Communication management device and communication management method

Abstract

To allocate wireless resources according to requests related to communication quality of network slices with a simpler configuration.SOLUTION: A communication management device 1 includes: a first acquisition unit 10 that acquires information related to multiple network slices, the information related to the multiple network slices including request information related to communication quality associated with each of the multiple network slices; a second acquisition unit 11 that acquires an initial value of the number of resource blocks; a calculation unit 12 that gives the initial value to a learned first machine learning model as an unknown input, and executes calculation of the learned first machine learning model to output the optimized number of resource blocks allocated to each of the multiple network slices associated with the request information; and a notification unit 15 that notifies a base station 30 of the optimized number of resource blocks allocated to each of the multiple network slices.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a communication management device and a communication management method. [Background technology]

[0002] Network slicing has been known as a technology that has attracted attention in the SA (Stand Alone) 5G (5th generation mobile communication system). Network slicing virtually divides a single physical network from the Radio Access Network (RAN) such as base stations to the core network, providing networks according to usage purposes.

[0003] Each network slice virtually divided by network slicing exists on the same physical network, and radio resources are allocated based on the necessary bandwidth and communication delay requirements according to service requests, etc. Radio resources are composed of multiple resource blocks (RBs) defined on a two-dimensional plane consisting of a time axis and a frequency axis, as shown in FIG. 16. Resource blocks are blocks obtained by dividing the plane consisting of the time axis and the frequency axis into a matrix shape by the minimum unit of frequency x time. The total number of resource blocks is given by frequency (number of subcarriers) x time (number of time slots) x space (number of spatial streams).

[0004] In conventional network slicing technology, as shown in FIG. 16, multiple divided network slices #1 to N share the entire wireless resource. That is, each of the multiple network slices has a configuration that allows it to access and use all of the resource blocks on each plane. As such, in conventional technology, each network slice is not configured to have a dedicated resource block. Therefore, for example, even if a high wireless communication speed is not required in a certain network slice, a resource block with a communication speed higher than the required speed may be assigned to the network slice.

[0005] For example, Patent Document 1 discloses a communication management system that determines the amount of resources to be allocated to communication for each communication service at a base station. The communication management system according to Patent Document 1 acquires information on communication quality in one or more communication terminals communicating with the base station, which is collected for each value indicating the communication service, from the base station. Furthermore, based on the acquired information, the amount of resources to be allocated to communication for each communication service at the base station is determined, and the determined amount of resources is notified to the base station.

[0006] However, since Patent Document 1 does not have a configuration having a dedicated resource block for each network slice, the process of allocating appropriate wireless resources based on the aggregation of communication quality, required throughput, and the like becomes complicated. [Prior art documents] [Patent documents]

[0007] [Patent Document 1] Patent Publication No. 2022-117825 Summary of the Invention [Problem to be solved by the invention]

[0008] As described above, conventional technologies have been unable to allocate radio resources in accordance with requirements regarding communication quality of network slices with a simpler configuration.

[0009] The present invention has been made to solve the above-mentioned problems, and aims to allocate radio resources in accordance with requirements regarding communication quality of a network slice with a simpler configuration. [Means for solving the problem]

[0010] In order to solve the above-mentioned problems, the communication management device of the present invention comprises a first acquisition unit configured to acquire information regarding a plurality of network slices to which resource blocks, which are division units of radio resources, are assigned, wherein the information regarding the plurality of network slices includes request information regarding communication quality associated with each of the plurality of network slices; a second acquisition unit configured to acquire an initial value of the number of resource blocks of the radio resources to be assigned to each of the plurality of network slices; a first calculation unit configured to provide the initial value acquired by the second acquisition unit as an unknown input to a trained first machine learning model, perform calculations of the trained first machine learning model, and output the number of optimized resource blocks to be assigned to each of the plurality of network slices to which the request information is associated; and a notification unit configured to notify a base station of the number of optimized resource blocks to be assigned to each of the plurality of network slices.

[0011] In addition, the communication management device of the present invention further includes a first memory unit configured to store a first machine learning model that outputs a predicted value of the number of resource blocks to be allocated to each of the plurality of network slices to which the request information is associated when the initial value of the number of resource blocks to be allocated to each of the plurality of network slices is given as input, and a first learning unit configured to learn parameters of the first machine learning model so that, when the initial value is given as input, the sum of the predicted values ​​of the number of resource blocks output from the first machine learning model becomes the total number of resource blocks that constitute the wireless resource, and the first memory unit may further store the trained first machine learning model constructed by the first learning unit, and the first calculation unit may read out the trained first machine learning model from the first memory unit and perform calculations on the trained first machine learning model.

[0012] In order to solve the above-mentioned problems, the communication management device of the present invention comprises a third acquisition unit configured to acquire information regarding a network slice to which resource blocks, which are division units of radio resources, are assigned, the information regarding the network slice including requirement information regarding communication quality associated with the network slice and a set value of the number of resource blocks assigned to the network slice; a second calculation unit configured to provide the requirement information associated with the network slice and the set value of the number of resource blocks as unknown inputs to a trained second machine learning model, perform calculations of the trained second machine learning model, and output information regarding the resource blocks to be assigned to the network slice for each resource element; and a notification unit configured to notify a base station of information regarding the resource blocks for each resource element to be assigned to the network slice, the resource elements including a frequency element, a time element, and a spatial element.

[0013] In addition, the communication management device of the present invention further includes a fourth acquisition unit configured to acquire element information including a set number of elements for any one or two of the resource elements among the frequency element, the time element, and the spatial element, and a third calculation unit configured to provide the request information associated with the network slice, the set value of the number of resource blocks, and the element information as unknown inputs to a trained third machine learning model, perform calculations of the trained third machine learning model, and output information regarding the resource blocks to be allocated to the network slice for each resource element among the frequency element, the time element, and the spatial element other than the resource element related to the element information acquired by the fourth acquisition unit, and the notification unit may notify a base station of information regarding the resource blocks for each resource element other than the resource element related to the element information to be allocated to the network slice.

[0014] In addition, the communication management device of the present invention further includes a second learning unit configured to learn the relationship between the request information and the set value of the number of resource blocks associated with the network slice, and information regarding the resource blocks for each resource element assigned to the network slice using a second machine learning model, and a second memory unit configured to store the trained second machine learning model constructed by the second learning unit, and the second calculation unit may read out the trained second machine learning model from the second memory unit and perform calculations of the trained second machine learning model.

[0015] In addition, the communication management device of the present invention further includes a third learning unit configured to learn, using a third machine learning model, the relationship between the request information associated with the network slice, the set value of the number of resource blocks, and the element information, and information regarding the resource blocks to be assigned to the network slice for each resource element among the frequency element, the time element, and the spatial element other than the resource element related to the element information, and a third memory unit configured to store the trained third machine learning model constructed by the third learning unit, and the third calculation unit may read out the trained third machine learning model from the third memory unit and perform calculations of the trained third machine learning model.

[0016] In order to solve the above-mentioned problems, the communication management method of the present invention includes a first acquisition step of acquiring information regarding a plurality of network slices to which resource blocks, which are division units of radio resources, are assigned, wherein the information regarding the plurality of network slices includes request information regarding communication quality associated with each of the plurality of network slices; a second acquisition step of acquiring an initial value of the number of resource blocks of the radio resources to be assigned to each of the plurality of network slices; a first calculation step of providing the initial value acquired in the second acquisition step as an unknown input to a trained first machine learning model, performing calculations of the trained first machine learning model, and outputting the number of optimized resource blocks to be assigned to each of the plurality of network slices to which the request information is associated; and a notification step configured to notify a base station of the number of optimized resource blocks to be assigned to each of the plurality of network slices.

[0017] In addition, the communication management method of the present invention further includes a first storage step of storing in a first memory unit a first machine learning model that outputs a predicted value of the number of resource blocks to be allocated to each of the plurality of network slices to which the request information is associated when the initial value of the number of resource blocks to be allocated to each of the plurality of network slices is given as input, and a first learning step of learning parameters of the first machine learning model so that, when the initial value is given as input, the sum of the predicted values ​​of the number of resource blocks output from the first machine learning model becomes the total number of resource blocks that constitute the radio resource, and the first storage step may further store the trained first machine learning model constructed in the first learning step in the first memory unit, and the first calculation step may read out the trained first machine learning model from the first memory unit and perform calculations on the trained first machine learning model.

[0018] In addition, the communication management method of the present invention includes a third acquisition step of acquiring information regarding a network slice to which resource blocks, which are division units of radio resources, are assigned, wherein the information regarding the network slice includes requirement information regarding communication quality associated with the network slice and a set value of the number of resource blocks assigned to the network slice; a second calculation step of providing the requirement information and the set value of the number of resource blocks associated with the network slice as unknown inputs to a trained second machine learning model, performing calculations of the trained second machine learning model, and outputting information regarding the resource blocks to be assigned to the network slice for each resource element; and a notification step of notifying a base station of the information regarding the resource blocks for each resource element to be assigned to the network slice, wherein the resource elements include a frequency element, a time element, and a spatial element.

[0019] In addition, the communication management method of the present invention further includes a fourth acquisition step of acquiring element information including a set element number for any one or two of the resource elements among the frequency element, the time element, and the spatial element, and a third calculation step configured to provide the request information associated with the network slice, the set value of the number of resource blocks, and the element information as unknown inputs to a trained third machine learning model, perform calculations of the trained third machine learning model, and output information regarding resource blocks to be allocated to the network slice for each resource element among the frequency element, the time element, and the spatial element other than the resource element related to the element information acquired in the fourth acquisition step, and the notification step may notify a base station of information regarding the resource blocks to be allocated to the network slice for each resource element other than the resource element related to the element information.

[0020] In addition, the communication management method of the present invention further includes a second learning step of learning the relationship between the request information and the set value of the number of resource blocks associated with the network slice and information regarding the resource blocks for each resource element assigned to the network slice using a second machine learning model, and a second storage step of storing the trained second machine learning model constructed by the second learning step in a second memory unit, and the second calculation step may read out the trained second machine learning model from the second memory unit and perform calculations on the trained second machine learning model.

[0021] In addition, the communication management method of the present invention further includes a third learning step of learning, using a third machine learning model, the relationship between the request information, the set value of the number of resource blocks, and the element information associated with the network slice, and information regarding the resource blocks to be assigned to the network slice for each of the resource elements among the frequency elements, the time elements, and the spatial elements other than the resource elements related to the element information, and a third storage step of storing the trained third machine learning model constructed by the third learning step in a third memory unit, and the third calculation step may read out the trained third machine learning model from the third memory unit and perform calculations on the trained third machine learning model. Effect of the Invention

[0022] According to the present invention, an initial value of the number of resource blocks of the wireless resources to be allocated to each of the plurality of network slices is provided as an unknown input to a trained first machine learning model, and the trained first machine learning model is operated to output an optimized number of resource blocks to be allocated to each of the plurality of network slices associated with the request information. Therefore, with a simpler configuration, wireless resources can be allocated in accordance with a request regarding the communication quality of the network slices. [Brief description of the drawings]

[0023] [Figure 1] FIG. 1 is a block diagram showing a configuration of a communication management system including a communication management device according to a first embodiment of the present invention. [Diagram 2] FIG. 2 is a diagram for explaining an overview of the communication management device according to the first embodiment. [Diagram 3] FIG. 3 is a block diagram illustrating a hardware configuration of the communication management device according to the first embodiment. As illustrated in FIG. [Figure 4] FIG. 4 is a diagram for explaining the learning process by the learning unit according to the first embodiment. [Diagram 5] FIG. 5 is a flowchart illustrating the operation of the communication management device according to the first embodiment. [Figure 6] FIG. 6 is a flowchart illustrating the operation of the communication management device according to the first embodiment. [Figure 7] FIG. 7 is a block diagram showing a configuration of a communication management system including a communication management device according to the second embodiment. [Figure 8] FIG. 8 is a diagram for explaining the learning process by the learning unit according to the second embodiment. [Figure 9] FIG. 9 is a diagram illustrating an overview of a communication management device according to the second embodiment. [Figure 10] FIG. 10 is a flowchart showing the operation of the communication management device according to the second embodiment. [Figure 11] FIG. 11 is a flowchart illustrating the operation of the communication management device according to the second embodiment. [Figure 12] FIG. 12 is a block diagram showing a configuration of a communication management system including a communication management device according to the third embodiment. [Figure 13] FIG. 13 is a diagram for explaining the learning process by the learning unit according to the third embodiment. [Figure 14] FIG. 14 is a flowchart showing the operation of the communication management device according to the third embodiment. [Figure 15]FIG. 15 is a flowchart illustrating the operation of the communication management device according to the third embodiment. [Figure 16] FIG. 16 is a diagram for explaining network slicing according to a conventional example. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0024] BEST MODE FOR CARRYING OUT THE PRESENT DISCLOSURE Hereinafter, preferred embodiments of the present invention will be described in detail with reference to FIGS.

[0025] [First embodiment] 1 is a block diagram showing a configuration of a communication management system including a communication management device 1 according to a first embodiment of the present invention. The communication management device 1 according to the present embodiment determines an optimized number of resource blocks to be allocated to each of network slices associated with request information regarding communication quality, and notifies a base station 30 of resource block allocation information.

[0026] [Communication management system configuration] First, an overview of a communication management system including a communication management device 1 according to an embodiment of the present invention will be described. As shown in Fig. 1, the communication management system includes, for example, a communication management device 1 that supports a 5G wireless communication system using the SA method, a communication terminal 2, a wireless access network 3 including a base station 30, and a core network 4.

[0027] The communication management device 1 and the core network 4 are connected via a network NW such as a LAN or a WAN. Furthermore, the base station 30 included in the wireless access network 3 and the core network 4 are connected via a network L such as a backhaul link. Furthermore, as an example in FIG. 1, the communication management device 1 and the base station 30 are connected via the network NW, but the communication management device 1 and the base station 30 may be configured to be connected via a dedicated communication network. Alternatively, the connection between the communication management device 1 and the base station 30 via the network NW can be omitted.

[0028] The communication terminal 2 may be a mobile communication terminal such as a smartphone equipped with a SIM, a PDA (Personal Digital Assistant), a tablet computer, or a laptop computer (a so-called notebook computer).The communication terminal 2 may also be an IoT device that has a unique IP address and can connect to the Internet.

[0029] The communication terminal 2 communicates with the core network 4 via the radio access network 3, and requests a service from the core network 4. Specifically, the communication terminal 2 sets an identifier indicating service characteristics according to the service to be used, and transmits it to the core network 4 via the radio access network 3. The communication terminal 2 communicates with the core network 4 using a resource block in a network slice according to the requested service, and is able to connect to an appropriate data network and perform data communication related to the service.

[0030] For the service requested by the communication terminal 2, a different network slice is set for each purpose. For example, a network slice that supports high speed and large capacity, a network slice that supports multiple simultaneous connections, a network slice that supports high reliability and low latency, etc. are provided. That is, each network slice requires a certain communication quality such as an appropriate communication speed and communication latency according to the purpose. In this embodiment, it is assumed that a preset number of network slices are set according to the service type and characteristics.

[0031] In addition, each network slice is assigned a unique network slice ID, which is associated with requirements regarding communication quality such as communication delay, bandwidth, and reliability, as well as information regarding security policies and authentication requirements.

[0032] The wireless access network 3 includes a plurality of base stations 30, and enables communication between a communication terminal 2 located within the coverage area of ​​each base station 30 and a core network 4.

[0033] The base station 30 is composed of a wireless base station compatible with the 5G system, and relays communications between the communication terminal 2 located within its coverage area and the core network 4. The base station 30 can be realized, for example, by a computer including a processor, a main memory device, a communication interface, an auxiliary memory device, and an input / output I / O device connected via a bus, and a program that controls these hardware resources.

[0034] The base station 30 receives an identifier indicating the service type and characteristics of the service used by the communication terminal 2 from the communication terminal 2, and transmits it to the core network 4. The base station 30 according to this embodiment also receives notification of allocation information of resource blocks to be allocated to each network slice from the communication management device 1. Furthermore, the base station 30 according to this embodiment allocates resource blocks to the network slice based on the allocation information notified from the communication management device 1. Furthermore, the base station 30 allocates resource blocks in the network slice according to the service to the communication terminal 2 based on the identifier indicating the service type and characteristics.

[0035] The core network 4 is configured, for example, by a 5G core network of the SA system. The core network 4 illustrated in FIG. 1 includes a Network Slice Selection Function (NSSF) 40 and an Access and Mobility Management Function (AMF) 41, and other devices and functions are omitted from the illustration.

[0036] The NSSF 40 is a network function that selects a network slice to be used by the communication terminal 2 when the communication terminal 2 connects to the core network 4 via the base station 30. The NSSF 40 selects available network slice candidates based on the type and characteristics of the service requested by the communication terminal 2, contract information, location information, terminal information, and the like, and notifies the AMF 41.

[0037] The AMF 41 is a network function that performs registration, updating, and mobility management of the location information and connection state of the communication terminal 2. The AMF 41 also selects and manages a network slice to be used by the communication terminal 2 based on available network slice candidates notified by the NSSF 40. Information on the network slice selected by the AMF 41 is notified to the base station 30.

[0038] [Communication management device functional block] As shown in FIG. 1, the communication management device 1 includes a first acquisition unit 10, a second acquisition unit 11, a learning unit (first learning unit) 12, a calculation unit (first calculation unit) 13, a memory unit (first memory unit) 14, and a notification unit 15.

[0039] The first acquisition unit 10 acquires information on a plurality of network slices to which resource blocks, which are division units of radio resources, are assigned. The information on the plurality of network slices acquired by the first acquisition unit 10 includes requirement information on communication quality associated with each network slice. The requirement information includes requirements on communication quality including communication delay, bandwidth, reliability, and the like.

[0040] The second acquisition unit 11 acquires an initial value of the number of resource blocks of the wireless resource to be assigned to each of the plurality of network slices. The second acquisition unit 11 can acquire the initial value of the number of resource blocks from an external server or the like via the network NW, for example. Alternatively, the second acquisition unit 11 can acquire the initial value of the number of resource blocks by accepting an input operation performed by a user. The initial value of the number of resource blocks of the wireless resource to be assigned to each of the plurality of network slices can be, for example, an approximate number of resource blocks that a user who manages and operates a wireless communication network desires to assign to each network slice. In addition, the initial value of the number of resource blocks can be set, for example, based on the total number of resource blocks set in the wireless resource.

[0041] The learning unit 12 learns parameters of the first machine learning model so that the sum of predicted values ​​of the number of resource blocks output from the first machine learning model becomes the total number of resource blocks constituting the wireless resource when an initial value of the number of resource blocks to be allocated to a plurality of network slices is given as an input. In addition, the learning unit 12 reads out the first machine learning model before learning stored in the first model storage unit 140 of the storage unit 14 and performs a learning process. As described above, the total number of resource blocks is a value given by frequency (number of subcarriers) × time (number of time slots) × space (number of spatial streams).

[0042] The first machine learning model learned by the learning unit 12 outputs a predicted value of the number of resource blocks to be allocated to each of the multiple network slices associated with the request information when an initial value of the number of resource blocks to be allocated to each of the multiple network slices is given as an input. The learning unit 12 can use the initial value of the number of resource blocks acquired by the second acquisition unit 11 as data for learning.

[0043] 4 shows a neural network structure adopted as an example of a first machine learning model for learning by the learning unit 12. The neural network includes an input layer x, a hidden layer h, and an output layer y. In the example of FIG. 4, the number of input nodes and the number of output nodes are the same, and these correspond to N network slices that are set in advance according to the number of services, etc.

[0044] The learning unit 12 provides the number of resource blocks to be assigned to each network slice to the input layer of the neural network, applies an activation function to the weighted sum of the inputs, and passes the output determined by threshold processing to the output layer. As shown in FIG. 4, each input node x 1 ~x N The initial value of the number of resource blocks (RB) from network slices #1 to #N is input to each output node y 1 ~y N is the neural network's prediction for the input value.

[0045] The size and elements of the machine learning model, including the number of layers in the hidden layer h and the density of the connections between nodes in the neural network, are not limited as long as the design provides sufficient inference accuracy. For example, the connections between nodes may be fully connected or sparsely connected.

[0046] The learning unit 12 further introduces an objective function that evaluates the error between the total number of resource blocks in the wireless resource and the neural network's predicted value y, and learns the parameters of the neural network so that the sum of the predicted values ​​of the number of resource blocks in each network slice becomes the total number of resource blocks that make up the wireless resource.

[0047] The learning unit 12 adjusts the weight parameters of the neural network so that the objective function E expressed by the following equation (1) is minimized, that is, becomes zero. E = {(y 1 +y 2 +y 3 +···+y N-1 +y N )-Total number of RBs} 2 (1) As the objective function, mean square error, cross entropy, cross covariance, structural similarity, clustering loss, etc. can be adopted. The learning unit 12 can optimize the objective function by a gradient method using an error backpropagation method, a stochastic gradient descent method, etc.

[0048] Returning to Figure 1, the calculation unit 13 provides the initial value of the number of resource blocks to be allocated to each network slice acquired by the second acquisition unit 11 as an unknown input to the trained first machine learning model, performs calculations of the trained first machine learning model, and outputs an optimized number of resource blocks to be allocated to each of the multiple network slices associated with the requirement information regarding communication quality.

[0049] As mentioned above, the initial value of the number of resource blocks to be assigned to each network slice acquired by the second acquisition unit 11 may not be the optimal number of resource blocks in relation to the total number of resource blocks and the communication quality that each network slice should satisfy.

[0050] For example, if the total number of resource blocks is 300, the initial value of the number of resource blocks for network slice #1 shown in FIG. 4 is 30, and the initial value of the number of resource blocks for network slice #2 is 40. By providing such initial values ​​of the number of resource blocks as input to the trained first machine learning model and performing calculations of the trained first machine learning model, the optimal number of resource blocks for each network slice is output in terms of the total number of resource blocks and the communication quality that each network slice should satisfy. For example, the optimized number of resource blocks for network slice #1 is 32, and the optimized initial number of resource blocks for network slice #2 is 38, etc. are output.

[0051] FIG. 2 is a schematic diagram showing resource blocks allocated to each network slice. FIG. 2 shows a two-dimensional plane in which radio resources are defined by a time axis and a frequency axis, and a spatial axis. As shown in FIG. 2, radio resources are divided into resource blocks consisting of time slots and subcarriers. In this embodiment, as shown in each hatched area from "NW slice #1" to "NW slice #N" in FIG. 2, a dedicated resource block is allocated on a network slice basis. In addition, an optimized number of resource blocks is allocated to each network slice by the learning process by the learning unit 12 and the calculation of the trained first machine learning model by the calculation unit 13.

[0052] More specifically, for example, in a 2×2 MIMO configuration with two transmit antennas and two receive antennas, spatial streams s are arranged along the spatial axis of FIG. 1 , s 2Therefore, the spatial stream s 1 In addition, spatial streams 2 The optimized number of resource blocks in

[0053] In addition, in this embodiment, when the optimized number of resource blocks calculated by the calculation unit 13 is allocated to the network slices, the range of allocatable resource blocks can be set in advance for each network slice. For example, as shown in FIG. 2, the network slices from "NW slice #1" to "NW slice #N" are each assigned to the time slot t 1 ~t k In addition, the subcarrier f can be used in the order of "NW slice #1" to "NW slice #N". 1 From f k The resource blocks can be allocated in the order of

[0054] In this manner, in this embodiment, it is possible to set in advance the range of resource blocks to be allocated to each network slice. Therefore, based on the optimal number of resource blocks output by the calculation unit 13, it is possible to allocate an optimized number of resource blocks in a predetermined frequency range, for example, in the order of "NW slice #1" to "NW slice #N".

[0055] Returning to Fig. 1, the storage unit 14 includes a first model storage unit 140. The storage unit 14 stores information about the network slice acquired by the first acquisition unit 10. The storage unit 14 also stores request information about communication quality associated with the network slice ID of the network slice.

[0056] The first model storage unit 140 stores the first machine learning model before learning and the first machine learning model after learning.

[0057] The notification unit 15 notifies the base station 30 of the number of optimized resource blocks to be allocated to each of the multiple network slices. Specifically, the notification unit 15 can associate the optimized number of resource blocks output by the calculation unit 13 with a network slice ID and notify the base station 30 via the network NW.

[0058] [Hardware configuration of communication management device] Next, an example of a hardware configuration for realizing the communication management device 1 having the above-mentioned functions will be described with reference to FIG.

[0059] As shown in Figure 3, the communication management device 1 can be realized, for example, by a computer having a processor 102, a main memory device 103, a communication interface 104, an auxiliary memory device 105, and an input / output (I / O) 106 connected via a bus 101, and a program that controls these hardware resources.

[0060] The main memory device 103 prestores programs for the processor 102 to perform various controls and calculations. The processor 102 and the main memory device 103 realize the functions of the communication management device 1, such as the first acquisition unit 10, the second acquisition unit 11, the learning unit 12, and the calculation unit 13 shown in FIG.

[0061] The communication interface 104 is an interface circuit for connecting the communication management device 1 to various external electronic devices via a network.

[0062] The auxiliary storage device 105 is composed of a readable / writable storage medium and a drive for reading and writing various information such as programs and data from and to the storage medium. The auxiliary storage device 105 can use a semiconductor memory such as a hard disk or a flash memory as the storage medium.

[0063] The auxiliary storage device 105 has a program storage area for storing the communication management program executed by the communication management device 1. The auxiliary storage device 105 also has an area for storing a learning program for learning the first machine learning model. The auxiliary storage device 105 realizes the storage unit 14 described in FIG. 1. Furthermore, the auxiliary storage device 105 may have, for example, a backup area for backing up the above-mentioned data, programs, and the like.

[0064] The input / output I / O 106 is an input / output device that inputs signals from an external device and outputs signals to an external device.

[0065] [Operation of the communication management device] Next, the operation of the communication management device 1 having the above-mentioned configuration will be described with reference to the flowcharts of FIG. 5 and FIG.

[0066] First, the learning process by the communication management device 1 will be described with reference to Fig. 5. First, the first acquisition unit 10 acquires information on a plurality of network slices to which resource blocks, which are division units of radio resources, are assigned (step S1). The information on the plurality of network slices acquired in step S1 includes request information on communication quality associated with each network slice.

[0067] Next, the second acquisition unit 11 acquires an initial value of the number of resource blocks to be assigned to each of the multiple network slices (step S2). Next, the learning unit 12 learns parameters of the first machine learning model so that the sum of the predicted values ​​of the number of resource blocks output from the first machine learning model becomes the total number of resource blocks constituting the wireless resource when the initial value acquired in step S2 is given as an input (step S3). Specifically, the learning unit 12 reads out the first machine learning model stored in the first model storage unit 140 of the storage unit 14 and performs a learning process.

[0068] The learning unit 12 employs, for example, a model of the neural network structure shown in FIG. 4 as the first machine learning model, and adjusts weight parameters of the neural network so that the objective function E expressed by the above formula (1) is minimized, that is, becomes 0. The learning unit 12 can optimize the objective function by a gradient method using backpropagation, stochastic gradient descent, or the like. The trained first machine learning model constructed by the learning unit 12 is stored in the first model storage unit 140 (step S4).

[0069] Next, the calculation process by the communication management device 1 will be described with reference to Fig. 6. First, the second acquisition unit 11 acquires an initial value of the number of resource blocks to be allocated to each network slice (step S10). Next, the calculation unit 13 loads the trained first machine learning model from the first model storage unit 140 (step S11).

[0070] Next, the calculation unit 13 provides the initial value of the number of resource blocks to be allocated to each network slice, acquired by the second acquisition unit 11 in step S10, as an unknown input to the trained first machine learning model, performs calculations of the trained first machine learning model, and outputs an optimized number of resource blocks to be allocated to each of the multiple network slices associated with the requirement information regarding communication quality (step S12).

[0071] Thereafter, the notification unit 15 notifies the base station 30 of the optimized number of resource blocks to be allocated to each of the network slices output in step S12 (step S13).

[0072] The base station 30 that has received the notification sets and registers the optimized number of resource blocks in association with the network slice ID of each network slice. The base station 30 allocates resource blocks in the network slice corresponding to the communication quality requirement to the communication terminal 2 that uses a predetermined service based on the number of resource blocks associated with the network slice ID. Furthermore, the notification unit 15 can allocate resource blocks for each network slice on a base station 30 basis.

[0073] As described above, according to the communication management device 1 of the first embodiment, the trained first machine learning model is used to output an optimized number of resource blocks to be allocated to each of multiple network slices associated with requirement information regarding communication quality, so that wireless resources can be allocated in accordance with requirements regarding communication quality of the network slices with a simpler configuration.

[0074] Moreover, the communication management device 1 according to the first embodiment outputs an optimized number of resource blocks to be allocated to a plurality of network slices associated with the request information regarding communication quality, so that it is possible to allocate dedicated resource blocks according to a Quality of Service (QoS) request on a network slice basis. Furthermore, it is possible to allocate resource blocks for each network slice according to a QoS request on a base station 30 basis.

[0075] Furthermore, according to the communication management device 1 according to the first embodiment, the first machine learning model is trained to learn the total number of resource blocks and the number of resource blocks optimized for the communication quality required for each network slice, relative to the initial value of the number of resource blocks. Therefore, it is possible to reduce the database capacity without requiring a huge database capacity due to the association of the number of subcarriers, the number of time slots, and the number of spatial streams, which are resource parameters of wireless resources using the network slice ID as a key.

[0076] [Second embodiment] Next, a second embodiment of the present invention will be described. In the following description, the same components as those in the first embodiment are given the same reference numerals, and the description thereof will be omitted.

[0077] In the first embodiment, a case has been described in which an optimized number of resource blocks relative to the total number of resource blocks is obtained for an initial value of the number of resource blocks to be allocated to each of a plurality of network slices. In contrast, in the second embodiment, when the number of resource blocks to be allocated to each network slice is assigned as a fixed value, resource block allocation information for the network slice is obtained for each resource element including a frequency element, a time element, and a space element of a radio resource.

[0078] [Communication management device functional block] 7 is a block diagram showing a configuration of a communication management device 1A according to the second embodiment. The communication management device 1A includes a learning unit (second learning unit) 12A, a calculation unit (second calculation unit) 13A, a storage unit (second storage unit) 14A, a notification unit 15, and a third acquisition unit 16.

[0079] First, the third acquisition unit 16 acquires information about a network slice to which resource blocks, which are division units of radio resources, are assigned. The information about the network slice acquired by the third acquisition unit 16 includes request information about communication quality associated with the network slice. In addition, the information about the network slice acquired by the third acquisition unit 16 includes a setting value of the number of resource blocks assigned to the network slice. The setting value of the number of resource blocks is the number of resource blocks to be assigned to the network slice, which is set in advance as a fixed value.

[0080] The learning unit 13A learns the relationship between the request information and the set value of the number of resource blocks associated with the network slice and the information regarding the resource blocks for each resource element of the radio resource to be allocated to the network slice using a second machine learning model.

[0081] The resource elements include subcarriers (frequency elements) on the frequency axis, time slots (time elements) on the time axis, and spatial streams (spatial elements) on the spatial axis that define the radio resource. Using the example of FIG. 2, the subcarriers f 1 ~f k , and time slot t on the time axis 1 ~t k In addition, the spatial stream s in the spatial axis shown in Fig. 2 is included in the resource element. 1 , s 2 is included in the resource element.

[0082] In this way, the number and value of each resource element are determined by the subcarrier f 1 ~f k , time slot t on the time axis 1 ~t k , and the spatial stream s in the spatial axis 1 , s 2 It can be expressed as a number and value of

[0083] FIG. 8 shows a neural network structure adopted as an example of a second machine learning model for learning by the learning unit 12A. The neural network includes an input layer x, a hidden layer h, and an output layer y. In the example of FIG. 8, a "NW slice ID" which is a network slice ID of a network slice and request information on communication quality associated with the "NW slice ID" are input to the input node. 1 ~y m corresponds to the values ​​of the "frequency element f", the "time element t", and the "spatial element s".

[0084] For example, the output node for "frequency element f" is subcarrier f on the frequency axis.1 ~f k The output node corresponding to time slot t is the output node for time element t. 1 ~t k and the output node for the spatial element s, 1 , s 2 It is possible to provide output nodes corresponding to the above-mentioned resource elements. The number of each resource element of the output node can be determined in advance.

[0085] The learning unit 12A provides the network slice ID of the network slice, required information regarding communication quality associated with the network slice ID, and a set value for the number of resource blocks to the input layer of the neural network, applies an activation function to the weighted sum of the inputs, and passes the output determined by threshold processing to the output layer.

[0086] The learning unit 12A further introduces an objective function that evaluates the error between the value of the correct label and the output value y of the neural network, and learns the parameters of the neural network so that the network slice ID of the network slice, the required information regarding communication quality associated with the network slice ID, and the setting value of the number of resource blocks become the value of the frequency element f, the value of the time element t, and the value of the spatial element s of the correct label.

[0087] The learning unit 12A learns the neural network using training data in which the value of the frequency element f, the value of the time element t, and the value of the spatial element s of the correct answer label are assigned to the input values ​​of the required information regarding communication quality associated with the network slice ID and the set value of the number of resource blocks.

[0088] The learning unit 12A adjusts the weight parameters of the neural network so that the objective function is minimized, that is, becomes 0. The learning unit 12A can optimize the objective function by a gradient method using backpropagation, stochastic gradient descent, or the like. The trained second machine learning model constructed by the learning unit 12A is stored in a second model storage unit 141 described later.

[0089] 7, the calculation unit 13A provides the trained second machine learning model with the required information on the communication quality associated with the network slice and the set value of the number of resource blocks as unknown inputs, performs calculations on the trained second machine learning model, and outputs information on the resource blocks to be assigned to the network slice for each resource element. The calculation unit 13A reads out the trained second machine learning model from the second model storage unit 141 and performs calculations. The information on the resource blocks for each resource element output by the calculation unit 13A is passed to the notification unit 15.

[0090] As shown in Fig. 9, in this embodiment, in a two-dimensional plane of radio resources formed by a time axis and a frequency axis, resource blocks in which the order of frequencies or time slots is not consecutive can be assigned to each network slice. In Fig. 9, the resource blocks in each hatched area indicate the resource blocks assigned to each network slice. Note that in Fig. 9, the spatial stream s on the spatial axis 1 , s 2 is omitted in the illustration.

[0091] The storage unit 14A includes a second model storage unit 141. The storage unit 14A stores information about resource blocks acquired by the third acquisition unit 16, request information about communication quality associated with the network slice, and a setting value of the number of resource blocks allocated to the network slice.

[0092] The second model storage unit 141 stores the trained second machine learning model constructed by the training unit 12A.

[0093] The notification unit 15 notifies the base station 30 of information on resource blocks for each resource element to be allocated to the network slice. More specifically, the notification unit 15 notifies the base station 30 of information on resource blocks identified by frequency elements, time elements, and space elements calculated by the calculation unit 13A.

[0094] [Operation of the communication management device] Next, the operation of the communication management device 1A having the above-mentioned configuration will be described with reference to the flowcharts of Fig. 10 and Fig. 11. Fig. 10 is a flowchart showing the learning process by the communication management device 1A. Fig. 11 is a flowchart showing the calculation process by the communication management device 1A.

[0095] First, as shown in Fig. 10, the learning unit 12A prepares training data (step S20). More specifically, the learning unit 12A performs training using training data in which information on resource blocks expressed by values ​​of frequency elements, values ​​of time elements, and values ​​of space elements is given as a correct answer label for input values ​​of required information on communication quality associated with a network slice ID and a set value of the number of resource blocks.

[0096] Next, the learning unit 12A learns the relationship between the request information on the communication quality associated with the network slice and the setting value of the number of resource blocks, and the information on the resource blocks for each resource element to be assigned to the network slice, using a second machine learning model (step S21). The learning unit 12A learns the second machine learning model using the teacher data prepared in step S20.

[0097] Next, the second model storage unit 141 stores the trained second machine learning model constructed in step S21 (step S22).

[0098] 11, the third acquisition unit 16 acquires information about a network slice to which resource blocks, which are division units of radio resources, are assigned (step S30). The information about the network slice acquired by the third acquisition unit 16 in step S30 includes request information about communication quality associated with the network slice and a setting value for the number of resource blocks assigned to the network slice.

[0099] Next, the calculation unit 13A loads the trained second machine learning model from the second model storage unit 141 (step S31). Then, the calculation unit 13A provides the trained second machine learning model with the required information on the communication quality associated with the network slice and the setting value of the number of resource blocks as unknown inputs, performs calculations on the trained second machine learning model, and outputs information on the resource blocks to be assigned to the network slice for each resource element (step S32).

[0100] Next, the notification unit 15 notifies the base station 30 of information on the resource blocks for each resource element to be allocated to the network slice obtained in step S32 (step S33). The notification unit 15 can notify the base station 30 of information on the resource blocks identified by the values ​​of the frequency element, the time element, and the space element associated with the network slice ID. Upon receiving the notification, the base station 30 allocates and registers the specific resource blocks related to the notification to the network slice related to the network slice ID.

[0101] As described above, according to the communication management device 1A of the second embodiment, the request information on the communication quality associated with the network slice ID and the setting value of the number of resource blocks are provided as unknown inputs to the trained second machine learning model, and the trained second machine learning model is operated to output information on the resource blocks to be assigned to the network slice for each resource element including a frequency element, a time element, and a space element. Therefore, it is possible to assign resource blocks specified by the value of the frequency element, the value of the time element, and the value of the space element to a network slice to which a fixed setting value of the number of resource blocks is assigned.

[0102] In addition, according to the communication management device 1A of the second embodiment, information regarding resource blocks to be allocated to a network slice is output for each resource element including frequency elements, time elements, and spatial elements, so that more appropriate resource blocks can be allocated to the network slice in response to requirements regarding communication quality.

[0103] [Third embodiment] Next, a third embodiment of the present invention will be described. In the following description, the same components as those in the first and second embodiments are given the same reference numerals, and the description thereof will be omitted.

[0104] In the second embodiment, a case has been described in which information on resource blocks for each resource element including a frequency element, a time element, and a space element is obtained when the number of resource blocks is fixedly assigned to the network slice. In contrast, in the third embodiment, information on resource blocks for each other resource element to be assigned to the network slice is obtained when information on any one or two of the frequency element, the time element, and the space element is fixed.

[0105] [Communication management device functional block] As shown in Fig. 12, communication management device 1B according to the present embodiment includes a learning unit (third learning unit) 12B, a calculation unit (third calculation unit) 13B, a memory unit (third memory unit) 14B, a notification unit 15, a third acquisition unit 16, and a fourth acquisition unit 17. Communication management device 1B according to the third embodiment differs in configuration from communication management device 1A according to the second embodiment in that it further includes fourth acquisition unit 17. The following description will focus on the configuration that differs from the second embodiment.

[0106] First, the fourth acquisition unit 17 acquires element information including the set element numbers for any one or two resource elements of the frequency element, the time element, and the space element. For example, the fourth acquisition unit 17 can acquire the number of subcarriers on the frequency axis when the frequency element is set as a fixed value. Alternatively, the fourth acquisition unit 17 can acquire the number of time slots on the time axis when the time element is set as a fixed value. Similarly, the fourth acquisition unit 17 can acquire the number of spatial streams on the space axis that is set as a fixed value.

[0107] In addition to the number of frequency elements, time elements, and space elements, the fourth acquisition unit 17 acquires the number of subcarriers f 1 ~f k The value of t 1 ~t k and the spatial stream s 1 , s 2 etc. may be obtained.

[0108] The learning unit 12B uses a third machine learning model to learn the relationship between the requirement information regarding the communication quality associated with the network slice, the set value of the number of resource blocks to be allocated to the network slice, and the element information acquired by the fourth acquisition unit 17, and information regarding resource blocks to be allocated to the network slice for each resource element, among frequency elements, time elements, and spatial elements, other than the resource elements related to the element information acquired by the fourth acquisition unit 17.

[0109] 13 shows a neural network structure adopted as an example of the third machine learning model for learning by the learning unit 12B. The neural network includes an input layer x, a hidden layer h, and an output layer y. In the example of FIG. 13, the input node x 1 The “NW slice ID”, which is the network slice ID of a specific network slice, the required information regarding the communication quality associated with the “NW slice ID”, and the number of resource blocks set as a fixed value are input.

[0110] In the example of Figure 13, input node x 2 ~x l The value of the "spatial element s" acquired by the fourth acquisition unit 17 is input to the output node y 1 ~y m corresponds to the value of "frequency element f" and "time element t". For example, the subcarrier f on the frequency axis is used as the output node of "frequency element f". 1 ~f k The output node corresponding to time slot t is the output node for time element t. 1 ~t k It is possible to provide output nodes corresponding to the above-mentioned resource elements. The number of each resource element of the output node can be determined in advance.

[0111] The learning unit 12B provides the network slice ID of the network slice, required information regarding communication quality associated with the network slice ID, the set value of the number of resource blocks, and element information of the resource elements acquired by the fourth acquisition unit 17 to the input layer of the neural network, applies an activation function to the weighted sum of the inputs, and passes the output determined by threshold processing to the output layer.

[0112] The learning unit 12B further introduces an objective function that evaluates the error between the value of the correct label and the output value y of the neural network, and learns the parameters of the neural network so that the network slice ID of the network slice, the requirement information regarding the communication quality associated with the network slice ID, the set value of the number of resource blocks, and the element information of the spatial element become the value of the frequency element f and the value of the time element t of the correct label.

[0113] The learning unit 12B learns the request information on communication quality associated with the network slice ID, the setting value of the number of resource blocks, and the value s of the spatial element s, which is element information. 1 , s 2 The neural network is trained using training data in which the value of the frequency element f and the value of the time element t are assigned as correct labels for the input values.

[0114] The learning unit 12B adjusts the weight parameters of the neural network so that the objective function is minimized, that is, becomes 0. The learning unit 12B can optimize the objective function by a gradient method using backpropagation, stochastic gradient descent, or the like. The trained third machine learning model constructed by the learning unit 12B is stored in a third model storage unit 142 described later.

[0115] Returning to Figure 12, the calculation unit 13B provides the required information regarding the communication quality associated with the network slice, the set value of the number of resource blocks to be assigned to the network slice as a fixed value, and element information of the resource elements as unknown inputs to the trained third machine learning model, and performs calculations of the trained third machine learning model to output information regarding the resource blocks to be assigned to the network slice for each resource element, among the frequency elements, time elements, and spatial elements, other than the resource elements related to the element information acquired by the fourth acquisition unit 17.

[0116] The storage unit 14B includes a third model storage unit 142. The storage unit 14B stores element information of one or two of the frequency element, the time element, and the space element acquired by the fourth acquisition unit 17.

[0117] The third model storage unit 142 stores the trained third machine learning model constructed by the training unit 12B.

[0118] The notification unit 15 notifies the base station 30 of information on resource blocks for each resource element to be allocated to the network slice. More specifically, the notification unit 15 notifies the base station 30 of information on resource blocks indicated by the values ​​of the resource elements calculated by the calculation unit 13B.

[0119] [Operation of the communication management device] Next, the operation of the communication management device 1B having the above-mentioned configuration will be described with reference to the flowcharts of Fig. 14 and Fig. 15. Fig. 14 is a flowchart showing the learning process by the communication management device 1B. Fig. 15 is a flowchart showing the calculation process by the communication management device 1B.

[0120] First, as shown in Fig. 14, the learning unit 12B acquires element information (step S200). More specifically, in step S200, element information on any one or two resource elements of a frequency element, a time element, and a space element to be assigned as a fixed value to a network slice is acquired. The learning unit 12B can acquire the element information acquired by the fourth acquisition unit 17.

[0121] Next, the learning unit 12B prepares teacher data to be used in the learning process (step S201). Specifically, the learning unit 12B prepares teacher data in which, for input values ​​including request information on communication quality associated with the network slice, a setting value for the number of resource blocks to be set as a fixed value, and element information of the resource element to be set as a fixed value, values ​​of resource elements other than the resource element to be set as a fixed value are given as correct answer labels.

[0122] Next, the learning unit 12B learns, using a third machine learning model, the relationship between the requirement information regarding the communication quality associated with the network slice, the setting value for the number of resource blocks to be set as a fixed value, and element information of the resource elements to be set as fixed values, and information regarding resource blocks to be assigned to the network slice for each resource element among the frequency elements, time elements, and spatial elements other than the resource elements related to the element information to be set as a fixed value (step S202).

[0123] The third model storage unit 142 stores the trained third machine learning model constructed in step S202 (step S203).

[0124] 15, the third acquisition unit 16 acquires information about the network slice to which the resource blocks are allocated (step S300). The information about the network slice acquired by the third acquisition unit 16 in step S300 includes required information about the communication quality associated with the network slice and a setting value of the number of resource blocks allocated to the network slice.

[0125] Next, the fourth acquisition unit 17 acquires element information including the set element number for any one or two resource elements among the frequency element, the time element, and the space element (step S301). Using the example of FIG. 13, in step S301, the fourth acquisition unit 17 acquires the spatial stream s 1 , s 2 The number of spatial streams s 1 , s 2 You can get the value of

[0126] Next, the calculation unit 13B loads the trained third machine learning model from the third model storage unit 142 (step S302). Next, the calculation unit 13B provides the trained third machine learning model with the requirement information on the communication quality associated with the network slice, the setting value of the number of resource blocks to be assigned to the network slice as a fixed value, and the element information of the resource elements as unknown inputs, performs calculations on the trained third machine learning model, and outputs information on the resource blocks to be assigned to the network slice for each resource element other than the resource element related to the element information acquired by the fourth acquisition unit 17 in step S301 among the frequency elements, time elements, and space elements (step S303).

[0127] 13, in step S303, the element information including the request information on the communication quality associated with the network slice ID, the number of resource blocks set as a fixed value, and the number of spatial elements s set as a fixed value is provided as an unknown input to the trained third machine learning model. The calculation unit 13B performs calculations on the trained third machine learning model and outputs information on the resource blocks given by the value of the frequency element f and the value of the time element t.

[0128] Next, the notification unit 15 notifies the base station 30 of the information on the resource blocks for each resource element obtained in step S303 (step S304). The base station 30 that receives the notification allocates and registers the resource blocks to the network slice. According to the example of Fig. 13, the notification unit 15 can notify the base station 30 of the value of the frequency element f and the value of the time element t associated with the network slice ID.

[0129] As described above, according to the communication management device 1B of the third embodiment, the request information on the communication quality associated with the network slice ID, the set value of the number of resource blocks, and the element information of the resource element set as a fixed value are provided as unknown inputs to the trained third machine learning model, and the trained third machine learning model is operated to output information on the resource blocks to be assigned to the network slice for each resource element other than the resource element set as a fixed value among the frequency element, the time element, and the space element. Therefore, it is possible to assign resource blocks identified by the values ​​of the resource elements other than the resource elements set as fixed values ​​to a network slice to which the set value of the number of resource blocks and a specific resource element are fixedly assigned.

[0130] In the above-mentioned third embodiment, as illustrated in FIG. 13, the element information on the spatial element as one resource element among the frequency element, the time element, and the space element is acquired as a fixed value, and the values ​​on the remaining frequency element and the time element are obtained. However, as described above, the resource element set as the input node of the third machine learning model may be a frequency element or a time element. Furthermore, the resource element set as the input node of the third machine learning model may be not only one type of resource element, but also two resource elements selected from three resource elements may be set as fixed values. In this case, the value of the remaining one resource element is output by the calculation unit 13B.

[0131] In the above embodiment, the first machine learning model, the second machine learning model, and the third machine learning model are each described as a neural network model having an input layer, a hidden layer, and an output layer. As the neural network model employed as the second machine learning model and the third machine learning model, a recurrent neural network (RNN) or a deep multimodal neural network can be used.

[0132] Furthermore, the first machine learning model, the second machine learning model, and the third machine learning model may use, in addition to the above-mentioned neural network model, logistic regression, random forest, decision tree, or deep learning with a multi-layered neural network. In addition to these supervised learning models, generative models such as a generative adversarial network and a variational autoencoder may be used as machine learning models that perform unsupervised learning.

[0133] In the above embodiment, a communication management system that complies with 5G has been described as an example, but the communication management system may also be one that complies with LTE or 6G.

[0134] The above describes the embodiments of the communication management device and communication management method of the present invention, but the present invention is not limited to the described embodiments, and various modifications that a person skilled in the art can imagine may be made within the scope of the invention described in the claims. [Explanation of symbols]

[0135] 1...communication management device, 10...first acquisition unit, 11...second acquisition unit, 12...learning unit, 13...calculation unit, 14...memory unit, 15...notification unit, 2...communication terminal, 3...radio access network, 30...base station, 4...core network, NSSF...40, AMF...41, 101...bus, 102...processor, 103...main memory device, 104...communication interface, 105...auxiliary memory device, 106...input / output I / O, 140...first model memory unit, L, NW...network.

Claims

1. a first acquisition unit configured to acquire information regarding a plurality of network slices to which resource blocks, which are division units of radio resources, are assigned, the information regarding the plurality of network slices including requirement information regarding communication quality associated with each of the plurality of network slices; a second acquisition unit configured to acquire an initial value of the number of resource blocks of the radio resources to be assigned to each of the plurality of network slices; a first calculation unit configured to provide the initial value acquired by the second acquisition unit as an unknown input to a trained first machine learning model, perform calculations on the trained first machine learning model, and output an optimized number of resource blocks to be assigned to each of the plurality of network slices with which the request information is associated; and a notification unit configured to notify a base station of the number of the optimized resource blocks to be assigned to each of the plurality of network slices; A communication management device comprising:

2. 2. The communication management device according to claim 1, Further, a first memory unit configured to store a first machine learning model that outputs a predicted value of the number of resource blocks to be allocated to each of the plurality of network slices associated with the request information when the initial value of the number of resource blocks to be allocated to each of the plurality of network slices is given as an input; and a first learning unit configured to learn parameters of the first machine learning model such that, when the initial value is provided as an input, the sum of the predicted values ​​of the number of the resource blocks output from the first machine learning model becomes the total number of the resource blocks constituting the wireless resource; Equipped with The first storage unit further stores the trained first machine learning model constructed by the first learning unit, The first calculation unit reads out the trained first machine learning model from the first storage unit and performs a calculation of the trained first machine learning model. A communication management device comprising:

3. a third acquisition unit configured to acquire information regarding a network slice to which a resource block, which is a division unit of a radio resource, is assigned, the information regarding the network slice including required information regarding a communication quality associated with the network slice and a setting value of the number of the resource blocks assigned to the network slice; a second calculation unit configured to provide the request information associated with the network slice and the setting value of the number of resource blocks as unknown inputs to a trained second machine learning model, perform calculations on the trained second machine learning model, and output information on the resource blocks to be allocated to the network slice for each resource element; a notification unit configured to notify a base station of information regarding the resource blocks for each of the resource elements to be assigned to the network slice; Equipped with The resource elements include a frequency element, a time element, and a spatial element. A communication management device comprising:

4. 4. The communication management device according to claim 3, A fourth acquisition unit configured to acquire element information including a set number of elements for any one or two of the resource elements among the frequency element, the time element, and the space element; a third calculation unit configured to provide the request information associated with the network slice, the setting value for the number of resource blocks, and the element information as unknown inputs to a trained third machine learning model, perform calculations on the trained third machine learning model, and output information regarding the resource blocks to be assigned to the network slice for each resource element among the frequency elements, the time elements, and the spatial elements other than the resource elements related to the element information acquired by the fourth acquisition unit; Equipped with The notification unit notifies the base station of information regarding the resource block for each of the resource elements other than the resource element related to the element information, which is to be assigned to the network slice. A communication management device comprising:

5. 4. The communication management device according to claim 3, a second learning unit configured to learn, using a second machine learning model, a relationship between the request information and the set value of the number of resource blocks associated with the network slice, and information about the resource blocks for each of the resource elements assigned to the network slice; and a second storage unit configured to store the trained second machine learning model constructed by the second learning unit; and Equipped with The second calculation unit reads out the trained second machine learning model from the second storage unit and performs calculations on the trained second machine learning model. A communication management device comprising:

6. 5. The communication management device according to claim 4, a third learning unit configured to learn, using a third machine learning model, a relationship between the request information associated with the network slice, the setting value of the number of resource blocks, and the element information, and information on the resource blocks to be assigned to the network slice for each of the resource elements other than the resource element related to the element information among the frequency element, the time element, and the space element; a third storage unit configured to store the trained third machine learning model constructed by the third learning unit; and Equipped with The third calculation unit reads out the trained third machine learning model from the third storage unit and performs calculations on the trained third machine learning model. A communication management device comprising:

7. a first acquisition step of acquiring information about a plurality of network slices to which resource blocks, which are division units of radio resources, are assigned, the information about the plurality of network slices including requirement information regarding communication quality associated with each of the plurality of network slices; a second acquisition step of acquiring an initial value of the number of resource blocks of the radio resources to be assigned to each of the plurality of network slices; a first calculation step of providing the initial value acquired in the second acquisition step as an unknown input to a trained first machine learning model, performing calculations on the trained first machine learning model, and outputting an optimized number of resource blocks to be allocated to each of the plurality of network slices with which the request information is associated; a notification step configured to notify a base station of the number of the optimized resource blocks to be assigned to each of the plurality of network slices; A communication management method comprising:

8. 8. The communication management method according to claim 7, Further, a first storage step of storing in a first storage unit a first machine learning model that outputs a predicted value of the number of resource blocks to be allocated to each of the plurality of network slices associated with the request information when the initial value of the number of resource blocks to be allocated to each of the plurality of network slices is given as an input; and a first learning step of learning parameters of the first machine learning model so that, when the initial value is given as an input, the sum of the predicted values ​​of the number of resource blocks output from the first machine learning model becomes the total number of the resource blocks constituting the wireless resource; Equipped with The first storage step further includes storing the trained first machine learning model constructed in the first learning step in the first storage unit; The first calculation step reads out the trained first machine learning model from the first storage unit and performs a calculation of the trained first machine learning model. A communication management method comprising:

9. a third acquisition step of acquiring information about a network slice to which a resource block, which is a division unit of a radio resource, is assigned, the information about the network slice including required information about communication quality associated with the network slice and a set value of the number of the resource blocks assigned to the network slice; a second calculation step of providing the request information associated with the network slice and the set value of the number of resource blocks to a trained second machine learning model as unknown inputs, performing calculations on the trained second machine learning model, and outputting information on the resource blocks to be assigned to the network slice for each resource element; a notification step of notifying a base station of information regarding the resource blocks for each of the resource elements to be allocated to the network slice; Equipped with The resource elements include a frequency element, a time element, and a spatial element. A communication management method comprising:

10. 10. The method of claim 9, further comprising: Further, a fourth acquisition step of acquiring element information including a set number of elements for any one or two of the resource elements among the frequency element, the time element, and the space element; a third calculation step configured to provide the request information associated with the network slice, the setting value for the number of resource blocks, and the element information as unknown inputs to a trained third machine learning model, perform calculations on the trained third machine learning model, and output information regarding the resource blocks to be assigned to the network slice for each resource element among the frequency elements, the time elements, and the spatial elements other than the resource elements related to the element information acquired in the fourth acquisition step; Equipped with The notification step notifies the base station of information on the resource blocks for each of the resource elements other than the resource elements related to the element information, the resource blocks being assigned to the network slice. A communication management method comprising:

11. 10. The method of claim 9, further comprising: Further, a second learning step of learning a relationship between the request information and the set value of the number of resource blocks associated with the network slice, and information about the resource blocks for each of the resource elements assigned to the network slice, using a second machine learning model; a second storage step of storing the trained second machine learning model constructed by the second learning step in a second storage unit; Equipped with The second calculation step reads out the trained second machine learning model from the second storage unit and performs a calculation of the trained second machine learning model. A communication management method comprising:

12. The method of managing communications according to claim 10, Further, a third learning step of learning, using a third machine learning model, a relationship between the request information associated with the network slice, the setting value of the number of resource blocks, and the element information, and information on the resource blocks to be assigned to the network slice for each of the resource elements other than the resource element related to the element information among the frequency element, the time element, and the space element; a third storage step of storing the trained third machine learning model constructed by the third learning step in a third storage unit; Equipped with The third calculation step reads out the trained third machine learning model from the third storage unit and performs a calculation of the trained third machine learning model. A communication management method comprising:

Images