A beam optimization method and apparatus

Abstract

Embodiments of the present application provide a beam optimization method and device, wherein the method comprises: obtaining evaluation data corresponding to each candidate beam weight value, determining an optimal beam weight value among the candidate beam weight values based on the evaluation data; obtaining beam conflict information between base stations after the optimal beam weight value is configured to multiple base stations; inputting the optimal beam weight value and the beam conflict information into a beam optimization model to obtain a sub-beam transmission sequence of each base station output by the beam optimization model; wherein the beam optimization model is constructed based on a greedy algorithm and a genetic algorithm. Embodiments of the present application combine the advantages of the greedy algorithm, such as high efficiency and easy implementation, and the advantages of the genetic algorithm, such as self-adaptation and global optimization, to obtain an optimal sub-beam transmission sequence scheme under the optimal beam weight value, effectively reduce the network-wide beam conflict, and improve the flexibility of the beam optimization method.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a beam optimization method and apparatus. Background Technology

[0002] Wireless access technologies can employ beam scanning when transmitting broadcast information, achieving a wide coverage effect similar to wideband coverage through narrow beam scanning. However, beam scanning also suffers from problems similar to wideband overlapping coverage: at the same time, sub-beams from different cells hit the same concentrated area, leading to a decrease in the signal-to-noise ratio of terminals in that area, increased difficulty in demodulating the serving beam, and ultimately a deterioration in the network quality of the terminal.

[0003] Currently, related technologies associate beam isolation optimization schemes with Physical Cell Identifiers (PCIs), which limits the flexibility of the schemes. Furthermore, when the cellular network distribution is irregular, PCI planning lacks regularity, and the associated beam isolation optimization schemes may not yield significant benefits. Summary of the Invention

[0004] This application provides a beam optimization method and apparatus to address the shortcomings of poor flexibility and low returns in existing beam optimization schemes, thereby improving the flexibility and returns of beam optimization schemes.

[0005] In a first aspect, embodiments of this application provide a beam optimization method, including:

[0006] Obtain the evaluation data corresponding to each candidate beam weight, and determine the optimal beam weight among the candidate beam weights based on the evaluation data;

[0007] After configuring the optimal beam weights for multiple base stations, beam conflict information between base stations is obtained;

[0008] The optimal beam weights and beam conflict information are input into the beam optimization model to obtain the sub-beam transmission order of each base station output by the beam optimization model.

[0009] The beam optimization model is constructed based on a greedy algorithm and a genetic algorithm.

[0010] Optionally, determining the optimal beam weights from the candidate beam weights based on the evaluation data includes:

[0011] Based on the evaluation data, determine the evaluation information corresponding to the weight of each candidate beam;

[0012] Based on the evaluation information, the optimal beam weights are determined from the candidate beam weights.

[0013] Optionally, the evaluation information includes any one or a combination of the following:

[0014] Coverage performance;

[0015] Sub-beam isolation within the community;

[0016] Key performance indicators (KPIs);

[0017] Split ratio.

[0018] Optionally, the beam conflict information between the base stations includes the overall network beam conflict level.

[0019] Optionally, the overall beam collision level is obtained through the following steps:

[0020] The initial quantity of each sampling point is weighted to obtain the weighted quantity of each sampling point, where the initial quantity is 1;

[0021] The beam conflict level of the entire network is determined based on the beam conflict situation of each sampling point and the weighted number of each sampling point.

[0022] Optionally, the step of weighting the initial number of each sampling point to obtain the weighted number of each sampling point includes:

[0023] The difference between the second reference signal received power RSRP and the first RSRP is substituted into the preset first weighted regression fitting equation to obtain the first weighted weight.

[0024] Substitute the second RSRP into the preset second weighted regression fitting equation to obtain the second weighted weight;

[0025] Multiply the first weighted value, the second weighted value, and the initial quantity to obtain the weighted number of sampling points;

[0026] Wherein, the first RSRP corresponds to the serving cell to which the sampling point belongs, and the second RSRP corresponds to the neighboring cell of the serving cell, wherein the neighboring cell and the serving cell belong to different base stations.

[0027] Optionally, the step of inputting the optimal beam weights and the beam conflict information into the beam optimization model to obtain the sub-beam transmission order of each base station output by the beam optimization model includes:

[0028] Based on a greedy algorithm, with the goal of minimizing the overall network beam conflict level, the sub-beam transmission order of each base station is solved one by one to obtain the initial sub-beam transmission order of each base station.

[0029] With the goal of minimizing the overall network beam conflict level, an initial population for the genetic algorithm is obtained based on the initial sub-beam transmission order and the default sub-beam transmission order. The sub-beam transmission order of each base station is then obtained through the genetic algorithm.

[0030] Optionally, the beam conflict information between base stations may further include: the comprehensive weighted number of beam conflict sampling points corresponding to each base station;

[0031] The step of solving for the sub-beam transmission order of the base station one by one includes:

[0032] Based on the comprehensive weighted number of beam collision sampling points corresponding to each base station, the base stations are arranged in descending order, and the sub-beam transmission order of each base station is solved one by one according to the arrangement order of the base stations;

[0033] The comprehensive weighted number is obtained based on the weighted number of beam conflict sampling points obtained when the cell is a serving cell and the weighted number of beam conflict sampling points obtained when the cell is a neighboring cell.

[0034] Optionally, obtaining the initial population for the genetic algorithm based on the initial sub-beam transmission order and the default sub-beam transmission order includes:

[0035] Based on the initial sub-beam transmission sequence and the preset first step length, a first number of initial samples are randomly generated; and

[0036] Based on the default sub-beam transmission order and the preset second step size, a second number of initial samples are randomly generated;

[0037] The first number of initial samples and the second number of initial samples are used as the initial population of the genetic algorithm.

[0038] Optionally, the method further includes:

[0039] After configuring the sub-beam transmission order for each base station, the optimized beam collision sampling points are obtained;

[0040] If the optimized beam collision sampling points do not meet the preset requirements, the beam collision information and the sub-beam transmission order of each base station are reacquired.

[0041] The preset requirements include:

[0042] The weighted number of optimized beam collision sampling points meets the preset requirement; and / or

[0043] The rate of change of beam collision sampling points meets the preset rate of change requirements.

[0044] Optionally, the method further includes:

[0045] Save the optimal beam weights and the sub-beam transmission order of each base station;

[0046] Based on changes in the network service model, the optimal beam weights and the sub-beam transmission order of each base station are iteratively updated.

[0047] Secondly, embodiments of this application also provide a beam optimization device, comprising:

[0048] The acquisition unit is used to acquire the evaluation data corresponding to each candidate beam weight, and determine the optimal beam weight among the candidate beam weights based on the evaluation data.

[0049] The acquisition unit is also used to acquire beam conflict information between base stations after configuring the optimal beam weights for multiple base stations;

[0050] The processing unit is used to input the optimal beam weights and the beam conflict information into the beam optimization model to obtain the sub-beam transmission order of each base station output by the beam optimization model;

[0051] The beam optimization model is constructed based on a greedy algorithm and a genetic algorithm.

[0052] Thirdly, embodiments of this application also provide an electronic device, including a memory, a transceiver, and a processor, wherein:

[0053] A memory for storing computer programs; a transceiver for transmitting and receiving data under the control of the processor; and a processor for reading the computer program from the memory and implementing the steps of the beam optimization method described in the first aspect above.

[0054] Fourthly, embodiments of this application also provide a processor-readable storage medium storing a computer program for causing the processor to perform the steps of the beam optimization method described in the first aspect above.

[0055] The beam optimization method and apparatus provided in this application first determine the optimal beam weights, obtain beam conflict information between base stations under the optimal beam weight configuration, and then, based on the beam conflict information, obtain the sub-beam transmission order of each base station through a beam optimization model constructed based on a greedy algorithm and a genetic algorithm. This application combines the advantages of the greedy algorithm (efficiency and ease of implementation) with the advantages of the genetic algorithm (adaptive and global optimization) to obtain the optimal sub-beam transmission order scheme under the optimal beam weights, effectively reducing beam conflict across the entire network and thus improving the signal-to-interference-plus-noise ratio (SINR). Furthermore, this application only requires obtaining the evaluation data after configuring candidate beam weights and the MR data after configuring the optimal beam weights, without needing to associate the beam optimization method with PCI, thus improving the flexibility of the beam optimization method. Attached Figure Description

[0056] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0057] Figure 1 This is a schematic diagram of beam scanning for a single cell provided in this application;

[0058] Figure 2 This is a schematic diagram of cellular network coverage provided in this application;

[0059] Figure 3 This is a schematic diagram of beam scanning over the common coverage area of ​​different base stations provided in this application;

[0060] Figure 4 This is one of the flowcharts illustrating the beam optimization method provided in the embodiments of this application;

[0061] Figure 5 This is a second schematic flowchart of the beam optimization method provided in the embodiments of this application;

[0062] Figure 6 This is a data diagram of net isolation provided in an embodiment of this application;

[0063] Figure 7 This is a schematic diagram of the beam optimization device provided in the embodiments of this application;

[0064] Figure 8 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0065] In the embodiments of this application, the term "and / or" describes the relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. The character " / " generally indicates that the preceding and following associated objects have an "or" relationship.

[0066] In the embodiments of this application, the term "multiple" refers to two or more, and other quantifiers are similar.

[0067] 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.

[0068] The technical solutions provided in this application can be applied to various systems, especially 5G (5th Generation Mobile Communication Technology) systems. For example, applicable systems include Global System for Mobile Communication (GSM), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA) General Packet Radio Service (GPRS), Long Term Evolution (LTE), LTE Frequency Division Duplex (FDD), LTE Time Division Duplex (TDD), Long Term Evolution Advanced (LTE-A), Universal Mobile Telecommunication System (UMTS), Worldwide Interoperability for Microwave Access (WiMAX), and 5G New Radio (NR). All of these systems include terminal equipment and network equipment. The system may also include a core network component, such as the Evolved Packet System (EPS) or the 5G system (5GS).

[0069] The terminal devices involved in the embodiments of this application can be devices that provide voice and / or data connectivity to users, handheld devices with wireless connectivity, or other processing devices connected to a wireless modem. The names of the terminal devices may differ in different systems; for example, in a 5G system, a terminal device can be called User Equipment (UE). Wireless terminal devices can communicate with one or more core networks (CNs) via a Radio Access Network (RAN). Wireless terminal devices can be mobile terminal devices, such as mobile phones (or "cellular" phones) and computers with mobile terminal devices, for example, portable, pocket-sized, handheld, computer-embedded, or vehicle-mounted mobile devices that exchange voice and / or data with the RAN. Examples include Personal Communication Service (PCS) phones, cordless phones, Session Initiated Protocol (SIP) phones, Wireless Local Loop (WLL) stations, and Personal Digital Assistants (PDAs). Wireless terminal equipment can also be referred to as a system, subscriber unit, subscriber station, mobile station, mobile station, remote station, access point, remote terminal, access terminal, user terminal, user agent, or user device, but is not limited to these terms in the embodiments of this application.

[0070] The network device involved in this application embodiment can be a base station, which may include multiple cells providing services to terminals. Depending on the specific application, a base station may also be called an access point, or a device in an access network that communicates with a wireless terminal device through one or more sectors on the air interface, or other names. The network device 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 device can also coordinate the attribute management of the air interface. For example, the network equipment involved in the embodiments of this application can be a base transceiver station (BTS) in a Global System for Mobile communications (GSM) or Code Division Multiple Access (CDMA), a NodeB in a Wide-band Code Division Multiple Access (WCDMA) system, an evolved Node B (eNB or e-NodeB) in a long term evolution (LTE) system, a 5G base station (gNB) in a next generation system, a Home evolved Node B (HeNB), a relay node, a femto, a pico, etc., and is not limited in the embodiments of this application. In some network structures, the network equipment may include centralized unit (CU) nodes and distributed unit (DU) nodes, and the centralized unit and distributed unit may be geographically separated.

[0071] Network devices and terminal devices can each use one or more antennas for multiple-input multiple-output (MIMO) transmission. MIMO transmission can be single-user MIMO (SU-MIMO) or multiple-user MIMO (MU-MIMO). Depending on the configuration and number of antenna combinations, MIMO transmission can be 2D-MIMO, 3D-MIMO, FD-MIMO, or massive-MIMO, and can also be diversity transmission, precoding transmission, or beamforming transmission, etc.

[0072] To facilitate understanding of the embodiments of this application, the following describes the terms or background related to the embodiments of this application:

[0073] According to relevant technologies, there are currently multiple schemes for beam scanning with different SCS (Sub-Carrier Space) and SSB (Synchronization Signaling Block) time-domain mappings within different frequency bands. Taking China Mobile's TDD 2.6G band and 30kHz SCS as an example, the SSB time-domain mapping is Case C, meaning that the first symbol index of the SSB block within half a frame (5ms period) is {2,8}+14*n, n=0,1,2,3, and the maximum number of transmissions is 8, i.e., 8 beams. Figure 1 This is a beam scanning diagram of a single cell provided in this application, such as... Figure 1 As shown in the figure, each beam is represented by #0-#7, and each beam transmits at different times.

[0074] Figure 2 This is a schematic diagram of cellular network coverage provided in this application, such as... Figure 2 As shown, in an ideal cellular network, Figure 2 The direction of the middle arrow indicates the antenna normal direction of each cell. The entire network area can be divided into independent areas covered by multiple cells. The area with diagonal lines is the area covered by different base stations, and the area without diagonal lines is the splicing of the coverage areas of different cells within a base station. The inventors have found that since the sub-beams of different cells with the same ID (Identity Document) within a base station already have nearly 120° of physical isolation, the impact of beam collisions on signal demodulation is relatively small. The impact of beam collisions between different base stations on the Signal to Interference plus Noise Ratio (SINR) is much greater than that of beam collisions within a base station.

[0075] Beam collision refers to beams with the same beam ID hitting the same area. Figure 3This is a beam scanning diagram of the common coverage area of ​​different base stations provided in this application, such as... Figure 3 As shown, there are three different base stations S1, S2 and S3, each with 8 beams, denoted as #0-#7. Beam #3 of base station S1 has the same beam ID as beam #3 of base station S2 and hits the same area, resulting in beam conflict. Beam #3 of base station S2 has the same beam ID as beam #3 of base station S3 and hits the same area, resulting in beam conflict.

[0076] Beam isolation strategies in related technologies are mainly related to the Physical Cell Identifier (PCI). By planning the PCI of the cellular network according to rules, the network can be roughly divided into similar... Figure 3 The three-element clusters allow for large-scale beam optimization, isolating beams and reducing beam collisions. However, associating beam optimization schemes with PCI limits the flexibility of the scheme and makes it difficult to adapt to changes in existing network service models, thus restricting the timeliness of the scheme. Furthermore, when cellular networks are irregularly distributed, PCI planning lacks a pattern corresponding to the distribution, and the associated beam optimization schemes may not yield significant benefits.

[0077] 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.

[0078] Figure 4 This is one of the flowcharts illustrating the beam optimization method provided in the embodiments of this application, such as... Figure 4 As shown in the figure, this application provides a beam optimization method, including:

[0079] Step 410: Obtain the evaluation data corresponding to each candidate beam weight, and determine the optimal beam weight among the candidate beam weights based on the evaluation data;

[0080] Specifically, the beam can be an SSB beam, and the beam weight is the SSB beam weight. The beam weight can include the following parameters: horizontal beamwidth, vertical beamwidth, tilt adjustable range, azimuth adjustable range, and number of beams, etc. The beam weight can be used for beamforming. Each candidate beam weight can correspond to a set of beams.

[0081] Evaluation data refers to data related to beam weight selection, reflecting the network performance under the current beam weight configuration. It should be understood that the metrics for selecting beam weights differ for different application scenarios. Taking coverage scenarios as an example, coverage scenarios can include various scenarios such as squares, low-rise buildings, mid-rise buildings, and high-rise buildings, each with different coverage performance requirements. Furthermore, the peak traffic periods within the same coverage scenario also differ. Therefore, different application scenarios have different requirements, and the evaluation data used will also differ. Optionally, evaluation data can include any one or a combination of the following: Measurement Report (MR) data, network-wide data, Key Performance Indicator (KPI) data, or traffic split ratio data. MR data can be obtained by the base station side after being reported by the terminal; network-wide data is obtained through network-wide testing; and KPI and traffic split ratio data can be obtained by the network side. It should be understood that the above are examples for understanding the embodiments of this application. The embodiments of this application do not limit the specific data types and acquisition methods of the evaluation data. The evaluation data can be specifically determined for the beam weight selection of different scenarios. The evaluation data can be obtained through the methods proposed in the embodiments of this application, or through other related technologies.

[0082] In one embodiment, candidate beam weights can be configured sequentially for the base station, and measurement report (MR) data reported by the terminal can be obtained through base station statistics. Taking a 5G new radio (NR) scenario as an example, the MR data can include the MR data of the serving cell and the MR data of neighboring cells. The MR data of each cell can include: sampling point number, sub-beam identifier, spectrum and frequency point number, PCI, Reference Signal Receiving Quality (RSRQ), Reference Signal Receiving Power (RSRP), and SINR, etc. Based on the MR data, the optimal beam weights that meet the current requirements (e.g., the highest RSRP of the serving cell) can be determined. It should be understood that the sub-beam referred to in the embodiments of this application refers to one beam in a group of beams. Figure 1 In the middle, beam #0 is a sub-beam.

[0083] Step 420: After configuring the optimal beam weights for multiple base stations, obtain beam conflict information between base stations;

[0084] Specifically, beam conflict information between base stations can be obtained through MR data. After deploying optimal beam weights for the base stations, a network test is conducted to obtain MR data under the scenario of configuring the optimal beam weights. Beam conflict information is obtained through the MR data. Beam conflict information refers to information related to beam conflict, which can include parameter information related to beam conflict (such as SINR), the distribution of all sampling points, beam conflict details (a list of sampling points with beam conflict), the number of beam conflict points, and the proportion of beam conflict in the entire network. Optionally, as mentioned above, beam conflict between different base stations has a much greater impact on signal and SINR than internal conflicts within base stations. Therefore, beam conflict in this embodiment can refer to cross-site cell beam-level beam conflict, which means that beam conflict occurs between the beams of two cells belonging to different base stations. It should be understood that sampling points from the same site can be removed based on relevant technologies, which will not be elaborated here.

[0085] Step 430: Input the optimal beam weights and the beam conflict information into the beam optimization model to obtain the sub-beam transmission order of each base station output by the beam optimization model;

[0086] The beam optimization model is constructed based on a greedy algorithm and a genetic algorithm.

[0087] Specifically, the sub-beam transmission order refers to the order in which sub-beams are transmitted within a group of sub-beams. Optionally, the sub-beam transmission order can be determined by identifying the beam transmission start point, which is the first sub-beam transmitted. The optimal beam weights are used to determine which beam is transmitted first within a group of beams (beam 0, beam 1, ..., beam n), and the subsequent beam transmission order can be determined based on the default configuration. For example, if the default sub-beam transmission order is beam 0, beam 1, beam 2, beam 3, and the first sub-beam transmitted by base station S1 is beam 2, then the sub-beam transmission order of base station S1 within one cycle is: beam 2, beam 3, beam 0, beam 1.

[0088] The beam optimization model leverages the advantages of greedy algorithms, which are easy to implement and highly efficient. Based on beam conflict information (such as simulation based on beam conflict information or using a specific beam conflict information as the optimization objective), it obtains the sub-beam transmission order of each base station under the optimal beam weights. The sub-beam transmission order of each base station obtained by the greedy algorithm may be a local optimum. Then, a genetic algorithm is introduced, utilizing its advantages of adaptability and global optimization, to further optimize the sub-beam transmission order obtained by the greedy algorithm, thus obtaining the final sub-beam transmission order of each base station, which is the sub-beam transmission order of each base station output by the beam optimization model.

[0089] It should be understood that the above examples are for the purpose of understanding this application and should not constitute any limitation on this application. For example, beam weights may include other parameters not mentioned or may not include one of the above parameters.

[0090] The beam optimization method provided in this application first determines the optimal beam weights, obtains beam conflict information between base stations under the optimal beam weight configuration, and then, based on the beam conflict information, obtains the sub-beam transmission order of each base station through a beam optimization model constructed based on a greedy algorithm and a genetic algorithm. This application combines the advantages of the greedy algorithm (efficiency and ease of implementation) with the advantages of the genetic algorithm (adaptive and global optimization) to obtain the optimal sub-beam transmission order scheme under the optimal beam weights, effectively reducing beam conflict across the entire network and thus improving SINR. It should be understood that for SSB beams, this can improve SSB-SINR (Synchronization Signaling Block-Signal to Interference plus Noise Ratio, also abbreviated as SSBSINR). Furthermore, this application only requires obtaining the evaluation data after configuring candidate beam weights and the MR data after configuring the optimal beam weights, without needing to associate the beam optimization method with PCI, thus improving the flexibility of the beam optimization method.

[0091] Optionally, determining the optimal beam weights from the candidate beam weights based on the evaluation data includes:

[0092] Based on the evaluation data, determine the evaluation information corresponding to the weight of each candidate beam;

[0093] Based on the evaluation information, the optimal beam weights are determined from the candidate beam weights.

[0094] Specifically, it should be understood that in the process of beam weight selection, since the needs of different scenarios vary, the evaluation indicators can be determined according to the applicable scenario. Evaluation information refers to information related to the beam weight selection criteria determined based on current needs, that is, information corresponding to the evaluation indicators. Evaluation data is unprocessed initial data. After organizing, analyzing, or otherwise processing the evaluation data, evaluation information can be obtained.

[0095] For example, taking MR coverage performance as an example, the evaluation data is MR data, which may include SSB-RSRP data and SSB-SINR data. MR coverage performance can be represented by MR coverage rate and average SINR. For example, the MR coverage rate can be set as:

[0096]

[0097] Therefore, the MR coverage and average SINR obtained based on MR data are used as evaluation information.

[0098] Optionally, the evaluation information includes any one or a combination of the following:

[0099] Coverage performance;

[0100] Sub-beam isolation within the community;

[0101] Key performance indicators (KPIs);

[0102] Split ratio.

[0103] Specifically, coverage performance can be divided into MR coverage performance and grid-based coverage performance. MR coverage performance can be determined based on MR data (such as SSB-RSRP and SSB-SINR). Optionally, MR performance can include MR coverage rate and average SINR. It should be understood that beam collision has a significant impact on SINR; therefore, when improving coverage performance in this application embodiment, it is necessary to focus on both MR coverage rate and average SINR. Grid-based coverage performance can be determined based on grid-based data. Sub-beam isolation within a cell can be obtained from grid-based data. Key performance indicators (KPIs) can be obtained from KPI data. Split ratio can be obtained from split ratio data.

[0104] It should be understood that the above assessment information can be combined in any way, and the combined information can be assessed in any order.

[0105] Optionally, the optimal beam weight can be determined based on coverage performance, and the candidate beam weight corresponding to the optimal coverage performance can be selected as the optimal beam weight.

[0106] If the optimal beam weight cannot be determined based on coverage performance, the optimal beam weight is determined based on the sub-beam isolation degree within the cell, and the candidate beam weight corresponding to the optimal sub-beam isolation degree within the cell is selected as the optimal beam weight.

[0107] If the optimal beam weight cannot be determined based on the sub-beam isolation degree within the cell, the optimal beam weight is determined based on the KPI, and the candidate beam weight corresponding to the optimal KPI is selected as the optimal beam weight.

[0108] In one embodiment, determining the optimal beam weights among the candidate beam weights based on the evaluation information may include:

[0109] (1) By means of network testing and observation of retained MR data, the candidate beam weights with better overall coverage performance (SSB-RSRP and SSB-SINR) are selected: the candidate beam weights corresponding to high RSRP are selected first; when RSRP is comparable (the difference is within the preset range, such as within 0.5dB), the candidate beam weights corresponding to the best SINR are selected.

[0110] (2) By using the network data, select the weight with higher sub-beam isolation within a single cell: The larger the difference in RSRP level between the strongest beam and the other beams in the serving cell, the higher the sub-beam isolation within the cell is considered. At this time, the terminal has a more stable serving beam, which is more conducive to subsequent beam optimization. The main reference is the distribution of RSRP level difference between the strongest beam and the second strongest beam in the serving cell. If the level is similar, the distribution of RSRP level difference between the strongest beam and the third, fourth, and fifth strongest beams will be considered in turn.

[0111] (3) By retaining MR data, observe the fluctuation of KPI and split ratio under different candidate beam weights, and select the weight with better network performance: prioritize the split ratio. If the split ratio has a significant advantage and the KPI fluctuation range is acceptable, the weight can be selected.

[0112] The beam optimization method provided in this application determines the optimal beam weight among the candidate beam weights based on the evaluation information. This method can meet the network performance requirements of the current network and optimize the beam under the premise of configuring the optimal beam weight for the base station, thereby reducing beam conflict.

[0113] Optionally, the beam conflict information between the base stations includes the overall network beam conflict level.

[0114] Specifically, the overall beam collision level is data used to represent the degree of beam collision across the entire network. The overall beam collision level can be expressed through the relationship between the number of sampling points. For example, the overall beam collision level can be: the total number of beam-colliding sampling points, the total number of non-colliding sampling points, or the percentage of beam-colliding sampling points. It should be understood that beam-colliding sampling points refer to sampling points where beam collisions have occurred; non-colliding sampling points refer to sampling points where no beam collisions have occurred. The percentage of beam-colliding sampling points = the total number of beam-colliding sampling points / the total number of all sampling points. The total number of all sampling points = the total number of beam-colliding sampling points + the total number of non-colliding sampling points.

[0115] Optionally, the overall beam collision level is obtained through the following steps:

[0116] The initial quantity of each sampling point is weighted to obtain the weighted quantity of each sampling point, where the initial quantity is 1;

[0117] The beam conflict level of the entire network is determined based on the beam conflict situation of each sampling point and the weighted number of each sampling point.

[0118] Specifically, weighting values ​​can be determined based on factors such as the importance of the sampling points or their impact on SINR, and the initial number of sampling points can be weighted accordingly to obtain the weighted number of each sampling point. The weighted number of a sampling point = the initial number of sampling points × the weighting value.

[0119] The beam conflict situation of a sampling point refers to whether there is beam conflict at the sampling point, which includes two situations: "conflict" and "non-conflict". As mentioned above, if a sampling point has beam conflict, it is a beam conflict sampling point; if a sampling point does not have beam conflict, it is a non-conflict sampling point.

[0120] The beam conflict level of the entire network is determined based on the beam conflict situation of each sampling point and the weighted number of each sampling point, which may include any of the following methods or a combination thereof:

[0121] (1) Calculate the weighted total number of beam conflict sampling points. The weighted total number of beam conflict sampling points represents the beam conflict level of the entire network. The larger the weighted total number of beam conflict sampling points, the higher the beam conflict level of the entire network.

[0122] (2) Calculate the weighted proportion of beam collision sampling points across the entire network:

[0123]

[0124] The weighted total of all sampled points can be the sum of the weighted total of conflicting sampled points and the weighted total of non-conflicting sampled points.

[0125] The weighted proportion of all conflict sampling points in the network represents the overall beam conflict level. The higher the weighted proportion of all conflict sampling points in the network, the higher the overall beam conflict level.

[0126] (3) Calculate the weighted total number of non-collision sampling points. The weighted total number of non-collision sampling points represents the beam collision level of the entire network. The smaller the weighted total number of non-collision sampling points, the higher the beam collision level of the entire network.

[0127] (4) Calculate the weighted descent ratio of all beam collision sampling points in the network:

[0128]

[0129] It should be understood that, without optimization, the weighted proportion of all network conflict sampling points after optimization is equal to the weighted proportion of all network conflict sampling points before optimization, and the weighted decrease rate of all network beam conflict sampling points is 0%.

[0130] It should be understood that the above examples are provided for the purpose of understanding this application and should not constitute any limitation on this application.

[0131] For example, Table 1 is a schematic table of weighted calculation of sampling points provided in the embodiments of this application, as shown in Table 1:

[0132] Table 1. Schematic diagram of weighted calculation of sampling points

[0133] Sampling point 1 Beam conflict 1 1 1 Sampling point 2 Beam conflict 1 1.5 1.5 Sampling point 3 Beam conflict 1 0.9 0.9 Sampling point 4 Non-conflict 1 1.2 1.2

[0134]

[0135] The beam optimization method provided in this application embodiment can more effectively represent the beam conflict situation of a sampling point by weighting the number of sampling points relative to the initial number of sampling points, thereby making the overall network beam conflict level obtained based on the weighted number more effective in representing the overall network beam conflict degree.

[0136] Optionally, the step of weighting the initial number of each sampling point to obtain the weighted number of each sampling point includes:

[0137] The difference between the second reference signal received power RSRP and the first RSRP is substituted into the preset first weighted regression fitting equation to obtain the first weighted weight.

[0138] Substitute the second RSRP into the preset second weighted regression fitting equation to obtain the second weighted weight;

[0139] Multiply the first weighted value, the second weighted value, and the initial quantity to obtain the weighted number of sampling points;

[0140] Wherein, the first RSRP corresponds to the serving cell to which the sampling point belongs, and the second RSRP corresponds to the neighboring cell of the serving cell, wherein the neighboring cell and the serving cell belong to different base stations.

[0141] Specifically, RSRP can be SSB-RSRP. The first weighted regression fitting equation can be obtained by fitting the difference interval between the second RSRP and the first RSRP to the first weight interval.

[0142] For example, taking linear fitting as an example, with the difference interval being [p, q] and the first weight interval being [m, n], the following first weighted regression fitting equation can be obtained:

[0143] First weighted value

[0144]

[0145] Where RSRP1 is the first RSRP, RSRP2 is the second RSRP, k1 is the first coefficient, b1 is the first intercept, when RSRP2-RSRP1=p, the first weighted value L1=m, and when RSRP2-RSRP1=q, the first weighted value L1=n.

[0146] Specifically, the second weighted regression fitting equation can be obtained by fitting the value range of the second RSRP to the second weight range. The fitting method is the same as that for the first weighted regression fitting equation described above, and will not be repeated here.

[0147] It should be understood that the weighting method provided in the embodiments of this application can be applied to all embodiments of this application.

[0148] Since the closer the neighboring cell's SSB-RSRP level is to or even higher than that of the serving cell's SSB-RSRP, and the higher the neighboring cell's SSB-RSRP level is, the greater the impact of beam conflict on SSB-SINR, the beam optimization method provided in this application provides weighted sampling points based on SSB-RSRP. This effectively reflects the impact of beam conflict on SINR, increases the weight of sampling points with a large impact on SINR, and thus more accurately reflects the beam conflict situation.

[0149] Optionally, the step of inputting the optimal beam weights and the beam conflict information into the waveform optimization model to obtain the sub-beam transmission order of each base station output by the beam optimization model includes:

[0150] Based on a greedy algorithm, with the goal of minimizing the overall network beam conflict level, the sub-beam transmission order of each base station is solved one by one to obtain the initial sub-beam transmission order of each base station.

[0151] With the goal of minimizing the overall network beam conflict level, an initial population for the genetic algorithm is obtained based on the initial sub-beam transmission order and the default sub-beam transmission order. The sub-beam transmission order of each base station is then obtained through the genetic algorithm.

[0152] Specifically, a greedy algorithm is one that always makes the best choice at the moment when solving a problem. The initial sub-beam transmission order refers to the sub-beam transmission order obtained through a greedy algorithm. Because greedy algorithms suffer from local optima, the desired optimization goal is generally not achieved with the initial sub-beam transmission order, and further optimization is required.

[0153] The optimization objective of minimizing the overall beam conflict level can refer to minimizing the weighted total number of beam conflict sampling points, minimizing the weighted proportion of beam conflict sampling points across the entire network, or maximizing the weighted total number of non-conflicting sampling points.

[0154] Genetic Algorithms (GA) are designed based on the laws of biological evolution in nature. They are computational models that simulate the biological evolutionary process based on natural selection and genetic mechanisms in Darwin's theory of evolution, and are a method for searching for optimal solutions by simulating the natural evolutionary process.

[0155] For the genetic algorithm, the optimization objective is to minimize the beam collision level of the entire network. Since the genetic algorithm usually uses the fitness value (also known as the fitness value) to measure the quality of individuals in the population, it is used to judge the quality of the current solution. Furthermore, the genetic algorithm usually seeks the solution with a larger fitness value. Therefore, the weighted number of non-collision sampling points can be used as the fitness value.

[0156] The default sub-beam transmission order refers to the sub-beam transmission order configured by the system. The starting point for beam transmission is the default, usually the beam numbered 0.

[0157] Genetic algorithms begin iterating from the initial population. Optionally, crossover probability, inheritance probability, and number of generations can be set. Using genetic algorithms, the desired optimization objective can ultimately be obtained.

[0158] In one embodiment, the optimization objective is to achieve a weighted decrease ratio of over 25% for the final solution (i.e., the sub-beam transmission order) across the entire network of beam collision sampling points. The algorithm is set to have a crossover probability of 0.8, a mutation probability of 0.01, and a genetic generation of 50 generations. If a solution with a weighted decrease ratio of over 25% for the entire network of beam collision sampling points is calculated in advance, the algorithm can be exited. Alternatively, the calculation can continue to obtain a better solution.

[0159] The beam optimization method provided in this application combines the advantages of the greedy algorithm (efficiency and ease of implementation) with the advantages of the genetic algorithm (adaptive and global optimization) to obtain the optimal sub-beam transmission order scheme under the optimal beam weight, effectively reducing beam collisions across the entire network.

[0160] Optionally, the beam conflict information between base stations may further include: the comprehensive weighted number of beam conflict sampling points corresponding to each base station;

[0161] The step of solving for the sub-beam transmission order of the base station one by one includes:

[0162] Based on the comprehensive weighted number of beam collision sampling points corresponding to each base station, the base stations are arranged in descending order, and the sub-beam transmission order of each base station is solved one by one according to the arrangement order of the base stations;

[0163] The comprehensive weighted number is obtained based on the weighted number of beam conflict sampling points obtained when the cell is a serving cell and the weighted number of beam conflict sampling points obtained when the cell is a neighboring cell.

[0164] Specifically, the comprehensive weighted number of beam conflict sampling points refers to the sum of the weighted total number of conflict sampling points corresponding to the base station's cell as a serving cell and the weighted total number of conflict sampling points corresponding to its serving cell when the cell is a neighboring cell, which is taken as the comprehensive weighted total number of beam conflict sampling points corresponding to the base station.

[0165] For example, base station S1 corresponds to cell 101, base station S2 corresponds to cell 102, and base station S3 corresponds to cell 103. Table 2 is a schematic table of comprehensive weighted quantity calculation provided in the embodiments of this application, as shown in Table 2:

[0166] Table 2. Schematic diagram of comprehensive weighted quantity calculation

[0167]

[0168]

[0169] The total weighted number of beam collision sampling points of base station S1 = the total weighted number of collision sampling points in cell 101 when cell 101 is the serving cell + the total weighted number of collision sampling points in the corresponding serving cell when cell 101 is a neighboring cell = Z1 + Z2 + Z3 + Z5 = 290;

[0170] The total weighted number of beam collision sampling points of base station S2 = the total weighted number of collision sampling points in cell 102 when cell 102 is the serving cell + the total weighted number of collision sampling points in the corresponding serving cell when cell 102 is a neighboring cell = Z1 + Z3 + Z4 + Z6 = 305;

[0171] The total weighted number of beam collision sampling points of base station S3 = the total weighted number of collision sampling points in cell 103 when cell 103 is the serving cell + the total weighted number of collision sampling points in the corresponding serving cell when cell 103 is a neighboring cell = Z2 + Z4 + Z5 + Z6 = 285.

[0172] Arranging the base stations in descending order based on the comprehensive weighted number of beam conflict sampling points corresponding to each base station means sorting the base stations from largest to smallest according to the comprehensive weighted number of beam conflict sampling points corresponding to each base station.

[0173] Taking the aforementioned base stations S1, S2, and S3 as examples, Table 3 is a schematic table of base station ordering provided in the embodiments of this application, as shown in Table 3:

[0174] Table 3. Base Station Ranking Diagram

[0175] 1 S2 305 2 S1 290 3 S3 285

[0176] Solving the sub-beam transmission order of each base station according to their arrangement means calculating the sub-beam transmission order (which can be understood as the starting point of beam transmission) for each base station sequentially according to their arrangement. The site for calculating the sub-beam transmission order can be called a pilot site. The sub-beam transmission order of the pilot site is calculated, and the solution that maximizes the reduction in beam collision level across the entire network among the candidate sub-beam transmission orders is selected as the current pilot site's sub-beam transmission order. This current pilot site's sub-beam transmission order is retained as the initial configuration before modification for the next pilot site.

[0177] Taking base stations S1, S2, and S3 as examples, the beam transmission starting point of base station S2 is first determined to be beam 2; given that the beam transmission starting point of base station S2 is beam 2, the beam transmission starting point of base station S1 is determined to be beam 4; given that the beam transmission starting point of base station S2 is beam 2 and the beam transmission starting point of base station S1 is beam 4, the beam transmission starting point of base station S3 is determined to be beam 1; thus, the determination of the sub-beam transmission order for each base station is completed.

[0178] Optionally, the calculation can be stopped when the modification of a single base station has a small impact on the overall beam collision level (e.g., the improvement is less than 0.1%), and the configuration of the calculated base stations can be recorded.

[0179] The beam optimization method provided in this application can quickly obtain the initial sub-beam transmission order through a greedy algorithm, thereby improving the speed of obtaining the beam optimization scheme (the final sub-beam transmission order of each base station).

[0180] Optionally, obtaining the initial population for the genetic algorithm based on the initial sub-beam transmission order and the default sub-beam transmission order includes:

[0181] Based on the initial sub-beam transmission sequence and the preset first step length, a first number of initial samples are randomly generated; and

[0182] Based on the default sub-beam transmission order and the preset second step size, a second number of initial samples are randomly generated;

[0183] The first number of initial samples and the second number of initial samples are used as the initial population of the genetic algorithm.

[0184] Specifically, based on the initial sub-beam transmission order obtained through a greedy algorithm, a first step length is set for the beam transmission start point corresponding to each base station, and a first number of initial samples are randomly generated. Based on the default sub-beam transmission order, a second step length is set for the beam transmission start point corresponding to each base station, and a second number of initial samples are randomly generated.

[0185] Taking base stations S1, S2, and S3 in the above embodiments as examples, the initial sub-beam transmission sequence {4,2,1} is obtained through a greedy algorithm. 4 indicates that the beam transmission starting point of base station S1 is beam 4, 2 indicates that the beam transmission starting point of base station S2 is beam 2, and 1 indicates that the beam transmission starting point of base station S3 is beam 1. It should be understood that the numbers in the sub-beam transmission sequence {……} represent the beam transmission starting points, and their order can correspond to the sub-beam numbering order. For example, the first step length can be ±1, that is, randomly adding or subtracting one from the initial sub-beam transmission sequence {4,2,1} to obtain a new initial sample. The method for generating initial samples based on the default sub-beam transmission sequence is the same as the method described above, and will not be repeated here. It should be understood that the above examples are for the purpose of understanding this application and should not constitute any limitation on this application.

[0186] It should be understood that, based on the initial sub-beam transmission sequence and the preset first step length, a first number of initial samples are randomly generated; and based on the default sub-beam transmission sequence and the preset second step length, a second number of initial samples are randomly generated; the two steps are not limited in the order of execution, and can be executed separately or simultaneously.

[0187] All initial samples are substituted into the genetic algorithm as the initial population. New samples can be obtained through mutation, crossover, and other operations within the genetic algorithm. Each sample corresponds to a beam optimization scheme for the entire network of base stations. It should be understood that a single number in the sample corresponds to the sub-beam transmission order (or beam transmission start point) of a base station, and a single sample can correspond to the sub-beam transmission order of all base stations in the current network (i.e., the beam optimization scheme for the entire network of base stations). MR data (e.g., obtained through simulation) can be obtained under the beam optimization scheme for the entire network of base stations corresponding to a sample. Based on the MR data, the weighted number of non-collision sampling points is determined, and the weighted number of non-collision sampling points is used as the fitness value of the sample.

[0188] The beam optimization method provided in this application obtains initial samples based on the initial sub-beam transmission order, which are derived from a solution obtained by a greedy algorithm. This means that these initial samples are obtained based on a relatively optimal solution, and while their randomness is somewhat limited, they can efficiently obtain better samples. In contrast, initial samples obtained based on the default sub-beam transmission order have greater randomness. Therefore, the beam optimization method provided in this application not only ensures the diversity of the search range during scheme search but also saves a significant amount of ineffective search processes.

[0189] Optionally, the method further includes:

[0190] After configuring the sub-beam transmission order for each base station, the optimized beam collision sampling points are obtained;

[0191] If the optimized beam collision sampling points do not meet the preset requirements, the beam collision information and the sub-beam transmission order of each base station are reacquired.

[0192] The preset requirements include:

[0193] The weighted number of optimized beam collision sampling points meets the preset requirement; and / or

[0194] The rate of change of beam collision sampling points meets the preset rate of change requirements.

[0195] Specifically, taking base stations S1, S2, and S3 in the above embodiment as examples, the initial sub-beam transmission sequence {4,2,1} is obtained through a greedy algorithm, and the final sub-beam transmission sequence is {3,0,1}. After configuring the beam transmission starting point of base station S1 as beam 3, the beam transmission starting point of base station S2 as beam 0, and the beam transmission starting point of base station S3 as beam 1, MR data is obtained.

[0196] The preset quantity requirement can be the weighted reduction ratio of beam collision sampling points across the entire network. It should be understood that during the solution process of the beam optimization model, the beam optimization scheme of the entire network base station corresponding to each sample will be simulated, and the weighted reduction ratio of beam collision sampling points across the entire network will be obtained through the simulation results.

[0197] The preset quantity requirement can be that the weighted reduction ratio of all network beam collision sampling points reaches 25%. If, after configuring the sub-beam transmission order for each base station, acquiring MR data, and calculating the weighted reduction ratio of all network beam collision sampling points based on the MR data, the weighted reduction ratio of all network beam collision sampling points does not reach 25%, then steps 420 and 430 are re-executed until the preset quantity requirement is met. It should be understood that the weighted reduction ratio of all network beam collision sampling points is related to the degree of network optimization. 25% is an example provided in this application embodiment; in practical applications, it is necessary to find a solution with the largest possible reduction ratio.

[0198] During the solution process of the beam optimization model, a list of beam collision sampling points corresponding to the final sub-beam transmission order can be simulated, hereinafter referred to as the expected details. The actual list of beam collision sampling points can be obtained by statistically analyzing the MR data reported by the terminal from the base station, hereinafter referred to as the actual details. For the beam collision sampling point change rate to meet the preset change rate requirement, it means that compared with the expected details, the actual details do not generate a large number of new or other conflicting beam sampling points. The change rate can be preset. It should be understood that due to data fluctuations, a certain amount of new conflicting beam sampling points will inevitably occur. If there are a large number of new conflicting beam sampling points, it indicates that the calculation results are incorrect or the network service model has changed significantly, requiring re-optimization: return to and re-execute steps 420 and 430 until the beam collision sampling point change rate is met.

[0199] If the preset requirements are met, it means that there is no significant contradiction between the actual results and the predicted results, and the beam optimization scheme is retained.

[0200] The beam optimization method provided in this application ensures the effectiveness of the beam optimization scheme in application and avoids errors caused by changes in calculation or network service models.

[0201] Optionally, the method further includes:

[0202] Save the optimal beam weights and the sub-beam transmission order of each base station;

[0203] Based on changes in the network service model, the optimal beam weights and the sub-beam transmission order of each base station are iteratively updated.

[0204] Specifically, the optimal beam weights obtained in step 410 and the final sub-beam transmission order of each base station are saved (i.e., the final beam optimization scheme).

[0205] A network service model can be understood as the application scenario of the current network. For example, the traffic volume and peak traffic periods differ in scenarios such as densely populated urban areas, general urban areas, suburbs (counties and townships), and rural areas. Due to changes in the network service model, the previously saved beam optimization scheme may no longer be applicable to the changed network service model. In this case, it is necessary to re-obtain the optimal beam weights and the sub-beam transmission order of each base station. The existing beam optimization scheme can be updated and optimized to obtain a new beam optimization scheme.

[0206] Optionally, if it is impossible to determine whether the network service model has changed, the optimization scheme can be iteratively updated based on the saved beam optimization scheme according to a preset period.

[0207] The beam optimization method provided in this application can flexibly respond to changes in the existing network service model and improve the timeliness of the beam optimization scheme.

[0208] In one embodiment, using the China Mobile 2.6G band 8-beam scenario, Table 4 is a candidate beam weight table provided in the embodiments of this application, and the beam information corresponding to the candidate beam weights is shown in Table 4:

[0209] Table 4. Candidate beam weights provided in this application

[0210]

[0211] Figure 5 This is a second schematic flowchart of the beam optimization method provided in the embodiments of this application, as shown below. Figure 5 As shown in the figure, this application provides a beam optimization method, including:

[0212] Step 1: Optimal beam weight selection. The beam weights below can be simply referred to as weights.

[0213] (1) Table 5 is one of the MR coverage performance tables provided in the embodiments of this application. As shown in Table 5, the MR coverage performance under the optimal beam weight configuration is as follows:

[0214] Table 5. MR Coverage Performance Table (Part 1)

[0215]

[0216]

[0217] In the table, CDF stands for Cumulative Distribution Function, also known as the distribution function, which is the integral of the probability density function, i.e., the integral of the distribution density function. Edge SSB SINR (the value where CDF equals 5%) refers to the SINR value of the sampling point corresponding to the 5th percentile from low to high. SSB RSRP (the value where CDF equals 5%) is similar and will not be elaborated here. SSB RSRP is the Synchronization Signaling Block-Reference Signal Receiving Power (also abbreviated as SSB-RSRP).

[0218] The MR data shows that the coverage performance of lossy weights is generally better than that of lossless weights, and the larger the sub-beam pointing angle and the closer the envelope is to 120°, the better the coverage performance.

[0219] Table 6 is the second MR coverage performance table provided in the embodiments of this application. As shown in Table 6, the coverage performance of multiple groups of lossy weights is further evaluated using MR data as follows:

[0220] Table 6. MR Coverage Performance Table II

[0221]

[0222]

[0223] In summary, based on the above verifications, in terms of coverage performance, the lossy 49° weight is the optimal candidate beam weight.

[0224] (2) Figure 6 This is a data diagram of net isolation provided in an embodiment of this application, such as... Figure 6 As shown, net isolation is represented by the difference and proportion between the strongest and second strongest beams. Net isolation can be used to represent the sub-beam isolation within a cell. The lossy 49° weighted net isolation is better for the strongest and second strongest beams. Statistically, the strongest beam has a similar trend to the third and fourth strongest beams in terms of isolation. In summary, the lossy 49° weighted net isolation also has certain advantages.

[0225] (3) Other network performance evaluation: According to conventional KPIs, traffic offloading ratio and other indicators that operators pay attention to, the lossy 49° weight is generally at a relatively good level.

[0226] In summary, the optimal beam weight is the lossy 49° beam weight.

[0227] Step 2: Deploy the optimal beam weights and obtain beam conflict information under this configuration.

[0228] Taking the calculation of the entire network beam collision level as an example:

[0229] After deploying lossy 49° weights, MR data for 2 working days was retained, and a total of 87,806,815 conflict beam sampling points were calculated in the pilot area of ​​the entire network, with the conflict sampling points accounting for 16.99%.

[0230] Experimental data shows that the closer the neighboring cell SSB-RSRP is to the serving cell SSB-RSRP level, or even higher than the serving cell SSB-RSRP level, and the higher the neighboring cell SSB-RSRP level itself, the greater the impact of beam collision on SSB-SINR.

[0231] The weighted processing method for each sampling point is as follows:

[0232] (1) Preset the first weighted regression fitting equation:

[0233] -10dB≤Neighboring cell SSB-RSRP(Second RSRP)-Serving cell SSB-RSRP(First RSRP)≤6dB, the first weighted value within the interval is processed by linear regression from [0.1,1]. If the level difference between the second RSRP and the first RSRP is less than -10dB, the first weighted value is 0.1. If the level difference between the second RSRP and the first RSRP is greater than 6dB, the first weighted value is 1.

[0234] The difference between the second RSRP and the first RSRP corresponding to the sampling point is substituted into the preset first weighted regression fitting equation to obtain the first weighted weight.

[0235] (2) Pre-set the second weighted regression fitting equation:

[0236] -110dBm≤neighboring cell SSB-RSRP(second RSRP)≤-70dBm, the second weighted value within the interval is processed by linear regression from [0.1,1]. If the second RSRP level is less than -110dBm, the second weighted value is 0.1. If the second RSRP level is greater than -70dBm, the second weighted value is 1.

[0237] Substitute the second RSRP into the preset second weighted regression fitting equation to obtain the second weighted weight.

[0238] (3) The product of the first weighted value obtained in (1) and the second weighted value obtained in (2) is taken as the final weighted value.

[0239] (4) 1 × final weighted value = weighted number of sampling points. It should be understood that 1 is the number of sampling points currently being processed. Since each sampling point is processed individually, the number is 1.

[0240] The total weighted number of sampling points was calculated to be 8,946,572.00, and the total weighted number of beam conflict sampling points was 1,034,720.76, with a weighting ratio of 11.57%.

[0241] Step 3: Perform beam isolation optimization based on the default beam configuration with optimal beam weights.

[0242] The sub-beam transmission order of each base station is adjusted using a greedy algorithm and a genetic algorithm. The overall network beam collision level under the new scheme (the sub-beam transmission order of each base station obtained through the greedy algorithm and genetic algorithm) is estimated. If the expected optimization objective (also known as the convergence condition) is achieved, it indicates that the optimal solution has been obtained, and a beam optimization scheme that meets the preset requirements is output. The expected optimization objective can be: a significant decrease in the weighted total number of SSB beam collision sampling points or a significant decrease in the weighted proportion of SSB beam collision sampling points. The degree of increase and the percentage decrease can be constrained by preset quantities.

[0243] By using a greedy algorithm, the initial sub-beam transmission order of each base station is obtained. After configuring the initial sub-beam transmission order for the base stations, the weighted total number of beam collision sampling points decreases to 770299.85, and the weighted proportion of beam collision sampling points decreases to 8.61%.

[0244] Based on the initial sub-beam transmission order of each base station obtained by the greedy algorithm, 50 initial samples are randomly generated for the beam transmission starting point of each base station using an offset within ±2 steps.

[0245] With the default sub-beam transmission order configured for each base station, the beam transmission start point of each base station uses an offset of no more than 7 steps to randomly generate 50 initial samples.

[0246] A total of 100 initial samples were used as the initial population.

[0247] After setting an 80% crossover probability and a 1% mutation probability for 50 generations, the optimal solution is calculated, which is the sub-beam transmission order output by the beam optimization model.

[0248] With the sub-beam transmission order output by the beam optimization model configured for the base station, the weighted total number of beam conflict sampling points decreased to 711358.30, and the weighted proportion of beam conflict sampling points decreased to 7.95%. It is estimated that compared with the situation before optimization and based on the default configuration, the weighted proportion of beam conflict sampling points has been improved by 31.25%.

[0249] Step 4: Deploy the beam optimization scheme and observe the beam conflict information under the new configuration in the short term to determine whether the beam optimization scheme meets the preset requirements. If it does not meet the preset requirements, revert to the original network configuration, redeploy the optimal beam weights, and obtain the beam conflict information under this configuration.

[0250] After deploying the beam optimization scheme, observe the trend of the total number of beam collision sampling points in the pilot area and whether the coverage performance meets expectations. If it does not meet expectations, revert to the original network configuration, that is, redeploy the optimal beam weights and obtain beam collision information under this configuration.

[0251] In this embodiment, after deploying the beam optimization scheme, MR data for two working days was retained to observe normal fluctuations in the overall SSB-RSRP within the pilot area. The SSB-SINR improved to 16.46 dB, an increase of 2.71 dB compared to the original network configuration of 13.75 dB, representing an improvement of 19.7%.

[0252] Step 5: Save the beam optimization scheme and use it for subsequent optimization iterations and updates.

[0253] The beam optimization scheme is the final optimal beam weight and the sub-beam transmission order of each base station.

[0254] Record and retain the beam optimization scheme, and iterate and update the optimization scheme on a monthly cycle.

[0255] Step 6: Periodically adjust the beam optimization scheme according to changes in the network service model.

[0256] The beam optimization method provided in this application is more flexible than the beam isolation method associated with PCI, and can be iteratively updated in a timely manner as the network service model changes, making it more service-oriented and timely. Furthermore, the beam optimization method provided in this application combines greedy algorithms and genetic algorithms in the process of scheme optimization, which can effectively reduce the high computational load caused by the scale of base stations, significantly improve computational efficiency, effectively reduce the degree of beam-level collision in large-scale networks, and effectively improve network quality.

[0257] refer to Figure 7 , Figure 7 This is a schematic diagram of the beam optimization device provided in an embodiment of the present application. The present application provides a beam optimization device, which includes: an acquisition unit 710 and a processing unit 720.

[0258] The acquisition unit 710 is used to acquire the evaluation data corresponding to each candidate beam weight, and determine the optimal beam weight among the candidate beam weights based on the evaluation data.

[0259] The acquisition unit 710 is also used to acquire beam conflict information between base stations after configuring the optimal beam weights for multiple base stations;

[0260] Processing unit 720 is used to input the optimal beam weight and the beam conflict information into the beam optimization model to obtain the sub-beam transmission order of each base station output by the beam optimization model;

[0261] The beam optimization model is constructed based on a greedy algorithm and a genetic algorithm.

[0262] The beam optimization apparatus provided in this application first determines the optimal beam weights, obtains beam conflict information between base stations under the optimal beam weight configuration, and then, based on the beam conflict information, obtains the sub-beam transmission order of each base station through a beam optimization model constructed based on a greedy algorithm and a genetic algorithm. This application combines the advantages of the greedy algorithm (efficiency and ease of implementation) with the advantages of the genetic algorithm (adaptive and global optimization) to obtain the optimal sub-beam transmission order scheme under the optimal beam weights, effectively reducing beam conflict across the entire network and thus improving SSB-SINR. Furthermore, this application only requires obtaining the evaluation data after configuring candidate beam weights and the MR data after configuring the optimal beam weights, without needing to associate the beam optimization method with PCI, thus improving the flexibility of the beam optimization method.

[0263] Optionally, the acquisition unit 710 is configured to determine the optimal beam weights among the candidate beam weights based on the evaluation data, including:

[0264] The acquisition unit 710 is used to determine the evaluation information corresponding to each candidate beam weight based on the evaluation data;

[0265] The acquisition unit 710 is used to determine the optimal beam weight among the candidate beam weights based on the evaluation information.

[0266] Optionally, the evaluation information includes any one or a combination of the following:

[0267] Coverage performance;

[0268] Sub-beam isolation within the community;

[0269] Key performance indicators (KPIs);

[0270] Split ratio.

[0271] Optionally, the beam conflict information between the base stations includes the overall network beam conflict level.

[0272] Optionally, the acquisition unit 710 is further configured to acquire the beam collision level of the entire network;

[0273] The overall network beam collision level is obtained through the following steps:

[0274] The acquisition unit 710 is used to weight the initial quantity of each sampling point to obtain the weighted quantity of each sampling point, wherein the initial quantity is 1;

[0275] The acquisition unit 710 is used to determine the beam conflict level of the entire network based on the beam conflict situation of each sampling point and the weighted number of each sampling point.

[0276] Optionally, the acquisition unit 710 is configured to weight the initial quantity of each sampling point to obtain a weighted quantity for each sampling point, including:

[0277] The acquisition unit 710 is used to substitute the difference between the second reference signal received power RSRP and the first RSRP into a preset first weighted regression fitting equation to obtain the first weighted weight.

[0278] The acquisition unit 710 is used to substitute the second RSRP into a preset second weighted regression fitting equation to obtain the second weighted weight;

[0279] The acquisition unit 710 is used to multiply the first weighted value, the second weighted value, and the initial quantity to obtain the weighted quantity of sampling points;

[0280] Wherein, the first RSRP corresponds to the serving cell to which the sampling point belongs, and the second RSRP corresponds to the neighboring cell of the serving cell, wherein the neighboring cell and the serving cell belong to different base stations.

[0281] Optionally, the processing unit 720 is configured to input the optimal beam weights and the beam conflict information into the beam optimization model to obtain the sub-beam transmission order of each base station output by the beam optimization model, including:

[0282] The processing unit 720 is used to solve the sub-beam transmission order of each base station one by one based on a greedy algorithm, with the goal of minimizing the beam collision level of the entire network, to obtain the initial sub-beam transmission order of each base station.

[0283] The processing unit 720 is used to obtain an initial population of a genetic algorithm based on the initial sub-beam transmission order and the default sub-beam transmission order, with the optimization objective of minimizing the overall network beam conflict level, and to obtain the sub-beam transmission order of each base station through the genetic algorithm.

[0284] Optionally, the beam conflict information between base stations may further include: the comprehensive weighted number of beam conflict sampling points corresponding to each base station;

[0285] The processing unit 720 is used to solve the sub-beam transmission order of the base station one by one, including:

[0286] The processing unit 720 is used to sort the base stations in descending order based on the comprehensive weighted number of beam collision sampling points corresponding to each base station, and solve the sub-beam transmission order of each base station one by one according to the sorting order of the base stations.

[0287] The comprehensive weighted number is obtained based on the weighted number of beam conflict sampling points obtained when the cell is a serving cell and the weighted number of beam conflict sampling points obtained when the cell is a neighboring cell.

[0288] Optionally, the processing unit 720 is configured to obtain an initial population for the genetic algorithm based on the initial sub-beam transmission order and the default sub-beam transmission order, including:

[0289] The processing unit 720 is configured to randomly generate a first number of initial samples based on the initial sub-beam transmission sequence and a preset first step length; and

[0290] The processing unit 720 is used to randomly generate a second number of initial samples based on the default sub-beam transmission order and the preset second step size;

[0291] The processing unit 720 is used to use the first number of initial samples and the second number of initial samples as the initial population of the genetic algorithm.

[0292] Optionally, the acquisition unit 710 is further configured to acquire optimized beam conflict sampling points after configuring the sub-beam transmission order for each of the base stations.

[0293] The processing unit 720 is also used to reacquire beam conflict information and the sub-beam transmission order of each base station when the optimized beam conflict sampling points do not meet the preset requirements.

[0294] The preset requirements include:

[0295] The weighted number of optimized beam collision sampling points meets the preset requirement; and / or

[0296] The rate of change of beam collision sampling points meets the preset rate of change requirements.

[0297] Optionally, the device further includes a storage unit and an update unit:

[0298] The storage unit is used to store the optimal beam weights and the sub-beam transmission order of each base station;

[0299] The update unit is used to iteratively update the optimal beam weights and the sub-beam transmission order of each base station based on changes in the network service model.

[0300] The methods and apparatus provided in the various embodiments of this application are based on the same concept. Since the beam optimization method and beam optimization apparatus have similar principles for solving problems and can achieve the same technical effect, the implementation of the apparatus and method can refer to each other, and repeated parts will not be described again.

[0301] 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.

[0302] 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.

[0303] Figure 8 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application, such as... Figure 8 As shown, the electronic device includes a memory 820, a transceiver 800, and a processor 810, wherein:

[0304] The memory 820 is used to store computer programs; the transceiver 800 is used to send and receive data under the control of the processor 810; the processor 810 is used to read the computer program in the memory 820 and perform the following operations:

[0305] Obtain the evaluation data corresponding to each candidate beam weight, and determine the optimal beam weight among the candidate beam weights based on the evaluation data;

[0306] After configuring the optimal beam weights for multiple base stations, beam conflict information between base stations is obtained;

[0307] The optimal beam weights and beam conflict information are input into the beam optimization model to obtain the sub-beam transmission order of each base station output by the beam optimization model.

[0308] The beam optimization model is constructed based on a greedy algorithm and a genetic algorithm.

[0309] Optionally, determining the optimal beam weights from the candidate beam weights based on the evaluation data includes:

[0310] Based on the evaluation data, determine the evaluation information corresponding to the weight of each candidate beam;

[0311] Based on the evaluation information, the optimal beam weights are determined from the candidate beam weights.

[0312] Optionally, the evaluation information includes any one or a combination of the following:

[0313] Coverage performance;

[0314] Sub-beam isolation within the community;

[0315] Key performance indicators (KPIs);

[0316] Split ratio.

[0317] Optionally, the beam conflict information between the base stations includes the overall network beam conflict level.

[0318] Optionally, the overall beam collision level is obtained through the following steps:

[0319] The initial quantity of each sampling point is weighted to obtain the weighted quantity of each sampling point, where the initial quantity is 1;

[0320] The beam conflict level of the entire network is determined based on the beam conflict situation of each sampling point and the weighted number of each sampling point.

[0321] Optionally, the step of weighting the initial number of each sampling point to obtain the weighted number of each sampling point includes:

[0322] The difference between the second reference signal received power RSRP and the first RSRP is substituted into the preset first weighted regression fitting equation to obtain the first weighted weight.

[0323] Substitute the second RSRP into the preset second weighted regression fitting equation to obtain the second weighted weight;

[0324] Multiply the first weighted value, the second weighted value, and the initial quantity to obtain the weighted number of sampling points;

[0325] Wherein, the first RSRP corresponds to the serving cell to which the sampling point belongs, and the second RSRP corresponds to the neighboring cell of the serving cell, wherein the neighboring cell and the serving cell belong to different base stations.

[0326] Optionally, the step of inputting the optimal beam weights and the beam conflict information into the beam optimization model to obtain the sub-beam transmission order of each base station output by the beam optimization model includes:

[0327] Based on a greedy algorithm, with the goal of minimizing the overall network beam conflict level, the sub-beam transmission order of each base station is solved one by one to obtain the initial sub-beam transmission order of each base station.

[0328] With the goal of minimizing the overall network beam conflict level, an initial population for the genetic algorithm is obtained based on the initial sub-beam transmission order and the default sub-beam transmission order. The sub-beam transmission order of each base station is then obtained through the genetic algorithm.

[0329] Optionally, the beam conflict information between base stations may further include: the comprehensive weighted number of beam conflict sampling points corresponding to each base station;

[0330] The step of solving for the sub-beam transmission order of the base station one by one includes:

[0331] Based on the comprehensive weighted number of beam collision sampling points corresponding to each base station, the base stations are arranged in descending order, and the sub-beam transmission order of each base station is solved one by one according to the arrangement order of the base stations;

[0332] The comprehensive weighted number is obtained based on the weighted number of beam conflict sampling points obtained when the cell is a serving cell and the weighted number of beam conflict sampling points obtained when the cell is a neighboring cell.

[0333] Optionally, obtaining the initial population for the genetic algorithm based on the initial sub-beam transmission order and the default sub-beam transmission order includes:

[0334] Based on the initial sub-beam transmission sequence and the preset first step length, a first number of initial samples are randomly generated; and

[0335] Based on the default sub-beam transmission order and the preset second step size, a second number of initial samples are randomly generated;

[0336] The first number of initial samples and the second number of initial samples are used as the initial population of the genetic algorithm.

[0337] Optionally, the operation further includes:

[0338] After configuring the sub-beam transmission order for each base station, the optimized beam collision sampling points are obtained;

[0339] If the optimized beam collision sampling points do not meet the preset requirements, the beam collision information and the sub-beam transmission order of each base station are reacquired.

[0340] The preset requirements include:

[0341] The weighted number of optimized beam collision sampling points meets the preset requirement; and / or

[0342] The rate of change of beam collision sampling points meets the preset rate of change requirements.

[0343] Optionally, the operation further includes:

[0344] Save the optimal beam weights and the sub-beam transmission order of each base station;

[0345] Based on changes in the network service model, the optimal beam weights and the sub-beam transmission order of each base station are iteratively updated.

[0346] Specifically, transceiver 800 is used to receive and send data under the control of processor 810.

[0347] Among them, Figure 8 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 810) and memory (memory 820). 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. Bus interface 830 provides an interface. Transceiver 800 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. Processor 810 is responsible for managing the bus architecture and general processing, and memory 820 can store data used by processor 810 during operation.

[0348] The processor 810 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.

[0349] It should be noted that the electronic device provided in this application embodiment can implement all the method steps implemented in the above beam optimization method embodiment and can achieve the same technical effect. Here, the parts that are the same as those in the method embodiment and the beneficial effects will not be described in detail.

[0350] On the other hand, embodiments of this application also provide a processor-readable storage medium storing a computer program for causing the processor to execute the methods provided in the above embodiments, including:

[0351] Obtain the evaluation data corresponding to each candidate beam weight, and determine the optimal beam weight among the candidate beam weights based on the evaluation data;

[0352] After configuring the optimal beam weights for multiple base stations, beam conflict information between base stations is obtained;

[0353] The optimal beam weights and beam conflict information are input into the beam optimization model to obtain the sub-beam transmission order of each base station output by the beam optimization model.

[0354] The beam optimization model is constructed based on a greedy algorithm and a genetic algorithm.

[0355] The processor-readable storage medium can be any available medium or data storage device that the processor can access, including but not limited to magnetic memory (e.g., floppy disk, hard disk, magnetic tape, magneto-optical disk (MO)), optical memory (e.g., CD, DVD, BD, HVD), and semiconductor memory (e.g., ROM, EPROM, EEPROM, non-volatile memory (NAND FLASH), solid-state drive (SSD)).

[0356] 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.

[0357] 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.

[0358] 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.

[0359] 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.

[0360] 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 optimization method, characterized in that, include: Obtain the evaluation data corresponding to each candidate beam weight, and determine the optimal beam weight among the candidate beam weights based on the evaluation data; After configuring the optimal beam weights for multiple base stations, beam conflict information between base stations is obtained; The optimal beam weights and beam conflict information are input into the beam optimization model to obtain the sub-beam transmission order of each base station output by the beam optimization model. The beam optimization model is constructed based on a greedy algorithm and a genetic algorithm. The beam conflict information between base stations includes: the comprehensive weighted number of beam conflict sampling points corresponding to each base station; wherein, the comprehensive weighted number is obtained based on the weighted number of beam conflict sampling points obtained when the cell is the serving cell and the weighted number of beam conflict sampling points obtained when the cell is a neighboring cell; The initial quantity of each sampling point is weighted to obtain the weighted quantity of each sampling point, where the initial quantity is 1; The step of weighting the initial number of each sampling point to obtain the weighted number of each sampling point includes: The difference between the second reference signal received power RSRP and the first RSRP is substituted into the preset first weighted regression fitting equation to obtain the first weighted weight. Substitute the second RSRP into the preset second weighted regression fitting equation to obtain the second weighted weight; Multiply the first weighted value, the second weighted value, and the initial quantity to obtain the weighted number of sampling points; Wherein, the first RSRP corresponds to the serving cell to which the sampling point belongs, and the second RSRP corresponds to the neighboring cell of the serving cell, wherein the neighboring cell and the serving cell belong to different base stations; The step of inputting the optimal beam weights and the beam conflict information into the beam optimization model to obtain the sub-beam transmission order of each base station output by the beam optimization model includes: Based on a greedy algorithm, with the goal of minimizing the overall network beam collision level, the sub-beam transmission order of each base station is solved one by one to obtain the initial sub-beam transmission order of each base station. With the goal of minimizing the overall network beam conflict level, an initial population for the genetic algorithm is obtained based on the initial sub-beam transmission order and the default sub-beam transmission order. The sub-beam transmission order of each base station is then obtained through the genetic algorithm. The step of solving for the sub-beam transmission order of the base station one by one includes: Based on the comprehensive weighted number of beam collision sampling points corresponding to each base station, the base stations are arranged in descending order, and the sub-beam transmission order of each base station is solved one by one according to the arrangement order of the base stations; The process of obtaining the initial population for the genetic algorithm based on the initial sub-beam transmission order and the default sub-beam transmission order includes: Based on the initial sub-beam transmission sequence and the preset first step length, a first number of initial samples are randomly generated; and Based on the default sub-beam transmission order and the preset second step size, a second number of initial samples are randomly generated; The first number of initial samples and the second number of initial samples are used as the initial population of the genetic algorithm.

2. The beam optimization method according to claim 1, characterized in that, The step of determining the optimal beam weights from the candidate beam weights based on the evaluation data includes: Based on the evaluation data, determine the evaluation information corresponding to the weight of each candidate beam; Based on the evaluation information, the optimal beam weights are determined from the candidate beam weights.

3. The beam optimization method according to claim 2, characterized in that, The evaluation information includes any one or a combination of the following: Coverage performance; Sub-beam isolation within the community; Key performance indicators (KPIs); Split ratio.

4. The beam optimization method according to claim 1, characterized in that, The beam conflict information between base stations includes the overall network beam conflict level.

5. The beam optimization method according to claim 4, characterized in that, The overall network beam collision level is obtained through the following steps: The initial quantity of each sampling point is weighted to obtain the weighted quantity of each sampling point, where the initial quantity is 1; The beam conflict level of the entire network is determined based on the beam conflict situation of each sampling point and the weighted number of each sampling point.

6. The beam optimization method according to any one of claims 1-5, characterized in that, The method further includes: After configuring the sub-beam transmission order for each base station, the optimized beam collision sampling points are obtained; If the optimized beam collision sampling points do not meet the preset requirements, the beam collision information and the sub-beam transmission order of each base station are reacquired. The preset requirements include: The weighted number of optimized beam collision sampling points meets the preset requirement; and / or The rate of change of beam collision sampling points meets the preset rate of change requirements.

7. The beam optimization method according to any one of claims 1-5, characterized in that, The method further includes: Save the optimal beam weights and the sub-beam transmission order of each base station; Based on changes in the network service model, the optimal beam weights and the sub-beam transmission order of each base station are iteratively updated.

8. An electronic device, characterized in that, Includes memory, transceiver, and processor: The memory is used to store computer programs; the transceiver is used to send and receive data under the control of the processor. Processor, configured to read the computer program in the memory and perform the following operations: Obtain the evaluation data corresponding to each candidate beam weight, and determine the optimal beam weight among the candidate beam weights based on the evaluation data; After configuring the optimal beam weights for multiple base stations, beam conflict information between base stations is obtained; The optimal beam weights and beam conflict information are input into the beam optimization model to obtain the sub-beam transmission order of each base station output by the beam optimization model. The beam optimization model is constructed based on a greedy algorithm and a genetic algorithm. The beam conflict information between base stations includes: the comprehensive weighted number of beam conflict sampling points corresponding to each base station; wherein, the comprehensive weighted number is obtained based on the weighted number of beam conflict sampling points obtained when the cell is the serving cell and the weighted number of beam conflict sampling points obtained when the cell is a neighboring cell; The initial quantity of each sampling point is weighted to obtain the weighted quantity of each sampling point, where the initial quantity is 1; The step of weighting the initial number of each sampling point to obtain the weighted number of each sampling point includes: The difference between the second reference signal received power RSRP and the first RSRP is substituted into the preset first weighted regression fitting equation to obtain the first weighted weight. Substitute the second RSRP into the preset second weighted regression fitting equation to obtain the second weighted weight; Multiply the first weighted value, the second weighted value, and the initial quantity to obtain the weighted number of sampling points; Wherein, the first RSRP corresponds to the serving cell to which the sampling point belongs, and the second RSRP corresponds to the neighboring cell of the serving cell, wherein the neighboring cell and the serving cell belong to different base stations; The step of inputting the optimal beam weights and the beam conflict information into the beam optimization model to obtain the sub-beam transmission order of each base station output by the beam optimization model includes: Based on a greedy algorithm, with the goal of minimizing the overall network beam collision level, the sub-beam transmission order of each base station is solved one by one to obtain the initial sub-beam transmission order of each base station. With the goal of minimizing the overall network beam conflict level, an initial population for the genetic algorithm is obtained based on the initial sub-beam transmission order and the default sub-beam transmission order. The sub-beam transmission order of each base station is then obtained through the genetic algorithm. The step of solving for the sub-beam transmission order of the base station one by one includes: Based on the comprehensive weighted number of beam collision sampling points corresponding to each base station, the base stations are arranged in descending order, and the sub-beam transmission order of each base station is solved one by one according to the arrangement order of the base stations; The process of obtaining the initial population for the genetic algorithm based on the initial sub-beam transmission order and the default sub-beam transmission order includes: Based on the initial sub-beam transmission sequence and the preset first step length, a first number of initial samples are randomly generated; and Based on the default sub-beam transmission order and the preset second step size, a second number of initial samples are randomly generated; The first number of initial samples and the second number of initial samples are used as the initial population of the genetic algorithm.

9. The electronic device according to claim 8, characterized in that, The step of determining the optimal beam weights from the candidate beam weights based on the evaluation data includes: Based on the evaluation data, determine the evaluation information corresponding to the weight of each candidate beam; Based on the evaluation information, the optimal beam weights are determined from the candidate beam weights.

10. The electronic device according to claim 9, characterized in that, The evaluation information includes any one or a combination of the following: Coverage performance; Sub-beam isolation within the community; Key performance indicators (KPIs); Split ratio.

11. The electronic device according to claim 8, characterized in that, The beam conflict information between base stations includes the overall network beam conflict level.

12. The electronic device according to claim 11, characterized in that, The overall network beam collision level is obtained through the following steps: The initial quantity of each sampling point is weighted to obtain the weighted quantity of each sampling point, where the initial quantity is 1; The beam conflict level of the entire network is determined based on the beam conflict situation of each sampling point and the weighted number of each sampling point.

13. The electronic device according to any one of claims 8-12, characterized in that, The operation also includes: After configuring the sub-beam transmission order for each base station, the optimized beam collision sampling points are obtained; If the optimized beam collision sampling points do not meet the preset requirements, the beam collision information and the sub-beam transmission order of each base station are reacquired. The preset requirements include: The weighted number of optimized beam collision sampling points meets the preset requirement; and / or The rate of change of beam collision sampling points meets the preset rate of change requirements.

14. The electronic device according to any one of claims 8-12, characterized in that, The operation also includes: Save the optimal beam weights and the sub-beam transmission order of each base station; Based on changes in the network service model, the optimal beam weights and the sub-beam transmission order of each base station are iteratively updated.

15. A beam optimization device, characterized in that, include: The acquisition unit is used to acquire the evaluation data corresponding to each candidate beam weight, and determine the optimal beam weight among the candidate beam weights based on the evaluation data. The acquisition unit is also used to acquire beam conflict information between base stations after configuring the optimal beam weights for multiple base stations; The processing unit is used to input the optimal beam weights and the beam conflict information into the beam optimization model to obtain the sub-beam transmission order of each base station output by the beam optimization model; The beam optimization model is constructed based on a greedy algorithm and a genetic algorithm. The beam conflict information between base stations includes: the comprehensive weighted number of beam conflict sampling points corresponding to each base station; wherein, the comprehensive weighted number is obtained based on the weighted number of beam conflict sampling points obtained when the cell is the serving cell and the weighted number of beam conflict sampling points obtained when the cell is a neighboring cell; The initial quantity of each sampling point is weighted to obtain the weighted quantity of each sampling point, where the initial quantity is 1; The step of weighting the initial number of each sampling point to obtain the weighted number of each sampling point includes: The difference between the second reference signal received power RSRP and the first RSRP is substituted into the preset first weighted regression fitting equation to obtain the first weighted weight. Substitute the second RSRP into the preset second weighted regression fitting equation to obtain the second weighted weight; Multiply the first weighted value, the second weighted value, and the initial quantity to obtain the weighted number of sampling points; Wherein, the first RSRP corresponds to the serving cell to which the sampling point belongs, and the second RSRP corresponds to the neighboring cell of the serving cell, wherein the neighboring cell and the serving cell belong to different base stations; The processing unit is specifically used for: Based on a greedy algorithm, with the goal of minimizing the overall network beam collision level, the sub-beam transmission order of each base station is solved one by one to obtain the initial sub-beam transmission order of each base station. With the goal of minimizing the overall network beam conflict level, an initial population for the genetic algorithm is obtained based on the initial sub-beam transmission order and the default sub-beam transmission order. The sub-beam transmission order of each base station is then obtained through the genetic algorithm. Based on the comprehensive weighted number of beam collision sampling points corresponding to each base station, the base stations are arranged in descending order, and the sub-beam transmission order of each base station is solved one by one according to the arrangement order of the base stations; Based on the initial sub-beam transmission sequence and the preset first step length, a first number of initial samples are randomly generated; and Based on the default sub-beam transmission order and the preset second step size, a second number of initial samples are randomly generated; The first number of initial samples and the second number of initial samples are used as the initial population of the genetic algorithm.

16. A processor-readable storage medium, characterized in that, The processor-readable storage medium stores a computer program for causing the processor to execute the beam optimization method according to any one of claims 1 to 7.

Images