Slice resource configuration method and device in 5G short slice communication private network

Abstract

The invention relates to a slice resource configuration method and device in a 5G short slice communication private network, and belongs to the technical field of wireless communication.The slice resource configuration method in the 5G short slice communication private network comprises the steps that slice resource use information of a target terminal in a preset time period is acquired; taking the preprocessed slice resource use information as the input of a slice resource configuration model, and based on the output of the slice resource configuration model, performing slice resource configuration on the target terminal; wherein the slice resource configuration model is obtained by training based on historical slice resource use information of a plurality of sample terminals and slice resource configuration information corresponding to the plurality of sample terminals, wherein the slice resource configuration information is marked manually. According to the invention, the slice resource configuration efficiency in the 5G short slice communication private network is improved, and the slice resource configuration cost is reduced.

Description

Technical Field

[0001] The present invention relates to the field of wireless communication technologies, and in particular to a method and device for configuring slice resources in a 5G short slice communication private network. Background Art

[0002] The 5G short-slice communication private network is a wireless communication private network that integrates 5G short slicing / 5G short multiplexing / 4G short multiplexing. It achieves shared access with telecom operators' base stations by slicing the air interface of the 5G wireless base station, using the shortest short slicing mode with the same route as the public network, and multiplexing the data on the same route for 4G / 5G wireless base stations.

[0003] At present, 5G short-slice communication private networks have been widely used in the field of power communication due to their advantages such as security, reliability, strong coverage, low cost, and strong scalability. However, the slice resource configuration in 5G short-slice communication private networks is mainly completed by business personnel in advance according to business needs, which requires high labor costs and is inefficient.

[0004] Therefore, how to improve the efficiency of slice resource allocation in 5G short-slice communication private networks and reduce the cost of slice resource allocation has become a technical problem that needs to be solved urgently. Summary of the invention

[0005] In view of this, it is necessary to provide a slice resource configuration method and device in a 5G short slice communication private network to solve the problems of low efficiency and high cost of slice resource configuration in the 5G short slice communication private network.

[0006] In order to solve the above problems, the present invention provides a method for configuring slice resources in a 5G short slice communication private network, comprising: Obtain slice resource usage information of the target terminal within a preset time period; Using the preprocessed slice resource usage information as an input of a slice resource configuration model, and performing slice resource configuration on the target terminal based on an output of the slice resource configuration model; The slice resource configuration model is trained based on historical slice resource usage information of multiple sample terminals and manually annotated slice resource configuration information corresponding to the multiple sample terminals.

[0007] In a possible implementation manner, the acquiring slice resource usage information of the target terminal within a preset time period includes: Obtain the average slice resource usage information of the target terminal every hour within a preset time period.

[0008] In a possible implementation, the preprocessing of the slice resource usage information includes: The slice resource usage information is filtered, denoised and normalized.

[0009] In a possible implementation manner, filtering the slice resource usage information includes: The slice resource usage information is filtered based on a sliding window filtering algorithm.

[0010] In one possible implementation, the slice resource configuration model is an LTSM model with an added attention mechanism.

[0011] In one possible implementation, the attention mechanism is used to assign weights to input features of the slice resource configuration model based on the hidden state of the LSTM model and the input features of the slice resource configuration model.

[0012] In a possible implementation, the slice resource usage information includes: The transmission bandwidth, transmission latency and resource utilization of slice resources.

[0013] The present invention also provides a slice resource configuration device in a 5G short slice communication private network, comprising: An acquisition module is used to obtain slice resource usage information of a target terminal within a preset time period; a configuration module, configured to use the preprocessed slice resource usage information as an input of a slice resource configuration model, and perform slice resource configuration on the target terminal based on an output of the slice resource configuration model; The slice resource configuration model is trained based on historical slice resource usage information of multiple sample terminals and manually annotated slice resource configuration information corresponding to the multiple sample terminals.

[0014] The present invention also provides an electronic device, including a memory and a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the slice resource configuration method in the 5G short slice communication private network as described above is implemented.

[0015] The present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the slice resource configuration method in the 5G short slice communication private network as described above is implemented.

[0016] The beneficial effect of the present invention is as follows: the slice resource configuration method and device in the 5G short slice communication private network provided by the present invention obtains a slice resource configuration model through training of historical slice resource usage information of multiple sample terminals and slice resource configuration information corresponding to multiple manually labeled sample terminals, and then uses the slice resource usage information of the target terminal within a preset time period as the input of the slice resource configuration model, and performs slice resource configuration on the target terminal according to the output of the slice resource configuration model, thereby improving the slice resource configuration efficiency in the 5G short slice communication private network and reducing the cost of slice resource configuration. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A schematic diagram of a flow chart of an embodiment of a method for configuring slice resources in a 5G short slice communication private network provided by the present invention; Figure 2 A schematic diagram of a flow chart of an embodiment of a slice resource configuration process provided by the present invention; Figure 3 A structural diagram of an embodiment of a slice resource configuration device in a 5G short slice communication private network provided by the present invention; Figure 4 A schematic structural diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The preferred embodiments of the present invention are described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not used to limit the scope of the present invention.

[0019] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0020] In the description of the present invention, reference to an "embodiment" means that a particular feature, structure, or characteristic described in conjunction with the embodiment may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive of other embodiments. It is explicitly and implicitly understood by those skilled in the art that the described embodiments may be combined with other embodiments.

[0021] The 5G short-slice communication private network is a wireless communication private network that integrates 5G short slicing / 5G short multiplexing / 4G short multiplexing. It achieves shared access with telecom operators' base stations by slicing the air interface of the 5G wireless base station, using the shortest short slicing mode with the same route as the public network, and multiplexing the data on the same route for 4G / 5G wireless base stations.

[0022] At present, 5G short-slice communication private networks have been widely used in the field of power communication due to their advantages such as security, reliability, strong coverage, low cost, and strong scalability. However, the slice resource configuration in 5G short-slice communication private networks is mainly completed by business personnel in advance according to business needs, which requires high labor costs and is inefficient.

[0023] In order to solve the above problems, the present invention provides a slice resource configuration method in a 5G short slice communication private network.

[0024] The specific embodiments are described in detail below: A specific embodiment of the present invention discloses a slice resource configuration method in a 5G short slice communication private network, combining Figure 1 Come and see, Figure 1 A flow chart of an embodiment of a method for configuring slice resources in a 5G short slice communication private network provided by the present invention includes step S101 and step S102, wherein: In step S101, slice resource usage information of a target terminal within a preset time period is obtained; In step S102, the preprocessed slice resource usage information is used as an input of a slice resource configuration model, and slice resource configuration is performed on the target terminal based on an output of the slice resource configuration model; The slice resource configuration model is trained based on historical slice resource usage information of multiple sample terminals and manually annotated slice resource configuration information corresponding to the multiple sample terminals.

[0025] During implementation, the slice resource usage information of the target terminal within a preset time period can be obtained first. The preset time period can be one week or one month. During the preset time period, redundant slice resource configuration can be performed on the target terminal to fully obtain the slice resource usage information of the target terminal. The slice resource usage information of the target terminal can be parameters such as transmission bandwidth and latency.

[0026] Then, the slice resource usage information of the target terminal within a preset time period can be preprocessed, and then the preprocessed slice resource usage information is used as the input of the slice resource configuration model, and slice resources are configured for the target terminal according to the output of the slice resource configuration model.

[0027] The slice resource configuration model is trained based on the historical slice resource usage information of multiple sample terminals and the slice resource configuration information corresponding to multiple sample terminals that are manually labeled. During manual labeling, the slice resource configuration information corresponding to multiple sample terminals can be labeled as good or bad, and the labeling is based on manual judgment on the rationality of the slice resource configuration information.

[0028] The slice resource configuration method in the 5G short slice communication private network provided by the present invention can be applied to power communication scenarios, and can also be applied to other scenarios using 5G short slice communication private networks. The present invention does not make specific limitations on this.

[0029] Compared with the prior art, the slice resource configuration method in the 5G short slice communication private network provided in this embodiment obtains a slice resource configuration model through training of historical slice resource usage information of multiple sample terminals and slice resource configuration information corresponding to multiple manually labeled sample terminals. Then, the slice resource usage information of the target terminal within a preset time period is used as the input of the slice resource configuration model, and slice resources are configured for the target terminal according to the output of the slice resource configuration model, thereby improving the slice resource configuration efficiency in the 5G short slice communication private network and reducing the cost of slice resource configuration.

[0030] Exemplarily, the acquiring slice resource usage information of the target terminal within a preset time period includes: Obtain the average slice resource usage information of the target terminal every hour within a preset time period.

[0031] Specifically, when obtaining the slice resource usage information of the target terminal in the preset time period, the average slice resource usage information of the target terminal per hour in the preset time period can be obtained. In addition, if higher configuration accuracy is sought, the average slice resource usage information of the target terminal per minute in the preset time period can also be obtained, and the present invention does not specifically limit this.

[0032] Exemplarily, the preprocessing of the slice resource usage information includes: The slice resource usage information is filtered, denoised and normalized.

[0033] Specifically, when preprocessing the slice resource usage information, the slice resource information may be filtered, denoised and normalized in sequence to reduce the computational complexity of subsequent model data processing. When normalizing, maximum and minimum normalization or mean normalization may be used, which is not specifically limited in the present invention.

[0034] Exemplarily, filtering the slice resource usage information includes: The slice resource usage information is filtered based on a sliding window filtering algorithm.

[0035] Specifically, when filtering the slice resource usage information, a sliding window filtering algorithm can be used to filter the slice resource usage information, thereby retaining the information in each timestamp in the slice resource usage information and improving the accuracy of subsequent slice resource configuration.

[0036] Exemplarily, the slice resource configuration model is an LTSM model with an added attention mechanism.

[0037] Specifically, the slice resource configuration model can be an LTSM model with an added attention mechanism, which can be used to assign weights to the input features of the slice resource model to further improve the accuracy of slice resource configuration.

[0038] Exemplarily, the attention mechanism is used to assign weights to the input features of the slice resource configuration model based on the hidden state of the LSTM model and the input features of the slice resource configuration model.

[0039] Specifically, when weights are assigned to the input features of the slice resource configuration model according to the attention mechanism, weights can be assigned to the input features of the slice resource configuration model according to the hidden state of the LSTM model at each time step and the input features of the slice resource configuration model.

[0040] Exemplarily, the slice resource usage information includes: The transmission bandwidth, transmission latency and resource utilization of slice resources.

[0041] Specifically, the slice resource usage information of the target terminal may include the transmission bandwidth, transmission delay and resource utilization of the slice resources. Through this information, the slice resources can be configured more reasonably.

[0042] The following is a specific application scenario to better illustrate the technical solution of the present invention: Combination Figure 2 Come and see, Figure 2 This is a flow chart of an embodiment of a slice resource configuration process provided by the present invention, and the process includes the following steps: 1. Acquisition of training data.

[0043] The historical slice resource usage information and slice resource configuration information of multiple sample terminals are obtained from the transmission management system, and the rationality of these slice resource configuration information is manually annotated, such as marking good or bad, to obtain training data.

[0044] 2. Model training.

[0045] The slice resource configuration model is trained with historical slice resource usage information of multiple sample terminals as model input and manually annotated slice resource configuration information as labels, wherein the slice resource configuration model is an LSTM model with an attention mechanism added. The attention mechanism is used to assign weights to the input features of the slice resource configuration model. When assigning weights to the input features of the slice resource configuration model according to the attention mechanism, weights can be assigned to the input features of the slice resource configuration model according to the hidden state of the LSTM model at each time step and the input features of the slice resource configuration model.

[0046] 3. Obtaining target terminal slice resource usage information.

[0047] Get the average slice resource usage information of the target terminal every hour within a month.

[0048] 4. Target terminal slice resource configuration.

[0049] The average slice resource usage information of the target terminal every hour in a month is used as the input of the slice resource configuration model, and slice resources are configured for the target terminal through the output of the slice resource configuration model.

[0050] The embodiment of the present invention also provides a slice resource configuration device in a 5G short slice communication private network, Figure 3 Come and see, Figure 3 The present invention is a structural diagram of an embodiment of a slice resource configuration device in a 5G short slice communication private network provided by the present invention. The slice resource configuration device 300 in a 5G short slice communication private network includes: The acquisition module 301 is used to obtain the slice resource usage information of the target terminal within a preset time period; A configuration module 302 is configured to use the preprocessed slice resource usage information as an input of a slice resource configuration model, and perform slice resource configuration on the target terminal based on an output of the slice resource configuration model; The slice resource configuration model is trained based on historical slice resource usage information of multiple sample terminals and manually annotated slice resource configuration information corresponding to the multiple sample terminals.

[0051] The specific implementation methods of each module of the slice resource configuration device in the 5G short slice communication private network can refer to the description of the slice resource configuration method in the above-mentioned 5G short slice communication private network, and have similar beneficial effects, which will not be repeated here.

[0052] The embodiment of the present invention further provides an electronic device, Figure 4 Come and see, Figure 4This is a structural diagram of an embodiment of an electronic device provided by the present invention. The electronic device 400 includes a processor 401, a memory 402, and a computer program stored in the memory 402 and executable on the processor 401. When the processor 401 executes the program, the slice resource configuration method in the 5G short slice communication private network as described above is implemented.

[0053] As a preferred embodiment, the above-mentioned electronic device 400 also includes a display 403, which is used to display that the processor 401 executes the slice resource configuration method in the 5G short slice communication private network as described above.

[0054] Exemplarily, the computer program may be divided into one or more modules / units, one or more modules / units are stored in the memory 402, and executed by the processor 401 to complete the present invention. One or more modules / units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program in the electronic device 400. For example, the computer program may be divided into the acquisition module 301 and the configuration module 302 in the above embodiment, and the specific functions of each module are as described above, and are not described one by one here.

[0055] The electronic device 400 may be a desktop computer, a notebook, a PDA or a smart phone with an adjustable camera module.

[0056] Among them, the processor 401 may be an integrated circuit chip with signal processing capabilities. The above-mentioned processor 401 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0057] The memory 402 may be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electric erasable programmable read-only memory (EEPROM), etc. The memory 402 is used to store programs, and the processor 401 executes the program after receiving the execution instruction. The process definition method disclosed in any of the embodiments of the present invention may be applied to the processor 401 or implemented by the processor 401.

[0058] The display 403 may be an LCD display screen or an LED display screen, for example, a display screen on a mobile phone.

[0059] Understandably, Figure 4 The structure shown is only a schematic diagram of a structure of the electronic device 400. The electronic device 400 may also include Figure 4 More or fewer components as shown. Figure 4 Each component shown in the figure can be implemented by hardware, software or a combination thereof.

[0060] The electronic device provided according to the above embodiment of the present invention can be implemented with reference to the specific description of the slice resource configuration method in the 5G short slice communication private network as described above according to the present invention, and has similar beneficial effects as the slice resource configuration method in the 5G short slice communication private network as described above, which will not be repeated here.

[0061] An embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the slice resource configuration method in the 5G short slice communication private network as described above is implemented.

[0062] Generally speaking, the computer instructions for implementing the method of the present invention can be carried by any combination of one or more computer-readable storage media. Non-transitory computer-readable storage media can include any computer-readable media except for the signal itself that is temporarily propagating.

[0063] Computer-readable storage media may be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium that contains or stores a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0064] Computer program codes for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages, in particular, Python suitable for neural network computing and platform frameworks based on TensorFlow, PyTorch, etc. may be used. The program code may be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0065] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0066] The present invention discloses a method and device for slice resource configuration in a 5G short slice communication private network. A slice resource configuration model is obtained by training with historical slice resource usage information of multiple sample terminals and slice resource configuration information corresponding to multiple manually labeled sample terminals. Then, the slice resource usage information of the target terminal within a preset time period is used as the input of the slice resource configuration model, and slice resource configuration is performed on the target terminal according to the output of the slice resource configuration model, thereby improving the slice resource configuration efficiency in the 5G short slice communication private network and reducing the cost of slice resource configuration.

[0067] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention.

Claims

1. A method for configuring slice resources in a 5G short slice communication private network, characterized in that: include: Obtain slice resource usage information of the target terminal within a preset time period; Using the preprocessed slice resource usage information as an input of a slice resource configuration model, and performing slice resource configuration on the target terminal based on an output of the slice resource configuration model; The slice resource configuration model is trained based on historical slice resource usage information of multiple sample terminals and manually annotated slice resource configuration information corresponding to the multiple sample terminals.

2. The method for configuring slice resources in a 5G short slice communication private network according to claim 1, characterized in that: The obtaining slice resource usage information of the target terminal within a preset time period includes: Obtain the average slice resource usage information of the target terminal every hour within a preset time period.

3. The method for configuring slice resources in a 5G short slice communication private network according to claim 2, characterized in that: The preprocessing of the slice resource usage information includes: The slice resource usage information is filtered, denoised and normalized.

4. The method for configuring slice resources in a 5G short slice communication private network according to claim 3, characterized in that: The filtering the slice resource usage information includes: The slice resource usage information is filtered based on a sliding window filtering algorithm.

5. The method for configuring slice resources in a 5G short slice communication private network according to claim 1, characterized in that: The slice resource configuration model is an LTSM model with an added attention mechanism.

6. The method for configuring slice resources in a 5G short slice communication private network according to claim 5, characterized in that: The attention mechanism is used to assign weights to the input features of the slice resource configuration model based on the hidden state of the LSTM model and the input features of the slice resource configuration model.

7. The method for configuring slice resources in a 5G short slice communication private network according to any one of claims 1 to 6, characterized in that: The slice resource usage information includes: The transmission bandwidth, transmission latency and resource utilization of slice resources.

8. A slice resource configuration device in a 5G short slice communication private network, characterized in that: include: An acquisition module is used to obtain slice resource usage information of a target terminal within a preset time period; a configuration module, configured to use the preprocessed slice resource usage information as an input of a slice resource configuration model, and perform slice resource configuration on the target terminal based on an output of the slice resource configuration model; The slice resource configuration model is trained based on historical slice resource usage information of multiple sample terminals and manually annotated slice resource configuration information corresponding to the multiple sample terminals.

9. An electronic device, characterized in that: It includes a memory and a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the slice resource configuration method in the 5G short slice communication private network according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the slice resource configuration method in the 5G short slice communication private network is implemented as described in any one of claims 1 to 7.

Images