5G base station operation control method and device, storage medium, terminal

Abstract

The present invention discloses an operation control method and device, storage medium, and terminal of a 5G base station, which relates to the field of information processing technology, and its main purpose is to solve the problem of low service support while energy saving of 5G base stations. It mainly includes obtaining the initial operation control information of the target base station, the target space grid, and the communication traffic of the target space grid, and the target space grid carries the service time attribute; identifying the target prediction network model that matches the service time attribute from the prediction network model, and predicting the communication traffic based on the target prediction network model to obtain the communication traffic prediction result of the target space grid; determining the target operation control information of the target base station according to at least one of the communication traffic prediction result, the initial operation control information, and the communication traffic, and sending the target operation control information to the target control terminal to control the operation of the target base station. It is mainly used to control the energy-saving operation of 5G base stations.

Description

Technical Field

[0001] The present invention relates to the field of communication technologies, and in particular to an operation control method and device, a storage medium, and a terminal for a 5G base station. Background Art

[0002] With the continuous development of mobile communication technology, my country has ushered in the 5G (5th Generation Mobile Communication Technology) era, the era of the fifth generation of mobile communication technology. 5G technology has become a new generation of broadband mobile communication technology with its high speed, low latency, and large connection characteristics, and has also provided strong support for the development of technologies such as the Internet of Things, cloud computing, artificial intelligence, and big data. Although 5G technology has many advantages, the core equipment of 5G network transmission is the 5G base station, whose energy consumption is three times that of the 4G base station. How to reduce the high energy consumption of 5G base stations is an important issue currently facing 5G technology.

[0003] The current 5G base station energy-saving methods mainly include deep shutdown method and dormancy energy-saving method. The deep shutdown method refers to directly shutting down the 5G channel during the period of low 5G business volume, and only retaining the 4G channel. However, this method limits the operation time of the 5G network and affects the full-time business support of the 5G network. The dormancy energy-saving method refers to putting the base station into a deep dormant state during the period of low 5G business volume. However, when the base station is enabled, it needs to be restarted and awakened. The awakening time is as long as several minutes, which will also cause the operation response delay of the 5G network and affect the business response speed of the 5G network. Therefore, a 5G base station operation control method is urgently needed to solve the above problems. Summary of the invention

[0004] In view of this, the present invention provides a 5G base station operation control method and device, a storage medium, and a terminal, the main purpose of which is to solve the problem of low service support while saving energy in 5G base stations.

[0005] According to one aspect of the present invention, a 5G base station operation control method is provided, comprising:

[0006] Acquire initial operation control information of a target base station, a target spatial grid, and a communication traffic volume of the target spatial grid, wherein the target spatial grid carries a traffic time attribute, and the traffic time attribute is determined based on historical communication traffic volume data of the target spatial grid;

[0007] Identifying a target prediction network model that matches the service time attribute from the prediction network model, and performing prediction processing on the communication traffic based on the target prediction network model to obtain a communication traffic prediction result of the target spatial grid;

[0008] The target operation control information of the target base station is determined according to at least one of the communication traffic prediction result, the initial operation control information and the communication traffic, and the target operation control information is sent to the target control terminal to control the operation of the target base station.

[0009] Furthermore, before obtaining the target spatial grid, communication traffic volume, and initial operation control information of the target base station, the method further includes:

[0010] Obtaining base station geographic coordinate information, signal coverage information, and building physical coordinate information of global base stations;

[0011] Using the equal-intersection tangent cylinder method, the base station geographic coordinate information, the signal coverage range information, and the building entity coordinate information are subjected to plane transformation processing, and the spatial grid of the global base station is divided based on the plane transformation result to obtain the global base station spatial grid;

[0012] The historical communication traffic volume data of each spatial grid in the global base station spatial grid is acquired, and the service time attribute of the spatial grid is determined based on the historical communication traffic volume data.

[0013] Further, the acquiring of historical communication traffic data of each spatial grid in the global base station spatial grid, and determining the service time attribute of the spatial grid based on the historical communication traffic data includes:

[0014] Acquiring historical communication traffic data of each of the spatial grids;

[0015] The spatial grids are clustered based on the communication traffic data corresponding to different time periods in the historical communication traffic data to obtain the service time attribute of each spatial grid.

[0016] Further, the determining the target operation control information of the target base station according to at least one of the communication traffic volume prediction result, the initial operation control information, and the communication traffic volume includes:

[0017] If the initial operation control information indicates that the operation state of the target base station is dormant, determining target operation control information according to the communication traffic prediction result;

[0018] If the initial operation control information indicates that the operation state of the target base station is operation, a communication traffic volume threshold is calculated according to the communication traffic volume and the initial operation control information, and target operation control information is determined according to a comparison result between the communication traffic volume and the communication traffic volume threshold.

[0019] Further, the communication traffic volume prediction result includes an expected communication traffic volume sequence based on time, and if the initial operation control information indicates that the operation state of the target base station is dormant, determining the target operation control information according to the communication traffic volume prediction result includes:

[0020] If the initial operation control information indicates that the operation state of the target base station is dormant, obtaining a wake-up time parameter of the target base station;

[0021] Extracting the first expected communication traffic volume greater than zero in the expected communication traffic volume sequence as the target expected communication traffic volume, and taking the time corresponding to the target expected communication traffic volume as the target time;

[0022] The expected start-up time of the target base station is calculated according to the target time and the wake-up time parameter, and the expected number of channel start-ups is calculated based on the target expected communication traffic volume;

[0023] The target operation control information is generated according to the expected startup time and the expected number of channel startups.

[0024] Further, the determining the target operation control information according to the comparison result between the communication traffic volume and the communication traffic volume threshold comprises:

[0025] If the communication traffic volume is less than the communication traffic volume threshold, the number of open channels in the initial operation control information is reduced, and the target operation control information is determined based on the reduction result;

[0026] If the communication traffic volume is greater than the communication traffic volume threshold, an incremental process is performed on the number of open channels in the initial operation control information, and target operation control information is determined based on the incremental process result.

[0027] Further, the predicting process of the communication traffic based on the target prediction network model to obtain the communication traffic prediction result of the target spatial grid includes:

[0028] Acquire social attribute characteristic information of each of the target spatial grids;

[0029] Based on the social attribute feature information and the communication traffic data of the target spatial grid in different time periods, the signal attraction flow of the target spatial grid to other spatial grids is calculated;

[0030] The target prediction network model is used to predict the communication traffic volume of the target space grid and the signal attraction flow to obtain a communication traffic volume prediction result of the target space grid.

[0031] According to another aspect of the present invention, there is provided an operation control device of a 5G base station, comprising:

[0032] An acquisition module, used to acquire initial operation control information of a target base station, a target spatial grid, and a communication traffic volume of the target spatial grid, wherein the target spatial grid carries a service time attribute, and the service time attribute is determined based on historical communication traffic volume data of the target spatial grid;

[0033] A prediction module, used to identify a target prediction network model that matches the service time attribute from the prediction network model, and perform prediction processing on the communication traffic based on the target prediction network model to obtain a communication traffic prediction result of the target spatial grid;

[0034] A determination module is used to determine the target operation control information of the target base station according to at least one of the communication traffic prediction result, the initial operation control information, and the communication traffic, and send the target operation control information to the target control terminal to control the operation of the target base station.

[0035] Furthermore, before obtaining the target spatial grid, communication traffic volume, and initial operation control information of the target base station, the method further includes:

[0036] The acquisition module is further used to acquire base station geographic coordinate information, signal coverage information, and building entity coordinate information of global base stations;

[0037] A conversion module is used to perform plane conversion processing on the geographic coordinate information of the base station, the signal coverage information, and the physical coordinate information of the building using the equal-intersection tangent cylinder method, and to perform spatial grid division of the global base station based on the plane conversion result to obtain a global base station spatial grid;

[0038] The determination module is further configured to obtain historical communication traffic volume data of each spatial grid in the global base station spatial grid, and determine the service time attribute of the spatial grid based on the historical communication traffic volume data.

[0039] Furthermore, the determination module includes:

[0040] A first acquisition unit, configured to acquire historical communication traffic data of each of the spatial grids;

[0041] The clustering unit is used to cluster each of the spatial grids based on the communication traffic data corresponding to different time periods in the historical communication traffic data to obtain the service time attribute of each of the spatial grids.

[0042] Furthermore, the determination module includes:

[0043] a first determining unit, configured to determine target operation control information according to the communication traffic volume prediction result if the initial operation control information indicates that the operation state of the target base station is dormant;

[0044] The second determination unit is used to calculate a communication traffic volume threshold according to the communication traffic volume and the initial operation control information if the initial operation control information indicates that the operation state of the target base station is operation, and determine the target operation control information according to the comparison result between the communication traffic volume and the communication traffic volume threshold.

[0045] Further, in a specific application scenario, the first determining unit is specifically configured to obtain a wake-up time parameter of the target base station if the initial operation control information indicates that the operation state of the target base station is dormant;

[0046] Extracting the first expected communication traffic volume greater than zero in the expected communication traffic volume sequence as the target expected communication traffic volume, and taking the time corresponding to the target expected communication traffic volume as the target time;

[0047] The expected start-up time of the target base station is calculated according to the target time and the wake-up time parameter, and the expected number of channel start-ups is calculated based on the target expected communication traffic volume;

[0048] The target operation control information is generated according to the expected startup time and the expected number of channel startups.

[0049] Furthermore, the determining module includes:

[0050] A first processing unit, configured to, if the communication traffic volume is less than the communication traffic volume threshold, decrement the number of open channels in the initial operation control information, and determine target operation control information based on the decrement result;

[0051] The second processing unit is configured to perform incremental processing on the number of open channels in the initial operation control information if the communication traffic volume is greater than the communication traffic volume threshold, and determine target operation control information based on the incremental processing result.

[0052] Furthermore, the prediction module includes:

[0053] A second acquisition unit is used to acquire social attribute feature information of each target space grid;

[0054] A calculation unit, configured to calculate the signal attraction flow of the target spatial grid to other spatial grids based on the social attribute feature information and the communication traffic data of the target spatial grid in different time periods;

[0055] The prediction unit is used to use the target prediction network model to predict the communication traffic volume of the target space grid and the signal attraction flow to obtain the communication traffic volume prediction result of the target space grid.

[0056] According to another aspect of the present invention, a storage medium is provided, wherein at least one executable instruction is stored in the storage medium, and the executable instruction enables a processor to perform operations corresponding to the above-mentioned 5G base station operation control method.

[0057] According to another aspect of the present invention, there is provided a terminal, comprising: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus;

[0058] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform operations corresponding to the above-mentioned 5G base station operation control method.

[0059] By means of the above technical solution, the technical solution provided by the embodiment of the present invention has at least the following advantages:

[0060] The present invention provides an operation control method and device, a storage medium, and a terminal for a 5G base station. The embodiment of the present invention obtains the initial operation control information of a target base station, a target spatial grid, and the communication traffic of the target spatial grid, wherein the target spatial grid carries a service time attribute, and the service time attribute is determined based on the historical communication traffic data of the target spatial grid; identifies a target prediction network model that matches the service time attribute from a prediction network model, and performs prediction processing on the communication traffic based on the target prediction network model to obtain a communication traffic prediction result of the target spatial grid; determines the target operation control information of the target base station according to at least one of the communication traffic prediction result, the initial operation control information, and the communication traffic, and sends the target operation control information to a target control terminal to control the operation of the target base station, thereby avoiding the lack of service support and delayed service response caused by the energy-saving operation function of a 5G base station, making the energy-saving operation control of the base station more flexible and timely, and at the same time, ensuring the realization of the energy-saving function of the base station, thereby greatly improving the support for the service during the energy-saving control of the base station.

[0061] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0063] Figure 1 A flow chart of an operation control method of a 5G base station provided by an embodiment of the present invention is shown;

[0064] Figure 2 A flow chart of another 5G base station operation control method provided by an embodiment of the present invention is shown;

[0065] Figure 3 A block diagram of a 5G base station operation control device provided by an embodiment of the present invention is shown;

[0066] Figure 4 A schematic diagram of the structure of a terminal provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0067] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0068] With regard to the current 5G base station energy-saving methods, the deep shutdown method only retains the 4G channel, which limits the operation time of the 5G network and affects the full-time service support of the 5G network; the sleep energy-saving method puts the base station into a deep sleep state. When the base station is enabled, it needs to be restarted and awakened. The wake-up time is as long as several minutes, causing the operation response delay of the 5G network, resulting in the problem of low service support of the 5G base station. The embodiment of the present invention provides an operation control method for a 5G base station, such as Figure 1 As shown, the method includes:

[0069] 101. Obtain initial operation control information of a target base station, a target spatial grid, and a communication traffic volume of the target spatial grid.

[0070] In an embodiment of the present invention, the target base station is a 5G base station that currently needs to be energy-saving controlled. The target spatial grid is a spatial grid within the coverage range of the target base station signal. Among them, the target spatial grid can be identified from the pre-constructed spatial grid of the global base station according to the target base station information. The spatial grid is divided based on the base station location information, base station signal coverage range, building geographical location and other information of the base station, and can be used as a service management unit for 5G communication signals, and may include exclusive grids and comprehensive grids. The communication traffic volume of the target spatial grid is the total traffic volume in the target spatial grid that uses the 5G network for communication, which can specifically be the number of 5G network users in the current target spatial grid. The international mobile equipment identity (IMEI) of the device can be used to identify whether the device belongs to a 5G smart device, and the signal of the 5G device can be used to determine whether the device has turned on the 5G signal, and the amount of equipment that turns on the 5G signal is recorded as the communication traffic volume.

[0071] In the embodiment of the present invention, the initial operation control information is the operation information of the power amplifier and the radio frequency unit of the base station antenna unit (active antenna unit, AAU) of the target base station, for example, the number of channels currently operated by the AUU power amplifier and the radio frequency unit of the target base station is 32 or 64. Since the AAU is the core energy-consuming component of the base station and its energy consumption accounts for 90% of the total energy consumption, using the operation information of the AUU as the operation control information of the base station for control can most effectively realize the control of the energy consumption of the base station.

[0072] It should be noted that each spatial grid carries a service time attribute, and the service time attribute is determined based on the historical communication traffic data corresponding to each spatial grid, that is, the service time attribute is an attribute feature determined according to the characteristics of the communication traffic in different time periods in each spatial grid that varies with the time period, and can specifically include service time attributes corresponding to different time periods. For example, if the peak of the communication traffic of spatial grid A is between 6:00 and 9:00, then the service time attribute can be a morning peak category, and if the peak of the communication traffic of spatial grid B is between 18:00 and 23:00, then the service time attribute can be a late peak category. The division of service time attributes can be customized according to application requirements, and the embodiments of the present invention do not make specific limitations.

[0073] It should be noted that by dividing the coverage area of ​​the base station into spatial grids, the statistics of the communication traffic are made in grids, which realizes accurate statistics of the traffic. At the same time, the service time attributes of the spatial grids are determined according to the characteristic data of the historical traffic volume of each spatial grid over time, and the service characteristics of the spatial grids are divided, so that the prediction of the traffic volume in the subsequent spatial grids can be performed based on the corresponding business-specific model, thereby improving the accuracy of the prediction.

[0074] 102. Identify a target prediction network model that matches the service time attribute from the prediction network model, and perform prediction processing on the communication service volume based on the target prediction network model to obtain a communication service volume prediction result of the target spatial grid.

[0075] In an embodiment of the present invention, the prediction network model is a pre-trained network model for predicting the expected communication traffic in the spatial grid. There are multiple prediction network models, and different prediction network models are obtained by training based on training samples of different business time attributes, and are used to predict the spatial grids corresponding to the business time attributes. For example, the prediction network model A is obtained by training based on samples of the peak time period of communication business traffic at 6:00 to 9:00, then this model can be used to predict the spatial grid corresponding to the peak time period of communication business traffic at 6:00 to 9:00. Among them, the basic model of the prediction network model can be a recurrent neural network model, preferably a long short-term memory network model (long short term memory, LSTM). Since this model is a neural network with a time cycle, it solves the problem of multi-time scale data dependency in the recurrent neural network, and can better realize the prediction of the communication traffic of the spatial grid in the future (the flow of people using 5G communication). Among them, the formula of the forget gate fa that determines the proportion of data saved at the previous moment in the target prediction network model is expressed as:

[0076]

[0077] Where: w z is the weight of the forget gate; p t-1 is the number of 5G signal personnel in the target space grid at the previous moment; a is the number of smart devices that turn off 5G signals; δ is the activation function of the forget gate of the target prediction network model; φ is the bias of the forget gate in the LSTM for spatial grid traffic prediction. The formula for the input gate fout that determines the next hidden state value in the target prediction network model is expressed as:

[0078] f out =δ(w m (p t-1 ,z a )+λ)tanh(v a )(2);

[0079] Where: w m is the weight of the output gate; λ is the bias of the output gate; v a is the cell state in the target prediction network model; tanh is the activation function of the output gate of the target prediction network model.

[0080] It should be noted that since the target prediction network model is trained based on the historical communication traffic data of the target space grid to be predicted, it has fully learned the characteristics of the change of the traffic of the target space grid over time. Therefore, in the prediction process of the target space grid, it can better predict based on the business time attributes of the target space grid and obtain more accurate prediction results.

[0081] 103. Determine target operation control information of the target base station according to at least one of the communication traffic prediction result, the initial operation control information, and the communication traffic, and send the target operation control information to a target control terminal to control the operation of the target base station.

[0082] In an embodiment of the present invention, after obtaining the communication traffic volume prediction result, the initial operation control information, and the communication traffic volume, the current operation state of the target base station is determined according to the initial operation control information, and the adjustment basis of the control scheme is determined according to the base station operation state, that is, the operation of the target base station is controlled based on the communication traffic volume prediction result and / or based on the communication traffic volume to obtain the target operation control information. For example, if the initial operation control information indicates that the current target base station is in a deep sleep state, it is necessary to determine the time and expected flow of people using 5G communication in the target space grid based on the communication traffic volume prediction result, and then determine the start-up operation time and the number of start-up operation channels of the target base station based on the time and expected flow of people. For example, if the initial operation control information indicates that the current target base station is in a normal operating state, the number of operation channels can be adjusted only according to the current communication traffic volume in the target space grid, or on the basis of adjusting the number of operation channels according to the communication traffic volume, the number of operation channels can be adjusted in combination with the communication traffic volume prediction result.

[0083] It should be noted that the number of base station channels is adjusted based on the communication traffic in the spatial grid, so that the energy consumption of the base station is adjusted in real time with the change of the communication traffic in the coverage area, avoiding the one-size-fits-all control of the base station operation according to a fixed period, which greatly improves the flexibility and accuracy of the base station energy-saving control, thereby saving energy and improving the base station's support for the business. In addition, the control of the base station operation based on the prediction of the expected communication traffic volume of the target spatial grid can realize the early start of the time-consuming equipment, eliminating the impact of the long time of equipment startup on the base station business, thereby further improving the base station's support for the business.

[0084] In an embodiment of the present invention, for further explanation and limitation, as Figure 2 As shown, before the step of obtaining the target spatial grid, communication traffic volume, and initial operation control information of the target base station, the method further includes:

[0085] 201. Obtain base station geographic coordinate information, signal coverage information, and building entity coordinate information of a global base station.

[0086] 202. Perform plane transformation processing on the geographic coordinate information of the base station, the signal coverage information, and the physical coordinate information of the building using the equal-intersection tangent cylinder method, and perform spatial grid division of the global base station based on the plane transformation result to obtain a global base station spatial grid.

[0087] 203. Obtain historical communication traffic data of each spatial grid in the global base station spatial grid, and determine the service time attribute of the spatial grid based on the historical communication traffic data.

[0088] In an embodiment of the present invention, the global base station is all 5G base stations operated by the same operator. In order to spatially grid the coverage of each base station, the longitude and latitude coordinate information of the 5G base station, the 5G, 4G, and 2G signal coverage of the 5G base station, and the longitude and latitude information of the building geographic entity are obtained, and the longitude and latitude coordinate information of the edge point of the base station coverage area is calculated according to the longitude and latitude coordinates of the base station and the base station signal coverage. Among them, the longitude and latitude information of the building geographic entity can obtain the urban building geographic information such as buildings and roads in the digital map through the application program interface. The longitude and latitude coordinate information of the edge point of the base station coverage area is combined with the longitude and latitude information of the building geographic entity, and mapped to the plane coordinate system of the algorithm to obtain a spatial grid. Among them, the longitude and latitude information is mapped based on the equal-intersection tangent cylindrical projection method, and the Mercator projection method is preferably used. The longitude and latitude of the earth of the base station, coverage, and building geographic entity are projected to the cylindrical surface through the equiangular condition, and the cylindrical surface is unfolded into a plane, so as to achieve the purpose of accurately mapping the longitude and latitude coordinates to the plane. Specifically, the mapping process of the longitude and latitude information of a building is taken as an example to illustrate that the horizontal coordinate of the geographic entity mapped to the algorithm plane of the building is represented by x a , then the formula is: a =S b (γ-γ 0 )(3); where S b is the radius of the earth, γ is the geographical entity longitude of the building, γ 0 is the longitude of the central meridian of the earth. Set the horizontal and vertical coordinates of the geographic entity of the building mapped to the algorithm plane as y a , then the formula is: (4); where σ is the latitude of the building's geographic entity, and π is the circumference of a circle. The plane coordinates of the base station and the plane vertical and horizontal coordinates of the edge points of the base station coverage area are calculated according to formulas (3) and (4). The spatial grid is divided based on the obtained plane vertical and horizontal coordinates of the base station, the edge points of the base station coverage area, and the plane horizontal and vertical coordinates of the building's geographic entity. The essence of spatial grid division is to divide the business management units covered by 5G communication signals, including exclusive grids, such as commercial entities, industrial parks, etc., and comprehensive grids, such as residential communities, buildings, etc.

[0089] Since the traffic characteristics corresponding to different spatial grids in different time dimensions are not the same, that is, the time corresponding to the peak and trough of the communication traffic of each spatial grid, or the law of the change of communication traffic over time has its own attribute characteristics, therefore, in order to make accurate predictions based on the business characteristics of each spatial grid in the subsequent communication traffic prediction process, after completing the spatial grid division, the historical communication traffic data of each spatial grid is obtained, and the business time attributes of the corresponding spatial grid are determined according to the historical communication traffic data.

[0090] It should be noted that grid division based on building geographic entities and base station coverage can not only realize the division of corresponding ranges of different base stations, but also realize the division of buildings with different communication business characteristics. For example, the communication business characteristics of office buildings are that the working time period on weekdays is the peak time of communication business volume, and the non-working time period on holidays and weekdays is the valley time of communication business volume. Further, on the basis of the spatial dimension, combined with the time dimension attribute based on the communication business volume, multiple divisions of base station coverage in the time dimension and space dimension are realized, providing a more accurate reference basis for subsequent base station energy-saving control.

[0091] In one embodiment of the present invention, for further explanation and limitation, the step of determining the service time attribute of the spatial grid based on the acquired historical communication traffic data of the spatial grid includes:

[0092] Acquiring historical communication traffic data of each of the spatial grids;

[0093] The spatial grids are clustered based on the communication traffic data corresponding to different time periods in the historical communication traffic data to obtain the service time attribute of each spatial grid.

[0094] In the embodiment of the present invention, in order to determine the service time attribute of each spatial grid, the grids are clustered based on the service characteristics of each spatial grid. Specifically, the Gaussian mixture model (GMM) is used for clustering, the number of grids is used as the number of cluster samples, the maximum likelihood of the clustering density function is calculated, the parameters of each Gaussian distribution are obtained, and then the probability of each spatial grid belonging to the corresponding service time attribute category is calculated based on the parameters of the Gaussian distribution, thereby completing the division of the spatial grid time service characteristics. Among them, the GMM clustering density function c of the spatiotemporal grid is a for: Among them, n a is the number of grids for GMM clustering; d i are different Gaussian distribution probabilities; l(e|g i ) are different Gaussian probability distribution densities; z i For different covariance matrices. The GMM clustering method uses Gaussian distribution as a parameter and uses approximation of data point distribution to calculate the classification of data points, which solves the problem that the k-means clustering algorithm cannot cluster with the same mean. The GMM method is used to cluster the time business characteristics of the grid, which can effectively improve the calculation efficiency.

[0095] In one embodiment of the present invention, for further explanation and limitation, the step of determining the target operation control information of the target base station according to at least one of the communication traffic volume prediction result, the initial operation control information, and the communication traffic volume includes:

[0096] If the initial operation control information indicates that the operation state of the target base station is dormant, determining target operation control information according to the communication traffic prediction result;

[0097] If the initial operation control information indicates that the operation state of the target base station is operation, a communication traffic volume threshold is calculated according to the communication traffic volume and the initial operation control information, and target operation control information is determined according to a comparison result between the communication traffic volume and the communication traffic volume threshold.

[0098] In an embodiment of the present invention, the initial operation control information mainly includes the number of channels currently controlled to be turned on and / or closed by the target base station. The operation state of the target base station can be determined according to the number of channels controlled to be turned on or off. If the number of channels turned on is equal to zero, or the number of channels turned off is equal to the number of all channels, it indicates that the target base station is in a dormant state. If the number of channels turned on is greater than the number, or the number of channels turned off is less than the number of all channels, it indicates that the target base station is in an operating state. The operating state here can be full channel operation or partial channel operation. If the target base station is in a dormant state, the target base station may not need to be turned on temporarily when it is idle. Therefore, it is necessary to determine the time point at which the target spatial grid is expected to have 5G communication traffic and the number of 5G communication traffic (communication traffic) at this time point according to the communication traffic prediction result, and then generate the target operation control information including the start time and the number of start channels of the target base station. If the target base station is in an operating state, the target base station may be in a busy state. The number of operating channels in the initial operation control information can be adjusted according to the real-time communication traffic data in the current target grid to obtain the target operation control information.

[0099] In one embodiment of the present invention, for further explanation and limitation, if the initial operation control information indicates that the operation state of the target base station is dormant, determining the target operation control information according to the communication traffic prediction result includes:

[0100] If the initial operation control information indicates that the operation state of the target base station is dormant, obtaining a wake-up time parameter of the target base station;

[0101] Extracting the first expected communication traffic volume greater than zero in the expected communication traffic volume sequence as the target expected communication traffic volume, and taking the time corresponding to the target expected communication traffic volume as the target time;

[0102] The expected start-up time of the target base station is calculated according to the target time and the wake-up time parameter, and the expected number of channel start-ups is calculated based on the target expected communication traffic volume;

[0103] The target operation control information is generated according to the expected startup time and the expected number of channel startups.

[0104] In an embodiment of the present invention, the communication traffic prediction result includes an expected communication traffic sequence based on time, that is, a set of communication traffic sequences expected at different time points in the future arranged in the order of occurrence of time. Since it takes a certain amount of time for the base station AAU to be awakened from a dormant state, in order to ensure that the target base station is in an on state when 5G users flow in, it is necessary to complete the wake-up of the target base station before the 5G user actually enters the target space grid. Specifically, the time when the expected communication traffic volume is greater than zero for the first time in the expected communication traffic sequence, that is, the time when the first batch of 5G users enter the target space grid after the target base station is dormant, is taken as the target time, and the wake-up time (wake-up time parameter) of the target base station is subtracted from this target time to obtain the latest time when the target base station needs to be started. This latest start time or a time earlier than this latest start time can be configured as the expected start time, and the embodiment of the present invention does not make specific limitations. In addition to the expected startup time, the number of channels of the target base station to be started can also be determined based on the expected communication traffic volume (target expected communication traffic volume) corresponding to the target time. The default minimum number of startup groups can be configured, and the default minimum number of startup groups can be used as the expected number of channel startups. The communication traffic volume threshold can also be preset, and the expected number of channel startups can be determined based on the comparison result between the preset communication traffic volume threshold and the expected communication traffic volume. For example, if the expected communication traffic volume is greater than the first expected communication traffic volume threshold, 2 groups are started; if it is greater than the expected communication traffic volume threshold, 4 groups are started, and so on. The embodiment of the present invention does not specifically limit the specific numerical value of the expected communication traffic volume threshold and the corresponding number of startup groups.

[0105] It should be noted that by predicting the communication service volume in the target space grid, the target base station can be awakened and started before the 5G user actually enters the target space grid, avoiding waking up the base station after the 5G user actually enters the target space grid, causing 5G communication service response delays, and ensuring that the target base station is awakened before the 5G user actually enters the target space network. While meeting the needs of base station dormancy and energy saving, 5G service support is achieved without interruption and delay, thereby effectively improving support for communication services.

[0106] In one embodiment of the present invention, for further explanation and limitation, the step of determining the target operation control information according to the comparison result between the communication traffic volume and the communication traffic volume threshold includes:

[0107] If the communication traffic volume is less than the communication traffic volume threshold, the number of open channels in the initial operation control information is reduced, and the target operation control information is determined based on the reduction result;

[0108] If the communication traffic volume is greater than the communication traffic volume threshold, an incremental process is performed on the number of open channels in the initial operation control information, and target operation control information is determined based on the incremental process result.

[0109] In the embodiment of the present invention, all channels are divided into groups with the same number of channels, and the channels are controlled by group. For example, 64 channels are grouped into 4 channels each, so 16 groups are obtained. When a group is opened, 4 channels are opened, and when a group is closed, 4 channels are closed. The communication traffic volume threshold is calculated based on the number of channels closed in the initial operation control information and the historical communication traffic volume of each target spatial grid, and the target operation control information is determined based on the comparison result of the communication traffic volume threshold and the real-time communication traffic volume. The communication traffic volume threshold calculation formula is:

[0110] Among them, n k is the number of target space grids; p mx i is the historical maximum number of people who hold and open 5G channel equipment in each target space grid (historical maximum communication business volume); ψ is the number of groups whose channels are closed at the current target base station. If the communication business volume of the target space grid is lower than Δf 1 When the number of personnel exceeds Δf, the number of channel groups is reduced; when the number of personnel exceeds Δf 1 When all channels are opened, or the number of channel groups is increased. For example, originally 2 groups are closed, increasing the number of channel groups increases the number of channel groups to the maximum, and decreasing the number of channel groups updates the closing of 2 groups to closing of 4 groups. The specific number of increasing or decreasing the number of channel groups can be determined according to the actual application scenario, and the embodiment of the present invention does not make a specific limitation.

[0111] In one embodiment of the present invention, for further explanation and limitation, the step of performing prediction processing on the communication traffic based on the target prediction network model to obtain the communication traffic prediction result of the target spatial grid includes:

[0112] Acquire social attribute characteristic information of each of the target spatial grids;

[0113] Based on the social attribute feature information and the communication traffic data of the target spatial grid in different time periods, the signal attraction flow of the target spatial grid to other spatial grids is calculated;

[0114] The target prediction network model is used to predict the communication traffic volume of the target space grid and the signal attraction flow to obtain a communication traffic volume prediction result of the target space grid.

[0115] In an embodiment of the present invention, the location of a 5G communication user is not fixed, but migrates between different building geographical entities. For example, the spatial grid migration of a user involves a comprehensive spatial grid for residence and an exclusive time grid for work. Since there are certain correlation characteristics between the spatial grids on the movement trajectory of each 5G signal user, communication traffic volume prediction based on this correlation characteristic can more accurately predict the expected communication traffic volume changes of the spatial grid, and this correlation characteristic can be characterized by a signal attraction flow. For example, the higher the capital cost of the spatial grid, the more attractive it is to personnel, and the greater the communication traffic volume of 5G communication. Therefore, using the signal attraction flow and communication traffic volume of the target spatial grid as the input of the target prediction network model can obtain a more accurate prediction result of the communication traffic volume of the target spatial grid. Among them, the signal attraction flow of the target spatial grid is calculated based on social attribute feature information and the communication traffic volume data of the target spatial grid in different time periods, and the social attribute feature information can be the gross social product. Set the signal attraction flow of the target spatial grid to be h a , the calculation formula is: Among them, r a The total social production value of the target space grid; r all is the total social production value of the global base station spatial grid; n b is the number of global base station spatial grids; p j is the communication traffic volume of different spatial grids, i.e., the number of people holding 5G smart devices; w j is the weight of different spatial grids; r aj is the total social production value of different spatial grids; u aj is the distance from different spatial grids to the target grid. Among them, the weights of different spatial grids can be determined according to the proportion of 5G smart devices in the spatiotemporal grid. For example, if the proportion of 5G smart devices is less than 30%, it corresponds to a lower weight. If the proportion of 5G smart devices in the target spatial grid is greater than 50%, it corresponds to a higher weight. The configuration of the weight can be customized according to the specific application scenario, and the embodiment of the present invention does not make specific limitations. The proportion of 5G smart devices in the target spatial grid qa is: Among them, q b is the number of 5G smart devices in the target space grid; q c It is a 5G smart device without 5G signal function turned on; all is the number of all devices in the target space grid.

[0116] The present invention provides an operation control method for a 5G base station. An embodiment of the present invention obtains initial operation control information of a target base station, a target spatial grid, and communication traffic of the target spatial grid, wherein the target spatial grid carries a service time attribute, and the service time attribute is determined based on historical communication traffic data of the target spatial grid; a target prediction network model matching the service time attribute is identified from a prediction network model, and the communication traffic is predicted based on the target prediction network model to obtain a communication traffic prediction result of the target spatial grid; target operation control information of the target base station is determined according to at least one of the communication traffic prediction result, the initial operation control information, and the communication traffic, and the target operation control information is sent to a target control terminal to control the operation of the target base station, thereby avoiding service lack of support and service delayed response caused by the energy-saving operation function of the 5G base station, making the energy-saving operation control of the base station more flexible and timely, and at the same time, ensuring the realization of the energy-saving function of the base station, thereby greatly improving the support for services during the energy-saving control of the base station.

[0117] Furthermore, as a response to the above Figure 1 The implementation of the method shown in the figure, the embodiment of the present invention provides an operation control device of a 5G base station, such as Figure 3 As shown, the device comprises:

[0118] An acquisition module 31 is used to acquire initial operation control information of a target base station, a target spatial grid, and a communication traffic volume of the target spatial grid, wherein the target spatial grid carries a service time attribute, and the service time attribute is determined based on historical communication traffic volume data of the target spatial grid;

[0119] A prediction module 32 is used to identify a target prediction network model that matches the service time attribute from the prediction network model, and perform prediction processing on the communication traffic based on the target prediction network model to obtain a communication traffic prediction result of the target spatial grid;

[0120] The determination module 33 is used to determine the target operation control information of the target base station according to at least one of the communication traffic prediction result, the initial operation control information, and the communication traffic, and send the target operation control information to the target control terminal to control the operation of the target base station.

[0121] Furthermore, before obtaining the target spatial grid, communication traffic volume, and initial operation control information of the target base station, the method further includes:

[0122] The acquisition module 31 is also used to acquire the base station geographic coordinate information, signal coverage information, and building entity coordinate information of the global base station;

[0123] A conversion module is used to perform plane conversion processing on the geographic coordinate information of the base station, the signal coverage information, and the physical coordinate information of the building using the equal-intersection tangent cylinder method, and to perform spatial grid division of the global base station based on the plane conversion result to obtain a global base station spatial grid;

[0124] The determination module 33 is further configured to obtain historical communication traffic volume data of each spatial grid in the global base station spatial grid, and determine the service time attribute of the spatial grid based on the historical communication traffic volume data.

[0125] Furthermore, the determination module 33 includes:

[0126] A first acquisition unit, configured to acquire historical communication traffic data of each of the spatial grids;

[0127] The clustering unit is used to cluster each of the spatial grids based on the communication traffic data corresponding to different time periods in the historical communication traffic data to obtain the service time attribute of each of the spatial grids.

[0128] Furthermore, the determination module 33 includes:

[0129] a first determining unit, configured to determine target operation control information according to the communication traffic volume prediction result if the initial operation control information indicates that the operation state of the target base station is dormant;

[0130] The second determination unit is used to calculate a communication traffic volume threshold according to the communication traffic volume and the initial operation control information if the initial operation control information indicates that the operation state of the target base station is operation, and determine the target operation control information according to the comparison result between the communication traffic volume and the communication traffic volume threshold.

[0131] Further, in a specific application scenario, the first determining unit is specifically configured to obtain a wake-up time parameter of the target base station if the initial operation control information indicates that the operation state of the target base station is dormant;

[0132] Extracting the first expected communication traffic volume greater than zero in the expected communication traffic volume sequence as the target expected communication traffic volume, and taking the time corresponding to the target expected communication traffic volume as the target time;

[0133] The expected start-up time of the target base station is calculated according to the target time and the wake-up time parameter, and the expected number of channel start-ups is calculated based on the target expected communication traffic volume;

[0134] The target operation control information is generated according to the expected startup time and the expected number of channel startups.

[0135] Furthermore, the determination module 33 includes:

[0136] A first processing unit, configured to, if the communication traffic volume is less than the communication traffic volume threshold, decrement the number of open channels in the initial operation control information, and determine target operation control information based on the decrement result;

[0137] The second processing unit is configured to perform incremental processing on the number of open channels in the initial operation control information if the communication traffic volume is greater than the communication traffic volume threshold, and determine target operation control information based on the incremental processing result.

[0138] Furthermore, the prediction module 32 includes:

[0139] A second acquisition unit is used to acquire social attribute feature information of each target space grid;

[0140] A calculation unit, configured to calculate the signal attraction flow of the target spatial grid to other spatial grids based on the social attribute feature information and the communication traffic data of the target spatial grid in different time periods;

[0141] The prediction unit is used to use the target prediction network model to predict the communication traffic volume of the target space grid and the signal attraction flow to obtain the communication traffic volume prediction result of the target space grid.

[0142] The present invention provides an operation control method and device, a storage medium, and a terminal for a 5G base station. The embodiment of the present invention obtains the initial operation control information of a target base station, a target spatial grid, and the communication traffic of the target spatial grid, wherein the target spatial grid carries a service time attribute, and the service time attribute is determined based on the historical communication traffic data of the target spatial grid; identifies a target prediction network model that matches the service time attribute from a prediction network model, and performs prediction processing on the communication traffic based on the target prediction network model to obtain a communication traffic prediction result of the target spatial grid; determines the target operation control information of the target base station according to at least one of the communication traffic prediction result, the initial operation control information, and the communication traffic, and sends the target operation control information to a target control terminal to control the operation of the target base station, thereby avoiding the lack of service support and delayed service response caused by the energy-saving operation function of a 5G base station, making the energy-saving operation control of the base station more flexible and timely, and at the same time, ensuring the realization of the energy-saving function of the base station, thereby greatly improving the support for the service during the energy-saving control of the base station.

[0143] According to one embodiment of the present invention, a storage medium is provided, wherein the storage medium stores at least one executable instruction, and the computer executable instruction can execute the operation control method of the 5G base station in any of the above method embodiments.

[0144] Figure 4 A schematic diagram of the structure of a terminal provided according to an embodiment of the present invention is shown. The specific embodiment of the present invention does not limit the specific implementation of the terminal.

[0145] like Figure 4 As shown, the terminal may include: a processor (processor) 402 , a communication interface (Communications Interface) 404 , a memory (memory) 406 , and a communication bus 408 .

[0146] The processor 402 , the communication interface 404 , and the memory 406 communicate with each other via a communication bus 408 .

[0147] The communication interface 404 is used to communicate with other devices such as clients or other servers.

[0148] Processor 402 is used to execute program 410, and specifically can execute the relevant steps in the above-mentioned 5G base station operation control method embodiment.

[0149] Specifically, the program 410 may include program codes, which include computer operation instructions.

[0150] The processor 402 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiment of the present invention. The one or more processors included in the terminal may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0151] The memory 406 is used to store the program 410. The memory 406 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0152] The program 410 may be specifically configured to enable the processor 402 to perform the following operations:

[0153] Acquire initial operation control information of a target base station, a target spatial grid, and a communication traffic volume of the target spatial grid, wherein the target spatial grid carries a traffic time attribute, and the traffic time attribute is determined based on historical communication traffic volume data of the target spatial grid;

[0154] Identifying a target prediction network model that matches the service time attribute from the prediction network model, and performing prediction processing on the communication traffic based on the target prediction network model to obtain a communication traffic prediction result of the target spatial grid;

[0155] The target operation control information of the target base station is determined according to at least one of the communication traffic prediction result, the initial operation control information and the communication traffic, and the target operation control information is sent to the target control terminal to control the operation of the target base station.

[0156] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0157] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A 5G base station operation control method, It is characterized in that include: Acquire initial operation control information of a target base station, a target spatial grid, and a communication traffic volume of the target spatial grid, wherein the target spatial grid carries a traffic time attribute, and the traffic time attribute is determined based on historical communication traffic volume data of the target spatial grid; Identify a target prediction network model that matches the service time attribute from the prediction network model, and perform prediction processing on the communication traffic based on the target prediction network model to obtain a communication traffic prediction result of the target space grid, specifically including: obtaining social attribute feature information of each of the target space grids; calculating the signal attraction flow of the target space grid to other space grids based on the social attribute feature information and the communication traffic data of the target space grid in different time periods; perform prediction processing on the communication traffic and the signal attraction flow of the target space grid using the target prediction network model to obtain a communication traffic prediction result of the target space grid; The calculation formula of the signal attraction flow is: Among them, the signal attraction flow is h a ; r a The total social production value of the target space grid; r all is the total social production value of the global base station spatial grid; n b is the number of global base station spatial grids; p j is the communication traffic volume of different spatial grids, i.e., the number of people holding 5G smart devices; w j is the weight of different spatial grids; r aj is the total social production value of different spatial grids; u aj is the distance from different spatial grids to the target grid; The target operation control information of the target base station is determined according to at least one of the communication traffic prediction result, the initial operation control information and the communication traffic, and the target operation control information is sent to the target control terminal to control the operation of the target base station.

2. The method according to claim 1, It is characterized in that Before acquiring the initial operation control information of the target base station, the target spatial grid, and the communication traffic volume of the target spatial grid, the method further includes: Obtaining base station geographic coordinate information, signal coverage information, and building physical coordinate information of global base stations; Using the equal-intersection tangent cylinder method, the base station geographic coordinate information, the signal coverage range information, and the building entity coordinate information are subjected to plane transformation processing, and the spatial grid of the global base station is divided based on the plane transformation result to obtain the global base station spatial grid; The historical communication traffic volume data of each spatial grid in the global base station spatial grid is acquired, and the service time attribute of the spatial grid is determined based on the historical communication traffic volume data.

3. The method according to claim 2, It is characterized in that The acquiring of historical communication traffic data of each spatial grid in the global base station spatial grid, and determining the service time attribute of the spatial grid based on the historical communication traffic data comprises: Acquiring historical communication traffic data of each of the spatial grids; The spatial grids are clustered based on the communication traffic data corresponding to different time periods in the historical communication traffic data to obtain the service time attribute of each spatial grid.

4. The method according to claim 1, It is characterized in that The determining the target operation control information of the target base station according to at least one of the communication traffic volume prediction result, the initial operation control information, and the communication traffic volume comprises: If the initial operation control information indicates that the operation state of the target base station is dormant, determining target operation control information according to the communication traffic prediction result; If the initial operation control information indicates that the operation state of the target base station is operation, a communication traffic volume threshold is calculated according to the communication traffic volume and the initial operation control information, and target operation control information is determined according to a comparison result between the communication traffic volume and the communication traffic volume threshold.

5. The method according to claim 4, It is characterized in that The communication traffic volume prediction result includes an expected communication traffic volume sequence based on time, and if the initial operation control information indicates that the operation state of the target base station is dormant, determining the target operation control information according to the communication traffic volume prediction result includes: If the initial operation control information indicates that the operation state of the target base station is dormant, obtaining a wake-up time parameter of the target base station; Extracting the first expected communication traffic volume greater than zero in the expected communication traffic volume sequence as the target expected communication traffic volume, and taking the time corresponding to the target expected communication traffic volume as the target time; The expected start-up time of the target base station is calculated according to the target time and the wake-up time parameter, and the expected number of channel start-ups is calculated based on the target expected communication traffic volume; The target operation control information is generated according to the expected startup time and the expected number of channel startups.

6. The method according to claim 4, It is characterized in that The determining of the target operation control information according to the comparison result between the communication traffic volume and the communication traffic volume threshold comprises: If the communication traffic volume is less than the communication traffic volume threshold, the number of open channels in the initial operation control information is reduced, and the target operation control information is determined based on the reduction result; If the communication traffic volume is greater than the communication traffic volume threshold, an incremental process is performed on the number of open channels in the initial operation control information, and target operation control information is determined based on the incremental process result.

7. An operation control device for a 5G base station, It is characterized in that include: An acquisition module, used to acquire initial operation control information of a target base station, a target spatial grid, and a communication traffic volume of the target spatial grid, wherein the target spatial grid carries a service time attribute, and the service time attribute is determined based on historical communication traffic volume data of the target spatial grid; A prediction module is used to identify a target prediction network model that matches the service time attribute from the prediction network model, and perform prediction processing on the communication traffic based on the target prediction network model to obtain a communication traffic prediction result of the target space grid, specifically including: obtaining social attribute feature information of each of the target space grids; calculating the signal attraction flow of the target space grid to other space grids based on the social attribute feature information and the communication traffic data of the target space grid in different time periods; performing prediction processing on the communication traffic of the target space grid and the signal attraction flow using the target prediction network model to obtain a communication traffic prediction result of the target space grid; The calculation formula of the signal attraction flow is: Among them, the signal attraction flow is h a ; r a The total social production value of the target space grid; r all is the total social production value of the global base station spatial grid; n b is the number of global base station spatial grids; p j is the communication traffic volume of different spatial grids, i.e., the number of people holding 5G smart devices; w j is the weight of different spatial grids; r aj is the total social production value of different spatial grids; u aj is the distance from different spatial grids to the target grid; A determination module is used to determine the target operation control information of the target base station according to at least one of the communication traffic prediction result, the initial operation control information, and the communication traffic, and send the target operation control information to the target control terminal to control the operation of the target base station.

8. A storage medium, wherein at least one executable instruction is stored in the storage medium, and the executable instruction enables a processor to perform an operation corresponding to the operation control method of a 5G base station as described in any one of claims 1-6.

9. A terminal, include: A processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform an operation corresponding to the operation control method of the 5G base station as described in any one of claims 1-6.

Images