and a PDCP (Packet Data Convergence Protocol) sublayer 304, which terminate at the gNB on the network side. PDCP sublayer 304 provides data encryption and integrity protection, and also supports inter-gNB mobility for UEs. RLC sublayer 303 provides packet segmentation and reassembly, and implements retransmission of lost packets via ARQ (Automatic Repeat Request). RLC sublayer 303 also provides duplicate packet detection and protocol error detection. MAC sublayer 302 provides mapping between logical channels and transport channels, and multiplexing of logical channels. MAC sublayer 302 is also responsible for allocating various radio resources (e.g., resource blocks) within a cell among UEs. MAC sublayer 302 is also responsible for HARQ (Hybrid Automatic Repeat Request) operations. RRC (Radio Resource Control) sublayer 306 in Layer 3 (L3) of the control plane 300 is responsible for obtaining radio resources (i.e., radio bearers) and configuring the lower layers using RRC signaling between the gNB and the UE. The wireless protocol architecture of user plane 350 includes layer 1 (L1 layer) and layer 2 (L2 layer). The wireless protocol architecture in user plane 350 is largely the same as the corresponding layers and sublayers in control plane 300 for physical layer 351, PDCP sublayer 354 in L2 layer 355, RLC sublayer 353 in L2 layer 355 and MAC sublayer 352 in L2 layer 355. However, PDCP sublayer 354 also provides header compression for upper layer data packets to reduce wireless transmission overhead.The L2 layer 355 in the user plane 350 also includes an SDAP (Service Data Adaptation Protocol) sublayer 356. The SDAP sublayer 356 is responsible for mapping between QoS flows and Data Radio Bearers (DRBs) to support service diversity. The UE's radio protocol architecture in the user plane 350 at the L2 layer may include some or all of the protocol sublayers of SDAP sublayer 356, PDCP sublayer 354, RLC sublayer 353, and MAC sublayer 352. Although not illustrated, the UE may also have several upper layers above the L2 layer 355, including a network layer (e.g., IP layer) terminating at the P-GW on the network side and an application layer terminating at the other end of the connection (e.g., a remote UE, server, etc.).

[0190] As an example, the wireless protocol architecture in Figure 3 is applicable to the first node in this application.

[0191] As an example, the wireless protocol architecture in Figure 3 is applicable to the second node in this application.

[0192] As an example, the first RRC message in this application is generated in RRC306.

[0193] As an example, the first report in this application is generated in the RRC306.

[0194] As an example, the L2 layer 305 or 355 belongs to a higher layer or an upper layer.

[0195] As an example, the RRC sublayer 306 in the L3 layer belongs to a higher layer or an upper layer.

[0196] As an example, the L1 layer is a lower layer, or a lower layer.

[0197] Example 4

[0198] Example 4 illustrates a hardware module schematic diagram of a communication device according to an embodiment of this application, as shown in Figure 4. Figure 4 is a block diagram of a first communication device 450 and a second communication device 410 communicating with each other in an access network.

[0199] The first communication device 450 includes a controller / processor 459, a memory 460, a data source 467, a transmitting processor 468, a receiving processor 456, a multi-antenna transmitting processor 457, a multi-antenna receiving processor 458, a transmitter / receiver 454, and an antenna 452.

[0200] The second communication device 410 includes a controller / processor 475, a memory 476, a data source 477, a receiver processor 470, a transmitter processor 416, a multi-antenna receiver processor 472, a multi-antenna transmitter processor 471, a transmitter / receiver 418, and an antenna 420.

[0201] In the transmission from the second communication device 410 to the first communication device 450, at the second communication device 410, upper-layer data packets from the core network or from the data source 477 are provided to the controller / processor 475. The core network and data source 477 represent all protocol layers above the L2 layer. The controller / processor 475 implements the functionality of the L2 layer. In the transmission from the second communication device 410 to the first communication device 450, the controller / processor 475 provides header compression, encryption, packet segmentation and reordering, multiplexing between logical and transport channels, and radio resource allocation for the first communication device 450 based on various priority metrics. The controller / processor 475 is also responsible for retransmitting lost packets and signaling to the first communication device 450. The transmit processor 416 and the multi-antenna transmit processor 471 implement various signal processing functions for the L1 layer (i.e., the physical layer). Transmit processor 416 performs encoding and interleaving to facilitate forward error correction (FEC) at the second communication device 410, and mapping of signal clusters based on various modulation schemes (e.g., Binary Phase Shift Keying (BPSK), Quadrature Phase Shift Keying (QPSK), M-Phase Shift Keying (M-PSK), M-QAM). Multi-antenna transmit processor 471 performs digital spatial precoding on the encoded and modulated symbols, including codebook-based and non-codebook-based precoding, and beamforming processing, generating one or more spatial streams. Transmit processor 416 then maps each spatial stream to subcarriers, multiplexes it with a reference signal (e.g., a pilot) in the time and / or frequency domains, and subsequently uses inverse fast Fourier transform (IFFT) to generate a physical channel carrying the time-domain multicarrier symbol stream. Multi-antenna transmit processor 471 then performs transmit analog precoding / beamforming operations on the time-domain multicarrier symbol stream. Each transmitter 418 converts the baseband multicarrier symbol stream provided by the multi-antenna transmitter processor 471 into an radio frequency stream, which is then provided to different antennas 420.

[0202] In the transmission from the second communication device 410 to the first communication device 450, at the first communication device 450, each receiver 454 receives a signal through its corresponding antenna 452. Each receiver 454 recovers the information modulated onto the radio frequency carrier and converts the radio frequency stream into a baseband multicarrier symbol stream, which is then provided to the receiver processor 456. The receiver processor 456 and the multi-antenna receiver processor 458 implement various signal processing functions of the L1 layer. The multi-antenna receiver processor 458 performs receive analog precoding / beamforming operations on the baseband multicarrier symbol stream from the receiver 454. The receiver processor 456 uses a Fast Fourier Transform (FFT) to convert the baseband multicarrier symbol stream after the receive analog precoding / beamforming operations from the time domain to the frequency domain. In the frequency domain, the physical layer data signal and the reference signal are demultiplexed by the receiver processor 456, where the reference signal is used for channel estimation, and the data signal is recovered in the multi-antenna receiver processor 458 after multi-antenna detection to recover any spatial stream destined for the first communication device 450. Symbols on each spatial stream are demodulated and recovered in the receive processor 456, generating soft decisions. The receive processor 456 then decodes and deinterleaves the soft decisions to recover the upper-layer data and control signals transmitted by the second communication device 410 over the physical channel. The upper-layer data and control signals are then provided to the controller / processor 459. The controller / processor 459 implements the functions of Layer 2. The controller / processor 459 may be associated with a memory 460 storing program code and data. The memory 460 may be referred to as computer-readable media. In the transmission from the second communication device 410 to the first communication device 450, the controller / processor 459 provides multiplexing, packet reassembly, decryption, header decompression, and control signal processing between the transport and logical channels to recover higher-layer data packets from the second communication device 410. The upper-layer data packets are then provided to all protocol layers above Layer 2. Various control signals may also be provided to Layer 3 for Layer 3 processing.

[0203] In the transmission from the first communication device 450 to the second communication device 410, at the first communication device 450, upper-layer data packets are provided to the controller / processor 459 using a data source 467. The data source 467 represents all protocol layers above the L2 layer. Similar to the transmission functions at the second communication device 410 described in the transmission from the second communication device 410 to the first communication device 450, the controller / processor 459 implements header compression, encryption, packet segmentation and reordering, and multiplexing between the logical and transport channels, implementing L2 layer functions for the user plane and control plane. The controller / processor 459 is also responsible for retransmitting lost packets and signaling to the second communication device 410. Transmit processor 468 performs modulation mapping and channel coding processing, while multi-antenna transmit processor 457 performs digital multi-antenna spatial precoding, including codebook-based and non-codebook-based precoding, and beamforming processing. Subsequently, transmit processor 468 modulates the generated spatial stream into a multi-carrier / single-carrier symbol stream. After analog precoding / beamforming operations in multi-antenna transmit processor 457, the stream is provided to different antennas 452 via transmitter 454. Each transmitter 454 first converts the baseband symbol stream provided by multi-antenna transmit processor 457 into a radio frequency symbol stream before providing it to antenna 452.

[0204] In the transmission from the first communication device 450 to the second communication device 410, the function at the second communication device 410 is similar to the receiving function at the first communication device 450 described in the transmission from the second communication device 410 to the first communication device 450. Each receiver 418 receives radio frequency signals through its corresponding antenna 420, converts the received radio frequency signals into baseband signals, and provides the baseband signals to the multi-antenna receiving processor 472 and the receiving processor 470. The receiving processor 470 and the multi-antenna receiving processor 472 jointly implement the L1 layer function. The controller / processor 475 implements the L2 layer function. The controller / processor 475 may be associated with a memory 476 storing program code and data. The memory 476 may be referred to as computer-readable media. In the transmission from the first communication device 450 to the second communication device 410, the controller / processor 475 provides multiplexing between the transmission and logical channels, packet reassembly, decryption, header decompression, and control signal processing to recover the upper-layer data packets from the first communication device 450. Upper-layer data packets from the controller / processor 475 can be provided to the core network or all protocol layers above the L2 layer, and various control signals can also be provided to the core network or L3 for L3 processing.

[0205] As one embodiment, the first communication device 450 includes: at least one processor and at least one memory, the at least one memory including computer program code; the at least one memory and the computer program code are configured to be used with the at least one processor, and the first communication device 450 at least: receives a first RRC message, the first RRC message including configuration for at least one handover candidate cell; performs a first prediction and a second prediction respectively, the result of the first prediction being that handover conditions to the first cell are met within a first time window, and the result of the second prediction being that a radio link failure occurs within a second time window; performs a first action according to the temporal positional relationship between the first time window and the second time window; wherein, the at least one handover candidate cell includes the first cell; the first action is to apply the stored configuration for the first cell at a first moment, or to send a first report; when the start time of the first time window is earlier than the start time of the second time window, the first action is to apply the stored configuration for the first cell at the first moment; when the start time of the first time window is later than the start time of the second time window, the first action is to send the first report.

[0206] As one embodiment, the first communication device 450 includes: a memory storing a computer-readable instruction program, which generates actions when executed by at least one processor, the actions including: receiving a first RRC message, the first RRC message including configuration for at least one handover candidate cell; performing a first prediction and a second prediction respectively, the result of the first prediction being that handover conditions to the first cell are met within a first time window, and the result of the second prediction being that a radio link failure occurs within a second time window; performing a first action according to the temporal positional relationship between the first time window and the second time window; wherein the at least one handover candidate cell includes the first cell; the first action is to apply the stored configuration for the first cell at a first moment, or to send a first report; when the start time of the first time window is earlier than the start time of the second time window, the first action is to apply the stored configuration for the first cell at the first moment; when the start time of the first time window is later than the start time of the second time window, the first action is to send the first report.

[0207] As one embodiment, the second communication device 410 includes: at least one processor and at least one memory, the at least one memory including computer program code; the at least one memory and the computer program code are configured to be used with the at least one processor. The second communication device 410 at least: transmits a first RRC message; and receives a first report.

[0208] As one embodiment, the second communication device 410 includes: a memory storing a computer-readable instruction program that produces actions when executed by at least one processor, the actions including: sending a first RRC message; and receiving a first report.

[0209] As an example, the first communication device 450 corresponds to the first node in this application.

[0210] As an example, the second communication device 410 corresponds to the second node in this application.

[0211] As one embodiment, the first communication device 450 is a UE, or a terminal.

[0212] As an example, the first communication device 450 is a relay node.

[0213] As one embodiment, the second communication device 410 is a base station.

[0214] As one embodiment, the second communication device 410 is a base station distribution unit.

[0215] As one embodiment, the second communication device 410 is a piece of code in the distribution unit of a base station.

[0216] As an example, at least one of the antenna 420, the transmitter 418, the multi-antenna transmitter processor 471, the transmitter processor 416, or the controller / processor 475 is used to transmit the first RRC message in this application.

[0217] As one embodiment, at least one of the antenna 452, the receiver 454, the multi-antenna receiving processor 458, the receiving processor 456, or the controller / processor 459 is used to receive the first RRC message in this application.

[0218] As one embodiment, at least one of the antenna 452, the transmitter 454, the multi-antenna transmitter processor 457, the transmitter processor 468, or the controller / processor 459 is used to transmit the first report in this application.

[0219] As an example, at least one of the antenna 420, the receiver 418, the multi-antenna receiving processor 472, the receiving processor 470, or the controller / processor 475 is used to receive the first report in this application.

[0220] As one embodiment, at least one of the antenna 452, the receiver 454, the multi-antenna receiver processor 458, the receiver processor 456, or the controller / processor 459 is used to perform the first prediction in this application.

[0221] As one embodiment, at least one of the antenna 452, the receiver 454, the multi-antenna receiver processor 458, the receiver processor 456, or the controller / processor 459 is used to perform the second prediction in this application.

[0222] As one embodiment, at least one of the antenna 452, the receiver 454, the multi-antenna receiving processor 458, the receiving processor 456, or the controller / processor 459 is used to execute the application-stored configuration for the first cell in this application.

[0223] Example 5

[0224] Example 5 illustrates a wireless signal transmission flowchart according to one embodiment of this application, as shown in Figure 5. In Figure 5, the first node N51 and the second node N52 communicate via a wireless interface. It should be noted that the order in this example does not limit the signal transmission order or the order of implementation in this application.

[0225] For the first node N51, in step S511, a first RRC message is received; in step S512, a first prediction is performed; in step S513, a second prediction is performed; and in step S514, the stored configuration for the first cell is applied starting at the first moment.

[0226] For the second node N52, a first RRC message is sent in step S521.

[0227] It should be noted that although it is not shown in Figure 5 of Embodiment 5, step S513 can occur before step S512 or before step S511.

[0228] In Example 5, a first RRC message is received, the first RRC message including configuration for at least one handover candidate cell; a first prediction and a second prediction are performed respectively, the result of the first prediction being that the handover conditions to the first cell are met within a first time window, and the result of the second prediction being that a radio link failure occurs within a second time window; a first action is performed according to the temporal positional relationship between the first time window and the second time window; wherein, the at least one handover candidate cell includes the first cell; the first action is to start applying the stored configuration for the first cell at a first moment, or to send a first report; when the start time of the first time window is earlier than the start time of the second time window, the first action is to start applying the stored configuration for the first cell at the first moment; the output of the first prediction is the handover probability to the first cell within a time window; when the handover probability to the first cell within the first time window is greater than a first threshold, it is predicted that the handover conditions to the first cell are met within the first time window; the output of the second prediction is the probability of a radio link failure occurring within a time window; when the probability of a radio link failure occurring within the second time window is greater than a third threshold, it is predicted that a radio link failure occurs within the second time window.

[0229] Example 5 applies to the case where the start time of the first time window is earlier than the start time of the second time window.

[0230] Example 5 applies to the case where the start time of the first time window is equal to the start time of the second time window.

[0231] As one embodiment, the second node N52 is the sustaining base station of the serving cell of the first node N51.

[0232] As an example, the second node N52 is the source gNB.

[0233] As an example, the second node N52 is MgNB (primary gNB).

[0234] As an example, the second node N52 is SgNB (auxiliary gNB).

[0235] As an example, the first node N51 is a UE.

[0236] As an example, the first node N51 is a terminal.

[0237] As an example, the first prediction is a direct prediction.

[0238] As an example, the output of the first prediction is the probability that the handover condition to the first cell is met within a time window.

[0239] As an example, the probability that the handover condition to the first cell is met is the probability of handover to the first cell.

[0240] As an example, the probability that the handover condition to the first cell is met is the probability that the first cell becomes the serving cell from the handover candidate cell.

[0241] As an example, when the probability of the handover condition to the first cell being met within the first time window is greater than a first threshold, it is predicted that the handover condition to the first cell will be met within the first time window.

[0242] As an example, when the probability that the handover condition to the first cell is met within the first time window is equal to the first threshold, it is predicted that the handover condition to the first cell will be met within the first time window.

[0243] As an example, when the probability of the handover condition to the first cell being met within the first time window is less than or equal to the first threshold, it is predicted that the handover condition to the first cell will not be met within the first time window.

[0244] As one embodiment, the input to the first prediction includes the measured or predicted channel quality of at least the first cell, and the measured or predicted channel quality of the second cell.

[0245] As an example, the second cell is the serving cell of the first node.

[0246] As an example, the second cell is SpCell (Special Cell), which is either PCell (Primary Cell) or PSCell (PrimarySCG (Secondary Cell Group) Cell).

[0247] As an example, the second prediction is a direct prediction.

[0248] As an example, the output of the second prediction is the probability of a wireless link failure occurring within a time window.

[0249] As an example, when the probability of a wireless link failure occurring within the second time window is greater than a third threshold, a wireless link failure is predicted to occur within the second time window.

[0250] As an example, when the probability of a wireless link failure occurring within the second time window is equal to the third threshold, a wireless link failure is predicted to occur within the second time window.

[0251] As an example, when the probability of a wireless link failure occurring within the second time window is less than or equal to the third threshold, it is predicted that no wireless link failure will occur within the second time window.

[0252] As one embodiment, the input to the second prediction includes the measured or predicted radio link quality of the second cell.

[0253] As one example, the input to the second prediction includes a monitored random access problem indication.

[0254] As one example, the input to the second prediction includes a monitored RLC (RadioLink Control) retransmission count indication.

[0255] As one example, the input to the second prediction includes a monitored LBT (Listen Before Talk) failure indication.

[0256] As an example, the duration of the first time window is the same as the duration of the second time window.

[0257] As an example, the duration of the first time window is different from the duration of the second time window.

[0258] As one example, the duration of the first time window and the duration of the second time window are configured or predefined.

[0259] As an example, the duration of the first time window and the duration of the second time window depend on the moving speed of the first node, respectively.

[0260] As an example, the first node begins to apply the stored configuration for the first cell at the first moment, and the first node sends RRCReconfigurationComplete to the target gNB to end the handover process; wherein, the first cell is a handover candidate cell.

[0261] As a sub-implementation of the above embodiments, the target gNB and the source gNB are the same gNB or different gNBs.

[0262] As a sub-implementation of the above embodiment, if the first node has not yet synchronized with the first cell, the first node first synchronizes with the first cell before sending the RRCReconfigurationComplete message.

[0263] As an example, the first node begins to apply the stored configuration for the first cell at the first moment in response to the first prediction result being that the handover conditions to the first cell are met within the first time window; wherein the start time of the first time window is earlier than the start time of the second time window.

[0264] Example 6

[0265] Example 6 illustrates a wireless signal transmission flowchart according to one embodiment of this application, as shown in Figure 6. In Figure 6, the first node N61 and the second node N62 communicate via a wireless interface. It should be noted that the order in this example does not limit the signal transmission order or the order of implementation in this application.

[0266] For the first node N61, a first RRC message is received in step S611; a first prediction is performed in step S612; a second prediction is performed in step S613; and a first report is sent in step S614.

[0267] For the second node N62, a first RRC message is sent in step S621; and a first report is received in step S622.

[0268] It should be noted that although it is not shown in Figure 6 of Embodiment 6, step S613 can occur before step S612 or before step S611.

[0269] In Example 6, a first RRC message is received, the first RRC message including configuration for at least one handover candidate cell; a first prediction and a second prediction are performed respectively, the result of the first prediction being that the handover conditions to the first cell are met within a first time window, and the result of the second prediction being that a radio link failure occurs within a second time window; a first action is performed according to the temporal positional relationship between the first time window and the second time window; wherein, the at least one handover candidate cell includes the first cell; the first action is to start applying the stored configuration for the first cell at a first moment, or to send a first report; when the start time of the first time window is later than the start time of the second time window, the first action is to send the first report; the first report includes at least one of the performance monitoring results of the first prediction and the performance monitoring results of the second prediction; wherein, the first prediction and the second prediction are respectively based on AI.

[0270] Example 6 applies to the case where the start time of the first time window is later than the start time of the second time window.

[0271] Example 6 applies to the case where the start time of the first time window is equal to the start time of the second time window.

[0272] The first node N61 and the second node N62 can be described with reference to Embodiment 5, and will not be repeated here.

[0273] As an example, the first report includes the performance monitoring results of the first prediction.

[0274] As an example, the first report includes the performance monitoring results of the second prediction.

[0275] As an example, the performance monitoring results include at least one of F1 score, precision, or recall; wherein, the F1 score = 2 × Precision × Recall / (Precision + Recall).

[0276] As an example, precision = n3 / (n1+n3); recall = n3 / (n2+n3); wherein the first prediction is an indirect measurement event prediction.

[0277] As an example, n1 is used for false event detection. When a predicted event occurs, but no actual event occurs within the predicted event window, n1 is incremented by 1.

[0278] As an example, n2 is used to count missed event detection. When a real event occurs, but the event was not predicted within the real event occurrence window, n2 is incremented by 1.

[0279] As a sub-implementation of the above embodiments, the real event occurrence window is a time window formed with the moment when the real event occurs as the center.

[0280] As an example, n3 is used to count true event predictions. When a predicted event occurs, and a true event occurs within the predicted event occurrence window, n3 is incremented by 1.

[0281] As an example, the precision = n3' / (n1'+n3'); the recall = n3' / (n2'+n3'); wherein, the first prediction is a direct measurement event prediction.

[0282] As an example, n1' is used for false event detection. When no real event occurs within the predicted event occurrence window, and the probability of a predicted event occurring within the predicted event occurrence window is higher than a predefined threshold, n1' is incremented by 1.

[0283] As an example, n2' is used to count missed event detection. When a real event does not fall within the predicted event occurrence window, and the probability of the predicted event occurring within the predicted event occurrence window is higher than a predefined threshold, n2' is incremented by 1.

[0284] As an example, n3' is used to count true event prediction. When a true event occurs within the prediction event occurrence window, and the probability of the predicted event occurring within the prediction event occurrence window is higher than a predefined threshold, n3' is incremented by 1.

[0285] As an example, for the first prediction, the predicted event and the actual event are that the handover conditions to the first cell are met; for the second prediction, the predicted event and the actual event are that a radio link failure occurs.

[0286] As an example, the predicted event window may have the same duration as the actual event window, or it may have a different duration.

[0287] As one embodiment, the prediction event occurrence window for the first prediction and the prediction event occurrence window for the second prediction have the same time length, or have different time lengths.

[0288] As an example, the first prediction and the second prediction are both based on AI.

[0289] As an example, the first prediction and the second prediction are based on AI, including: the model for the first prediction and the model for the second prediction are both AI models.

[0290] As a sub-example of the above embodiments, the AI ​​model is deployed over a network.

[0291] As a sub-example of the above embodiments, the AI ​​model is UE-sided.

[0292] As a sub-example of the above embodiments, the AI ​​model is NW-sided (network-side).

[0293] As a sub-example of the above embodiments, the AI ​​model is two-sided.

[0294] As an example, the AI-based prediction includes at least one of frequency domain prediction, time domain prediction, and spatial domain prediction.

[0295] As one embodiment, the first report includes channel measurements used for the first prediction and channel prediction values ​​obtained by the first prediction based on the channel measurements.

[0296] As one embodiment, the first report includes channel measurements used for the second prediction and channel prediction values ​​obtained by the second prediction based on the channel measurements.

[0297] As an example, the measured value and the predicted value are respectively the channel quality.

[0298] As an example, the measured value and the predicted value are respectively the wireless link quality.

[0299] As an example, the measured value is obtained by performing a measurement against a reference signal.

[0300] As an example, the first report indicates the temporal information of the second time window.

[0301] As a sub-implementation of the above embodiments, the time-domain information includes at least two of the start time, end time, and duration.

[0302] As an example, the first report includes the probability of a wireless link failure occurring within the second time window.

[0303] Example 7

[0304] Example 7 illustrates a signal processing flowchart in a first node according to an embodiment of this application, as shown in Figure 7.

[0305] In Example 7, a first prediction is performed in step S701a; a handover condition to the first cell is predicted to be met within the first time window in step S702a; a second prediction is performed in step S701b; a radio link failure is predicted to occur within the second time window in step S702b; in step S703, it is determined whether the start time of the first time window is earlier than the start time of the second time window. If yes, step S704 is executed; if no, step S705 is executed; in step S704, the stored configuration for the first cell is applied at the first moment; and in step S705, a first report is sent.

[0306] As an example, the first prediction and the second prediction are two parallel functions. When the result of the first prediction is that the handover conditions to the first cell are met within the first time window, and the result of the second prediction is that a radio link failure occurs within the second time window, it is determined whether to apply the stored configuration for the first cell or send the first report based on the temporal position relationship between the first time window and the second time window.

[0307] Example 8

[0308] Example 8 illustrates a schematic diagram of the relationship between a first time window and a second time window at a first moment according to an embodiment of this application, as shown in Figure 8. Example 8 is applicable to the case where the start time of the first time window is earlier than the start time of the second time window.

[0309] As an example, when the start time of the first time window is earlier than the start time of the second time window, the first action is to start applying the stored configuration for the first cell at the first moment.

[0310] As an example, the first moment is not earlier than the start time of the first time window and not later than the earlier of the end time of the first time window and the start time of the second time window.

[0311] As an example, when the end time of the first time window is earlier than or equal to the start time of the second time window, the first moment is not earlier than the start time of the first time window and not later than the end time of the first time window; that is, the first moment is located within the first time window.

[0312] As an example, when the end time of the first time window is later than the start time of the second time window, the first moment is neither earlier than the start time of the first time window nor later than the start time of the second time window.

[0313] As one embodiment, the first moment is any moment between the start time and the reference time of the first time window; wherein the reference time is the earlier of the end time of the first time window and the start time of the second time window.

[0314] As an example, the first moment is determined by the first node itself.

[0315] As an example, the first moment is randomly selected by the first node.

[0316] As an example, the first moment is related to the implementation of the first node.

[0317] As an example, the first moment is determined by the first node based on the result of the first prediction and the measurement result obtained by performing channel measurement after the first prediction.

[0318] In Case A of Example 8, the start time of the first time window is earlier than the start time of the second time window, and the first time window and the second time window do not overlap; the first moment is not earlier than the start time of the first time window, and not later than the end time of the first time window.

[0319] In Case B of Example 8, the start time of the first time window is earlier than the start time of the second time window, and the first time window and the second time window overlap; the first moment is not earlier than the start time of the first time window and not later than the start time of the second time window.

[0320] Example 9

[0321] Example 9 illustrates a schematic diagram of the relationship between a first time window and a second time window in sending a first report according to an embodiment of this application, as shown in Figure 9. Example 9 is applicable to the case where the start time of the first time window is later than the start time of the second time window.

[0322] As an example, when the start time of the first time window is later than the start time of the second time window, the first node performs the first action, which is to send the first report.

[0323] As an example, sending the first report is a response to the second prediction that the result is a wireless link failure occurring within the second time window; wherein the start time of the first time window is later than the start time of the second time window.

[0324] As an example, when the result of the second prediction is that a wireless link failure occurs within the second time window, the first report is sent.

[0325] As an example, the first report is sent earlier than the start time of the second time window.

[0326] Example 9 illustrates that the start time of the first time window is later than the start time of the second time window, and the sending time of the first report is earlier than the start time of the second time window; wherein, in case A of Example 9, the first time window and the second time window do not overlap; in case B of Example 9, the first time window and the second time window overlap.

[0327] Example 10

[0328] Example 10 illustrates a schematic diagram of the relationship between the first prediction, the second time point, the first time window, and the first time length according to an embodiment of this application, as shown in Figure 10. Example 10 is applicable to the case where the first prediction is an indirect prediction.

[0329] As an example, the first prediction is an indirect prediction, the output of which is the cell channel quality; at least based on the cell channel quality, it is determined whether the handover conditions to the first cell at a certain time are met.

[0330] As an example, performing the first prediction includes: making a prediction for at least one of the channel quality of the first cell and the channel quality of the second cell.

[0331] As one embodiment, performing the first prediction includes: measuring the channel quality of the first cell and predicting the channel quality of the second cell.

[0332] As one embodiment, performing the first prediction includes: predicting the channel quality of the first cell and measuring the channel quality of the second cell.

[0333] As one embodiment, performing the first prediction includes: predicting the channel quality of the first cell and predicting the channel quality of the second cell.

[0334] As a sub-example of the four embodiments described above, the measurement is performed with respect to a reference signal.

[0335] As a sub-example of the above four embodiments, the channel quality is at least one of the three: RSRP, RSRQ, or SINR of the reference signal.

[0336] As an example, the first prediction is performed to obtain the channel quality of the first cell and the channel quality of the second cell at the second time.

[0337] As an example, when any one of the conditions in at least one of the conditions is met at the second time, it is predicted that the handover condition to the first cell will be met within the first time window.

[0338] As an example, the first time window is a time window formed by shifting the second time point forward along the time axis by a first time length to shifting the second time point backward along the time axis by the first time length.

[0339] As an example, the first time length is Q1 milliseconds, where Q1 is a positive integer.

[0340] As an example, the first time length is configured by the network.

[0341] As an example, the first time length is determined by the UE itself.

[0342] As an example, the first time length depends on the performance of the first prediction.

[0343] As a sub-implementation of the above embodiments, the better the performance of the first prediction, the shorter the first time length; the worse the performance of the first prediction, the longer the first time length.

[0344] As an example, the at least one condition includes the channel quality of the first cell being better than the channel quality of the second cell by more than a second threshold.

[0345] As a sub-example of the above embodiment, the channel quality of the first cell is better than the channel quality of the second cell by more than the second threshold for at least a trigger time (TimeToTrigger, TTT).

[0346] As an example, the at least one condition includes the channel quality of the first cell being better than a fifth threshold, and the channel quality of the second cell being worse than a sixth threshold.

[0347] As a sub-example of the above embodiment, the channel quality of the first cell is better than the fifth threshold, and the channel quality of the second cell is worse than the sixth threshold for at least a time-to-trigger (TTT).

[0348] As an example, the second threshold is configured.

[0349] As an example, the fifth threshold and the sixth threshold are configured.

[0350] As an example, the first RRC message includes the second threshold.

[0351] As an example, the first RRC message includes the fifth threshold and the sixth threshold.

[0352] As an example, the triggering time is configured.

[0353] As an example, the trigger time is 0.

[0354] As an example, the trigger time is a value greater than 0.

[0355] As an example, the channel quality of the first cell and the channel quality of the second cell are obtained based on physical layer measurements.

[0356] As an example, the channel quality of the first cell and the channel quality of the second cell are obtained based on layer 3 measurements.

[0357] As an example, the channel quality of the first cell and the channel quality of the second cell are both beam-level.

[0358] As an example, the channel quality of the first cell and the channel quality of the second cell are both cell-level.

[0359] As an example, the channel quality of the first cell is based on the reference signal of the first cell, and the channel quality of the second cell is based on the reference signal of the second cell; wherein, the reference signal includes SSB (SS / PBCH block, Synchronization Signals / Physical Broadcast Channel block), or CSI-RS (Channel Status Information-Reference Signal).

[0360] As an example, the channel quality of the first cell and the channel quality of the second cell are obtained by L1 measurement values ​​after L1 filtering or L3 filtering, respectively.

[0361] In Figure 10 of Embodiment 10, a first prediction is performed. The first prediction is an indirect prediction. When it is predicted that any one of the at least one conditions is met at the second time, a first time window is formed by shifting the second time forward along the time axis to the second time backward along the time axis. The result of the first prediction is that the handover condition to the first cell is met within the first time window; wherein, any one of the at least one conditions is a handover condition to the first cell.

[0362] As one embodiment, the second moment is shifted forward along the time axis by the first time length, which is equal to or later than the time when the first prediction was performed.

[0363] Example 11

[0364] Example 11 illustrates a schematic diagram of the relationship between the second prediction, the first timer, the second time window, and the second time length according to an embodiment of this application, as shown in Figure 11. Example 11 is applicable to the case where the second prediction is an indirect prediction.

[0365] As an example, the second prediction is an indirect prediction.

[0366] As one embodiment, performing the second prediction includes: measuring the first reference signal resource and predicting future radio link quality based on the measured radio link quality.

[0367] As an example, the first reference signal resource is configured by the network.

[0368] As an example, the first reference signal resource is an SSB (SS / PBCH block) or a CSI-RS.

[0369] As an example, the first reference signal resource is indicated by RadioLinkMonitoringRS.

[0370] As an example, the wireless link quality measured with respect to the first reference signal resource is SINR.

[0371] As an example, the radio link quality measured for the first reference signal resource is BLER (Block Error Rate).

[0372] As an example, during the first timer duration, it is predicted whether a wireless link failure will occur based on at least the latter of the measured wireless link quality and the predicted wireless link quality.

[0373] As an example, when the quality of N consecutive wireless links is lower than a seventh threshold, the first timer is considered to be activated when the quality of the last wireless link in the N consecutive wireless link quality is lower than the seventh threshold; wherein, the quality of the N consecutive wireless links is measured or predicted.

[0374] As an example, N is a positive integer.

[0375] As an example, N is a network configuration.

[0376] As an example, N is N310.

[0377] As an example, the seventh threshold is configured by the network.

[0378] As one example, the first timer is maintained at the physical layer.

[0379] As one embodiment, the activation of the first timer includes: the first timer being activated.

[0380] As a sub-implementation of the above embodiments, the duration of the first timer includes: before the first timer expires.

[0381] As a sub-implementation of the above embodiments, the duration of the first timer includes: during the operation of the first timer.

[0382] As one embodiment, the first timer being considered to start includes: the first timer being predicted to start.

[0383] As a sub-implementation of the above embodiments, the first timer duration includes: predicting before the first timer expires.

[0384] As a sub-implementation of the above embodiments, the first timer duration includes: predicting when the first timer is running.

[0385] As an example, if no K consecutive wireless link qualities are higher than the fourth threshold within the duration of the first timer, a wireless link failure is predicted to occur within the second time window.

[0386] As an example, K is a positive integer.

[0387] As an example, K is a network configuration.

[0388] As an example, K is N311.

[0389] As an example, the quality of each of the K consecutive wireless link qualities is measured or predicted.

[0390] As an example, the fourth threshold is configured by the network.

[0391] As an example, when it is predicted that the first timer will expire, a wireless link failure is predicted to occur within the second time window.

[0392] As a sub-example of the above embodiment, if either the measured wireless link quality or the predicted wireless link quality falls below the seventh threshold during the duration of the first timer, the first timer will be restarted.

[0393] As one embodiment, the second time window is a time window formed by shifting the expiration time of the first timer forward along the time axis by a second time length to shifting the expiration time of the first timer backward along the time axis by a second time length.

[0394] As an example, the second time length is Q2 milliseconds, where Q2 is a positive integer.

[0395] As one example, the second time length is configured by the network.

[0396] As an example, the second time length is determined by the UE itself.

[0397] As one example, the second time length depends on the performance of the second prediction.

[0398] As a sub-implementation of the above embodiments, the better the performance of the second prediction, the shorter the second time length; the worse the performance of the second prediction, the longer the second time length.

[0399] In Figure 11 of Embodiment 11, a second prediction is performed. The second prediction is an indirect prediction. When it is predicted that there are no consecutive K wireless link qualities higher than the fourth threshold within the duration of the first timer, the second time window is formed by shifting the expiration time of the first timer forward along the time axis by the second time length, and then shifting the expiration time of the first timer backward along the time axis by the second time length. The result of the second prediction is that a wireless link failure occurs within the second time window.

[0400] As an example, the time when the expiration time of the first timer is shifted forward along the time axis by the second time length is equal to or later than the time when the second prediction is executed.

[0401] Example 12

[0402] Example 12 illustrates a schematic diagram of the relationship between measurement time, measurement, prediction time, and prediction according to an embodiment of this application. In Figure 12, solid rectangles represent measurements, and dashed rectangles represent predictions.

[0403] As an example, the network is configured to measure and predict time.

[0404] As an example, the measurement is performed within the measurement time.

[0405] As one example, the measurement time includes a positive integer number of measurement cycles.

[0406] As an example, a measurement is performed once per measurement cycle included in the measurement time to obtain a measurement value.

[0407] As an example, the radio link quality, or cell channel quality, within the prediction time is obtained through prediction.

[0408] As one example, the prediction time includes a positive integer number of measurement periods.

[0409] As an example, no measurement is performed in each measurement period included in the prediction time, and the corresponding radio link quality or cell channel quality is obtained based on prediction.

[0410] As one example, the measurement time and the prediction time are orthogonal.

[0411] As one embodiment, the measurement time and the prediction time partially overlap, and the first node performs measurement and prediction simultaneously for the overlapping time portion.

[0412] As a sub-implementation of the above embodiments, the above method can promptly determine the accuracy of the prediction.

[0413] In Figure 12 of Embodiment 12, the measurement time includes 2 measurement cycles, 2 measurements are performed, and 2 measurement values ​​are obtained; the prediction time includes 3 prediction values, which are predicted based on at least the 2 measurement values.

[0414] Example 13

[0415] Example 13 illustrates a schematic diagram of an AI processing system according to an embodiment of this application, as shown in Figure 13. Figure 13 includes a first processor, a second processor, and a third processor. In Example 13, the third processor sends a first dataset to the second processor and a second dataset to the first processor; the second processor generates a target parameter set based on the first dataset and sends the generated target parameter set to the first processor; the first processor processes the second dataset using the target parameter set to obtain a first type of output. In Figure 13, the first type of feedback is optional.

[0416] As one embodiment, the third processor performs measurements on the reference signal to obtain a first dataset and a second dataset; wherein the first dataset and the second dataset each include at least one measurement result for the reference signal.

[0417] As an example, the reference signal includes at least one of CSI-RS (Channel Status Information-Reference Signal), DMRS (DeModulation Reference Signal), SRS (Sounding Reference Signal), PRS (Positioning Reference Signal), or SSB (Synchronization Signals / Physical Broadcast Channel block).

[0418] As an example, the data included in the first dataset and the data included in the second dataset are at least partially different.

[0419] As an example, the first dataset and the second dataset are obtained by performing measurements on the reference signal on different time domain resources, or on different frequency domain resources, or on different spatial domain resources.

[0420] As one embodiment, the second processor is an AI training producer.

[0421] As one embodiment, the second processor includes an AI training function.

[0422] As an example, the first dataset includes training data.

[0423] As an example, the first dataset includes measurements for AI, which are used for AI model training.

[0424] As one embodiment, the second processor is trained based on the input first dataset, and the trained model is described by the target parameter set.

[0425] As one embodiment, the third processor is located at the first node, and the second processor is located at the second node.

[0426] The above embodiments can reduce the computational burden on the UE.

[0427] As one embodiment, the third processor is located at the first node, and the second processor is located at the first node.

[0428] The above embodiments can reduce signaling overhead and optimize the training system.

[0429] As an example, the target parameter set is input to the first processor.

[0430] As an example, the first processor is an AI inference producer.

[0431] As one embodiment, the first processor includes AI inference functionality.

[0432] As an example, the second dataset includes inference data.

[0433] As an example, the first processor constructs a model based on the target parameter set and inputs the second dataset into the constructed model to obtain the first type of output.

[0434] As an example, different sets of target parameters can construct different models, and the corresponding first type of output will also be different.

[0435] As an example, the target parameter set includes at least one of layer 1 filtering coefficients, layer 3 filtering coefficients, beam management criteria, mobility management criteria, handover judgment criteria, radio link failure judgment criteria, interpolation algorithm, filtering algorithm, and prediction algorithm.

[0436] As an example, the target parameter set includes at least one of the parameters of the interpolation algorithm, the parameters of the filtering algorithm, and the parameters of the prediction algorithm.

[0437] As an example, the first type of output is based on reasoning.

[0438] As an example, the first type of output is a predicted value.

[0439] As an example, when the first processor completes the AI-based handover management function, the first type of output is a prediction of whether the handover conditions to a cell have been met.

[0440] As an example, when the first processor completes AI-based wireless link management, the first type of output is a prediction of whether a wireless link failure has occurred.

[0441] As one embodiment, the first processor is located at the first node.

[0442] As a sub-implementation of the above embodiment, when the second processor is located at the second node, the target parameter group is sent to the first node via the air interface.

[0443] As an example, the first processor generates the first type of feedback from the first type of output and the error based on the measured output.

[0444] As an example, the first type of feedback is used to reflect the performance of the trained model; when the performance of the trained model fails to meet the requirements, the second processing opportunity recalculates the target parameter set.

[0445] As an example, the target parameter set includes the first time length.

[0446] As an example, the first type of feedback includes the performance monitoring results of the first prediction.

[0447] As a sub-implementation of the two embodiments described above, the first processor executes the first prediction.

[0448] As an example, the target parameter set includes the second time length.

[0449] As an example, the first type of feedback includes the performance monitoring results of the second prediction included in the first report.

[0450] As a sub-implementation of the two embodiments described above, the first processor executes the second prediction.

[0451] Example 6 applies to a scenario where the second processor is located at the second node and the first processor is located at the first node.

[0452] Example 14

[0453] Example 14 illustrates an AI-based schematic diagram according to an embodiment of this application, as shown in Figure 14. Figure 14 includes five operations: AI training, AI testing, AI emulation, AI entity loading, and AI inference. In Example 14, AI training and AI testing belong to the training phase, AI simulation belongs to the simulation phase, AI entity loading belongs to the deployment phase, and AI inference belongs to the inference phase. In Figure 14, the lines with arrows indicate the sequence of processes.

[0454] As one embodiment, the AI ​​training, the AI ​​testing, and the AI ​​simulation are performed on the second processor described in embodiment 13; the AI ​​inference is performed on the first processor described in embodiment 13.

[0455] As one example, the AI ​​training includes initial training and re-training of one or a group of AI entities.

[0456] As an example, the AI ​​training relies on training data.

[0457] As one example, the AI ​​training includes AI entity validation.

[0458] As an example, the AI ​​entity verification is used to evaluate the performance of the AI ​​entity.

[0459] As an example, the AI ​​entity verification relies on verification data.

[0460] As an example, if the AI ​​entity verification result does not meet expectations, the AI ​​entity will be retrained.

[0461] As one example, the AI ​​testing includes testing the validated AI entity to estimate the performance obtained from training.

[0462] As an example, if the AI ​​test results meet expectations, the AI ​​entity proceeds to the next stage; otherwise, the AI ​​entity will be retrained.

[0463] As an example, the AI ​​test relies on test data.

[0464] As an example, the AI ​​simulation performs inference of AI entities in a simulation environment.

[0465] As an example, the AI ​​simulation estimates the performance of AI entity reasoning in a simulation environment before using the AI ​​entity.

[0466] As an example, the simulation phase is optional.

[0467] As an example, the AI ​​entity loading is to obtain a trained AI entity to achieve the desired AI inference function.

[0468] As an example, the deployment phase is optional.

[0469] As an example, this deployment is no longer needed when the training and inference functions are co-located.

[0470] As one example, the AI ​​inference function includes a prediction function.

[0471] As one embodiment, the AI ​​inference includes inferring whether the handover conditions to the first cell are met based on the channel quality measured for the first cell and the channel quality measured for the second cell.

[0472] As one example, the AI ​​inference includes inferring the channel quality of the first cell at future times based on the channel quality measured for the first cell.

[0473] As one example, the AI ​​inference includes inferring the channel quality of the second cell at future times based on the channel quality measurements for the second cell.

[0474] As one example, the AI ​​inference includes inferring whether a wireless link failure has occurred based on the wireless link quality measured for the second cell.

[0475] As one example, the AI ​​inference includes inferring the future radio link quality of the second cell based on radio link quality measurements taken for the second cell.

[0476] Example 15

[0477] Example 15 illustrates a structural block diagram of a processing apparatus in a first node according to an embodiment of this application, as shown in Figure 15. In Figure 15, the first node processing apparatus 1500 includes a first transceiver 1501. The first node 1500 is a UE or a terminal.

[0478] In embodiment 15, a first transceiver 1501 receives a first RRC message, the first RRC message including configuration for at least one handover candidate cell; performs a first prediction and a second prediction respectively, the result of the first prediction being that the handover conditions to the first cell are met within a first time window, and the result of the second prediction being that a radio link failure occurs within a second time window; performs a first action according to the temporal positional relationship between the first time window and the second time window; wherein, the at least one handover candidate cell includes the first cell; the first action is to start applying the stored configuration for the first cell at a first moment, or to send a first report; when the start time of the first time window is earlier than the start time of the second time window, the first action is to start applying the stored configuration for the first cell at the first moment; when the start time of the first time window is later than the start time of the second time window, the first action is to send the first report.

[0479] As an example, the first moment is not earlier than the start time of the first time window and not later than the earlier of the end time of the first time window and the start time of the second time window.

[0480] As an example, the first report is sent earlier than the start time of the second time window.

[0481] As an example, the output of the first prediction is the probability that the handover condition to the first cell is met within a time window; when the probability that the handover condition to the first cell is met within the first time window is greater than a first threshold, it is predicted that the handover condition to the first cell will be met within the first time window.

[0482] As an example, performing the first prediction includes: predicting at least one of the channel quality of the first cell and the channel quality of the second cell; predicting that the handover condition to the first cell is satisfied within the first time window when any one of the at least one conditions at the second time moment is satisfied; wherein, the first time window is a time window formed by shifting the second time moment forward along the time axis by a first time length to shifting the second time moment backward along the time axis by the first time length; the at least one condition includes that the channel quality of the first cell is better than the channel quality of the second cell by more than a second threshold; and the second cell is the serving cell.

[0483] As an example, the output of the second prediction is the probability of a wireless link failure occurring within a time window; when the probability of a wireless link failure occurring within the second time window is greater than a third threshold, a wireless link failure is predicted to occur within the second time window.

[0484] As one embodiment, performing the second prediction includes: measuring a first reference signal resource and predicting future wireless link quality based on the measured wireless link quality; and predicting whether a wireless link failure will occur within a first timer duration based on at least the latter of the measured wireless link quality and the predicted wireless link quality.

[0485] As one embodiment, performing the second prediction includes: measuring a first reference signal resource and predicting future wireless link quality based on the measured wireless link quality; predicting whether a wireless link failure will occur within a first timer duration based on at least the latter of the measured wireless link quality and the predicted wireless link quality; predicting that a wireless link failure will occur within a second time window when there are no consecutive K wireless link qualities higher than a fourth threshold within the first timer duration; wherein the second time window is a time window formed by shifting the expiration time of the first timer forward along the time axis by a second time length to shifting the expiration time of the first timer backward along the time axis by a second time length.

[0486] As an example, the first report includes at least one of the performance monitoring results of the first prediction and the performance monitoring results of the second prediction; wherein the first prediction and the second prediction are respectively based on AI.

[0487] As one embodiment, the first transceiver 1501 includes a receiver 454 (including an antenna 452) as shown in Figure 4 of this application, a receiver processor 456, a multi-antenna receiver processor 458, and a controller / processor 459.

[0488] As one embodiment, the first transceiver 1501 includes at least one of the following in Figure 4 of this application: receiver 454 (including antenna 452), receiver processor 456, multi-antenna receiver processor 458, or controller / processor 459.

[0489] As one embodiment, the first transceiver 1501 includes a transmitter 454 (including an antenna 452) as shown in Figure 4 of this application, a transmission processor 468, a multi-antenna transmission processor 457, and a controller / processor 459.

[0490] As one embodiment, the first transceiver 1501 includes at least one of the transmitter 454 (including antenna 452) in Figure 4 of this application, a transmission processor 468, a multi-antenna transmission processor 457, or a controller / processor 459.

[0491] As an example, although not shown in Figure 15, the first node 1500 also includes the third processor and the first processor of embodiment 13, wherein the third processor is optional.

[0492] As one embodiment, the third processor includes a receiver 454 (including an antenna 452) as shown in Figure 4 of this application, a receiver processor 456, a multi-antenna receiver processor 458, and a controller / processor 459.

[0493] As an example, the first transceiver 1501 performs the functions of the first processor in Example 13.

[0494] Those skilled in the art will understand that all or part of the steps in the above methods can be implemented by a program instructing related hardware, and the program can be stored in a computer-readable storage medium, such as a read-only memory, hard disk, or optical disk. Optionally, all or part of the steps in the above embodiments can also be implemented using one or more integrated circuits. Correspondingly, each module unit in the above embodiments can be implemented in hardware or in the form of software functional modules. This application is not limited to any specific combination of software and hardware. The first type of communication node or UE or terminal in this application includes, but is not limited to, mobile phones, tablets, laptops, network cards, low-power devices, eMTC (enhanced Machine Type Communication) devices, NB-IoT devices, vehicle communication devices, aircraft, drones, remote-controlled aircraft, and other wireless communication devices. The second type of communication node or base station or network-side equipment in this application includes, but is not limited to, macrocell base stations, microcell base stations, home base stations, relay base stations, eNBs, gNBs, Transmission and Reception Points (TRPs), relay satellites, satellite base stations, airborne base stations, and testing equipment, such as transceivers simulating some functions of a base station, signaling testers, and other wireless communication equipment.

[0495] Those skilled in the art will understand that the present invention can be practiced in other specified forms without departing from its core or essential characteristics. Therefore, the embodiments disclosed herein should in any way be considered descriptive rather than restrictive. The scope of the invention is defined by the appended claims rather than the foregoing description, and all modifications within their equivalent meaning and scope are considered to be included therein.

Claims

1. A method used in a first node of wireless communication, characterized in that, include: Receive a first RRC message, the first RRC message including configuration for at least one handover candidate cell; The first prediction and the second prediction are performed respectively. The result of the first prediction is that the handover conditions to the first cell are met within the first time window, and the result of the second prediction is that a radio link failure occurs within the second time window. The first action is executed based on the temporal positional relationship between the first time window and the second time window; Wherein, the at least one handover candidate cell includes the first cell; the first action is to start applying the stored configuration for the first cell at a first moment, or to send a first report; when the start time of the first time window is earlier than the start time of the second time window, the first action is to start applying the stored configuration for the first cell at the first moment; when the start time of the first time window is later than the start time of the second time window, the first action is to send the first report.

2. The method in the first node according to claim 1, characterized in that, The first moment is not earlier than the start time of the first time window and not later than the earlier of the end time of the first time window and the start time of the second time window.

3. The method in the first node according to claim 1 or 2, characterized in that, The first report was sent earlier than the start time of the second time window.

4. The method in the first node according to any one of claims 1 to 3, characterized in that, The first prediction output is the probability that the handover condition to the first cell is met within a time window; when the probability that the handover condition to the first cell is met within the first time window is greater than a first threshold, it is predicted that the handover condition to the first cell will be met within the first time window.

5. The method in the first node according to any one of claims 1 to 4, characterized in that, The first prediction includes: predicting at least one of the channel quality of the first cell and the channel quality of the second cell; and predicting that the handover condition to the first cell is met within the first time window when any one of the at least one conditions at the second time point is met. Wherein, the first time window is a time window formed by shifting the second time point forward along the time axis by a first time length to shifting the second time point backward along the time axis by the first time length; the at least one condition includes the channel quality of the first cell being better than the channel quality of the second cell by more than a second threshold; the second cell is a serving cell.

6. The method in the first node according to any one of claims 1 to 5, characterized in that, The output of the second prediction is the probability of a wireless link failure occurring within a time window; when the probability of a wireless link failure occurring within the second time window is greater than a third threshold, a wireless link failure is predicted to occur within the second time window.

7. The method in the first node according to any one of claims 1 to 6, characterized in that, The second prediction includes: measuring a first reference signal resource and predicting future wireless link quality based on the measured wireless link quality; and predicting whether a wireless link failure will occur within a first timer duration based on at least the latter of the measured wireless link quality and the predicted wireless link quality.

8. The method in the first node according to claim 7, characterized in that, If no K consecutive wireless link qualities are higher than the fourth threshold within the duration of the first timer, a wireless link failure is predicted to occur within the second time window. The second time window is formed by shifting the expiration time of the first timer forward along the time axis by a second time length to shifting the expiration time of the first timer backward along the time axis by a second time length.

9. The method in the first node according to any one of claims 1 to 8, characterized in that, The first report includes at least one of the performance monitoring results of the first prediction and the performance monitoring results of the second prediction; The first prediction and the second prediction are both based on AI.

10. A terminal, characterized in that, The terminal includes: one or more processors and memory; The memory is coupled to the one or more processors, the memory being used to store computer program code, the computer program code including computer instructions, the one or more processors invoking the computer instructions to cause the terminal to perform the method as described in any one of claims 1-9.

Images