Device and method for use in wireless communication system

Abstract

The present disclosure relates to a device and a method for use in a wireless communication system. Described is a method for a user equipment in a wireless communication system. The user equipment communicates with a network device in the wireless communication system. The method may comprise deploying a beam prediction model, wherein an input of the beam prediction model comprises at least historical data previously collected by a user equipment, an output of the beam prediction model comprises at least a candidate beam corresponding to each time point among a plurality of future time points, and the plurality of time points are within a prediction time window. On the basis of some embodiments of the present disclosure, time intervals between adjacent time points among the plurality of time points within the prediction time window are the same. On the basis of other embodiments of the present disclosure, time intervals between adjacent time points among the plurality of time points within the prediction time window are different.

Description

Apparatus and method for use in a wireless communication system Priority claim

[0001] This application claims priority to Chinese Patent Application No. 202411012517.2, filed on July 26, 2024, and titled “Apparatus and method for use in a wireless communication system,” the entire contents of which are incorporated herein by reference. TECHNICAL FIELD

[0002] The present disclosure relates generally to techniques for use in a wireless communication system, and in particular to techniques of applying a beam prediction model to a beam failure recovery procedure in a wireless communication system. BACKGROUND

[0003] Wireless communication systems can use a variety of protocols and standards for data transmission between devices. These protocols and standards have evolved over a long period of time, including but not limited to the Third Generation Partnership Project (3GPP), 3GPP Long Term Evolution (LTE) (e.g., 4G communication), 3GPP New Radio (NR) (e.g., 5G communication), and IEEE 802.11 standards for wireless local area networks (WLANs) (also commonly referred to as Wi-Fi), among others.

[0004] In new types of communication systems, the use of higher frequency bands for communication has become an important and highly promising technology. Directional transmission can be achieved in this frequency band using large-scale multiple-input multiple-output (MIMO) technology. Specifically, large-scale MIMO technology can enable precise beamforming between network devices and user devices, so that wireless signals concentrate energy in a narrower beam to enhance the coverage of communication and reduce interference.

[0005] Generally speaking, the position of a user device is not static, and when its position changes (typically due to device position changes caused by, for example, hand jitter or slight displacement of the user), it is easy to cause the beam state to change from beam alignment to beam misalignment. In addition, when there is an obstruction between the network device and the user device, the beam state can also change from beam alignment to beam misalignment. Specifically, when the quality of the beam is below a certain threshold, it can be considered that a beam failure has occurred, and thus beam training for beam failure recovery needs to be re-executed and beam alignment needs to be re-implemented.

[0006] In traditional beam recovery management, there are two types of random access procedures: contention-based and non-contention-based. Contention-based random access involves four random access steps, with different user equipments (UEs) competing for access. Non-contention-based random access involves two random access steps, where the network device allocates resources and a dedicated preamble sequence to the UE for beam failure recovery. During beam failure recovery, the UE can report a Physical Random Access Channel (PRACH) based on a preferred candidate beam, which can be obtained by measuring a reference signal set configured by the network device.

[0007] However, the traditional beam failure recovery management methods described above typically result in frequent signaling overhead and reduced communication quality. Therefore, there is a need to find an efficient and reliable mechanism for beam failure recovery, thereby enhancing and improving communication performance indicators. Summary of the Invention

[0008] This disclosure presents devices and methods for use in wireless communication systems. More specifically, this disclosure presents a technical solution for time-domain beam prediction models.

[0009] According to a first aspect of this disclosure, an electronic device for a user equipment in a wireless communication system is provided, the user equipment communicating with a network device in the wireless communication system, the electronic device including at least one processor and at least one memory, the at least one memory including computer program instructions, wherein the at least one memory and the computer program instructions are configured, through the at least one processor, to cause the user equipment to perform the following operations: deploying a beam prediction model, wherein the input of the beam prediction model includes at least historical data previously collected by the user equipment, and wherein the output of the beam prediction model includes at least candidate beams corresponding to each of a plurality of future time points, and wherein the plurality of time points are within a prediction time window.

[0010] Correspondingly, according to a first aspect of this disclosure, a method for a user equipment in a wireless communication system is also provided, the user equipment communicating with a network device in the wireless communication system, the method comprising: deploying a beam prediction model, wherein the input of the beam prediction model includes at least historical data previously collected by the user equipment, and wherein the output of the beam prediction model includes at least candidate beams corresponding to each of a plurality of future time points, and wherein the plurality of time points are within a prediction time window.

[0011] According to a second aspect of this disclosure, an electronic device for a network device in a wireless communication system is provided, the network device communicating with a user equipment in the wireless communication system, the electronic device including at least one processor and at least one memory, the at least one memory including computer program instructions, wherein the at least one memory and the computer program instructions are configured, via the at least one processor, to cause the network device to perform the following operations: performing beam switching of the network device based on candidate beams reported by the user equipment to the network device, wherein a beam prediction model is deployed at the user equipment, wherein the input of the beam prediction model includes at least historical data previously collected by the user equipment, and wherein the output of the beam prediction model includes at least candidate beams corresponding to each of a plurality of future time points, wherein the plurality of time points are within a prediction time window.

[0012] Correspondingly, according to a second aspect of this disclosure, a method for a network device in a wireless communication system is also provided, the network device communicating with a user equipment in the wireless communication system, the method comprising: performing beam switching of the network device based on candidate beams reported by the user equipment to the network device, wherein a beam prediction model is deployed at the user equipment, wherein the input of the beam prediction model includes at least historical data previously collected by the user equipment, and wherein the output of the beam prediction model includes at least candidate beams corresponding to each of a plurality of future time points, and wherein the plurality of time points are within a prediction time window.

[0013] According to a third aspect of this disclosure, a computer-readable storage medium having one or more instructions stored thereon is provided, which, when executed by one or more processors of an electronic device, cause the electronic device to perform methods according to various embodiments of this disclosure.

[0014] According to a fourth aspect of this disclosure, a computer program product including program instructions is provided, which, when executed by one or more processors of a computer, cause the computer to perform methods according to various embodiments of this disclosure.

[0015] The above overview is provided to summarize some exemplary embodiments to provide a basic understanding of the aspects of the subject matter described herein. Therefore, the features described above are merely examples and should not be construed as narrowing the scope or spirit of the subject matter described herein in any way. Other features, aspects, and advantages of the subject matter described herein will become apparent from the following detailed description, taken in conjunction with the accompanying drawings. Attached Figure Description

[0016] A better understanding of this disclosure can be obtained by considering the following detailed description of the embodiments in conjunction with the accompanying drawings. The same or similar reference numerals are used in the drawings to denote the same or similar parts. The drawings, together with the following detailed description, are incorporated in and form a part of this specification to illustrate embodiments of the disclosure and explain the principles and advantages of the disclosure. Wherein:

[0017] Figure 1 illustrates an example scenario of a wireless communication system according to an embodiment of the present disclosure.

[0018] Figure 2 illustrates an exemplary electronic device for a user equipment according to an embodiment of the present disclosure.

[0019] Figure 3 illustrates an exemplary electronic device for a network device according to an embodiment of the present disclosure.

[0020] Figure 4 shows a schematic diagram of the beam prediction model according to an embodiment of the present disclosure in a scenario where the time interval between adjacent time points is the same.

[0021] Figure 5 shows a schematic diagram of the beam prediction model according to an embodiment of the present disclosure in a scenario where the time interval between adjacent time points is different.

[0022] Figure 6 shows a flowchart of an example method for a user equipment in a wireless communication system according to an embodiment of the present disclosure.

[0023] Figure 7 shows a flowchart of an example method for a network device in a wireless communication system according to an embodiment of the present disclosure.

[0024] Figure 8 is a block diagram of an example structure of a personal computer that may be used as an information processing device in an embodiment of this disclosure.

[0025] Figure 9 is a block diagram illustrating a first example of a schematic configuration of a base station to which the techniques of this disclosure can be applied.

[0026] Figure 10 is a block diagram illustrating a second example of a schematic configuration of a base station to which the techniques of this disclosure can be applied.

[0027] Figure 11 is a block diagram illustrating an example of a schematic configuration of a smartphone to which the techniques of this disclosure can be applied.

[0028] Figure 12 is a block diagram illustrating an example of a schematic configuration of a car navigation device to which the technology of this disclosure can be applied.

[0029] While the embodiments described in this disclosure may be readily available for various modifications and alternatives, specific embodiments thereof are shown by way of example in the accompanying drawings and are described in detail herein. However, it should be understood that the drawings and the detailed description thereof are not intended to limit the embodiments to the specific forms disclosed, but rather are intended to cover all modifications, equivalents, and alternatives that fall within the spirit and scope of the claims. Detailed Implementation

[0030] The following description illustrates representative applications of the devices and methods described herein. These examples are provided merely to provide context and aid in understanding the described embodiments. Therefore, it will be apparent to those skilled in the art that the embodiments described below can be practiced without some or all of the specific details provided. In other instances, well-known process steps have not been described in detail to avoid unnecessarily obscuring the described embodiments. Other applications are also possible, and the scope of this disclosure is not limited to these examples.

[0031] Typically, a wireless communication system includes at least network equipment and user equipment, with the network equipment providing communication services to one or more user equipment.

[0032] In this disclosure, the term "network device" (or "base station," "control device") has the full breadth of its usual meaning and includes at least a wireless communication station that is part of a wireless communication system or radio system to facilitate communication. As examples, a network device may be an eNB of the 4G communication standard, a gNB of the 5G communication standard, a remote radio head, a wireless access point, a drone control tower, or a communication device performing similar functions. It should be understood that, more broadly, a network device may additionally include core network equipment and / or remote application servers, etc. In this disclosure, "network device," "base station," and "control device" are used interchangeably, or a "network device" may be implemented as part of a "base station." Application examples will be described in detail below using network devices as examples and with reference to the accompanying drawings.

[0033] In this disclosure, the terms "user equipment (UE)" or "terminal equipment" are used in their full breadth of their usual meaning and include at least a terminal device that is part of a wireless communication system or radio system to facilitate communication. For example, a user equipment may be a terminal device or a component thereof, such as a mobile phone, laptop computer, tablet computer, vehicle communication device, wearable device, sensor, etc. In this disclosure, "user equipment" (hereinafter referred to as "UE") and "terminal equipment" may be used interchangeably, or a "user equipment" may be implemented as part of a "terminal equipment".

[0034] In this disclosure, the term "network equipment side" / "base station side" has the full breadth of its usual meaning and generally refers to the side of a communication system that transmits data in the downlink or the side that receives data in the uplink. Similarly, the term "user equipment side" / "terminal equipment side" has the full breadth of its usual meaning and can accordingly refer to the side of a communication system that receives data in the downlink or the side that transmits data in the uplink.

[0035] It should be noted that although the following description is primarily based on embodiments of this disclosure within a communication system that includes network devices and user equipment, these descriptions can be extended accordingly to communication systems that include any other types of network device side and user equipment side. For example, operation on the network device side may correspond to operation on the base station, and operation on the user equipment side may correspondingly correspond to operation on the terminal device.

[0036] Figure 1 illustrates an example scenario of a wireless communication system according to an embodiment of the present disclosure. It should be understood that Figure 1 only shows one of many types and possible arrangements of wireless communication systems; the features of the present disclosure can be implemented in any of various systems as needed.

[0037] As shown in Figure 1, the wireless communication system 100 includes one or more user equipment 101 and one or more network devices 102. User equipment 101 and network devices 102 can be configured to communicate via a wireless transmission medium. Network devices 102 can also be configured to communicate with entities such as location management function entities (not shown) in the core network.

[0038] As shown in Figure 1, user equipment 101 is located at a first position at a first time point. Network device 102 can transmit multiple beams it can transmit at all angles to user equipment 101. Terminal device 101 scans these beams, measures the communication quality corresponding to each beam, and then selects a transmission beam (e.g., the optimal beam that achieves the best communication quality) and notifies network device 102 of the beam's number (or ID) (e.g., the beam is shown as a dotted shaded area in Figure 1). This allows network device 102 to schedule the optimal beam to align with terminal device 101 and use that beam for communication, thus achieving beam alignment. Subsequently, at a second time point, user equipment 101 has moved from the first position to the second position. At the second time point, the optimal beam corresponding to the first time point may no longer be able to achieve the desired communication quality, i.e., the beam quality is below a certain threshold. In this case, beam failure can be considered to have occurred, thus requiring the initiation of a beam failure recovery process. As previously mentioned, User Equipment 101 may employ either contention-based or non-contention-based random access to report the optimal beam after beam failure (e.g., the beam shown as a vertical shaded line in Figure 1). However, this approach typically results in frequent signaling overhead and a reduction in communication quality.

[0039] Artificial intelligence (AI) is a newly emerging technological science used in recent years to study and develop methods to simulate, extend, and expand human intelligence. As an example, and not a limitation, AI algorithms may include one or more of the following: linear regression, logistic regression, decision trees, Naive Bayes, support vector machines, random forests, artificial neural networks, and K-nearest neighbors. Those skilled in the art will understand that machine learning (ML) is a type of AI technology that may involve processes such as data collection, model training, and data analysis and reasoning. As an example, machine learning techniques may involve data collection, model training, model deployment, model inference, model selection, activation, deactivation, switching and rollback, model testing, model updating, and model transfer.

[0040] According to embodiments of this disclosure, applying artificial intelligence / machine learning techniques to the beam failure recovery process in a wireless communication system can make the process intelligent and reduce overhead. Specifically, according to embodiments of this disclosure, a beam prediction model can be used to select candidate beams at an appropriate time, thereby achieving effective beam switching in cases of beam failure or poor beam quality.

[0041] It should be recognized that Figure 1 merely illustrates one example scenario of beam failure recovery and is not intended to be limiting. In reality, there may be multiple beam failure recovery scenarios. For example, at a first time point, there is no obstruction between user equipment 101 and network device 102 (such as a line-of-sight (LOS) transmission path between them), then the optimal beam for the network device at that time point could be, for example, a dotted shadow beam. At a second time point, an obstruction occurs between user equipment 101 and network device 102, but a non-line-of-sight (NLOS) transmission path exists between them (such as a reflection path), then the optimal beam at that time point changes, requiring a beam failure recovery process to obtain and switch to the optimal beam at the second time point.

[0042] It should be understood that beam prediction models can include spatial beam prediction models and temporal beam prediction models. Spatial beam prediction models can predict candidate beams based on a small number of measured beams. Temporal beam prediction models can predict candidate beams for each of multiple future time points based on predictions of multiple beams within a historical time window. The embodiments of this disclosure primarily pertain to the scenario of temporal beam prediction models (in other words, in the following text, "beam prediction model" and "temporal beam prediction model" can be used interchangeably). Furthermore, the embodiments of this disclosure primarily pertain to temporal beam prediction of downlink beams.

[0043] It should also be understood that the devices shown in Figure 1 are merely examples, and in practice, a much larger number of network devices and user equipment can be used. Furthermore, Figure 1 only shows the use of multiple beams at the network devices; in practice, multiple antenna structures can also be used at the user equipment to generate multiple beams.

[0044] It should be recognized that, according to embodiments of this disclosure, the beam prediction model can be deployed at the user equipment. It should be understood that the beam prediction model can be generated by the user equipment, or it can be generated by other devices in the wireless communication system (such as network devices, core network devices, etc.) and transmitted to the user equipment.

[0045] Figure 2 illustrates an exemplary electronic device 200 for a user equipment 101 (also referred to herein as a "UE") in a system 100 according to an embodiment of the present disclosure. The electronic device 200 shown in Figure 2 may include various units to implement the various embodiments according to the present disclosure. In this example, the electronic device 200 includes a communication unit 202 and a processing unit 204. In one embodiment, the electronic device 200 is implemented as the user equipment 101 itself or a portion thereof, or as a device or part thereof for controlling the user equipment 101 or otherwise associated with the user equipment 101. The various operations described below in connection with the user equipment can be implemented by units 202, 204, or other possible units of the electronic device 200.

[0046] According to embodiments of this disclosure, the communication unit 202 of the electronic device 200 can be configured to communicate with a network device in a wireless communication system. The processing unit 204 can be configured to deploy a beam prediction model. The input to the beam prediction model may include at least historical data previously collected by the user equipment, and the output of the beam prediction model may include at least candidate beams corresponding to each of a plurality of future time points. The time window containing the plurality of time points may be referred to as a prediction time window.

[0047] It should be understood that the time intervals between adjacent time points within multiple time points in a prediction time window can be the same or different.

[0048] Figure 3 illustrates an exemplary electronic device for a network device 102 (also referred to herein as a "gNB") according to an embodiment of the present disclosure. The electronic device 300 shown in Figure 3 may include various units to implement the various embodiments according to the present disclosure. In this example, the electronic device 300 includes a communication unit 302 and a processing unit 304. In one embodiment, the electronic device 300 is implemented as the network device 102 itself or as part of it, or as a device associated with or part of the network device 102. The various operations described below in connection with the network device can be implemented by units 302, 304, or other possible units of the electronic device 300.

[0049] According to embodiments of this disclosure, the communication unit 302 of the electronic device 300 can be configured to communicate with a user equipment in a wireless communication system. The processing unit 304 can be configured to perform beam switching of the network device based on candidate beams reported by the user equipment to the network device. A beam prediction model can be deployed at the user equipment. The input to the beam prediction model can include at least historical data previously collected by the user equipment, and the output of the beam prediction model can include at least the candidate beams corresponding to each of a plurality of future time points. The time window containing these plurality of time points can be referred to as a prediction time window.

[0050] It should be understood that the time intervals between adjacent time points within multiple time points in a prediction time window can be the same or different.

[0051] In some embodiments, electronic devices 200 or 300 may be implemented at the chip level, or at the device level by including other external components (e.g., radio links, antennas, etc.). For example, each electronic device may function as a communication device as a complete unit.

[0052] It should be noted that the above-mentioned units are merely logical modules divided according to their specific functions, and are not intended to limit the specific implementation methods. For example, they can be implemented in software, hardware, or a combination of both. In a hardware implementation, the hardware can be programmed or configured to perform functions. In a software or combined software-hardware implementation, the software can be used to configure the hardware and / or processor. In actual implementation, the above-mentioned units can be implemented as independent physical entities, or they can be implemented by a single entity (e.g., a processor (CPU or DSP, etc.), integrated circuit, etc.). The processing circuit can refer to various implementations of digital circuit systems, analog circuit systems, or mixed-signal (analog and digital combination) circuit systems that perform functions in a computing system. The processing circuit can include circuits such as integrated circuits (ICs), application-specific integrated circuits (ASICs), portions or circuits of a single processor core, the entire processor core, a single processor, programmable hardware devices such as field-programmable gate arrays (FPGAs), and / or systems including multiple processors.

[0053] As mentioned earlier, in the time-domain beam prediction model, the time intervals between adjacent time points within multiple time points in the prediction time window can be the same or different. The following sections, with reference to Figures 4 and 5, will detail the beam prediction models for these two scenarios, along with related beam switching and historical data collection processes. Scenario with the same time intervals

[0054] Figure 4 illustrates a schematic diagram of the beam prediction model according to an embodiment of the present disclosure in a scenario where the time interval between adjacent time points is the same. Figure 4(a) shows a beam switching scenario utilizing a conventional beam failure recovery mechanism. A beam failure is considered to have occurred when the beam quality of the current beam is below a certain threshold (by way of example and not limitation, the reference signal received power (RSRP) or reference signal received quality (RSRQ) corresponding to the beam is below a certain threshold, or the signal-to-interference-plus-noise ratio (SINR) corresponding to the beam is above a certain threshold), thus requiring beam failure recovery to find a new optimal beam and switch to it. As previously mentioned, user equipment can perform beam switching through contention-based random access, or it can perform beam switching based on a new beam indicated by downlink control information (DCI) from network equipment based on some previous measurements. The horizontal axis in Figure 4 is the time axis, and the horizontal length of each colored block in (a) represents the actual dwell time of the corresponding beam. It can be seen that the actual dwell times of different beams are usually different.

[0055] Figure 4(b) illustrates a beam prediction model where the time intervals between adjacent time points are equal. As shown, there are multiple time points (also referred to herein as moments) within the prediction time window: N#1, N#2, N#3, N#4, etc. The time intervals between adjacent time points are the same. The beam prediction model can output the beam corresponding to each of the multiple time points within the prediction time window (e.g., output the beam number), which can remain until the next time point. For example, the beam prediction model outputs beam TX#1 at time point N#1, which can remain until the next time point N#2. According to embodiments of this disclosure, the candidate beams output by the beam prediction model can be used for beam switching of devices (e.g., network devices).

[0056] As an example, according to Figure 4(b), the beam prediction model outputs candidate beam TX#2 of the network device at time point N#2, and candidate beam TX#3 at time point N#3. Correspondingly, according to Figure 4(a), in reality, the actual dwell time of the optimal beam TX#2 is slightly less than the time interval between time points N#2 and N#3. As another example, according to Figure 4(b), the beam prediction model outputs candidate beam TX#3 at time point N#4. Correspondingly, according to Figure 4(a), in reality, the actual dwell time of the optimal beam TX#3 is only a short period after time point N#4, after which the optimal beam changes to TX#4.

[0057] It can be seen that using beam prediction models with the same time intervals may not be able to avoid beam failures within the prediction time window. However, since information such as the dwell time of all measured beams is not required during the historical data collection period of the beam prediction model, the reporting signaling overhead of the beam prediction model deployed at the user equipment is relatively small when reporting prediction results. To further reduce the overhead of beam failure recovery, this disclosure avoids using traditional beam failure recovery management methods as much as possible when using beam prediction models. For example, switching to beam TX#3 using a traditional beam failure recovery mechanism after the actual dwell time of beam TX#2 ends will incur significant measurement overhead. Since the beam prediction model based on AI / ML technology will also switch to beam TX#3 at the N#3 time point shortly thereafter, the overhead of the traditional beam failure recovery mechanism is redundant and unnecessary.

[0058] To reduce the aforementioned unnecessary overhead, this disclosure proposes the following three schemes for applying beam prediction models in scenarios with equal time intervals. i. Within the prediction time window, in response to detecting that the beam quality at the current time point is lower than a first beam quality threshold, the user equipment can report the candidate beam for the next time point output by the beam prediction model to the network device via the Physical Random Access Channel (PRACH) for beam switching by the network device. In this paper, when the beam quality is lower than the first beam quality threshold, it can be considered that a beam failure has occurred. Referring to Figure 4, for example, if beam failure of beam TX#2 is detected at a time point close to N#3 after N#2, then according to scheme (i) of this disclosure, the user equipment can report TX#3 as a candidate beam to the network device via PRACH for beam switching by the network device. ii. Within the prediction time window, in response to detecting that the beam quality at the current time point is lower than the second beam quality threshold but higher than the first beam quality threshold, the candidate beam for the next time point output by the beam prediction model is reported to the network device via uplink channel information (UCI) for beam switching by the network device. In this paper, the second beam quality threshold is higher than the first beam quality threshold. When the beam quality is lower than the second beam quality threshold but higher than the first beam quality threshold, it can be considered that the current beam quality is poor, but beam failure has not yet occurred. Referring to Figure 4, if the poor quality of beam TX#2 (but beam failure has not yet occurred) can be detected at a time point earlier than scheme (i) (i.e., closer to N#2), then according to scheme (ii) of this disclosure, the user equipment can report TX#3 as a candidate beam to the network device via physical layer uplink channels such as UCI for early beam switching by the network device. iii. Within the prediction time window, in response to the detection of a frequency higher than a first beam quality threshold, the length of the time interval between future adjacent time points is reduced to allow the beam prediction model to output candidate beams more frequently. Referring to Figure 4(c), after frequent beam failures are detected, the time interval between two adjacent outputs of the beam prediction model can be adjusted (e.g., reduced). For example, the density of prediction output time points in the time domain can be increased. It should be understood that, according to scheme (iii) of this disclosure, the size of the prediction time window can be adjusted, but this does not affect the adjustment of the density of output time points.

[0059] It should be understood that the above-described schemes (i), (ii), and (iii) of this disclosure are predicated on the user equipment having already reported all beam prediction results to the network equipment. Specifically, the user equipment can report beam prediction results for each of multiple future time points in a single report, thereby enabling the network equipment to cooperate with the user equipment to complete beam switching in advance.

[0060] It should be recognized that, compared to traditional beam failure recovery mechanisms, scheme (i) of this disclosure avoids the operation of user equipment measuring the beam set configured by the network equipment to find the optimal beam. According to this disclosure, the reported candidate beam is the output of the beam prediction model at the next time point, thus greatly reducing the measurement overhead of the network equipment. Scheme (ii) of this disclosure also does not require measurement. Compared to scheme (i), since candidate beams can be reported via UCI before beam failure, latency overhead can be further reduced. Scheme (iii) of this disclosure further improves the accuracy of prediction by increasing the density of output time points in the time domain within the prediction time window, thereby reducing the occurrence of beam failure and beam failure recovery.

[0061] According to embodiments of this disclosure, the input to the beam prediction model may include at least historical data previously collected by the user equipment. As an example, and not a limitation, the historical data may include reference signal received power (RSRP) for multiple beams of the network device previously measured by the user equipment, or more specifically, Layer 1-RSRP (L1-RSRP). Additionally or optionally, the historical data may also include auxiliary data. Auxiliary data may include timestamps corresponding to each historical data point and / or the user equipment's movement speed, etc. It should be understood that the set of multiple beams transmitted by the network device during the historical data collection period may or may not have an inclusion relationship with the set of beams output by the beam prediction model. (Scenarios with different time intervals)

[0062] Figure 5 illustrates a schematic diagram of the beam prediction model according to embodiments of the present disclosure in scenarios where the time interval between adjacent time points is different. Similar to Figure 4(a), Figure 5(a) shows a beam switching scenario using conventional beam failure recovery management. When the beam quality of the current beam is below a certain threshold (by way of example and not limitation, the reference signal received power (RSRP) or reference signal received quality (RSRQ) corresponding to the beam is below a certain threshold, or the signal-to-interference-plus-noise ratio (SINR) corresponding to the beam is above a certain threshold), a beam failure can be considered to have occurred, thus requiring beam failure recovery to find a new optimal beam and switch to it. The horizontal axis in Figure 5 is the time axis, and the horizontal length of each colored block in (a) represents the actual dwell time of the corresponding beam. It can be seen that the actual dwell times of different beams are usually different.

[0063] Figure 5(b) illustrates a beam prediction model with unequal time intervals between adjacent time points. As shown, there are multiple time points (also referred to herein as moments) within the prediction time window: N#1, N#2, N#3, N#4, etc. The time intervals between adjacent time points are different. The beam prediction model can output the beam corresponding to each of the multiple time points within the prediction time window (e.g., output the beam number), which can remain stationary until the next time point. According to embodiments of this disclosure, the candidate beams output by the beam prediction model can be used for beam switching.

[0064] It can be seen that using beam prediction models with different time intervals can avoid beam failures to some extent. Figures 5(a) and (b) are very similar (it should be understood that there may be slight errors in the dwell time of some beams), indicating that the output of the beam prediction model in this scenario depends to some extent on the dwell time of the candidate beams. Therefore, for scenarios with different time intervals, the collection of historical data is very important, which needs to consider information such as the dwell time of the measured beams. In practice, obtaining the dwell time information of some practical application beams may be easy, but obtaining the dwell time information of all measured beams may not be easy.

[0065] Because the time intervals between adjacent time points in the output of the beam prediction model are different, it can predict the dwell time of each candidate beam, meaning that the beam prediction model is capable of predicting beam failure. For user equipment, using a beam prediction model based on AI / ML technology to replace the traditional beam failure detection and recovery mechanism can significantly reduce measurement overhead and latency. However, the beam prediction model in this scenario has higher requirements for historical data collection. The following will describe two schemes for collecting historical data for the beam prediction model in scenarios with different time intervals, according to embodiments of this disclosure. iv. Within the time window for collecting historical data, the user equipment can measure and record the signal attenuation of the network device's beam. Subsequently, the user equipment can estimate the predicted dwell time of the network device's beam based on the recorded signal attenuation for use in the beam prediction model. According to scheme (iv) of this disclosure, inference can be made based on the measured dwell time of the beam. Since it may not be possible to obtain the dwell time of all measured beams in a real-world scenario, the beam fading can be estimated by measuring the beam fading multiple times within the time window for collecting historical data. v. Within the time window for collecting historical data, the user equipment can measure and record the beam failure frequency of the network device. Subsequently, the user equipment can estimate the predicted failure probability of the network device's beams based on the recorded beam failure frequency for use in a beam prediction model. Accordingly, within the prediction time window, if the predicted failure probability of the beam at the current time point is greater than a failure probability threshold, the user equipment can report the candidate beams for the next time point output by the beam prediction model to the network device for beam switching. According to scheme (v) of this disclosure, inferences can be made based on collected historical beam failure information. By way of example and not limitation, historical beam failure information may include the beam failure frequency (or number of beam failures) within the time window for collecting historical data, or the time location corresponding to the beam failure. Based on this information, the failure probability of a candidate beam at a future time point can be predicted, and beam switching can be performed in advance if the failure probability is higher than a certain threshold.

[0066] It should be understood that, according to scheme (iv) of this disclosure, the dwell time of the measurement beam can be estimated after collecting historical data. According to scheme (v) of this disclosure, the failure of the predicted candidate beam can be determined using the collected historical data.

[0067] It should be understood that, for scenarios where the time intervals between adjacent time points in the beam prediction model are the same or different, Figures 4 and 5 only show examples of outputting one candidate beam at each time point within the prediction time window. In practice, those skilled in the art can output multiple candidate beams at each time point as needed. Additionally or optionally, the multiple candidate beams output at each time point can each have a corresponding priority for more precise beam switching. Technical Effects

[0068] According to embodiments of this disclosure, several technical solutions are proposed for applying AI / ML-based beam prediction models to beam failure detection / recovery in wireless communication systems. According to embodiments of this disclosure, the beam prediction model can predict candidate beams for each of multiple future time points based on collected historical data, for use in beam switching. Within the prediction time window, the time intervals between adjacent time points can be the same or different.

[0069] In scenarios with the same time interval, this disclosure proposes the aforementioned schemes (i), (ii), and (iii), which, compared to traditional beam failure recovery mechanisms, can optimize (e.g., reduce) the measurement overhead and latency caused by beam failure recovery. In scenarios with different time intervals, this disclosure proposes the aforementioned schemes (iv) and (v), which can achieve more comprehensive historical data collection, thereby ensuring that the beam prediction model is capable of determining the dwell time of the predicted candidate beam or the beam failure probability of the predicted candidate beam, for more accurate beam switching. Exemplary Methods

[0070] Figure 6 illustrates a flowchart of an example method 600 for a user equipment (or more specifically, electronic device 200) in a wireless communication system according to an embodiment of the present disclosure. As shown in Figure 6, method 600 may include the user equipment deploying a beam prediction model (block S602). The input to the beam prediction model may include at least historical data previously collected by the user equipment, and the output of the beam prediction model may include at least candidate beams corresponding to each of a plurality of future time points. These plurality of time points are within a prediction time window. The time intervals between adjacent time points within the plurality of time points in the prediction time window may be the same or different. Detailed example operations of this method can be found in the above description of the operation of user equipment 101 (or more specifically, electronic device 200), and will not be repeated here.

[0071] Figure 7 illustrates a flowchart of an example method 700 for a network device (or more specifically, electronic device 300) in a wireless communication system according to an embodiment of the present disclosure. As shown in Figure 7, method 700 may include the network device performing beam switching (block S702) based on candidate beams reported by a user equipment to the network device. A beam prediction model may be deployed at the user equipment. The input to the beam prediction model may include at least historical data previously collected by the user equipment, and the output of the beam prediction model may include at least the candidate beams corresponding to each of a plurality of future time points. These plurality of time points are within a prediction time window. The time intervals between adjacent time points within the plurality of time points in the prediction time window may be the same or different. Detailed example operations of this method can be found in the above description of the operation of network device 102 (or more specifically, electronic device 300), and will not be repeated here.

[0072] The solutions disclosed herein can be implemented in the following exemplary manner. (1) An electronic device for a user equipment in a wireless communication system, the user equipment communicating with a network device in the wireless communication system, the electronic device including at least one processor and at least one memory, the at least one memory including computer program instructions, wherein the at least one memory and the computer program instructions are configured to cause the user equipment to perform the following operations via the at least one processor: deploying a beam prediction model, wherein the input of the beam prediction model includes at least historical data previously collected by the user equipment, and wherein the output of the beam prediction model includes at least candidate beams corresponding to each of a plurality of future time points, and wherein the plurality of time points are within a prediction time window. (2) The electronic device of (1), wherein the candidate beams include downlink beams of the network device and are used for beam switching of the network device. (3) The electronic device of (1), wherein the time interval between adjacent time points among the plurality of time points within the prediction time window is the same. (4) The electronic device of (1), wherein the time interval between adjacent time points among the plurality of time points within the prediction time window is different. (5) The electronic device according to (3), wherein the at least one memory and computer program instructions are further configured, through the at least one processor, to cause the user equipment to perform the following operations: within the prediction time window, in response to detecting that the beam quality at the current time point is lower than a first beam quality threshold, to report the candidate beams for the next time point output by the beam prediction model to the network device via a Physical Random Access Channel (PRACH) for beam switching by the network device. (6) The electronic device according to (5), wherein a beam failure occurs when the beam quality is lower than the first beam quality threshold. (7) The electronic device according to (3), wherein the at least one memory and computer program instructions are further configured, through the at least one processor, to cause the user equipment to perform the following operations: within the prediction time window, in response to detecting that the beam quality at the current time point is lower than a second beam quality threshold but higher than a first beam quality threshold, to report the candidate beams for the next time point output by the beam prediction model to the network device via Uplink Channel Information (UCI) for beam switching by the network device, wherein the second beam quality threshold is higher than the first beam quality threshold. (8) The electronic device according to (7) wherein beam failure has not yet occurred when the beam quality is lower than the second beam quality threshold but higher than the first beam quality threshold.(9) The electronic device of claim (3), wherein the at least one memory and computer program instructions are further configured, via the at least one processor, to cause the user equipment to perform the following operations: within the prediction time window, in response to detecting a frequency higher than a first beam quality threshold, reducing the length of the time interval between future adjacent time points, so as to allow the beam prediction model to output candidate beams more frequently. (10) The electronic device of claim (1), wherein the historical data includes reference signal received power (RSRP) of multiple beams of the network device previously measured by the user equipment. (11) The electronic device of claim (10), wherein the historical data further includes auxiliary data, the auxiliary data including timestamps corresponding to each historical data point and / or the moving speed of the user equipment. (12) The electronic device of claim (4), wherein the at least one memory and computer program instructions are further configured, via the at least one processor, to cause the user equipment to perform the following operations: within the time window for collecting historical data, measuring and recording signal attenuation of the beams of the network device; and based on the recorded signal attenuation, estimating the predicted dwell time of the beams of the network device for use in the beam prediction model. (13) The electronic device according to (4), wherein the at least one memory and computer program instructions are further configured, via the at least one processor, to cause the user equipment to perform the following operations: within a time window for collecting historical data, measuring and recording the beam failure frequency of the network device; and based on the recorded beam failure frequency, estimating the predicted failure probability of the network device's beam for use in a beam prediction model. (14) The electronic device according to (13), wherein the at least one memory and computer program instructions are further configured, via the at least one processor, to cause the user equipment to perform the following operations: within a prediction time window, in response to the predicted failure probability of the beam at the current time point being greater than a failure probability threshold, reporting the candidate beam for the next time point output by the beam prediction model to the network device for use in beam switching of the network device.(15) An electronic device for a network device in a wireless communication system, the network device communicating with a user equipment in the wireless communication system, the electronic device including at least one processor and at least one memory, the at least one memory including computer program instructions, wherein the at least one memory and the computer program instructions are configured, via the at least one processor, to cause the network device to perform the following operations: performing beam switching of the network device based on candidate beams reported by the user equipment to the network device, wherein a beam prediction model is deployed at the user equipment, wherein the input of the beam prediction model includes at least historical data previously collected by the user equipment, and wherein the output of the beam prediction model includes at least candidate beams corresponding to each of a plurality of future time points, and wherein the plurality of time points are within a prediction time window. (16) The electronic device of (15), wherein the candidate beams include downlink beams of the network device. (17) The electronic device of (15), wherein the time intervals between adjacent time points within the plurality of time points in the prediction time window are the same. (18) The electronic device of (15), wherein the time intervals between adjacent time points within the plurality of time points in the prediction time window are different. (19) The electronic device according to (17), wherein the at least one memory and computer program instructions are further configured, via the at least one processor, to cause the network device to perform the following operations: within the prediction time window, receiving a switching beam for the network device from a user equipment via a physical random access channel (PRACH), wherein the user equipment, in response to detecting that the beam quality at the current time point is lower than a first beam quality threshold, reports a candidate beam for the next time point output by the beam prediction model to the network device as the switching beam. (20) The electronic device according to (19), wherein a beam failure occurs when the beam quality is lower than the first beam quality threshold. (21) According to the electronic device of (17), wherein the at least one memory and computer program instructions are further configured, via the at least one processor, to cause the network device to perform the following operations: within the prediction time window, receiving a switching beam for the network device via uplink channel information (UCI), wherein the user equipment, in response to detecting that the beam quality at the current time point is lower than a second beam quality threshold but higher than a first beam quality threshold, reports the candidate beam for the next time point output by the beam prediction model to the network device as the switching beam, wherein the second beam quality threshold is higher than the first beam quality threshold. (22) According to the electronic device of (21), wherein when the beam quality is lower than the second beam quality threshold but higher than the first beam quality threshold, beam failure has not yet occurred.(23) The electronic device of (17), wherein the user equipment, within the prediction time window, in response to detecting a frequency higher than a first beam quality threshold where the beam quality is lower than a first beam quality threshold, reduces the time interval between future adjacent time points to allow the beam prediction model to output candidate beams more frequently. (24) The electronic device of (15), wherein the historical data includes reference signal received power (RSRP) of multiple beams of the network device previously measured by the user equipment. (25) The electronic device of (24), wherein the historical data further includes auxiliary data, the auxiliary data including timestamps corresponding to each historical data point and / or the moving speed of the user equipment. (26) The electronic device of (18), wherein the at least one memory and computer program instructions are further configured, through the at least one processor, to cause the network device to perform the following operations: within the time window for collecting historical data, sending multiple beams to the user equipment, wherein the user equipment measures and records signal attenuation of the beams of the network device within the time window for collecting historical data, and wherein the user equipment estimates the predicted dwell time of the beams of the network device based on the recorded signal attenuation for use in the beam prediction model. (27) The electronic device according to (18), wherein the at least one memory and computer program instructions are further configured, via the at least one processor, to cause the network device to perform the following operations: During a time window for collecting historical data, sending multiple beams to a user equipment, wherein the user equipment measures and records beam failure frequencies of the network device during the time window for collecting historical data, and wherein the user equipment estimates the predicted failure probability of the network device's beams based on the recorded beam failure frequencies for use in a beam prediction model. (28) The electronic device according to (27), wherein the at least one memory and computer program instructions are further configured, via the at least one processor, to cause the network device to perform the following operations: During the prediction time window, receiving a switching beam from a user equipment for the network device, wherein the user equipment, in response to a predicted failure probability of the beam at the current time point being greater than a failure probability threshold, reports a candidate beam for the next time point output by the beam prediction model to the network device as the switching beam. (29) A method for a user equipment in a wireless communication system, the user equipment communicating with a network device in the wireless communication system, the method comprising: deploying a beam prediction model, wherein the input of the beam prediction model includes at least historical data previously collected by the user equipment, and wherein the output of the beam prediction model includes at least candidate beams corresponding to each of a plurality of future time points, and wherein the plurality of time points are within a prediction time window.(30) A method for a network device in a wireless communication system, the network device communicating with a user equipment in the wireless communication system, the method comprising: performing beam switching of the network device based on candidate beams reported by the user equipment to the network device, wherein a beam prediction model is deployed at the user equipment, wherein the input of the beam prediction model includes at least historical data previously collected by the user equipment, and wherein the output of the beam prediction model includes at least candidate beams corresponding to each of a plurality of future time points, and wherein the plurality of time points are within a prediction time window. (31) A computer-readable storage medium having one or more instructions stored thereon, the one or more instructions, when executed by one or more processors of an electronic device, causing the electronic device to perform the method according to (29) or (30). (32) A computer program product including program instructions, the program instructions, when executed by one or more processors of a computer, causing the computer to perform the method according to (29) or (30).

[0073] It should be noted that the above application examples are merely exemplary. The embodiments of this disclosure can also be implemented in any other suitable manner within the above application examples, and the advantageous effects obtained by the embodiments of this disclosure can still be achieved. Furthermore, the embodiments of this disclosure can also be applied to other similar application examples, and the advantageous effects obtained by the embodiments of this disclosure can still be achieved.

[0074] It should be understood that the machine-executable instructions in a machine-readable storage medium or program product according to embodiments of this disclosure can be configured to perform operations corresponding to the above-described device and method embodiments. Embodiments of the machine-readable storage medium or program product will be apparent to those skilled in the art when referring to the above-described device and method embodiments, and therefore will not be described again. Machine-readable storage media and program products used to carry or include the above-described machine-executable instructions also fall within the scope of this disclosure. Such storage media may include, but are not limited to, floppy disks, optical disks, magneto-optical disks, memory cards, memory sticks, etc.

[0075] Furthermore, it should be understood that the aforementioned series of processes and devices can also be implemented via software and / or firmware. In the case of software and / or firmware implementation, programs constituting the software are installed from a storage medium or network onto a computer with a dedicated hardware architecture, such as the general-purpose personal computer 1200 shown in FIG. 8. This computer, when various programs are installed, is capable of performing various functions, etc. FIG. 8 is a block diagram illustrating an example structure of a personal computer as an information processing device that can be employed in embodiments of this disclosure. In one example, this personal computer may correspond to the exemplary terminal device described above according to this disclosure.

[0076] In Figure 8, the Central Processing Unit (CPU) 1201 performs various processes according to the program stored in the Read-Only Memory (ROM) 1202 or the program loaded from the storage section 1208 into the Random Access Memory (RAM) 1203. The RAM 1203 also stores, as needed, the data required when the CPU 1201 performs various processes, etc.

[0077] CPU 1201, ROM 1202 and RAM 1203 are connected to each other via bus 1204. Input / output interface 1205 is also connected to bus 1204.

[0078] The following components are connected to the input / output interface 1205: input section 1206, including a keyboard, mouse, etc.; output section 1207, including a display, such as a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; storage section 1208, including a hard disk, etc.; and communication section 1209, including a network interface card, such as a LAN card, modem, etc. The communication section 1209 performs communication processing via a network, such as the Internet.

[0079] As needed, drive 1210 is also connected to input / output interface 1205. Removable media 1211, such as disks, optical disks, magneto-optical disks, semiconductor memories, etc., are installed on drive 1210 as needed, so that computer programs read from them can be installed into storage section 1208 as needed.

[0080] When the above series of processes are implemented by software, the program constituting the software is installed from a network such as the Internet or a storage medium such as removable medium 1211.

[0081] Those skilled in the art will understand that such storage media are not limited to the removable medium 1211 shown in FIG. 8, which stores programs and is distributed separately from the device to provide programs to users. Examples of removable media 1211 include magnetic disks (including floppy disks (registered trademark)), optical disks (including optical disc read-only memory (CD-ROM) and digital versatile disks (DVD)), magneto-optical disks (including mini-discs (MD) (registered trademark)), and semiconductor memories. Alternatively, the storage medium may be ROM 1202, a hard disk included in storage section 1208, etc., which stores programs and is distributed to users along with the device containing them.

[0082] The technology disclosed herein can be applied to a variety of products.

[0083] For example, the electronic device 300 according to an embodiment of the present disclosure can be implemented as various network devices / base stations or included in various network devices / base stations, and the method shown in FIG. 7 can also be implemented by various network devices / base stations. For example, the electronic device 200 according to an embodiment of the present disclosure can be implemented as various user equipment / terminal devices or included in various user equipment / terminal devices, and the method shown in FIG. 6 can also be implemented by various user equipment / terminal devices.

[0084] For example, the network devices / base stations mentioned in this disclosure can be implemented as any type of base station, such as an evolved Node B (gNB). A gNB may include one or more Transmit and Receive Points (TRPs). User equipment can connect to one or more TRPs within one or more gNBs. For example, a user equipment may be able to receive transmissions from multiple gNBs (and / or multiple TRPs provided by the same gNB). For example, a gNB may include macro gNBs and small gNBs. A small gNB can be a gNB that covers a cell smaller than a macro cell, such as a pico gNB, micro gNB, and femtocell gNB. Alternatively, a base station can be implemented as any other type of base station, such as a NodeB and a Base Transceiver Station (BTS). A base station may include: a subject configured to control wireless communication (also called a base station device); and one or more remote radio heads (RRHs) located in a different location from the subject. In addition, the various types of terminals described below can operate as base stations by temporarily or semi-persistently performing base station functions.

[0085] For example, the user equipment mentioned in this disclosure, also referred to in some examples as a terminal device or UE, can be implemented as a mobile terminal (such as a smartphone, tablet PC, laptop PC, portable gaming terminal, portable / dongle-type mobile router, and digital camera device) or an in-vehicle terminal (such as a car navigation device). The user equipment can also be implemented as a terminal performing machine-to-machine (M2M) communication (also referred to as a machine-type communication (MTC) terminal). Furthermore, the user equipment can be a wireless communication module (such as an integrated circuit module comprising a single chip) installed on each of the aforementioned terminals. In some cases, the user equipment can communicate using multiple wireless communication technologies. For example, the user equipment can be configured to communicate using two or more of GSM, UMTS, CDMA2000, WiMAX, LTE, LTE-A, WLAN, NR, Bluetooth, etc. In some cases, the user equipment can also be configured to communicate using only one wireless communication technology.

[0086] Examples according to this disclosure will now be described with reference to Figures 9 to 12. Example of a base station

[0087] It should be understood that the term "base station" as used in this disclosure has the full breadth of its usual meaning and includes at least a wireless communication station used as part of a wireless communication system or radio system to facilitate communication. Examples of base stations may include, but are not limited to, the following: a base station may be one or both of a Base Transceiver Station (BTS) and a Base Station Controller (BSC) in a GSM system, one or both of a Radio Network Controller (RNC) and a Node B in a WCDMA system, an eNB in ​​LTE and LTE-Advanced systems, or a corresponding network node in a future communication system (e.g., a gNB, eLTE eNB, etc., that may appear in a 5G communication system). Some functions of the base station in this disclosure may also be implemented as an entity that controls communication in D2D, M2M, and V2V communication scenarios, or as an entity that plays a role in spectrum coordination in cognitive radio communication scenarios. First Example

[0088] Figure 9 is a block diagram illustrating a first example of a schematic configuration of a base station (gNB as an example in this figure) to which the technologies of this disclosure can be applied. The gNB 1300 includes a plurality of antennas 1310 and a base station device 1320. The base station device 1320 and each antenna 1310 can be connected to each other via RF cables. In one implementation, the gNB 1300 (or base station device 1320) here may correspond to the network device 102 described above (or more specifically, electronic device 300).

[0089] Each of the antennas 1310 includes one or more antenna elements (such as multiple antenna elements included in a multiple-input multiple-output (MIMO) antenna) and is used by the base station device 1320 to transmit and receive wireless signals. As shown in FIG9, the gNB 1300 may include multiple antennas 1310. For example, the multiple antennas 1310 may be compatible with multiple frequency bands used by the gNB 1300.

[0090] The base station equipment 1320 includes a controller 1321, a memory 1322, a network interface 1323, and a wireless communication interface 1325.

[0091] The controller 1321 can be, for example, a CPU or a DSP, and operates various higher-level functions of the base station equipment 1320. For example, the controller 1321 generates data packets based on data in signals processed by the wireless communication interface 1325, and transmits the generated packets via the network interface 1323. The controller 1321 can bundle data from multiple baseband processors to generate bundled packets and transmit the generated bundled packets. The controller 1321 may have logical functions that perform controls such as radio resource control, radio bearer control, mobility management, admission control, and scheduling. This control can be performed in conjunction with nearby gNBs or core network nodes. The memory 1322 includes RAM and ROM, and stores programs executed by the controller 1321 and various types of control data (such as terminal lists, transmission power data, and scheduling data).

[0092] Network interface 1323 is a communication interface for connecting base station equipment 1320 to core network 1324. Controller 1321 can communicate with core network nodes or other gNBs via network interface 1323. In this case, gNB 1300 and core network nodes or other gNBs can be connected to each other via logical interfaces (such as S1 and X2 interfaces). Network interface 1323 can also be a wired communication interface or a wireless communication interface for wireless backhaul. If network interface 1323 is a wireless communication interface, it can use a higher frequency band for wireless communication compared to the frequency band used by wireless communication interface 1325.

[0093] Wireless communication interface 1325 supports any cellular communication scheme (such as LTE and LTE-Advanced) and provides wireless connectivity to terminals located in the cell of gNB 1300 via antenna 1310. Wireless communication interface 1325 typically includes, for example, a baseband (BB) processor 1326 and RF circuitry 1327. BB processor 1326 can perform, for example, encoding / decoding, modulation / demodulation, and multiplexing / demultiplexing, and performs various types of signal processing at layers such as L1, Media Access Control (MAC), Radio Link Control (RLC), and Packet Data Convergence Protocol (PDCP). Instead of controller 1321, BB processor 1326 may have some or all of the above-described logical functions. BB processor 1326 may be a memory storing communication control programs, or a module including a processor and associated circuitry configured to execute programs. Update programs can change the functionality of BB processor 1326. The module may be a card or blade inserted into a slot in base station equipment 1320. Alternatively, the module may be a chip mounted on a card or blade. Meanwhile, the RF circuit 1327 may include, for example, a mixer, a filter, and an amplifier, and transmits and receives wireless signals via the antenna 1310. Although Figure 9 shows an example of an RF circuit 1327 connected to one antenna 1310, this disclosure is not limited to this illustration, but an RF circuit 1327 may be connected to multiple antennas 1310 simultaneously.

[0094] As shown in Figure 9, the wireless communication interface 1325 may include multiple BB processors 1326. For example, the multiple BB processors 1326 may be compatible with multiple frequency bands used by the gNB 1300. As shown in Figure 9, the wireless communication interface 1325 may include multiple RF circuits 1327. For example, the multiple RF circuits 1327 may be compatible with multiple antenna elements. Although Figure 9 shows an example in which the wireless communication interface 1325 includes multiple BB processors 1326 and multiple RF circuits 1327, the wireless communication interface 1325 may also include a single BB processor 1326 or a single RF circuit 1327. Second Example

[0095] Figure 10 is a block diagram illustrating a second example of a schematic configuration of a base station (gNB as an example in this figure) to which the technologies of this disclosure can be applied. The gNB 1430 includes multiple antennas 1440, a base station device 1450, and an RRH 1460. The RRH 1460 and each antenna 1440 can be connected to each other via RF cables. The base station device 1450 and the RRH 1460 can be connected to each other via high-speed lines such as fiber optic cables. In one implementation, the gNB 1430 (or base station device 1450) here may correspond to the network device 102 described above (or more specifically, electronic device 300).

[0096] Each of the antennas 1440 includes one or more antenna elements (such as multiple antenna elements included in a MIMO antenna) and is used by the RRH 1460 to transmit and receive wireless signals. As shown in Figure 10, the gNB 1430 may include multiple antennas 1440. For example, multiple antennas 1440 may be compatible with multiple frequency bands used by the gNB 1430.

[0097] The base station device 1450 includes a controller 1451, a memory 1452, a network interface 1453, a wireless communication interface 1455, and a connection interface 1457. The controller 1451, memory 1452, and network interface 1453 are the same as the controller 1321, memory 1322, and network interface 1323 described with reference to FIG9.

[0098] Wireless communication interface 1455 supports any cellular communication scheme (such as LTE and LTE-Advanced) and provides wireless communication to terminals located in the sector corresponding to RRH 1460 via RRH 1460 and antenna 1440. Wireless communication interface 1455 may typically include, for example, a BB processor 1456. The BB processor 1456 is identical to the BB processor 1326 described with reference to FIG9, except that it is connected to the RF circuitry 1464 of RRH 1460 via connection interface 1457. As shown in FIG10, wireless communication interface 1455 may include multiple BB processors 1456. For example, multiple BB processors 1456 may be compatible with multiple frequency bands used by gNB 1430. Although FIG10 shows an example in which wireless communication interface 1455 includes multiple BB processors 1456, wireless communication interface 1455 may also include a single BB processor 1456.

[0099] Connection interface 1457 is an interface for connecting base station device 1450 (wireless communication interface 1455) to RRH 1460. Connection interface 1457 may also be a communication module for communication in the aforementioned high-speed line connecting base station device 1450 (wireless communication interface 1455) to RRH 1460.

[0100] The RRH 1460 includes a connectivity interface 1461 and a wireless communication interface 1463.

[0101] Connection interface 1461 is an interface for connecting RRH 1460 (wireless communication interface 1463) to base station equipment 1450. Connection interface 1461 can also be a communication module for communication in the aforementioned high-speed line.

[0102] Wireless communication interface 1463 transmits and receives wireless signals via antenna 1440. Wireless communication interface 1463 typically includes, for example, RF circuitry 1464. RF circuitry 1464 may include, for example, a mixer, filter, and amplifier, and transmits and receives wireless signals via antenna 1440. Although Figure 10 shows an example of an RF circuitry 1464 connected to one antenna 1440, this disclosure is not limited to this illustration, and an RF circuitry 1464 may be connected to multiple antennas 1440 simultaneously.

[0103] As shown in Figure 10, the wireless communication interface 1463 may include multiple RF circuits 1464. For example, multiple RF circuits 1464 may support multiple antenna elements. Although Figure 10 shows an example in which the wireless communication interface 1463 includes multiple RF circuits 1464, the wireless communication interface 1463 may also include a single RF circuit 1464.

[0104] In the gNB 1300 shown in Figure 9 and the gNB 1430 shown in Figure 10, the communication unit 302, such as that in Figure 3, can be implemented by the wireless communication interface 1325, the wireless communication interface 1455 and / or the wireless communication interface 1463; the processing unit 304 can be implemented by the controller 1321 and the controller 1451.

[0105] Example 1 regarding user equipment

[0106] Figure 11 is a block diagram illustrating an example of a schematic configuration of a smartphone 1500 to which the technology of this disclosure can be applied. The smartphone 1500 includes a processor 1501, a memory 1502, a storage device 1503, an external connection interface 1504, a camera device 1506, a sensor 1507, a microphone 1508, an input device 1509, a display device 1510, a speaker 1511, a wireless communication interface 1512, one or more antenna switches 1515, one or more antennas 1516, a bus 1517, a battery 1518, and an auxiliary controller 1519. In one implementation, the smartphone 1500 (or processor 1501) herein may correspond to the user equipment 101 described above (or more specifically, electronic device 200).

[0107] Processor 1501 may be, for example, a CPU or a system-on-a-chip (SoC), and controls the application layer and other functions of smartphone 1500. Memory 1502 includes RAM and ROM, and stores data and programs executed by processor 1501. Storage device 1503 may include storage media such as semiconductor memory and hard disk. External connectivity interface 1504 is an interface for connecting external devices, such as memory cards and Universal Serial Bus (USB) devices, to smartphone 1500.

[0108] The camera device 1506 includes an image sensor (such as a charge-coupled device (CCD) and complementary metal-oxide-semiconductor (CMOS)) and generates captured images. The sensor 1507 may include a set of sensors, such as a measurement sensor, a gyroscope sensor, a magnetometer sensor, and an accelerometer sensor. The microphone 1508 converts sound input to the smartphone 1500 into an audio signal. The input device 1509 includes, for example, a touch sensor, keypad, keyboard, buttons, or switches configured to detect touches on the screen of the display device 1510 and receives operations or information input from the user. The display device 1510 includes a screen (such as a liquid crystal display (LCD) and an organic light-emitting diode (OLED) display) and displays the output image of the smartphone 1500. The speaker 1511 converts the audio signal output from the smartphone 1500 into sound.

[0109] Wireless communication interface 1512 supports any cellular communication scheme (such as LTE and LTE-Advanced) and performs wireless communication. Wireless communication interface 1512 typically includes, for example, a BB processor 1513 and RF circuitry 1514. BB processor 1513 can perform, for example, encoding / decoding, modulation / demodulation, and multiplexing / demultiplexing, and performs various types of signal processing for wireless communication. Meanwhile, RF circuitry 1514 can include, for example, mixers, filters, and amplifiers, and transmits and receives wireless signals via antenna 1516. Wireless communication interface 1512 can be a single chip module on which BB processor 1513 and RF circuitry 1514 are integrated. As shown in Figure 11, wireless communication interface 1512 can include multiple BB processors 1513 and multiple RF circuits 1514. Although Figure 11 shows an example where wireless communication interface 1512 includes multiple BB processors 1513 and multiple RF circuits 1514, wireless communication interface 1512 can also include a single BB processor 1513 or a single RF circuitry 1514.

[0110] In addition to cellular communication schemes, wireless communication interface 1512 can support other types of wireless communication schemes, such as short-range wireless communication schemes, near-field communication schemes, and wireless local area network (LAN) schemes. In this case, wireless communication interface 1512 may include a BB processor 1513 and RF circuitry 1514 for each wireless communication scheme.

[0111] Each of the antenna switches 1515 switches the connection destination of the antenna 1516 among multiple circuits (e.g., circuits for different wireless communication schemes) included in the wireless communication interface 1512.

[0112] Each of the antennas 1516 includes one or more antenna elements (such as multiple antenna elements included in a MIMO antenna) and is used for transmitting and receiving wireless signals through the wireless communication interface 1512. As shown in Figure 11, the smartphone 1500 may include multiple antennas 1516. Although Figure 11 shows an example in which the smartphone 1500 includes multiple antennas 1516, the smartphone 1500 may also include a single antenna 1516.

[0113] Furthermore, the smartphone 1500 may include an antenna 1516 for each wireless communication scheme. In this case, the antenna switch 1515 can be omitted from the configuration of the smartphone 1500.

[0114] Bus 1517 connects the processor 1501, memory 1502, storage device 1503, external connection interface 1504, camera device 1506, sensor 1507, microphone 1508, input device 1509, display device 1510, speaker 1511, wireless communication interface 1512, and auxiliary controller 1519 to each other. Battery 1518 supplies power to the various blocks of smartphone 1500 shown in FIG11 via feeders, which are partially shown as dashed lines in the figure. Auxiliary controller 1519 operates the minimum necessary functions of smartphone 1500, for example, in sleep mode.

[0115] In the smartphone 1500 shown in Figure 11, the communication unit 202, such as that in Figure 2, can be implemented by the wireless communication interface 1512; the processing unit 204 can be implemented by the processor 1501 or the auxiliary controller 1519. Second Example

[0116] Figure 12 is a block diagram illustrating an example of a schematic configuration of a car navigation device 1620 to which the technology of this disclosure can be applied. The car navigation device 1620 includes a processor 1621, a memory 1622, a Global Positioning System (GPS) module 1624, a sensor 1625, a data interface 1626, a content player 1627, a storage medium interface 1628, an input device 1629, a display device 1630, a speaker 1631, a wireless communication interface 1633, one or more antenna switches 1636, one or more antennas 1637, and a battery 1638. In one implementation, the car navigation device 1620 (or processor 1621) described herein may correspond to the user equipment 101 described above (or more specifically, electronic device 200).

[0117] The processor 1621 can be, for example, a CPU or a SoC, and controls the navigation functions and other functions of the car navigation device 1620. The memory 1622 includes RAM and ROM, and stores data and programs executed by the processor 1621.

[0118] GPS module 1624 uses GPS signals received from GPS satellites to measure the location (such as latitude, longitude, and altitude) of car navigation device 1620. Sensor 1625 may include a set of sensors, such as a gyroscope sensor, a geomagnetic sensor, and an air pressure sensor. Data interface 1626 is connected to, for example, an in-vehicle network 1641 via a terminal not shown, and acquires data generated by the vehicle (such as vehicle speed data).

[0119] Content player 1627 reproduces content stored on storage media (such as CDs and DVDs), which is inserted into storage media interface 1628. Input device 1629 includes, for example, a touch sensor, button, or switch configured to detect touch on the screen of display device 1630, and receives operations or information input from the user. Display device 1630 includes a screen such as an LCD or OLED display and displays images or reproduced content for navigation functions. Speaker 1631 outputs sound for navigation functions or reproduced content.

[0120] The wireless communication interface 1633 supports any cellular communication scheme (such as LTE and LTE-Advanced) and performs wireless communication. The wireless communication interface 1633 typically includes, for example, a BB processor 1634 and RF circuitry 1635. The BB processor 1634 can perform, for example, encoding / decoding, modulation / demodulation, and multiplexing / demultiplexing, and performs various types of signal processing for wireless communication. Meanwhile, the RF circuitry 1635 can include, for example, mixers, filters, and amplifiers, and transmits and receives wireless signals via antenna 1637. The wireless communication interface 1633 can also be a chip module on which the BB processor 1634 and RF circuitry 1635 are integrated. As shown in Figure 12, the wireless communication interface 1633 can include multiple BB processors 1634 and multiple RF circuits 1635. Although Figure 12 shows an example where the wireless communication interface 1633 includes multiple BB processors 1634 and multiple RF circuits 1635, the wireless communication interface 1633 can also include a single BB processor 1634 or a single RF circuitry 1635.

[0121] In addition to cellular communication schemes, the wireless communication interface 1633 can support other types of wireless communication schemes, such as short-range wireless communication schemes, near-field communication schemes, and wireless LAN schemes. In this case, for each wireless communication scheme, the wireless communication interface 1633 may include a BB processor 1634 and an RF circuit 1635.

[0122] Each of the antenna switches 1636 switches the connection destination of the antenna 1637 among multiple circuits (such as circuits for different wireless communication schemes) included in the wireless communication interface 1633.

[0123] Each of the antennas 1637 includes one or more antenna elements (such as multiple antenna elements included in a MIMO antenna) and is used for transmitting and receiving wireless signals through the wireless communication interface 1633. As shown in Figure 12, the car navigation device 1620 may include multiple antennas 1637. Although Figure 12 shows an example in which the car navigation device 1620 includes multiple antennas 1637, the car navigation device 1620 may also include a single antenna 1637.

[0124] Furthermore, the car navigation device 1620 may include an antenna 1637 for each wireless communication scheme. In this case, the antenna switch 1636 can be omitted from the configuration of the car navigation device 1620.

[0125] Battery 1638 supplies power to the various blocks of the car navigation device 1620 shown in Figure 12 via feeders, which are partially shown as dashed lines in the figure. Battery 1638 accumulates the power supplied from the vehicle.

[0126] In the car navigation device 1620 shown in Figure 12, the communication unit 202, such as that in Figure 2, can be implemented by the wireless communication interface 1633; the processing unit 204 can be implemented by the processor 1621.

[0127] The technology disclosed herein can also be implemented as an in-vehicle system (or vehicle) 1640 including one or more blocks of an automotive navigation device 1620, an in-vehicle network 1641, and a vehicle module 1642. The vehicle module 1642 generates vehicle data (such as vehicle speed, engine speed, and fault information) and outputs the generated data to the in-vehicle network 1641.

[0128] Exemplary embodiments of the present disclosure have been described above with reference to the accompanying drawings; however, the present disclosure is by no means limited to the examples described above. Various changes and modifications can be made by those skilled in the art within the scope of the appended claims, and it should be understood that such changes and modifications naturally fall within the technical scope of the present disclosure.

[0129] For example, the multiple functions included in one unit in the above embodiments can be implemented by separate devices. Alternatively, the multiple functions implemented by multiple units in the above embodiments can be implemented by separate devices respectively. In addition, one of the above functions can be implemented by multiple units. Needless to say, such a configuration is included within the scope of the present disclosure.

[0130] In this specification, the steps described in the flowchart include not only processes executed sequentially in the stated order, but also processes executed in parallel or individually, rather than necessarily sequentially. Furthermore, even within the steps of sequential processing, needless to say, the order can be appropriately altered.

[0131] While this disclosure and its advantages have been described in detail, it should be understood that various changes, substitutions, and modifications can be made without departing from the spirit and scope of this disclosure as defined by the appended claims. Furthermore, the terms "comprising," "including," or any other variations thereof used in embodiments of this disclosure are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

Claims

1. An electronic device for a user equipment in a wireless communication system, the user equipment communicating with a network device in the wireless communication system, the electronic device comprising at least one processor and at least one memory including computer program instructions, wherein the at least one memory and the computer program instructions are configured to, with the at least one processor, cause the user equipment to perform the following operations: deploy a beam prediction model, wherein inputs of the beam prediction model comprise at least historical data previously collected by the user equipment, and wherein outputs of the beam prediction model comprise at least a candidate beam corresponding to each of a plurality of time points in the future, and wherein the plurality of time points are within a prediction time window. 2.The electronic device of claim 1, wherein the candidate beam comprises a downlink beam of the network device and is for a beam switch of the network device. 3.The electronic device of claim 1, wherein time intervals between adjacent time points of the plurality of time points within the prediction time window are the same. 4.The electronic device of claim 1, wherein time intervals between adjacent time points of the plurality of time points within the prediction time window are different. 5.The electronic device of claim 3, wherein the at least one memory and the computer program instructions are further configured to, with the at least one processor, cause the user equipment to perform the following operation: within the prediction time window, in response to detecting that a beam quality of a current time point is below a first beam quality threshold, report a candidate beam of a next time point output by the beam prediction model to the network device through a physical random access channel (PRACH) for a beam switch of the network device. 6.The electronic device of claim 5, wherein a beam failure occurs when the beam quality is below the first beam quality threshold. 7.The electronic device of claim 3, wherein the at least one memory and the computer program instructions are further configured to, with the at least one processor, cause the user equipment to perform the following operation: within the prediction time window, in response to detecting that a beam quality of a current time point is below a second beam quality threshold but above the first beam quality threshold, report a candidate beam of a next time point output by the beam prediction model to the network device through an uplink channel information (UCI) for a beam switch of the network device, wherein the second beam quality threshold is higher than the first beam quality threshold. 8.The electronic device of claim 7, wherein a beam failure has not occurred when the beam quality is below the second beam quality threshold but above the first beam quality threshold. 9.The electronic device of claim 3, wherein the at least one memory and the computer program instructions are further configured to, with the at least one processor, cause the user equipment to perform the following operation: In the prediction time window, in response to detecting that the frequency of the beam quality being lower than the first beam quality threshold is higher than a frequency threshold, reducing the length of the time interval between future adjacent time points for the beam prediction model to output candidate beams more frequently.

10. The electronic device of claim 1, wherein the historical data comprises reference signal received power (RSRP) of a plurality of beams of the network device previously measured by the user device.

11. The electronic device of claim 10, wherein the historical data further comprises auxiliary data comprising a timestamp corresponding to each historical data and / or a moving speed of the user device.

12. The electronic device of claim 4, wherein the at least one memory and computer program instructions are further configured to, with the at least one processor, cause the user device to perform the following operations: measuring and recording signal attenuation conditions of beams of the network device within a time window of collecting the historical data; and estimating predicted dwell time of the beams of the network device based on the recorded signal attenuation conditions for the beam prediction model.

13. The electronic device of claim 4, wherein the at least one memory and computer program instructions are further configured to, with the at least one processor, cause the user device to perform the following operations: measuring and recording beam failure frequency of beams of the network device within a time window of collecting the historical data; and estimating predicted failure probability of the beams of the network device based on the recorded beam failure frequency for the beam prediction model.

14. The electronic device of claim 13, wherein the at least one memory and computer program instructions are further configured to, with the at least one processor, cause the user device to perform the following operations: in a prediction time window, in response to the predicted failure probability of a beam of a current time point being greater than a failure probability threshold, reporting a candidate beam of a next time point output by the beam prediction model to the network device for beam switching of the network device.

15. An electronic device for a network device in a wireless communication system, the network device communicating with a user device in the wireless communication system, the electronic device comprising at least one processor and at least one memory including computer program instructions, wherein the at least one memory and the computer program instructions are configured to, with the at least one processor, cause the network device to perform the following operations: performing beam switching of the network device based on a candidate beam reported by the user device to the network device, wherein a beam prediction model is deployed at the user device, wherein inputs of the beam prediction model comprise at least historical data previously collected by the user device, and wherein outputs of the beam prediction model comprise at least a candidate beam corresponding to each of a plurality of future time points, and wherein the plurality of time points are within a prediction time window.

16. The electronic device of claim 15, wherein the candidate beam comprises a downlink beam of the network device.

17. The electronic device of claim 15, wherein a time interval between adjacent time points of the plurality of time points within the prediction time window is the same.

18. The electronic device of claim 15, wherein a time interval between adjacent time points of the plurality of time points within the prediction time window is different.

19. The electronic device of claim 17, wherein the at least one memory and the computer program instructions are further configured to, with the at least one processor, cause the network device to perform operations of: receiving, from a user device, a switching beam for the network device through a physical random access channel (PRACH) within the prediction time window, wherein the user device reports a candidate beam at a next time point output by the beam prediction model to the network device as the switching beam in response to detecting that a beam quality at a current time point is below a first beam quality threshold.

20. The electronic device of claim 19, wherein a beam failure occurs when the beam quality is below the first beam quality threshold.

21. The electronic device of claim 17, wherein the at least one memory and the computer program instructions are further configured to, with the at least one processor, cause the network device to perform operations of: receiving, from a user device, a switching beam for the network device through uplink channel information (UCI) within the prediction time window, wherein the user device reports a candidate beam at a next time point output by the beam prediction model to the network device as the switching beam in response to detecting that a beam quality at a current time point is below a second beam quality threshold but above a first beam quality threshold, wherein the second beam quality threshold is higher than the first beam quality threshold.

22. The electronic device of claim 21, wherein a beam failure has not occurred when the beam quality is below the second beam quality threshold but above the first beam quality threshold.

23. The electronic device of claim 17, wherein the user device, within the prediction time window, decreases a time interval between future adjacent time points for the beam prediction model to output candidate beams more frequently in response to detecting that a frequency of beam qualities being below the first beam quality threshold is higher than a frequency threshold.

24. The electronic device of claim 15, wherein the historical data comprises reference signal received power (RSRP) of a plurality of beams of a network device previously measured by the user device.

25. The electronic device of claim 24, wherein the historical data further comprises auxiliary data comprising a timestamp corresponding to each historical data and / or a moving speed of the user device.

26. The electronic device of claim 18, wherein the at least one memory and the computer program instructions are further configured to, with the at least one processor, cause the network device to perform operations of: transmitting, to a user device, a plurality of beams within a time window in which the historical data is collected, ​ ​ ​ wherein the user device measures and records signal attenuation conditions with respect to beams of the network device within a time window of collecting historical data, and wherein the user device estimates predicted dwell times of beams of the network device based on the recorded signal attenuation conditions for a beam prediction model. 27.The electronic device of claim 18, wherein the at least one memory and the computer program instructions are further configured to, with the at least one processor, cause the network device to perform the following operations: sending a plurality of beams to the user device within a time window of collecting historical data, wherein the user device measures and records beam failure frequencies with respect to beams of the network device within the time window of collecting historical data, and wherein the user device estimates predicted failure probabilities of beams of the network device based on the recorded beam failure frequencies for the beam prediction model. 28.The electronic device of claim 27, wherein the at least one memory and the computer program instructions are further configured to, with the at least one processor, cause the network device to perform the following operations: receiving a handover beam for the network device from the user device within the predicted time window, wherein the user device reports a candidate beam outputted by the beam prediction model at a next time point to the network device as the handover beam in response to a predicted failure probability of a beam at a current time point being greater than a failure probability threshold. 29.A method for a user device in a wireless communication system, the user device being in communication with a network device in the wireless communication system, the method comprising: deploying a beam prediction model, wherein inputs of the beam prediction model comprise at least historical data previously collected by the user device, and wherein outputs of the beam prediction model comprise at least candidate beams corresponding to each of a plurality of time points in the future, and wherein the plurality of time points are within a predicted time window. 30.A method for a network device in a wireless communication system, the network device being in communication with a user device in the wireless communication system, the method comprising: performing beam handover of the network device based on candidate beams reported by the user device to the network device, wherein a beam prediction model is deployed at the user device, wherein inputs of the beam prediction model comprise at least historical data previously collected by the user device, and wherein outputs of the beam prediction model comprise at least candidate beams corresponding to each of a plurality of time points in the future, and wherein the plurality of time points are within a predicted time window. 31.A computer-readable storage medium having stored thereon one or more instructions that, when executed by one or more processors of an electronic device, cause the electronic device to perform the method of claim 29 or 30. 32.A computer program product comprising program instructions that, when executed by one or more processors of a computer, cause the computer to perform the method of claim 29 or 30.

Images