Network optimization method, device, storage medium, and program product

Abstract

A network optimization method, a device, a storage medium, and a program product, related to the technical field of communications. The method comprises: acquiring a digital twin model of a target network device (S100); acquiring terminal data reported by a user terminal located within a range of a signal to be optimized of the target network device (S200); on the basis of the terminal data, performing beam prediction on the target network device by means of the digital twin model, to obtain target beam prediction data (S300); and on the basis of the target beam prediction data, performing optimization processing on a beam of the target network device (S400).

Description

Method, device, storage medium and program product for network optimization

[0001] Cross-reference to related applications

[0002] The present application is based on the Chinese patent application No. 202410907695.5, filed on July 5, 2024, and claims priority to the Chinese patent application No. 202410907695.5, the entire contents of which are incorporated herein by reference. TECHNICAL FIELD

[0003] Embodiments of the present application relate to, but are not limited to, the field of communication technology, and in particular to a network optimization method, device, storage medium and program product. BACKGROUND

[0004] In the field of communication technology, network devices provide more stable and high-quality communication services for user terminals by improving their network quality (such as capacity and coverage). Network quality is often related to the beams of network devices, but in actual applications, network quality is often determined based on beam compliance and management, but beam shaping and management often rely on a large amount of measurement information. In scenarios with a large number of user terminals or user terminal movement, more frequent measurement of beam information is required, which can lead to low utilization of measurement resources and large measurement information, resulting in low optimization efficiency. Therefore, in related technologies, how to balance the utilization of measurement resources and optimization efficiency to optimize the network of network devices is a technical problem to be solved. SUMMARY

[0005] The following is a summary of the subject matter described in detail herein. This summary is not intended to limit the scope of the claims.

[0006] Embodiments of the present application provide a network optimization method, device, storage medium and program product.

[0007] In a first aspect, a network optimization method according to embodiments of the present application includes: obtaining a digital twin model of a target network device; obtaining terminal data reported by a user terminal located within a to-be-optimized signal range of the target network device; performing beam prediction on the target network device through the digital twin model according to the terminal data to obtain target beam prediction data; and performing optimization processing on the beams of the target network device according to the target beam prediction data.

[0008] In a second aspect, a network device according to embodiments of the present application includes at least one processor and at least one memory for storing at least one program; when the at least one program is executed by the at least one processor, the network optimization method of any one of the first aspect is implemented.

[0009] In a third aspect, a computer-readable storage medium storing computer-executable instructions for causing a network device to perform the method of network optimization of any of the first aspect is provided.

[0010] In a fourth aspect, a computer program product is provided, which includes a computer program or computer instructions stored in a computer-readable storage medium, and a processor of a network device reads the computer program or the computer instructions from the computer-readable storage medium, and the processor executes the computer program or the computer instructions, so that the network device performs the method of network optimization of any of the first aspect. BRIEF DESCRIPTION OF DRAWINGS

[0011] FIG. 1 is a schematic diagram of a system framework of an embodiment of the network optimization system provided by the present application;

[0012] FIG. 2 is a schematic diagram of a system framework of another embodiment of the network optimization system provided by the present application;

[0013] FIG. 3 is a schematic diagram of a flow of an embodiment of the method of network optimization provided by the present application;

[0014] FIG. 4 is a schematic diagram of a scenario of application of the method of network optimization provided by the present application;

[0015] FIG. 5 is a schematic diagram of another scenario of application of the method of network optimization provided by the present application;

[0016] FIG. 6 is a schematic diagram of another scenario of application of the method of network optimization provided by the present application;

[0017] FIG. 7 is a schematic diagram of a hardware structure of a device corresponding to the method of network optimization provided by the present application. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical scheme and advantages of the present application clearer, the present application is further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

[0019] It should be noted that although the functional modules are divided in the device schematic diagram, and the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a manner different from the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification and claims and the above drawings are used to distinguish similar objects, and do not necessarily describe a specific order or sequence.

[0020] The flowchart shown in the drawing is only an exemplary illustration, and does not necessarily include all contents and operations / steps, nor does it necessarily have to be executed in the order described. For example, some operations / steps can be further decomposed, and some operations / steps can be combined or partially combined, so the actual execution order can be changed according to actual conditions.

[0021] In the field of communication technology, beam management is a key technology in 5G NR (New Radio) network, which mainly dynamically selects the direction of the beam between each user equipment and network equipment for communication according to the channel measurement result. In practical application, the network equipment improves its network quality (such as capacity and coverage) to provide more stable and high-quality communication services for user terminals. The network quality is often related to the beam of the network equipment, especially for millimeter wave systems, because of the large propagation loss and attenuation, a large-scale antenna array is generally installed at the receiving / transmitting end to offset the path loss, that is, multi-input-multi-output (MIMO) is introduced to improve the gain of the signal, and beamforming technology is used to make the beam more accurate. Beam management and beamforming both need to rely on a large amount of measurement information, when there are many users or in a mobile scenario, more frequent measurement of beam information is needed, which will cause a large overhead and delay. Therefore, in the related technology, how to consider the measurement resource utilization rate and optimization efficiency to optimize the network of the network equipment is a technical problem to be solved. Based on this, the embodiments of the present application provide a network optimization method, device, storage medium and program product, which can optimize the network of the network equipment while considering the measurement resource utilization rate and optimization efficiency.

[0022] Referring to FIG. 1, according to a network optimization system according to an embodiment of the present application, the network optimization system comprises a target network equipment and a user terminal, the target network equipment and the user terminal are in communication connection, and the target network equipment performs the following steps: obtaining a digital twin model of the target network equipment; obtaining terminal data reported by the user terminal located in the to-be-optimized signal range of the target network equipment; performing beam prediction on the target network equipment through the digital twin model according to the terminal data to obtain target beam prediction data; and performing optimization processing on the beam of the target network equipment according to the target beam prediction data.

[0023] Referring to FIG. 2, according to an embodiment of the present application, a network optimization system includes a third-party device, a target network device, and a user terminal. The target network device is in communication connection with the user terminal and the third-party device. The third-party device obtains a digital twin model of the target network device. The third-party device obtains terminal data reported by the user terminal located within a to-be-optimized signal range of the target network device. The third-party device performs beam prediction on the target network device through the digital twin model based on the terminal data to obtain target beam prediction data. The third-party device performs optimization processing on the beam of the target network device based on the target beam prediction data.

[0024] The target network device can be an access network device or a core network device of NR, LTE, etc., or a network device of other vehicle networking, satellite communication, etc. The user terminal can be a mobile phone, a computer, a tablet, etc. The third-party device is relative to the target network device. One third-party device can correspond to multiple target network devices, i.e., multiple digital twin models of the target network devices can be deployed on one third-party device. The third-party device can be a general server, a cloud server, or a network device other than the target network device.

[0025] It should be noted that for FIG. 1, the digital twin model is deployed in the target network device. The target network device calls the deployed digital twin model and performs beam prediction based on the terminal data reported by the user terminal within the to-be-optimized signal range to obtain target beam prediction data. For FIG. 2, the digital model is deployed in the third-party device. The third-party device calls the digital twin model of the target network device and performs beam prediction based on the terminal data reported by the user terminal within the to-be-optimized signal range to obtain target beam prediction data.

[0026] It should be noted that the digital twin model is obtained by training a digital model based on a digital twin physical model constructed based on the digital twin technology of the target network device. Therefore, due to the difference in configuration and physical environment of each target network device, the digital twin model is set in one-to-one correspondence with the target network device.

[0027] It should be noted that the coverage range of the target network device is also clear after the antenna deployment of the target network device is completed, and the present application is based on the optimization of the beams of the target device within the coverage range. The to-be-optimized signal range can represent the entire signal coverage range of the network device, or a specific area within the entire signal coverage range of the network device, and the embodiments of the present application do not make specific limitations on the to-be-optimized signal range. It should be noted that the target beam prediction data is used to record the beam performance of the target network device, such as the direction of each beam within the coverage range of the target device, the signal strength and quality of the beam, and the corresponding configuration parameters in some embodiments; in other embodiments, the target beam prediction data includes the configuration parameters of the beam with the optimal performance within the coverage range. The configuration parameters are, for example, the array amplitude and phase of the antenna; the target beam prediction data includes multiple groups of beamforming data (such as the direction of the beam, the signal strength and quality of the beam, etc.) distributed by time within a prediction time period.

[0028] The embodiments of the present application are applicable to a beam-based communication system, such as an NR base station, a satellite communication system, a vehicle-to-everything (V2X) system, etc., and can effectively improve the resource utilization and reduce the communication delay.

[0029] Referring to FIG. 3, according to a network optimization method according to an embodiment of the present application, the method includes steps S100 to S400.

[0030] Step S100: Obtain a digital twin model of a target network device.

[0031] Step S200: Obtain terminal data reported by a user terminal located within a to-be-optimized signal range of the target network device.

[0032] Step S300: Perform beam prediction on the target network device through the digital twin model according to the terminal data, to obtain target beam prediction data.

[0033] Step S400: Perform optimization processing on the beams of the target network device according to the target beam prediction data.

[0034] Therefore, the terminal data reported by the user terminal within the to-be-optimized signal range is subjected to beam prediction through the digital twin model corresponding to the target network device, to obtain target beam prediction data, and the beams of the target network device are subjected to optimization processing according to the target beam prediction data. At this time, only a small amount of terminal data reported by the user terminal is required to obtain the target beam prediction data within the to-be-optimized signal range, thereby shortening the measurement data amount of the terminal data and improving the measurement resource utilization. Therefore, the embodiments of the present application can perform network optimization on the network device while taking into account the beam utilization and optimization efficiency.

[0035] It should be noted that the target network device is a network device that uses a digital twin model for network optimization. When the digital twin model is deployed based on the system shown in FIG. 1, step S100 represents that the target network device loads the digital twin model deployed by itself. When the digital twin model is deployed based on the system shown in FIG. 2, step S100 represents that the third-party device runs the digital twin model corresponding to the target network device.

[0036] It should be noted that the digital twin model of step S100 is a trained digital model, which is constructed based on digital twin technology, and then trained according to the current configuration data and measurement data of the network device. The digital twin model can be trained online or offline. It should be noted that the digital twin model is obtained based on a ray tracing propagation model to obtain a wireless signal propagation path and attenuation parameters, and is trained based on the measurement data. Therefore, a small amount of measurement data can also complete the training of the digital twin model.

[0037] It should be noted that the signal range to be optimized is the area in the coverage range of the target network device that needs to be optimized.

[0038] It should be noted that the terminal data is a performance indicator of the user terminal. The number of user terminals and the reporting time of the terminal data are not limited in the embodiments of the present application.

[0039] It should be noted that the target beam prediction data is a performance indicator of each beam of the target network device in its signal coverage range. The beam performance can be the performance within a prediction time, or the performance at the current time. For example, in some embodiments, the terminal data is obtained at time t, and the target beam prediction data output at time t includes the direction of each beam, the corresponding signal strength, and the user terminal signal quality indicator, etc. In other embodiments, the target beam prediction data output can also include multiple sets of beamforming data (such as beam direction, signal strength, etc.) that change with time within a time period T.

[0040] It should be noted that, with reference to FIG. 1, when the digital twin model is deployed in the target network terminal, the target network device directly configures the relevant antenna parameters based on the target beam prediction data to process the direction and number of beams, etc. The antenna parameters include array amplitude and phase, etc. With reference to FIG. 2, when the digital twin model is deployed in the third-party device, the target network device antenna parameters are determined based on the target beam prediction data output by the third-party device, and the target network device configures the antenna parameters to achieve optimization.

[0041] It should be noted that, by using a small amount of terminal data as measurement data to replace the original beam measurement (such as beam measurement information used for space division decision) to perform beam management and beamforming, the application embodiment can reduce the test resource overhead of the actual running of the target network device, and effectively improve the resource utilization, wherein the small amount of terminal data can also be realized by prolonging the measurement period or reducing the measurement times, so as to reduce the measurement resource overhead.

[0042] The network optimization method of the application embodiment can be used in the scene of dynamically selecting the beam most pointing to the user terminal from the configured preset beam, realizing dynamic beamforming, such as outputting the position information changing over time (which can indicate the position where the user terminal is located) within the prediction duration based on the digital twin model, combining the output beam information (such as beam signal strength, signal quality), dynamically adjusting the amplitude and phase of the antenna array, and generating the beam in real time, so that the generated beam accurately points to the user terminal. At this time, for the target network device, steps S200-S400 can be periodically repeated to realize dynamic beamforming for the user terminal.

[0043] The network optimization method of the application embodiment can also be used for beam optimization in the space division multiplexing scene, such as judging whether different user terminals have space division multiplexing conditions based on the beam information output by the digital twin model and the interference of related beams, and performing space division multiplexing under the condition of having space division multiplexing conditions, thereby improving the resource utilization.

[0044] The network optimization method of the application embodiment can also be used for beam optimization in the scene of a large number of user devices, such as selecting the optimal beam combination covering the user terminal based on the position information (such as the position of the terminal under each beam coverage range or beam direction) output by the digital twin model.

[0045] For this, the application embodiment does not limit the specific application scene, and the person skilled in the art can select the digital twin model for training according to the actual needs, so that the target beam prediction data contains the data required for optimization processing.

[0046] It can be understood that the terminal data reported by the user terminal located in the target network device within the range of the signal to be optimized is obtained, including at least one of the following:

[0047] The terminal data reported by the user terminal is obtained from the predetermined position within the range of the signal to be optimized of the target network device multiple times within a preset time duration;

[0048] The terminal data reported by the user terminal is obtained from multiple different predetermined positions within the range of the signal to be optimized of the target network device.

[0049] It should be noted that the terminal data can be acquired multiple times from the same predetermined position and the terminal data can be acquired from multiple different predetermined positions, which can enrich the input data of the digital twin model and further ensure the accuracy of the target beam prediction data.

[0050] It should be noted that in some embodiments, the terminal data can be acquired multiple times within a preset time period for multiple different predetermined positions, and in other embodiments, the terminal data can be acquired multiple times for the same predetermined position within a preset time period. In other embodiments, the terminal data can be acquired only once for multiple different predetermined positions. Those skilled in the art can selectively set according to actual needs.

[0051] It should be noted that in actual applications, when the terminal data of the same predetermined position is acquired multiple times, beam prediction can be performed on each acquired terminal data, so that multiple target beam prediction data can be obtained. Alternatively, beam prediction can be performed on the terminal data of the same predetermined position acquired multiple times at the same time, so that one target beam prediction data can be obtained. In actual applications, when the terminal data is acquired from different predetermined positions, the terminal data acquired from each predetermined position can be predicted or the terminal data acquired from different predetermined positions can be predicted at the same time. Those skilled in the art can selectively set according to actual needs.

[0052] It can be understood that in some embodiments, the target beam prediction data is a set of beamforming data corresponding to user terminals at multiple different positions varying with time within a prediction time period. Taking dynamic beamforming in a mobile scenario as an example, referring to FIG. 4, the beam and beam information within the prediction time period output by the digital twin model can be used to dynamically adjust the amplitude and phase of the array element to generate a precise beam pointing to the user equipment in real time. The beamforming data is used to implement beamforming.

[0053] As shown in FIG. 4, the user terminal is terminal device 1, the terminal data reported by terminal device 1 at the first position under beam 2 is obtained, and the digital twin model outputs target beam prediction data according to the terminal data reported by terminal device 1 at the first position, so as to predict the moving track of terminal device 1 within a prediction time length. The target beam prediction data includes the position information of the beam where terminal device 1 is located at different time points when moving within the prediction time length and the corresponding beamforming data. At this time, the target network device does not need to rely on too much measurement report of the user terminal, and can obtain the target beam prediction data by using a small amount of terminal data. When terminal device 1 moves from the first position to the second position within the prediction time length, the network device finds the beamforming data of the second position in the target beam prediction data generated based on the first position, that is, the beamforming data corresponding to beam 1 in FIG. 4, so as to optimize the network based on the beamforming data of beam 2. Specifically, the amplitude and phase information of the antenna array are dynamically adjusted to accurately point the beam to terminal device 1. By repeating the above steps, the target network device can track terminal device 1 in real time and dynamically adjust the beam of the user terminal.

[0054] It should be noted that the prediction time length can be in units of time slots (slots), subframes, frames, or fixed time periods for outputting beamforming data. For example, the target beam prediction data can be a set of positions of the user terminal and beamforming data in each time slot within the prediction time length, or a set of positions of the user terminal and beamforming data in each subframe or frame within the prediction time length, or a set of positions of the user terminal and beamforming data in each time period within the prediction time length.

[0055] It can be understood that the target beam prediction data includes beamforming data; multiple user terminals in different spatial directions within the signal range to be optimized support spatial division multiplexing. According to the terminal data, the target network device is predicted by the digital twin model to obtain target beam prediction data, including:

[0056] Based on the terminal data of the user terminals in different spatial directions, the beamforming of the target network device is predicted by the digital twin model to obtain the beamforming data of the candidate beams corresponding to each user terminal;

[0057] According to the target beam prediction data, the beam of the target network device is optimized and processed, including:

[0058] According to the beamforming data, the user terminals in the signal range to be optimized of the target network device are determined, which can be configured for spatial division multiplexing;

[0059] According to the beamforming data, the target network device is subjected to beamforming processing.

[0060] It should be noted that the beamforming data is used for beamforming, which contains at least one of the beam direction, signal strength, coverage range. Since each user terminal has performed beam prediction in the coverage range of the target network device, it can be determined whether there is interference between the beams corresponding to the user terminals based on the beamforming data of the two user terminals, such as judging whether there is interference based on the coverage range, beam direction, such as filtering based on the coverage range, beam direction and signal strength to judge whether there is interference.

[0061] In some embodiments, as shown in FIG. 5, in a spatial division multiplexing scenario, terminal device 1 and terminal device 2 are user terminals in different spatial directions, and the beamforming data of terminal device 1 and terminal device 2 output by the digital twin model can be used to determine whether terminal device 1 and terminal device 2 meet the spatial division multiplexing condition, and the user equipment meeting the spatial division multiplexing condition is subjected to spatial division multiplexing. Compared with the related art, the method of determining whether the spatial division multiplexing condition is met needs a large number of measurements. By using the digital twin model, the beamforming data of different beam directions can be continuously output without measurement. As shown in FIG. 5, the mutual interference of the predicted beams 2 and beams 1 used by terminal device 1 and terminal device 2 is relatively low, so terminal device 1 and terminal device 2 can be configured for spatial division multiplexing, thereby improving the resource utilization rate.

[0062] It should be noted that the beamforming prediction of the user terminals in multiple different spatial directions can be continuously performed within a preset time period, and at this time, multiple target beam prediction data within the preset time period can be obtained. It can also be that the target beam data within the prediction time period after the terminal data is reported is predicted according to the terminal data, wherein the preset time period and the prediction time period can be output in units of time slots (slots), subframes or frames, or a fixed time period.

[0063] It can be understood that the target beam prediction data includes interference data; there are multiple user terminals in different spatial directions within the signal range to be optimized, which support spatial division multiplexing, and the target network device is subjected to beam prediction by the digital twin model according to the terminal data to obtain target beam prediction data, including:

[0064] Based on the terminal data of the user terminals in multiple different spatial directions, the digital twin model is used to perform beam interference analysis on the target network device to obtain interference data;

[0065] According to the target beam prediction data, the beam of the target network device is subjected to optimization processing, and the method further includes:

[0066] According to the interference data, the terminal devices in at least two different spatial directions where no interference exists are determined as configurable spatial division multiplexing.

[0067] It should be noted that in some embodiments, the digital twin model can perform prediction on the beam where the user terminal is located, and then perform interference analysis based on the predicted beamforming data to obtain the interference data.

[0068] As shown in FIG. 5, if the digital twin model predicts that the mutual interference of the beams used by terminal device 1 and terminal device 2 is relatively low, the beamforming data of beams 1 and 2 where terminal device 1 and terminal device 2 do not interfere with each other is directly output. At this time, the network device can configure terminal device 1 and terminal device 2 for spatial division multiplexing, thereby improving the utilization rate of resources.

[0069] It should be noted that in some embodiments, the digital twin model can output the beamforming data and interference data of the user terminal in different directions.

[0070] It can be understood that, according to the terminal data, the digital twin model is used to perform beam prediction on the target network device to obtain target beam prediction data, including:

[0071] - determining a first user terminal and a second user terminal according to the terminal data; wherein the user density of the area where the first user terminal and the second user terminal are jointly distributed satisfies a preset density threshold, the signal quality of the first user terminal satisfies a preset quality requirement, and the signal quality of the second user terminal does not satisfy the preset quality requirement;

[0072] - performing beam prediction on the terminal data of the first user terminal and the second user terminal within a preset time period by using the digital twin model to obtain candidate beam prediction data that satisfies the preset quality requirement for both the first user terminal and the second user terminal;

[0073] - combining the candidate beam prediction data obtained within the preset time period to obtain the target beam prediction data.

[0074] It should be noted that the density threshold can be selectively set according to actual needs. The preset quality requirement can be selectively set according to needs.

[0075] It should be noted that in some embodiments, the coverage range of the network device is basically determined after the configuration of the network device is determined, but in actual application, when there are a large number of users in the coverage range, there may still be some areas in the coverage range of the target network device that do not achieve optimal coverage, such as the signal quality of the user terminal at the edge not meeting the preset quality requirement. At this time, based on the terminal data reported by the user terminal, candidate beam prediction data of multiple time units in a preset time period or candidate beam prediction data of multiple time units at the current time are output, wherein the time unit can be one of a time slot, a frame, a subframe, or a fixed time period. At this time, the optimal one is selected from the multiple candidate beam prediction data for network optimization. Each candidate beam prediction data reflects the signal strength of the beam in the different beam directions output in the corresponding unit time and the signal quality of the user terminal.

[0076] In some embodiments, referring to FIG. 6, there are a large number of users in the area covered by the beam 1 of the target network device, and some areas of the beam 1 may not achieve optimal coverage. With the help of the digital twin model, the digital twin model can give the target beam prediction data that meets the signal quality of the first user terminal and the second user terminal. The target beam prediction data includes the antenna parameters of the optimal beam that meets the first user terminal and the second user terminal. At this time, the target network terminal can directly configure based on the antenna parameters to perform beamforming on the beam 1.

[0077] It can be understood that, according to the terminal data, the target network device is subjected to beam prediction by the digital twin model to obtain target beam prediction data, including:

[0078] - determining the first user terminal and the second user terminal according to the terminal data; wherein the user density of the area where the first user terminal and the second user terminal are jointly distributed meets a preset density threshold, the signal quality of the first user terminal meets a preset quality requirement, and the signal quality of the second user terminal does not meet the preset quality requirement;

[0079] - performing beam prediction on the terminal data of the first user terminal and the second user terminal in a preset time period by the digital twin model to obtain first candidate beam prediction data of the first user terminal and second candidate beam prediction data of the second user terminal;

[0080] - obtaining the target beam prediction data according to the first candidate beam prediction data and the second candidate beam prediction data.

[0081] In some embodiments, as shown in FIG. 6, there are a large number of users in the area covered by the network device beam 1, and part of the area of the beam can not achieve optimal coverage. With the help of the digital twin model, the optimal beam conditions of all user terminals under the network device (i.e., the first candidate beam prediction data and the second candidate beam data) are output, including the optimal beam conditions in the subsequent period of time, obtaining the target beam prediction data. According to the output target beam prediction data of the digital twin model, the network device dynamically adjusts the overall coverage of the beam of the network device. At this time, in the case of a large number of terminal devices, the network device dynamically adjusts the optimal beam coverage according to the optimization output of the digital twin model.

[0082] It can be understood that the digital twin model is obtained by the following steps:

[0083] - obtaining configuration data and sample measurement data of the target network device;

[0084] - training the configuration data and the sample measurement data by the digital model determined based on the twin physical model of the target network device, to obtain the trained digital twin model.

[0085] It should be noted that the training of the digital twin model is based on the ray tracing propagation model to obtain the wireless signal propagation path and attenuation parameters, and therefore, after training based on the measurement data, the beam and signal strength, signal quality, and other information at different position points within the overall coverage range of the target network device can be predicted. Thus, after online deployment of the finally trained digital twin model, by inputting current terminal data, such as configuration and a small amount of measurement information of the current user, target beam prediction data composed of terminal position and beam information can be output.

[0086] It should be noted that the training and inference process of the digital model can use artificial intelligence (AI) related technology, which can include but is not limited to deep learning methods such as convolutional neural network (CNN), recurrent neural network (RNN), long short-term memory network (LSTM), and other non-AI methods such as polynomial fitting, Kalman filtering, random forest algorithm, etc.

[0087] It should be noted that the twin physical model is a digital twin scene constructed based on the coverage area of the network device. Taking the network device of the 5G NR (New Radio) system as an example, the digital twin scene can include but is not limited to base station information, antenna information, environmental information, etc. The base station information can include but is not limited to the components of the base station, the location information of the base station, etc.; the antenna information can include but is not limited to the number of antennas, the type of antennas, the antenna gain, etc.; the environmental information can include but is not limited to the buildings, roads, trees, etc. around the base station. The skilled in the art can selectively set according to the actual data.

[0088] It should be noted that the current configuration of the network device used for training can include but is not limited to the beam configuration, the power configuration, the cell configuration, etc. of the current environment.

[0089] It should be noted that the training process of the digital twin model can be in an online manner or an offline manner. The trained digital twin model can be deployed in the network device or the server or other third-party deployable devices. According to the terminal data of the current user terminal (such as including the state and a small amount of related measurement data), the deployed digital twin model can generate beamforming data or position information of the user terminal through online inference, and provide it to the network device. The network device selects the final beam according to the output information of the twin model, and communicates with the user equipment in a beamforming manner. In the spatial division multiplexing scenario, the network device can determine whether to perform spatial division multiplexing based on the output of the twin model. In the large user scenario, the network device can also select the optimal beam combination covering the user equipment based on the output of the twin model.

[0090] It can be understood that the sample measurement data includes terminal sample data, and the terminal sample data includes first sounding reference signal quality index data and channel quality index data.

[0091] It should be noted that the channel quality index data is an index obtained by the user terminal based on channel measurement, which can include the channel quality indication (CQI, Channel Quality Indication) measured by the user equipment, and the first sounding reference signal quality index data is an index obtained by the base station on the user terminal, which can include the precoding matrix indication (PMI, Precoding Matrix Indicator).

[0092] It can be understood that the terminal sample data further includes user position data, downlink performance data, and beam parameters.

[0093] It should be noted that the beam parameter can include RSRP of the serving beam and the surrounding beam; the downlink performance data can include at least one of downlink RSRP, SINR, CQI, etc. It should be noted that the user position data can be longitude and latitude measured by GPS in a data format, can be angle information, or other position information.

[0094] It can be understood that the sample measurement data further includes network device measurement data of the target network device; the network device measurement data includes at least one of second sounding reference signal quality index data and physical uplink shared channel quality index data.

[0095] It should be noted that the first sounding reference signal quality index data is index data measured based on a sounding reference signal (SRS), and can include at least one or more of reference signal receiving power (RSRP), signal to interference plus noise ratio (SINR), direction of arrival (DOA), etc. The channel quality index data is index data measured based on a physical uplink shared channel (PUSCH), and can include one or more of RSPR and SINR.

[0096] It can be understood that the configuration data includes at least one of beam configuration parameters, power configuration parameters, and cell configuration parameters.

[0097] It should be noted that the beam configuration is, for example, phase, array amplitude, etc., the cell configuration is, for example, a cell covered by a beam, etc., and the power configuration is, for example, a power size of a beam, etc. The embodiments of the present application do not limit this.

[0098] It can be understood that the twin physical model includes at least one of base station data, antenna data, and environment data of the target network device.

[0099] It can be understood that the base station data includes at least one of base station position data and base station device composition data.

[0100] The antenna data includes at least one of the number of antennas, antenna gain, and antenna type.

[0101] The environment data includes at least one of natural environment data, building data, and road data.

[0102] It can be understood that the sample measurement data is at least one of historical measurement data or real-time measurement data, and the real-time measurement data is measurement data requested by the digital twin model to collect before starting training.

[0103] The following takes online training with real-time measurement data as an example, and the specific steps include the following steps one to five.

[0104] Step one: based on the digital twin model, the network device's work parameter information is collected, which is applied by the digital twin model or actively reported by the target network device. The target network device reports the work parameter information to the digital twin model, so that the corresponding digital model based on the twin physical model can be obtained, wherein the work parameter information includes but is not limited to the latitude, longitude, height, azimuth angle, downtilt angle, antenna type, antenna number and the like of the network device.

[0105] Step two: the user terminal in the coverage range of the target network device reports sample measurement data to the digital twin model, and the terminal data includes but is not limited to RSRP, SINR, DOA, CQI and the like.

[0106] Step three: after the digital twin model receives sufficient sample measurement data, the digital twin model training is started, wherein the training method includes but is not limited to some LTSM, CNN and other AI algorithms, as well as some non-AI polynomial fitting, Kalman filtering and other algorithms.

[0107] Step four: after the digital twin model training is completed, it is directly deployed online.

[0108] Step five: the digital twin model continuously receives the terminal data reported by the user terminal and infers the target beam prediction data, and further optimizes according to the target beam prediction data.

[0109] It can be understood that the method further includes:

[0110] - obtaining the optimized terminal performance data;

[0111] - comparing the optimized terminal performance data with the terminal performance data before optimization to obtain a comparison result;

[0112] - in the case that the comparison result indicates that the performance of the target network device is deteriorated, the optimization processing is performed through the digital twin model.

[0113] It should be noted that the network device can monitor the process of the system key indicators in real time by comparing the optimized terminal data with the terminal data before optimization, monitor the key indicators of the communication indicators of the target network device before and after adjustment, the key indicators can include but are not limited to the traffic of the user terminal, the signal quality of the user terminal, the block error rate (Bler) of the user terminal, and the like, and feed back the index information to the digital twin model, and the digital twin model can consider further optimization processing in the case of index deterioration.

[0114] It should be noted that the terminal performance data can be included in the terminal data or not. The optimization processing by the digital twin model can include retraining the digital twin model based on existing data and making predictions based on the retrained model, or using the existing digital twin model to make predictions again.

[0115] Therefore, the embodiments of the present application predict the data related to the beam by the digital twin model, so that the network device can dynamically adjust the beam direction according to the output of the digital twin model, and monitor the key indicators of the communication system in which the network device is located before and after adjustment in real time, and feed back the indicators to the twin model for further optimization. By this method, the resource utilization can be effectively improved, and the communication quality can be improved.

[0116] It can be understood that the network device provided by the embodiments of the present application comprises a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor executes the computer program to realize the network optimization method as described above.

[0117] It can be understood that referring to FIG. 7, the embodiments of the present application further provide a network device, which comprises:

[0118] at least one processor 701;

[0119] at least one memory 702 for storing at least one program, when the at least one program is executed by the at least one processor 701, the network optimization method is realized.

[0120] The memory 702 as a kind of non-transient network system, it can be used to store non-transient software programs and non-transient computer executable programs.In addition, the memory 702 can include high-speed random access memory, and can also include non-transient memory, such as at least one disk storage device, flash memory device, or other non-transient solid-state memory device.In some embodiments, the memory 702 includes a memory 702 remotely arranged relative to the processor 701, and these remote memories 702 can be connected to the processor 701 through network.The above-mentioned network includes but is not limited to the Internet, enterprise intranet, local area network, mobile communication network and combination thereof.

[0121] The memory 702 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM), etc. The memory 702 can store an operating system and other application programs. When the technical solutions provided by the embodiments of the present specification are implemented by software or firmware, the related program codes are stored in the memory 702 and are invoked and executed by the processor 701 to implement the method of the embodiments of the present application.

[0122] The processor 701 can be implemented in the form of a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, etc., for executing related programs to implement the technical solutions provided by the embodiments of the present application.

[0123] In some embodiments, the network device further comprises:

[0124] The input / output interface is used to realize information input and output.

[0125] The communication interface is used to realize the communication interaction between the device and other devices. The communication can be realized by wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0126] The bus is used to transmit information between various components (such as the processor 701, the memory 702, the input / output interface, and the communication interface) of the device.

[0127] The processor 701, the memory 702, the input / output interface, and the communication interface can be connected to each other through the bus for internal communication within the device.

[0128] In a fourth aspect, an embodiment of the present application further provides a computer readable storage medium storing computer executable instructions. The computer executable instructions are used to execute the above method.

[0129] In a fifth aspect, an embodiment of the present application further provides a computer program product including a computer program or computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer program or computer instructions from the computer readable storage medium, and the processor executes the computer program or computer instructions to make the computer device execute the above method.

[0130] The target network device corresponding to the digital twin model is used to perform beam prediction on terminal data reported by a user terminal in a to-be-optimized signal range, target beam prediction data is obtained, and the beam of the target network device is optimized according to the target beam prediction data. At this time, only a small amount of terminal data reported by the user terminal can obtain the target beam prediction data in the to-be-optimized signal range, the measurement data amount of the terminal data is shortened, and the measurement resource utilization rate is higher. Therefore, the network optimization of the network device can be performed while the beam utilization rate and the optimization efficiency are taken into account.

[0131] The system architecture and application scenarios described in the embodiments of the present application are used to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. It can be known by those skilled in the art that, with the evolution of system architecture and the appearance of new application scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0132] Those of ordinary skill in the art can understand that all or some of the steps in the method disclosed above can be implemented as software, firmware, hardware, and appropriate combinations thereof. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include computer storage media (or non-transitory media) and communication media (or transitory media). As known by those of ordinary skill in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage, or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. In addition, it is known by those of ordinary skill in the art that communication media typically includes computer readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and can include any information delivery medium.

[0133] Some embodiments of the present application are described above with reference to the accompanying drawings, and the scope of the right of the present application is not limited thereto. Any modifications, equivalent replacements, and improvements made by those skilled in the art without departing from the scope and spirit of the present application shall be within the scope of the right of the present application.

Claims

1. A network optimization method, the method comprising: obtaining a digital twin model of a target network device; obtaining terminal data reported by a user terminal located within a signal range to be optimized of the target network device; performing beam prediction on the target network device through the digital twin model according to the terminal data to obtain target beam prediction data; performing optimization processing on a beam of the target network device according to the target beam prediction data.

2. The method of network optimization of claim 1, wherein, The obtaining of the terminal data reported by the user terminal located within the signal range to be optimized of the target network device comprises at least one of the following: obtaining terminal data reported by a user terminal from a predetermined position within the signal range to be optimized of the target network device multiple times within a preset time period; obtaining terminal data reported by a user terminal from multiple different predetermined positions within the signal range to be optimized of the target network device.

3. The method of network optimization of claim 1, wherein, The target beam prediction data comprises beamforming data; the user terminals in multiple different spatial directions within the signal range to be optimized all support spatial division multiplexing, and the performing of the beam prediction on the target network device through the digital twin model according to the terminal data to obtain target beam prediction data comprises: performing beamforming prediction on the target network device through the digital twin model based on terminal data of the user terminals in multiple different spatial directions to obtain beamforming data of candidate beams corresponding to the user terminals; The performing of the optimization processing on the beam of the target network device according to the target beam prediction data comprises: determining user terminals that can be configured for spatial division multiplexing within the signal range to be optimized of the target network device according to the beamforming data; performing beamforming processing on the target network device according to the beamforming data.

4. The method of network optimization of claim 1, wherein, The target beam prediction data comprises interference data; the user terminals in multiple different spatial directions within the signal range to be optimized all support spatial division multiplexing, and the performing of the beam prediction on the target network device through the digital twin model according to the terminal data to obtain target beam prediction data comprises: performing beam interference analysis on the target network device through the digital twin model based on terminal data of the user terminals in multiple different spatial directions to obtain interference data; The performing of the optimization processing on the beam of the target network device according to the target beam prediction data further comprises: determining terminal devices in at least two different spatial directions in which no interference exists as user terminals that can be configured for spatial division multiplexing according to the interference data.

5. The method of network optimization of claim 1, wherein, The performing of the beam prediction on the target network device through the digital twin model according to the terminal data to obtain target beam prediction data comprises: determining a first user terminal and a second user terminal according to the terminal data; wherein a user density of a region in which the first user terminal and the second user terminal are jointly distributed satisfies a preset density threshold, a signal quality of the first user terminal satisfies a preset quality requirement, and a signal quality of the second user terminal does not satisfy the preset quality requirement. The terminal data of the first user terminal and the second user terminal within a preset time period is combined to obtain the target beam prediction data. The terminal data of the first user terminal and the second user terminal within a preset time period is combined to obtain the target beam prediction data.

6. The method of network optimization of claim 1, wherein, The terminal data of the first user terminal and the second user terminal within a preset time period is combined to obtain the target beam prediction data. The terminal data of the first user terminal and the second user terminal within a preset time period is combined to obtain the target beam prediction data. The terminal data of the first user terminal and the second user terminal within a preset time period is combined to obtain the target beam prediction data. The terminal data of the first user terminal and the second user terminal within a preset time period is combined to obtain the target beam prediction data.

7. The method of network optimization of claim 1, wherein, The digital twin model is trained by the following steps: Obtain configuration data and sample measurement data of the target network device; The configuration data and the sample measurement data are trained by a digital model determined based on a twin physical model of the target network device to obtain a trained digital twin model.

8. The method of network optimization of claim 7, wherein, The sample measurement data includes terminal sample data, and the terminal sample data includes first sounding reference signal quality index data and channel quality index data.

9. The method of network optimization of claim 8, wherein, The terminal sample data further includes user location data, downlink performance data, and beam parameters.

10. The method of network optimization of claim 8, wherein, The sample measurement data further includes network device measurement data of the target network device; and the network device measurement data includes at least one of second sounding reference signal quality index data and physical uplink shared channel quality index data.

11. The method of network optimization of claim 8, wherein, The configuration data includes at least one of beam configuration parameters, power configuration parameters, and cell configuration parameters.

12. The method of network optimization of claim 7, wherein, The twin physical model includes at least one of base station data, antenna data, and environment data of the target network device.

13. The method of network optimization of claim 12, wherein, The base station data includes at least one of base station location data and base station device composition data; The antenna data includes at least one of antenna quantity, antenna gain, and antenna type; The environment data includes at least one of natural environment data, building data, and road data.

14. The method of network optimization of claim 7, wherein, The sample measurement data is at least one of historical measurement data or real-time measurement data, and the real-time measurement data is measurement data collected by the target network device before the digital twin model starts training.

15. The network optimization method of claim 1, further comprising: Obtaining optimized terminal performance data; Comparing the optimized terminal performance data with terminal performance data before optimization to obtain a comparison result; and In a case where the comparison result indicates that the performance of the target network device is deteriorated, optimization processing is performed by the digital twin model.

16. A network device comprising: at least one processor; at least one memory for storing at least one program; wherein the at least one program, when executed by the at least one processor, implements the method for network optimization of any one of claims 1 to 15.

17. A computer-readable storage medium storing computer-executable instructions, wherein, The computer executable instructions are for performing the method for network optimization of any one of claims 1 to 15.

18. A computer program product comprising computer programs or computer instructions, wherein, The computer program or the computer instructions are stored in a computer readable storage medium, and the processor of the network device reads the computer program or the computer instructions from the computer readable storage medium, and executes the computer program or the computer instructions, so that the network device performs the method for network optimization of any one of claims 1 to 15.

Images