Beam switching method, apparatus, and processor-readable storage medium

Abstract

The application provides a beam switching method, comprising: obtaining first quality information corresponding to a plurality of first beams respectively in a first time period, wherein the first quality information corresponding to the plurality of first beams respectively comprises first quality information sent by at least one user equipment (UE) to a first network node; determining first average channel quality corresponding to the plurality of first beams based on the first quality information corresponding to the plurality of first beams respectively; determining a first state vector based on the first average channel quality corresponding to the plurality of first beams and second average channel quality corresponding to a plurality of second beams in at least one second time period; the at least one second time period is before the first time period; and determining a beam switching threshold corresponding to at least one UE based on the first state vector. The method dynamically adjusts the beam switching threshold corresponding to the at least one UE, and ensures appropriate beam switching frequency.

Description

Technical Field

[0001] This application relates to the field of wireless communication technology, and more specifically, to beam switching methods, apparatus, and processor-readable storage media. Background Technology

[0002] In existing technologies, the channel between a network node and a UE (User Equipment) may change due to obstacles or UE rotation or movement, resulting in reduced beam quality or the use of other beams with better quality. In such cases, beam handover is necessary to achieve better system performance. During handover based on a fixed handover threshold, a low threshold, while maintaining good system performance, leads to frequent or even unnecessary handovers, increasing load overhead. Conversely, a high threshold reduces handover frequency, but some handovers may not trigger in a timely manner, compromising system performance. Summary of the Invention

[0003] This application addresses the shortcomings of existing methods by proposing a beam switching method, apparatus, and processor-readable storage medium to resolve the aforementioned technical deficiencies.

[0004] Firstly, a beam switching method is provided, executed by a first network node, including:

[0005] Obtain first quality information corresponding to multiple first beams within a first time period, wherein the first quality information corresponding to multiple first beams includes first quality information sent by at least one user equipment (UE) to a first network node.

[0006] Based on the first quality information corresponding to each of the multiple first beams, the first average channel quality corresponding to the multiple first beams is determined.

[0007] A first state vector is determined based on the first average channel quality corresponding to multiple first beams and the second average channel quality corresponding to multiple second beams within at least one second time period; the at least one second time period is prior to the first time period.

[0008] Based on the first state vector, determine the beam switching threshold corresponding to at least one UE.

[0009] In one embodiment, obtaining the first quality information corresponding to multiple first beams within a first time period includes:

[0010] Acquire the first quality information sent by the second network node within the first time period; and receive the first quality information sent by at least one UE;

[0011] The first quality information includes at least one of the following: signal-to-noise ratio (SINR), received power (RSRP), and received quality (RSRQ).

[0012] In one embodiment, a first state vector is determined based on the first average channel quality corresponding to multiple first beams and the second average channel quality corresponding to multiple second beams within at least one second time period, including:

[0013] The first average channel quality is quantized and mapped to obtain the value of the first information vector corresponding to the first average channel quality; the second average channel quality is quantized and mapped to obtain the value of the second information vector corresponding to the second average channel quality.

[0014] A first state vector is obtained based on a first information vector and at least one second information vector.

[0015] In one embodiment, determining the beam switching threshold for at least one UE based on the first state vector includes:

[0016] The first state vector is input into the first relation model for matching processing to obtain one or more reward values ​​that match the first state vector. The beam switching threshold corresponding to the largest reward value among the one or more reward values ​​is determined as the beam switching threshold corresponding to the UE.

[0017] The first relational model is used to characterize the relationship between the first state vector, the reward value, and the beam switching threshold.

[0018] In one embodiment, the first relationship model is determined by a first parameter corresponding to a change in a first metric of at least one UE, and a second parameter corresponding to the beam switching cost.

[0019] In one embodiment, the first relational model is trained in the following way:

[0020] Construct a training sample set; based on the training sample set, train the relation model to obtain the first relation model;

[0021] Training a relational model based on a training sample set includes at least the following:

[0022] The second state vector from the training sample set is input into the relational model to determine the beam switching threshold corresponding to the second state vector.

[0023] Based on the beam switching threshold and reward function corresponding to the second state vector, the reward value corresponding to the second state vector is determined.

[0024] The loss function value is determined based on the second state vector, the reward value corresponding to the second state vector, and the loss function corresponding to the relation model.

[0025] Based on the loss function value, the model parameters of the relational model are updated to obtain the updated relational model.

[0026] In one embodiment, training the relation model based on a training sample set further includes:

[0027] If the termination condition is not met, repeat the following steps:

[0028] The second state vector from the training sample set is input into the updated relational model to determine the beam switching threshold corresponding to the second state vector.

[0029] Based on the beam switching threshold and reward function corresponding to the second state vector, the reward value corresponding to the second state vector is determined.

[0030] The loss function value is determined based on the second state vector, the reward value corresponding to the second state vector, and the loss function corresponding to the updated relation model.

[0031] Based on the loss function value, the model parameters of the updated relational model are updated to obtain the updated relational model.

[0032] In one embodiment, after determining the loss function value based on the second state vector, the reward value corresponding to the second state vector, and the loss function corresponding to the relation model, the method further includes:

[0033] Determine whether the termination condition has been met;

[0034] If the termination condition is determined to be met, the first relation model is obtained;

[0035] The termination condition is one of the following:

[0036] The loss function value is less than or equal to the loss function value threshold; or,

[0037] The loss function value is greater than or equal to the loss function value threshold.

[0038] In one embodiment, first quality information sent by at least one UE to a first network node is sent to a second network node.

[0039] Secondly, a beam switching method is provided, executed by the UE, including:

[0040] Send the first quality information corresponding to the first beam within a first time period to the first network node; so that the first network node obtains the first quality information corresponding to multiple beams within the first time period, and determines the beam switching threshold corresponding to the UE based on the first quality information corresponding to multiple beams and the average channel quality corresponding to multiple beams within at least one second time period.

[0041] Receive the beam switching threshold corresponding to the UE sent by the first network node, and perform beam switching based on the beam switching threshold.

[0042] Thirdly, a beam switching device is provided for use in a first network node, including a memory, a transceiver, and a processor.

[0043] Memory is used to store computer programs; transceiver is used to send and receive data under the control of the processor; processor is used to read the computer programs from memory and perform the following operations:

[0044] Obtain first quality information corresponding to multiple first beams within a first time period, wherein the first quality information corresponding to multiple first beams includes first quality information sent by at least one user equipment (UE) to a first network node.

[0045] Based on the first quality information corresponding to each of the multiple first beams, the first average channel quality corresponding to the multiple first beams is determined.

[0046] A first state vector is determined based on the first average channel quality corresponding to multiple first beams and the second average channel quality corresponding to multiple second beams within at least one second time period; the at least one second time period is prior to the first time period.

[0047] Based on the first state vector, determine the beam switching threshold corresponding to at least one UE.

[0048] Fourthly, a beam switching device is provided for use in a UE, including a memory, a transceiver, and a processor.

[0049] Memory is used to store computer programs; transceiver is used to send and receive data under the control of the processor; processor is used to read the computer programs from memory and perform the following operations:

[0050] Send the first quality information corresponding to the first beam within a first time period to the first network node; so that the first network node obtains the first quality information corresponding to multiple beams within the first time period, and determines the beam switching threshold corresponding to the UE based on the first quality information corresponding to multiple beams and the average channel quality corresponding to multiple beams within at least one second time period.

[0051] Receive the beam switching threshold corresponding to the UE sent by the first network node, and perform beam switching based on the beam switching threshold.

[0052] Fifthly, this application provides a beam switching device applied to a first network node, comprising:

[0053] The first processing unit is configured to acquire first quality information corresponding to multiple first beams within a first time period, wherein the first quality information corresponding to multiple first beams includes first quality information sent by at least one user equipment (UE) to the first network node.

[0054] The second processing unit is used to determine the first average channel quality corresponding to the multiple first beams based on the first quality information corresponding to the multiple first beams respectively.

[0055] The third processing unit is used to determine a first state vector based on the first average channel quality corresponding to multiple first beams and the second average channel quality corresponding to multiple second beams within at least one second time period; the at least one second time period is before the first time period.

[0056] The fourth processing unit is used to determine the beam switching threshold corresponding to at least one UE based on the first state vector.

[0057] Sixthly, this application provides a beam switching device applied to a UE, comprising:

[0058] The fifth processing unit is used to send the first quality information corresponding to the first beam within a first time period to the first network node; so that the first network node can obtain the first quality information corresponding to multiple beams within the first time period, and determine the beam switching threshold corresponding to the UE based on the first quality information corresponding to multiple beams and the average channel quality corresponding to multiple beams within at least one second time period.

[0059] The sixth processing unit is used to receive the beam switching threshold corresponding to the UE sent by the first network node, and to perform beam switching based on the beam switching threshold.

[0060] A seventh aspect provides a processor-readable storage medium, characterized in that the processor-readable storage medium stores a computer program for causing the processor to perform the methods described in the first and second aspects.

[0061] The technical solution provided in this application has at least the following beneficial effects:

[0062] It enables dynamic adjustment of the beam switching threshold for at least one UE, thereby ensuring an appropriate beam switching frequency while maintaining system performance.

[0063] Additional aspects and advantages of this application will be set forth in part in the description which follows, and will become apparent from the description or may be learned by practice of this application. Attached Figure Description

[0064] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments of this application will be briefly introduced below.

[0065] Figure 1 A schematic diagram of the system architecture provided for embodiments of this application;

[0066] Figure 2 A schematic flowchart illustrating a beam switching method provided in an embodiment of this application;

[0067] Figure 3 A schematic diagram of beam switching provided in an embodiment of this application;

[0068] Figure 4 A flowchart illustrating another beam switching method provided in an embodiment of this application;

[0069] Figure 5 A schematic diagram of the reinforcement learning process provided in the embodiments of this application;

[0070] Figure 6 A flowchart illustrating another beam switching method provided in an embodiment of this application;

[0071] Figure 7 A flowchart illustrating another beam switching method provided in an embodiment of this application;

[0072] Figure 8 A schematic diagram of SINR statistics provided in the embodiments of this application;

[0073] Figure 9 A schematic diagram of SINR statistics provided in the embodiments of this application;

[0074] Figure 10 A schematic diagram illustrating the switching count statistics provided in an embodiment of this application;

[0075] Figure 11 This is a schematic diagram of the structure of a beam switching device provided in an embodiment of this application;

[0076] Figure 12 This is a schematic diagram of the structure of a beam switching device provided in an embodiment of this application;

[0077] Figure 13 This is a schematic diagram of the structure of a beam switching device provided in an embodiment of this application;

[0078] Figure 14 This is a schematic diagram of the structure of a beam switching device provided in an embodiment of this application. Detailed Implementation

[0079] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain this application, and should not be construed as limiting this application.

[0080] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this application means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It should be understood that when we say an element is “connected” or “coupled” to another element, it can be directly connected or coupled to the other element, or there may be intermediate elements. Furthermore, “connected” or “coupled” as used herein can include wireless connections or wireless coupling. The term “and / or” as used herein includes all or any units and all combinations of one or more associated listed items.

[0081] In this application's embodiments, the term "and / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship. In this application's embodiments, the term "multiple" refers to two or more, and other quantifiers are similar.

[0082] In this application, "determining B based on A" means that factor A must be considered when determining B. It is not limited to "B can be determined based solely on A," but should also include: "determining B based on A and C," "determining B based on A, C, and E," "determining C based on A, and further determining B based on C," etc. Additionally, it can include using A as a condition for determining B, for example, "when A satisfies the first condition, B is determined using the first method"; another example, "when A satisfies the second condition, B is determined," etc.; another example, "when A satisfies the third condition, B is determined based on the first parameter," etc. Of course, it can also be a condition where A is a factor in determining B, for example, "when A satisfies the first condition, C is determined using the first method, and B is further determined based on C," etc.

[0083] In this application, "determine B based on A" means that factor A must be considered when determining B. It is not limited to "B can be determined based solely on A," but should also include: "determine B based on A and C," "determine B based on A, C, and E," "determine C based on A, and further determine B based on C," etc. Additionally, it can include using A as a condition for determining B, for example, "when A satisfies the first condition, determine B using the first method"; another example, "when A satisfies the second condition, determine B," etc.; another example, "when A satisfies the third condition, determine B based on the first parameter," etc. Of course, it can also be a condition where A is a factor in determining B, for example, "when A satisfies the first condition, determine C using the first method, and further determine B based on C," etc.

[0084] To better understand and explain the solutions of the embodiments of this disclosure, some technical terms involved in the embodiments of this disclosure will be briefly explained below.

[0085] (1) Beam switching technology

[0086] With the increasing demand for data traffic in communication systems, millimeter wave technology has become a key technology in 5G (5th Generation Mobile Communication Technology). However, due to the high frequency characteristics of millimeter waves, their links may suffer severe path loss. To overcome this drawback, millimeter wave communication systems need to use Massive MIMO (Multiple-input Multiple-output) technology based on beamforming. Beamforming technology can effectively improve the spectral efficiency of mobile communication systems; however, the coverage area of ​​each beam is limited, requiring beam switching to maintain good system performance. For example, when a UE leaves the coverage area of ​​the serving beam, that serving beam will no longer be suitable for the UE, requiring beam switching; or, if there are obstacles between network nodes and the UE that cause a sharp drop in the quality of the current serving beam, beam switching is also necessary.

[0087] In practical applications, network nodes such as millimeter-wave base stations have a smaller coverage area, so their deployment density needs to be higher than that of LTE (Long Term Evolution) base stations. In millimeter-wave networks using beams, beam switching occurs not only between millimeter-wave base stations but also between beams within the same millimeter-wave base station. The dense deployment of millimeter-wave base stations and the use of beams further increase the frequency of beam switching, which may limit the performance of the actual system, thus requiring optimization of the beam switching process.

[0088] During beam management, beam scanning and reporting are performed periodically. Based on the beam report results, when the quality of the currently serving beam fluctuates, beam switching can be performed to obtain better communication performance. For this type of beam switching, the switching parameters can be optimized to improve system performance and reduce the probability of beam failure, while reducing the number of beam switching operations to reduce system load.

[0089] (2) Beam switching based on a fixed threshold (fixed handover threshold)

[0090] For network nodes such as base stations, beam switching based on measurement reports includes two parts: beam switching across base stations and beam switching within a base station. Actual simulations show that most beam switching occurs between different base stations. Therefore, referring to the A3 event in cell handover mode, after the UE accesses a network node, such as an AP (Access Point), beam scanning is performed periodically. After measuring all beams, the UE saves the best N beam numbers and their quality, obtaining candidate beams. The UE feeds back relevant beam information (such as SINR (Signal to Interference plus Noise Ratio)) to the AP. The AP then determines whether to perform beam switching based on a fixed threshold method.

[0091] SINR is used as a reference indicator for beam quality; the handover trigger is determined each time all beam quality is reported. Parameters related to the fixed threshold determination method include: TTT (Time-to-trigger) and HM (Hysteresis Margin). HM represents the minimum difference between the SINR of the current serving beam and the SINR of the target beam, denoted as Δ. TTT represents the duration for which the target beam meets the trigger difference condition. In a fixed threshold-based handover setting, if another beam is measured to have better quality than the serving beam, exceeding a certain threshold Δ, and this condition is maintained for a period of time (TTT), then beam handover is triggered. The handover determination process includes: the AP, based on the reported beam quality, determines whether a candidate beam should enter the beam handover determination process; if the SINR is met... serve +Δ<SINR candidate If the conditions are met, the handover decision process begins, which requires a TTT (Time To Watch) period. After entering the handover decision process, if the SINR (Signal Indicator Ratio) is satisfied within the TTT period... serve +Δ<SINR candidate If the above conditions are met, a beam switch will occur after the determination is completed, and the serving beam will be switched to the candidate beam; if the above conditions are not met at any time, the determination process will be interrupted, the determination will end, and no beam switch will occur.

[0092] In the handover determination process, the beam with the highest SINR in each UE measurement result from the beam report is selected as the candidate beam and added to the candidate beam set. If the candidate beam is the serving beam of another user, to avoid beam conflict, the beam with the second highest SINR is selected as the candidate beam, and so on. If the candidate beam meets the threshold requirements, the handover determination process is triggered. During the beam handover determination process, the candidate beam will no longer be selected by other users, and the user will no longer select other beams for handover determination, until one beam handover determination is completed.

[0093] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0094] A schematic diagram of a system architecture provided in this application embodiment is shown below. Figure 1 As shown, the system architecture includes: a UE and a network node, wherein the UE, for example... Figure 1 UE110, UE111, UE112, and UE113, network nodes such as Figure 1 Network nodes 120 and 121 are included. These network nodes are deployed in the access network, for example, in the NG-RAN (New Generation-Radio Access Network) access network of a 5G system. The UE and the network nodes communicate with each other via some air interface technology, such as cellular technology.

[0095] The UE involved in the embodiments of this application can be a device that provides voice and / or data connectivity to a user, a handheld device with wireless connectivity, or other processing devices connected to a wireless modem. Types of UEs include mobile phones, vehicle user terminals, tablet computers, laptops, personal digital assistants, mobile internet devices, wearable devices, etc.

[0096] The network node involved in this application embodiment can be a base station, which may include multiple cells providing services to terminals. Depending on the specific application, the base station may also be called an access point (AP), or it may be a device in the access network that communicates with the wireless terminal device through one or more sectors on the air interface, or other names. The network node can be used to exchange received air frames with Internet Protocol (IP) packets, acting as a router between the wireless terminal device and the rest of the access network, where the rest of the access network may include an Internet Protocol (IP) communication network. The network node can also coordinate the attribute management of the air interface. For example, the network nodes involved in the embodiments of this application can be network equipment (Base Transceiver Station, BTS) in Global System for Mobile communications (GSM) or Code Division Multiple Access (CDMA), network equipment (NodeB) in Wide-band Code Division Multiple Access (WCDMA), evolved network equipment (eNB or e-NodeB) in long term evolution (LTE) systems, 5G base stations (gNB) in next generation systems, B5G base stations in B5G systems, 6G base stations in 6G (6th Generation Mobile Communication Technology) network architectures, or home evolved Node B (HeNB), relay node, femto, pico, millimeter wave base station, etc., and are not limited in the embodiments of this application. In some network structures, network nodes may include centralized unit (CU) nodes and distributed unit (DU) nodes, and the centralized unit and distributed unit may also be geographically separated.

[0097] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0098] This application provides a beam switching method, executed by a first network node, as illustrated in the flowchart below. Figure 2As shown, the method includes:

[0099] S201, Obtain first quality information corresponding to multiple first beams within a first time period, wherein the first quality information corresponding to multiple first beams includes first quality information sent by at least one user equipment (UE) to the first network node.

[0100] Specifically, the first network node acquires first quality information corresponding to multiple beams of at least one second network node within a first time period; and receives first quality information transmitted by at least one UE; wherein, the first quality information may include at least one of SINR, RSRP (Reference Signal Receiving Power), and RSRQ (Reference Signal Receiving Quality). For example, the first network node acquires first quality information corresponding to 20 first beams within the first time period, that is, within the first time period, the first network node acquires 20 pieces of first quality information, which include 10 pieces of first quality information transmitted to the first network node by one or more second network nodes, and first quality information transmitted to the first network node by 10 UEs respectively.

[0101] S202, based on the first quality information corresponding to the multiple first beams respectively, determine the first average channel quality corresponding to the multiple first beams.

[0102] Specifically, for example, if a first network node obtains 20 first quality information points, and the first quality information points are SINR, and these 20 first quality information points are 20 SINR, then the average value of these 20 SINR is calculated, and the average value of these 20 SINR is used as the first average channel quality.

[0103] S203, based on the first average channel quality corresponding to multiple first beams and the second average channel quality corresponding to multiple second beams within at least one second time period, determine the first state vector; at least one second time period is before the first time period.

[0104] Specifically, such as Figure 3As shown, the sliding window includes N time windows, which are the first time window, the second time window, the third time window, ... the Nth time window. The duration of the first time window, the second time window, the third time window, ... the Nth time window can be preset, and N is a positive integer. The first time period is the first time window, which is the current window. Multiple second time periods can be designated as the second, third, ..., Nth time windows, where the second, third, ..., Nth time windows are all historical windows. The average channel quality of the first time window can be the first average channel quality, and the average channel quality of the second, third, ..., Nth time windows can all be the second average channel quality. The average channel quality of the second, third, ..., Nth time windows can be different from each other. The average channel quality of the first time window can be represented by SINR1, and the average channel quality of the second, third, ..., Nth time windows can be represented by SINR2, SINR3, ..., SINR1, respectively. N express.

[0105] It should be noted that, considering the trend of system performance changes over time and to avoid unnecessary beam switching in the future, using a sliding window can take into account the influence of historical experience.

[0106] S204, based on the first state vector, determine the beam switching threshold corresponding to at least one UE.

[0107] Specifically, beam switching thresholds may include TTT, HM, etc.

[0108] In this embodiment, the beam switching threshold corresponding to at least one UE is dynamically adjusted, thereby ensuring an appropriate beam switching frequency while maintaining system performance.

[0109] In one embodiment, obtaining the first quality information corresponding to multiple first beams within a first time period includes:

[0110] Acquire the first quality information sent by the second network node within the first time period; and receive the first quality information sent by at least one UE;

[0111] The first quality information includes at least one of the following: signal-to-noise ratio (SINR), received power (RSRP), and received quality (RSRQ).

[0112] In one embodiment, the first network node can acquire first quality information corresponding to multiple beams of at least one second network node within a first time period; and receive first quality information sent by at least one UE.

[0113] In one embodiment, a first state vector is determined based on the first average channel quality corresponding to multiple first beams and the second average channel quality corresponding to multiple second beams within at least one second time period, including:

[0114] The first average channel quality is quantized and mapped to obtain the value of the first information vector corresponding to the first average channel quality; the second average channel quality is quantized and mapped to obtain the value of the second information vector corresponding to the second average channel quality.

[0115] A first state vector is obtained based on a first information vector and at least one second information vector.

[0116] Specifically, the values ​​of both the first and second information vectors are discrete values. These values ​​can be used to characterize signal strength levels, which can be 1, 2, 3, ..., m, where m is a positive integer. For example, if the first information vector is b1, multiple second information vectors can be b2, b3, ..., b... n Then the first state vector is (b1, b2, b3, ... b n ).

[0117] In one embodiment, determining the beam switching threshold for at least one UE based on the first state vector includes:

[0118] The first state vector is input into the first relation model for matching processing to obtain one or more reward values ​​that match the first state vector. The beam switching threshold corresponding to the largest reward value among the one or more reward values ​​is determined as the beam switching threshold corresponding to the UE.

[0119] The first relational model is used to characterize the relationship between the first state vector, the reward value, and the beam switching threshold.

[0120] Specifically, the first relationship model can be a table, which can be used to represent the relationship between the first state vector, the reward value, and the beam switching threshold. The reward value can be used to represent the effect of the UE performing beam switching based on the beam switching threshold corresponding to the UE. The maximum reward value can be used to represent the best effect of the UE performing beam switching based on the beam switching threshold corresponding to the UE.

[0121] In one embodiment, the first relationship model is determined by a first parameter corresponding to a change in a first metric of at least one UE, and a second parameter corresponding to the beam switching cost.

[0122] Specifically, the first metric may include at least one of channel capacity, signal-to-noise ratio, and block error rate (BLER).

[0123] In one embodiment, the first relationship model can be a table, which can be determined by a first parameter corresponding to the channel capacity change of at least one UE and a second parameter corresponding to the beam switching cost.

[0124] Specifically, the first parameter corresponding to the channel capacity change of at least one UE can be The second parameter corresponding to the beam switching cost can be β. c *H n ,in, This indicates that the beam switching threshold corresponding to the state vector causes... Capacity change, β represents the average channel capacity C of at least one UE. c H is the preset penalty factor. n This represents the average number of handovers.

[0125] In one embodiment, the first relational model is trained in the following way:

[0126] Construct a training sample set; based on the training sample set, train the relation model to obtain the first relation model;

[0127] Training a relational model based on a training sample set includes at least the following:

[0128] The second state vector from the training sample set is input into the relational model to determine the beam switching threshold corresponding to the second state vector.

[0129] Based on the beam switching threshold and reward function corresponding to the second state vector, the reward value corresponding to the second state vector is determined.

[0130] The loss function value is determined based on the second state vector, the reward value corresponding to the second state vector, and the loss function corresponding to the relation model.

[0131] Based on the loss function value, the model parameters of the relational model are updated to obtain the updated relational model.

[0132] In one embodiment, after determining the loss function value based on the second state vector, the reward value corresponding to the second state vector, and the loss function corresponding to the relation model, the method further includes:

[0133] Determine whether the termination condition has been met;

[0134] If the termination condition is determined to be met, the first relation model is obtained;

[0135] The termination condition is one of the following:

[0136] The loss function value is less than or equal to the loss function value threshold; or,

[0137] The loss function value is greater than or equal to the loss function value threshold.

[0138] Specifically, the second state vector from the training sample set is input into the relational model to determine the beam switching threshold corresponding to the second state vector. Based on the beam switching threshold, the reward value corresponding to the second state vector is obtained through the reward function. The second state vector and its corresponding reward value are then substituted into the loss function of the relational model to obtain the loss function value. Based on the loss function value, the model parameters of the relational model are updated. This process continues until a termination condition is reached, at which point the relational model at which the termination condition is met is taken as the first relational model.

[0139] In one embodiment, training the relation model based on a training sample set further includes:

[0140] If the termination condition is not met, repeat the following steps:

[0141] The second state vector from the training sample set is input into the updated relational model to determine the beam switching threshold corresponding to the second state vector.

[0142] Based on the beam switching threshold and reward function corresponding to the second state vector, the reward value corresponding to the second state vector is determined.

[0143] The loss function value is determined based on the second state vector, the reward value corresponding to the second state vector, and the loss function corresponding to the updated relation model.

[0144] Based on the loss function value, the model parameters of the updated relational model are updated to obtain the updated relational model.

[0145] Specifically, if the first indicator is channel capacity, the second state vector in the training sample set is input into the relational model, and the beam switching threshold corresponding to the second state vector is determined based on a greedy strategy; the second state vector is used to characterize the average channel quality of multiple beams in each training time period.

[0146] Based on the beam switching threshold corresponding to the second state vector, the reward value corresponding to the second state vector is obtained through the reward function; wherein, the reward function is as shown in formula (1):

[0147]

[0148] in, This indicates that the beam switching threshold corresponding to the second state vector causes... Capacity change, β represents the average channel capacity C of at least one UE. c H is the preset penalty factor. n This represents the average number of handovers.

[0149] The first relational model can be deployed in network nodes.

[0150] In one embodiment, first quality information sent by at least one UE to a first network node is sent to a second network node.

[0151] Specifically, the first network node can share the first quality information as edge information with other network nodes (e.g., one or more second network nodes); whereby the edge information is information that can be shared among the network nodes.

[0152] This application provides another beam switching method, executed by the UE, and the flowchart of this method is shown below. Figure 4 As shown, the method includes:

[0153] S401, send the first quality information corresponding to the first beam within the first time period to the first network node; so that the first network node obtains the first quality information corresponding to multiple beams within the first time period, and determines the beam switching threshold corresponding to the UE based on the first quality information corresponding to multiple beams and the average channel quality corresponding to multiple beams within at least one second time period.

[0154] S402, receive the beam switching threshold corresponding to the UE sent by the first network node, and perform beam switching based on the beam switching threshold.

[0155] It should be noted that if the UE measures that a beam other than the serving beam has better quality than the serving beam (e.g., the first beam), a beam switching can be triggered based on the beam switching threshold, allowing the UE to switch from the serving beam to another beam.

[0156] In this embodiment, the beam switching threshold corresponding to the UE is dynamically adjusted, thereby maintaining system performance while ensuring an appropriate beam switching frequency.

[0157] The beam switching method of the above embodiments of this application will be fully and thoroughly described through the following examples:

[0158] This application provides reinforcement learning in beam switching scenarios, and the flowchart of the reinforcement learning is shown below. Figure 5 As shown, it includes:

[0159] S501, preset beam switching threshold.

[0160] Specifically, beam switching thresholds may include TTT, HM, etc.

[0161] S502, Construct the training sample set.

[0162] Specifically, each state vector in the training sample set can be used to characterize the average channel quality of multiple beams over a training time period.

[0163] S503, pre-set reward function.

[0164] Specifically, set the reward function as shown in formula (1).

[0165] S504, based on the training sample set, trains the relation model to obtain the trained relation model.

[0166] Specifically, the trained relational model is the first relational model. Based on the Q-learning algorithm and the training sample set, the relational model is trained. The relational model can be a table, specifically a Q-table (Q-table) in the Q-learning algorithm. This table can represent the relationship between state vectors, reward values, and beam switching thresholds. State vectors from the training sample set are input into the table to determine the beam switching thresholds corresponding to the state vectors. Based on the beam switching thresholds, the reward value corresponding to the state vector is obtained through the reward function. The state vectors and their corresponding reward values ​​are substituted into the loss function corresponding to the table to obtain the loss function value, and the model parameters of the table are updated based on the loss function value. The following steps are repeated: inputting state vectors from the training sample set into the table to determine the beam switching thresholds corresponding to the state vectors; obtaining the reward value corresponding to the state vector based on the beam switching thresholds; substituting the state vectors and their corresponding reward values ​​into the loss function corresponding to the table to obtain the loss function value, and updating the model parameters of the table based on the loss function value. The process continues until a termination condition is met, at which point the table at which the termination condition is met is used as the first table (the trained relational model); the termination condition can be that the loss function value is less than or equal to a loss function value threshold.

[0167] S505 deploys the trained relational model in network nodes.

[0168] Specifically, the trained relational model can be a first table, which is then deployed in network nodes.

[0169] This application provides yet another beam switching method, the flowchart of which is shown below. Figure 6 As shown, the method includes:

[0170] S601, the network node sends a reference signal for beam scanning to the UE.

[0171] Specifically, the reference signal can be an SSB (Synchronization Signal Block).

[0172] S602, the UE performs beam measurement to obtain the quality information corresponding to the serving beam.

[0173] S603, the UE feeds back the quality information corresponding to the serving beam and the quality information corresponding to the candidate beam to the network node.

[0174] S604, the network node uses the quality information corresponding to the service beam as edge information and shares this edge information with other network nodes.

[0175] It should be noted that if there are no other network nodes, step S604 is not required; the quality information corresponding to the serving beam can be SINR, RSRP, or RSRQ.

[0176] S605, the network node determines the state vector based on all edge information, and finds the beam switching threshold corresponding to the UE based on the relation model trained by reinforcement learning.

[0177] Specifically, the network node stores all edge information, which includes the edge information corresponding to the service beam, as well as the edge information sent to the network node by other network nodes.

[0178] S606, the network node makes a beam switching decision based on the beam switching threshold; if the network node determines that the UE should switch from the serving beam to another beam, the network node instructs the UE to switch from the serving beam to another beam and proceeds to step S607 for execution.

[0179] Specifically, other beams can be candidate beams.

[0180] S607, the UE performs beam switching.

[0181] This application provides another beam switching method in a multi-AP millimeter-wave network scenario. The topology of this scenario is as follows: in a scenario with a radius of 30m, 3 APs and 7 users are evenly deployed. Three of the 7 users move in a straight line along a certain path at a speed of 5km / h. Each of the 3 APs has 32 beams, and hybrid beamforming technology is used. The beam scanning period is set to 10ms. Switching occurs when the UE meets the beam switching conditions. A flowchart of this method is shown below. Figure 7 As shown, the method includes:

[0182] S701, network nodes determine beam switching thresholds using a greedy strategy.

[0183] Specifically, the beam switching threshold options are: (HM=1dB and TTT=100ms), (HM=1dB and TTT=100ms), (HM=3dB and TTT=100ms), (HM=5dB and TTT=100ms), (HM=7dB and TTT=100ms), etc.

[0184] S702, the UE performs beam switching based on the beam switching threshold.

[0185] S703, the network node determines the second state vector through a sliding window.

[0186] For example, the sliding window consists of 5 time windows, meaning the sliding window has a length of 5. These 5 time windows are the first time window, the second time window, the third time window, the fourth time window, and the fifth time window. The first time window has a duration of 10ms, and the second, third, fourth, and fifth time windows each have a duration of 40ms.

[0187] S704, network nodes update the Q table through the reward function.

[0188] Specifically, reinforcement learning training is performed according to the reward function shown in formula (1), that is, the relation model is trained. This relation model is a Q-table, where the penalty factor β in the reward function is... c It can be set to 0.75.

[0189] S705, the network node deploys the updated Q table to the network node; proceed to steps S701 and S706 respectively.

[0190] S706, the network node determines the first state vector and obtains the beam switching threshold by looking up the Q table.

[0191] Specifically, the first state vector can be (b1, b2, b3, ... b n b1, b2, b3, ... b n The value can be used to characterize the signal strength level, which can be 1, 2, 3, ... m, etc. For example, the signal strength level can be 1, 2, 3, 4 and 5, that is, there are 5 levels of signal strength.

[0192] S707, network nodes perform beam switching determination.

[0193] S708, network nodes perform periodic beam scanning.

[0194] S709, UE performs beam measurement.

[0195] S710, UE feeds back the quality information corresponding to the beam; proceed to step S706 for execution.

[0196] Specifically, the quality information can be SINR, RSRP, or RSRQ.

[0197] It should be noted that steps S701-S705 are steps in reinforcement learning training, and the update interval T for each reinforcement learning training can be 10ms (milliseconds); steps S706-S710 are steps in online execution.

[0198] In one embodiment, such as Figure 8 and Figure 9 As shown ( Figure 9 for Figure 8 (Enlarged image), based on a fixed threshold, the CDF (Cumulative Distribution Function) statistical results of the SINR corresponding to the serving beam within 20 seconds; the beam switching method based on reinforcement learning (e.g., Q-learning) in this application, the CDF statistical results of the SINR corresponding to the serving beam within 20 seconds; the beam switching based on reinforcement learning in this application has superior performance.

[0199] In one embodiment, such as Figure 10 As shown, the beam switching based on reinforcement learning (e.g., Q-learning) in this application results in the fewest beam switching operations.

[0200] Based on the same inventive concept, this application also provides a beam switching device applied to a first network node, the structural schematic diagram of which is shown below. Figure 11 As shown, transceiver 1300 is used to receive and send data under the control of processor 1310.

[0201] Among them, Figure 11 In this context, the bus architecture can include any number of interconnected buses and bridges, specifically linking various circuits together, represented by one or more processors (processor 1310) and memory (memory 1320). The bus architecture can also link together various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. The bus interface provides an interface. The transceiver 1300 can be multiple elements, including transmitters and receivers, providing units for communicating with various other devices over transmission media, including wireless channels, wired channels, optical fibers, etc. The processor 1310 is responsible for managing the bus architecture and general processing, and the memory 1320 can store data used by the processor 1310 during operation.

[0202] The processor 1310 can be a central processing unit (CPU), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a complex programmable logic device (CPLD). The processor can also adopt a multi-core architecture.

[0203] Processor 1310 is configured to read the computer program in the memory and perform the following operations:

[0204] Obtain first quality information corresponding to multiple first beams within a first time period, wherein the first quality information corresponding to multiple first beams includes first quality information sent by at least one user equipment (UE) to a first network node.

[0205] Based on the first quality information corresponding to each of the multiple first beams, the first average channel quality corresponding to the multiple first beams is determined.

[0206] A first state vector is determined based on the first average channel quality corresponding to multiple first beams and the second average channel quality corresponding to multiple second beams within at least one second time period; the at least one second time period is prior to the first time period.

[0207] Based on the first state vector, determine the beam switching threshold corresponding to at least one UE.

[0208] In one embodiment, obtaining the first quality information corresponding to multiple first beams within a first time period includes:

[0209] Acquire the first quality information sent by the second network node within the first time period; and receive the first quality information sent by at least one UE;

[0210] The first quality information includes at least one of the following: signal-to-noise ratio (SINR), received power (RSRP), and received quality (RSRQ).

[0211] In one embodiment, a first state vector is determined based on the first average channel quality corresponding to multiple first beams and the second average channel quality corresponding to multiple second beams within at least one second time period, including:

[0212] The first average channel quality is quantized and mapped to obtain the value of the first information vector corresponding to the first average channel quality; the second average channel quality is quantized and mapped to obtain the value of the second information vector corresponding to the second average channel quality.

[0213] A first state vector is obtained based on a first information vector and at least one second information vector.

[0214] In one embodiment, determining the beam switching threshold for at least one UE based on the first state vector includes:

[0215] The first state vector is input into the first relation model for matching processing to obtain one or more reward values ​​that match the first state vector. The beam switching threshold corresponding to the largest reward value among the one or more reward values ​​is determined as the beam switching threshold corresponding to the UE.

[0216] The first relational model is used to characterize the relationship between the first state vector, the reward value, and the beam switching threshold.

[0217] In one embodiment, the first relationship model is determined by a first parameter corresponding to a change in a first metric of at least one UE, and a second parameter corresponding to the beam switching cost.

[0218] In one embodiment, the first relational model is trained in the following way:

[0219] Construct a training sample set; based on the training sample set, train the relation model to obtain the first relation model;

[0220] Training a relational model based on a training sample set includes at least the following:

[0221] The second state vector from the training sample set is input into the relational model to determine the beam switching threshold corresponding to the second state vector.

[0222] Based on the beam switching threshold and reward function corresponding to the second state vector, the reward value corresponding to the second state vector is determined.

[0223] The loss function value is determined based on the second state vector, the reward value corresponding to the second state vector, and the loss function corresponding to the relation model.

[0224] Based on the loss function value, the model parameters of the relational model are updated to obtain the updated relational model.

[0225] In one embodiment, training the relation model based on a training sample set further includes:

[0226] If the termination condition is not met, repeat the following steps:

[0227] The second state vector from the training sample set is input into the updated relational model to determine the beam switching threshold corresponding to the second state vector.

[0228] Based on the beam switching threshold and reward function corresponding to the second state vector, the reward value corresponding to the second state vector is determined.

[0229] The loss function value is determined based on the second state vector, the reward value corresponding to the second state vector, and the loss function corresponding to the updated relation model.

[0230] Based on the loss function value, the model parameters of the updated relational model are updated to obtain the updated relational model.

[0231] In one embodiment, after determining the loss function value based on the second state vector, the reward value corresponding to the second state vector, and the loss function corresponding to the relation model, the method further includes:

[0232] Determine whether the termination condition has been met;

[0233] If the termination condition is determined to be met, the first relation model is obtained;

[0234] The termination condition is one of the following:

[0235] The loss function value is less than or equal to the loss function value threshold; or,

[0236] The loss function value is greater than or equal to the loss function value threshold.

[0237] In one embodiment, first quality information sent by at least one UE to a first network node is sent to a second network node.

[0238] It should be noted that the apparatus provided in this embodiment of the invention can implement all the method steps implemented in the above method embodiment and can achieve the same technical effect. Therefore, the parts and beneficial effects that are the same as those in the method embodiment will not be described in detail here.

[0239] Based on the same inventive concept, this application also provides a beam switching device applied to a UE, the structural schematic diagram of which is shown below. Figure 12 As shown, transceiver 1400 is used to receive and send data under the control of processor 1410.

[0240] Among them, Figure 12In this context, the bus architecture can include any number of interconnected buses and bridges, specifically linking various circuits of one or more processors represented by processor 1410 and memory represented by memory 1420 together. The bus architecture can also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. The bus interface provides an interface. The transceiver 1400 can be multiple components, including transmitters and receivers, providing a unit for communicating with various other devices over a transmission medium, including wireless channels, wired channels, optical fibers, etc. For different user equipment, the user interface 1430 can also be an interface capable of connecting external or internal devices, including but not limited to keypads, displays, speakers, microphones, joysticks, etc.

[0241] Processor 1410 is responsible for managing the bus architecture and general processing, while memory 1420 can store data used by processor 1410 when performing operations.

[0242] Optionally, the processor 1410 can be a CPU (Central Processing Unit), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array), or CPLD (Complex Programmable Logic Device), and the processor can also adopt a multi-core architecture.

[0243] The processor invokes a computer program stored in memory to execute the method described in the second aspect of this application according to the obtained executable instructions. The processor and memory may also be physically separated.

[0244] Processor 1410 is configured to read a computer program from memory 1420 and perform the following operations:

[0245] Send the first quality information corresponding to the first beam within a first time period to the first network node; so that the first network node obtains the first quality information corresponding to multiple beams within the first time period, and determines the beam switching threshold corresponding to the UE based on the first quality information corresponding to multiple beams and the average channel quality corresponding to multiple beams within at least one second time period.

[0246] Receive the beam switching threshold corresponding to the UE sent by the first network node, and perform beam switching based on the beam switching threshold.

[0247] It should be noted that the apparatus provided in this embodiment of the invention can implement all the method steps implemented in the above method embodiment and can achieve the same technical effect. Therefore, the parts and beneficial effects that are the same as those in the method embodiment will not be described in detail here.

[0248] Based on the same inventive concept as the foregoing embodiments, this application also provides a beam switching device applied to a first network node, the structural schematic diagram of which is shown below. Figure 13 As shown, the beam switching device 80 includes a first processing unit 801, a second processing unit 802, a third processing unit 803, and a fourth processing unit 804.

[0249] The first processing unit 801 is used to obtain first quality information corresponding to multiple first beams within a first time period. The first quality information corresponding to multiple first beams includes first quality information sent by at least one user equipment (UE) to the first network node.

[0250] The second processing unit 802 is used to determine the first average channel quality corresponding to the multiple first beams based on the first quality information corresponding to the multiple first beams respectively.

[0251] The third processing unit 803 is used to determine a first state vector based on the first average channel quality corresponding to multiple first beams and the second average channel quality corresponding to multiple second beams within at least one second time period; the at least one second time period is before the first time period.

[0252] The fourth processing unit 804 is used to determine the beam switching threshold corresponding to at least one UE based on the first state vector.

[0253] In one embodiment, the first processing unit 801 is specifically used for:

[0254] Acquire the first quality information sent by the second network node within the first time period; and receive the first quality information sent by at least one UE;

[0255] The first quality information includes at least one of the following: signal-to-noise ratio (SINR), received power (RSRP), and received quality (RSRQ).

[0256] In one embodiment, the third processing unit 803 is specifically used for:

[0257] The first average channel quality is quantized and mapped to obtain the value of the first information vector corresponding to the first average channel quality; the second average channel quality is quantized and mapped to obtain the value of the second information vector corresponding to the second average channel quality.

[0258] A first state vector is obtained based on a first information vector and at least one second information vector.

[0259] In one embodiment, the fourth processing unit 804 is specifically used for:

[0260] The first state vector is input into the first relation model for matching processing to obtain one or more reward values ​​that match the first state vector. The beam switching threshold corresponding to the largest reward value among the one or more reward values ​​is determined as the beam switching threshold corresponding to the UE.

[0261] The first relational model is used to characterize the relationship between the first state vector, the reward value, and the beam switching threshold.

[0262] In one embodiment, the first relationship model is determined by a first parameter corresponding to a change in a first metric of at least one UE, and a second parameter corresponding to the beam switching cost.

[0263] In one embodiment, the first relational model is trained in the following way:

[0264] Construct a training sample set; based on the training sample set, train the relation model to obtain the first relation model;

[0265] Training a relational model based on a training sample set includes at least the following:

[0266] The second state vector from the training sample set is input into the relational model to determine the beam switching threshold corresponding to the second state vector.

[0267] Based on the beam switching threshold and reward function corresponding to the second state vector, the reward value corresponding to the second state vector is determined.

[0268] The loss function value is determined based on the second state vector, the reward value corresponding to the second state vector, and the loss function corresponding to the relation model.

[0269] Based on the loss function value, the model parameters of the relational model are updated to obtain the updated relational model.

[0270] In one embodiment, training the relation model based on a training sample set further includes:

[0271] If the termination condition is not met, repeat the following steps:

[0272] The second state vector from the training sample set is input into the updated relational model to determine the beam switching threshold corresponding to the second state vector.

[0273] Based on the beam switching threshold and reward function corresponding to the second state vector, the reward value corresponding to the second state vector is determined.

[0274] The loss function value is determined based on the second state vector, the reward value corresponding to the second state vector, and the loss function corresponding to the updated relation model.

[0275] Based on the loss function value, the model parameters of the updated relational model are updated to obtain the updated relational model.

[0276] In one embodiment, after determining the loss function value based on the second state vector, the reward value corresponding to the second state vector, and the loss function corresponding to the relation model, the method further includes:

[0277] Determine whether the termination condition has been met;

[0278] If the termination condition is determined to be met, the first relation model is obtained;

[0279] The termination condition is one of the following:

[0280] The loss function value is less than or equal to the loss function value threshold; or,

[0281] The loss function value is greater than or equal to the loss function value threshold.

[0282] In one embodiment, the first processing unit 801 is further configured to:

[0283] First quality information sent by at least one UE to the first network node is sent to the second network node.

[0284] It should be noted that the apparatus provided in this embodiment of the invention can implement all the method steps implemented in the above method embodiment and can achieve the same technical effect. Therefore, the parts and beneficial effects that are the same as those in the method embodiment will not be described in detail here.

[0285] Based on the same inventive concept as the foregoing embodiments, this application also provides a beam switching device applied to a UE, the structural schematic diagram of which is shown below. Figure 14 As shown, the beam switching device 90 includes a fifth processing unit 901 and a sixth processing unit 902.

[0286] The fifth processing unit 901 is used to send the first quality information corresponding to the first beam within a first time period to the first network node; so that the first network node obtains the first quality information corresponding to multiple beams within the first time period, and determines the beam switching threshold corresponding to the UE based on the first quality information corresponding to multiple beams and the average channel quality corresponding to multiple beams within at least one second time period.

[0287] The sixth processing unit 902 is used to receive the beam switching threshold corresponding to the UE sent by the first network node, and to perform beam switching based on the beam switching threshold.

[0288] It should be noted that the apparatus provided in this embodiment of the invention can implement all the method steps implemented in the above method embodiment and can achieve the same technical effect. Therefore, the parts and beneficial effects that are the same as those in the method embodiment will not be described in detail here.

[0289] It should be noted that the division of units in the embodiments of this application is illustrative and only represents one logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated units described above can be implemented in hardware or as software functional units.

[0290] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a processor-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0291] Based on the same inventive concept, embodiments of this application also provide a processor-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of any cell handover time determination method provided in any embodiment or any optional implementation of this application.

[0292] Processor-readable storage media can be any available medium or data storage device that the processor can access, including but not limited to magnetic storage (e.g., floppy disks, hard disks, magnetic tapes, magneto-optical disks (MOs), etc.), optical storage (e.g., CDs, DVDs, BDs, HVDs, etc.), and semiconductor storage (e.g., ROMs, EPROMs, EEPROMs, non-volatile memory (NAND flash), solid-state drives (SSDs)).

[0293] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0294] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-executable instructions. These computer-executable instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0295] These processor-executable instructions may also be stored in a processor-readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the processor-readable memory produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0296] These processors can execute instructions that can also be loaded onto a computer or other programmable data processing device, causing a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable device for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0297] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A beam switching method, executed by a first network node, characterized in that, include: Obtain first quality information corresponding to multiple first beams within a first time period, wherein the first quality information corresponding to multiple first beams includes first quality information sent by at least one user equipment (UE) to the first network node. Based on the first quality information corresponding to the plurality of first beams respectively, the first average channel quality corresponding to the plurality of first beams is determined; Based on the first average channel quality corresponding to the plurality of first beams and the second average channel quality corresponding to the plurality of second beams within at least one second time period, a first state vector is determined. The at least one second time period is prior to the first time period; Based on the first state vector, determine the beam switching threshold corresponding to the at least one UE; The step of obtaining the first quality information corresponding to multiple first beams within a first time period includes: Acquire first quality information sent by the second network node within a first time period; and receive first quality information sent by the at least one UE; The first quality information includes at least one of the following: signal-to-noise ratio (SINR), received power (RSRP), and received quality (RSRQ). The step of determining the first state vector based on the first average channel quality corresponding to the plurality of first beams and the second average channel quality corresponding to the plurality of second beams within at least one second time period includes: The first average channel quality is quantized and mapped to obtain the value of the first information vector corresponding to the first average channel quality; and the second average channel quality is quantized and mapped to obtain the value of the second information vector corresponding to the second average channel quality. Based on the first information vector and at least one of the second information vectors, a first state vector is obtained; Determining the beam switching threshold corresponding to the at least one UE based on the first state vector includes: The first state vector is input into the first relation model for matching processing to obtain one or more reward values ​​that match the first state vector. The beam switching threshold corresponding to the largest reward value among the one or more reward values ​​is determined as the beam switching threshold corresponding to the UE. The first relationship model is used to characterize the relationship between the first state vector, the reward value, and the beam switching threshold.

2. The method according to claim 1, characterized in that, The first relationship model is determined by a first parameter corresponding to the change of the first indicator of the at least one UE, and a second parameter corresponding to the beam switching cost.

3. The method according to claim 1, characterized in that, The first relational model was trained in the following way: Construct a training sample set; based on the training sample set, train the relation model to obtain the first relation model; The training of the relation model based on the training sample set includes at least the following: The second state vector from the training sample set is input into the relation model to determine the beam switching threshold corresponding to the second state vector; Based on the beam switching threshold and reward function corresponding to the second state vector, the reward value corresponding to the second state vector is determined; Based on the second state vector, the reward value corresponding to the second state vector, and the loss function corresponding to the relationship model, the loss function value is determined; Based on the loss function value, the model parameters of the relation model are updated to obtain the updated relation model.

4. The method according to claim 3, characterized in that, The step of training the relation model based on the training sample set further includes: If the termination condition is not met, repeat the following steps: The second state vector in the training sample set is input into the updated relational model to determine the beam switching threshold corresponding to the second state vector. Based on the beam switching threshold and reward function corresponding to the second state vector, the reward value corresponding to the second state vector is determined; The loss function value is determined based on the second state vector, the reward value corresponding to the second state vector, and the loss function corresponding to the updated relation model. Based on the loss function value, the model parameters of the updated relational model are updated to obtain the updated relational model.

5. The method according to claim 3, characterized in that, After determining the loss function value based on the second state vector, the reward value corresponding to the second state vector, and the loss function corresponding to the relationship model, the method further includes: Determine whether the termination condition has been met; If the termination condition is determined to be met, the first relational model is obtained; The termination condition is one of the following: The loss function value is less than or equal to the loss function value threshold; or... The loss function value is greater than or equal to the loss function value threshold.

6. The method according to claim 1, characterized in that, Also includes: The first quality information sent by the at least one UE to the first network node is then sent to the second network node.

7. A beam switching method, executed by a UE, characterized in that, include: Send the first quality information corresponding to the first beam within the first time period to the first network node; To enable the first network node to acquire first quality information corresponding to multiple beams within the first time period, and to determine the beam switching threshold corresponding to the UE based on the first quality information corresponding to the multiple beams and the average channel quality corresponding to multiple beams within at least one second time period; the step of enabling the first network node to acquire the first quality information corresponding to multiple beams within the first time period includes: enabling the first network node to acquire first quality information sent by a second network node within the first time period, and receiving first quality information sent by at least one UE; wherein, the first quality information includes at least one of Signal-to-Interference-Noise Ratio (SINR), Received Power RSRRP, and Received Quality RSRQ; The system receives the beam switching threshold corresponding to the UE sent by the first network node, and performs beam switching based on the beam switching threshold.

8. A beam switching device, applied to a first network node, characterized in that, Includes memory, transceiver, and processor: A memory for storing computer programs; a transceiver for sending and receiving data under the control of the processor; and a processor for reading the computer programs from the memory and performing the following operations: Obtain first quality information corresponding to multiple first beams within a first time period, wherein the first quality information corresponding to multiple first beams includes first quality information sent by at least one user equipment (UE) to the first network node. Based on the first quality information corresponding to the plurality of first beams respectively, the first average channel quality corresponding to the plurality of first beams is determined; Based on the first average channel quality corresponding to the plurality of first beams and the second average channel quality corresponding to the plurality of second beams within at least one second time period, a first state vector is determined. The at least one second time period is prior to the first time period; Based on the first state vector, determine the beam switching threshold corresponding to the at least one UE; The step of obtaining the first quality information corresponding to multiple first beams within a first time period includes: Acquire first quality information sent by the second network node within a first time period; and receive first quality information sent by the at least one UE; The first quality information includes at least one of the following: signal-to-noise ratio (SINR), received power (RSRP), and received quality (RSRQ). The step of determining the first state vector based on the first average channel quality corresponding to the plurality of first beams and the second average channel quality corresponding to the plurality of second beams within at least one second time period includes: The first average channel quality is quantized and mapped to obtain the value of the first information vector corresponding to the first average channel quality; and the second average channel quality is quantized and mapped to obtain the value of the second information vector corresponding to the second average channel quality. Based on the first information vector and at least one of the second information vectors, a first state vector is obtained; Determining the beam switching threshold corresponding to the at least one UE based on the first state vector includes: The first state vector is input into the first relation model for matching processing to obtain one or more reward values ​​that match the first state vector. The beam switching threshold corresponding to the largest reward value among the one or more reward values ​​is determined as the beam switching threshold corresponding to the UE. The first relationship model is used to characterize the relationship between the first state vector, the reward value, and the beam switching threshold.

9. A beam switching device, applied to a UE, characterized in that, Includes memory, transceiver, and processor: Sending first quality information corresponding to a first beam within a first time period to a first network node; enabling the first network node to acquire first quality information corresponding to multiple beams respectively within the first time period, and determining a beam switching threshold corresponding to the UE based on the first quality information corresponding to the multiple beams respectively, and the average channel quality corresponding to multiple beams within at least one second time period; the step of enabling the first network node to acquire first quality information corresponding to multiple beams respectively within the first time period includes: enabling the first network node to acquire first quality information sent by a second network node within the first time period, and receiving first quality information sent by at least one UE; wherein, the first quality information includes at least one of signal-to-interference-noise ratio (SINR), received power (RSRP), and received quality (RSRQ); The system receives the beam switching threshold corresponding to the UE sent by the first network node, and performs beam switching based on the beam switching threshold.

10. A beam switching device, applied to a first network node, characterized in that, include: The first processing unit is configured to acquire first quality information corresponding to multiple first beams within a first time period, wherein the first quality information corresponding to multiple first beams includes first quality information sent by at least one user equipment (UE) to the first network node. The second processing unit is used to determine the first average channel quality corresponding to the plurality of first beams based on the first quality information corresponding to the plurality of first beams respectively. The third processing unit is used to determine a first state vector based on the first average channel quality corresponding to the plurality of first beams and the second average channel quality corresponding to the plurality of second beams within at least one second time period. The at least one second time period is prior to the first time period; The fourth processing unit is used to determine the beam switching threshold corresponding to the at least one UE based on the first state vector. The first processing unit is specifically used for: Acquire first quality information sent by the second network node within a first time period; and receive first quality information sent by the at least one UE; The first quality information includes at least one of the following: signal-to-noise ratio (SINR), received power (RSRP), and received quality (RSRQ). The third processing unit is specifically used for: The first average channel quality is quantized and mapped to obtain the value of the first information vector corresponding to the first average channel quality; and the second average channel quality is quantized and mapped to obtain the value of the second information vector corresponding to the second average channel quality. Based on the first information vector and at least one of the second information vectors, a first state vector is obtained; The fourth processing unit is specifically used for: The first state vector is input into the first relation model for matching processing to obtain one or more reward values ​​that match the first state vector. The beam switching threshold corresponding to the largest reward value among the one or more reward values ​​is determined as the beam switching threshold corresponding to the UE. The first relationship model is used to characterize the relationship between the first state vector, the reward value, and the beam switching threshold.

11. A beam switching device, applied to a UE, characterized in that, include: The fifth processing unit is used to send the first quality information corresponding to the first beam within the first time period to the first network node; To enable the first network node to acquire first quality information corresponding to multiple beams within the first time period, and to determine the beam switching threshold corresponding to the UE based on the first quality information corresponding to the multiple beams and the average channel quality corresponding to multiple beams within at least one second time period; the step of enabling the first network node to acquire the first quality information corresponding to multiple beams within the first time period includes: enabling the first network node to acquire first quality information sent by a second network node within the first time period, and receiving first quality information sent by at least one UE; wherein, the first quality information includes at least one of Signal-to-Interference-Noise Ratio (SINR), Received Power RSRRP, and Received Quality RSRQ; The sixth processing unit is used to receive the beam switching threshold corresponding to the UE sent by the first network node, and to perform beam switching based on the beam switching threshold.

12. A processor-readable storage medium, characterized in that, The processor-readable storage medium stores a computer program for causing the processor to perform the method of any one of claims 1 to 7.

Images