Communication control device and communication control method

Abstract

The aim is to reduce communication delays among multiple user terminals through a simpler configuration. [Solution] The communication control device 1 includes a calculation unit 13 that provides information of multiple base stations 3 where each of the multiple user terminals 2 is located as unknown input to a trained machine learning model, performs calculations on the trained machine learning model, and outputs network configuration information for a destination cloud 5 that suppresses communication delays with the multiple user terminals 2, which is one of multiple clouds 5 that are data final processing nodes to which the multiple user terminals 2 can connect; and a communication control unit 14 that instructs the core network 4 to set up a data communication path between each of the multiple user terminals 2 and the destination cloud 5 based on the network configuration information output by the calculation unit 13.

Description

Technical Field

[0001] The present invention relates to a communication control device and a communication control method.

Background Art

[0002] Conventionally, in a mobile communication network, MEC (Multi-access Edge Computing), which is a technique for providing a cloud computing function at a location physically close to a user terminal, is known (see Patent Document 1).

[0003] In the technique described in Patent Document 1, for each user terminal, a user plane function (UPF) of a core network for suppressing the delay of data communication is set. Therefore, even when a plurality of user terminals connect to a cloud that provides the same website, or when data communication is performed between a plurality of user terminals, edge computing considering the delay of the overall transmission time of the plurality of user terminals has not been performed.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] Conventional techniques have not been able to suppress the communication delay of a plurality of user terminals with a simpler configuration. [[ID=?]]

[0006] The present invention has been made to solve the above-described problems, and an object thereof is to suppress the communication delay of a plurality of user terminals with a simpler configuration.

Means for Solving the Problems

[0007] It seems there is a missing ID in the original text where it says " " which is not translated correctly in the provided solution. The above translation is based on the correct translation rules applied to the rest of the text.To solve the above-mentioned problems, the communication control device according to the present invention comprises a calculation unit configured to provide a trained machine learning model with information of multiple base stations in which each of the multiple user terminals is located as unknown input, perform calculations on the trained machine learning model, and output network setting information relating to a destination data processing device that suppresses communication delay with the multiple user terminals, among a plurality of data processing devices which are data final processing nodes to which the multiple user terminals can connect; and a communication control unit configured to instruct the core network to set a data communication path between each of the multiple user terminals and the destination data processing device based on the network setting information output by the calculation unit.

[0008] Furthermore, the communication control device according to the present invention further includes a learning unit configured to learn, using a machine learning model, the relationship between a combination of the plurality of base stations in which each of the plurality of user terminals is located and the network setting information relating to the data processing device to which the plurality of user terminals can connect, which suppresses the delay of communication with the plurality of user terminals; and a storage unit configured to store the learned machine learning model constructed by the learning unit, wherein the calculation unit may read the learned machine learning model stored in the storage unit and perform calculations.

[0009] Furthermore, the communication control device according to the present invention further includes an acquisition unit configured to acquire information of the multiple base stations in which each of the multiple user terminals is located, based on a location registration request signal transmitted when each of the multiple user terminals is in the area of ​​the multiple base stations, and the calculation unit may use the information of the multiple base stations acquired by the acquisition unit as the unknown input.

[0010] Furthermore, in the communication control device according to the present invention, the location registration request signal is associated with a group identifier of the group to which the plurality of user terminals belong, the acquisition unit acquires the group identifier associated with the location registration request signal in association with the information of the plurality of base stations, the storage unit stores the group identifier in association with the trained machine learning model, and the communication control unit may specify the plurality of user terminals having the group identifier and instruct the core network to set up the data communication path between each of the plurality of user terminals and the data processing device to which it is connected.

[0011] Furthermore, in the communication control device according to the present invention, the network setting information may include information on the destination data processing device which is located at a position where the physical distance from the base stations is shorter for each of the plurality of user terminals, and a common user plane function for the data communication of each of the plurality of user terminals can be set based on the information of the destination data processing device.

[0012] To solve the above-mentioned problems, the communication control method according to the present invention comprises a calculation step of providing information of multiple base stations in which each of the multiple user terminals is located as unknown input to a trained machine learning model, performing calculations on the trained machine learning model, and outputting network setting information relating to a destination data processing device that suppresses communication delay with the multiple user terminals, among a plurality of data processing devices which are data final processing nodes to which the multiple user terminals can connect; and a communication control step of instructing the core network to set up a data communication path between each of the multiple user terminals and the destination data processing device based on the network setting information output in the calculation step.

[0013] Furthermore, the communication control method according to the present invention further includes a learning step in which a machine learning model is used to learn the relationship between a combination of a plurality of base stations in which each of the plurality of user terminals is located and the network setting information relating to the data processing device to which the plurality of user terminals can connect, which suppresses the delay of communication with the plurality of user terminals; and a storage step in which the learned machine learning model constructed in the learning step is stored in a storage unit, and the calculation step may read the learned machine learning model stored in the storage unit and perform calculations.

[0014] Furthermore, the communication control method according to the present invention further includes an acquisition step in which each of the plurality of user terminals is located, based on a location registration request signal transmitted when each of the plurality of user terminals is located at one of the plurality of base stations, and the calculation step may use the information of the plurality of base stations acquired in the acquisition step as the unknown input.

[0015] Furthermore, in the communication control method according to the present invention, the location registration request signal is associated with a group identifier of the group to which the plurality of user terminals belong, the acquisition step acquires the group identifier associated with the location registration request signal by associating it with the information of the plurality of base stations, the storage step stores the group identifier in the storage unit by associating it with the trained machine learning model, and the communication control step may instruct the core network to set up the data communication path between each of the plurality of user terminals and the data processing device to which it is connected by specifying the plurality of user terminals having the group identifier.

[0016] Furthermore, in the communication control method according to the present invention, the network setting information may include information on the destination data processing device which is located at a position where the physical distance from the base stations is shorter for each of the plurality of user terminals, and a common user plane function for the data communication of each of the plurality of user terminals may be set based on the information of the destination data processing device. [Effects of the Invention]

[0017] According to the present invention, information on multiple base stations in which each of multiple user terminals is located is provided as unknown input to a trained machine learning model. The trained machine learning model performs calculations and outputs network configuration information for a data processing device to which the multiple user terminals can connect, which is a data final processing node that the multiple user terminals can connect to, thereby suppressing the delay in communication with the multiple user terminals. Therefore, the delay in communication between multiple user terminals can be suppressed with a simpler configuration. [Brief explanation of the drawing]

[0018] [Figure 1] Figure 1 is a block diagram showing the configuration of a communication control system equipped with a communication control device according to an embodiment of the present invention. [Figure 2] Figure 2 is a diagram illustrating the configuration of the first storage unit of the communication control device according to this embodiment. [Figure 3] Figure 3 is a diagram illustrating the learning process performed by the learning unit of the communication control device according to this embodiment. [Figure 4] Figure 4 is a block diagram showing the hardware configuration of the communication control device according to this embodiment. [Figure 5] Figure 5 is a sequence diagram illustrating the operation of a communication control system equipped with a communication control device according to this embodiment. [Figure 6] Figure 6 is a flowchart illustrating the operation of the communication control device according to this embodiment. [Figure 7]FIG. 7 is a flowchart for explaining the operation of the communication control device according to the present embodiment.

Embodiments for Carrying Out the Invention

[0019] Hereinafter, preferred embodiments of the present invention will be described in detail with reference to FIGS. 1 to 7.

[0020] [Configuration of Communication Control System] First, referring to FIG. 1, an overview of a communication control system including a communication control device 1 according to an embodiment of the present invention will be described.

[0021] The communication control system according to the present embodiment includes a communication control device 1, user terminals 2, a base station 3, a core network 4, and a cloud (data processing device) 5. The communication control system is provided in a 5G mobile communication network. The communication control system predicts a specific cloud 5 that further suppresses communication delay among a plurality of clouds 5 to which each of the plurality of user terminals 2 can be connected via a base station 3 where each user terminal 2 is located. Further, an optimal UPF 44 for connecting to the specific cloud 5 is set for each of the plurality of user terminals 2. The communication control device 1 is connected to the core network 4 via a network NW.

[0022] The user terminal 2 is realized as a mobile communication terminal such as a smartphone, a tablet computer, a laptop computer, etc. The user terminal 2 includes a SIM, and the SIM contract profile stores the subscriber identification information of the user, including an identifier information such as a subscriber identification number (IMSI: International Mobile Subscriber Identity) assigned to the mobile phone line contract, the phone number (MSISDN: Mobile Subscriber International Subscriber Directory Number) of the user who is the subscriber, and the SIM card number (ICCID: Integrated Circuit Card Identifier). The user terminal 2 is uniquely identified by the IMSI.

[0023] Each user terminal 2 is also assigned a terminal IP address that uniquely identifies the terminal. The IP address is assigned to the user terminal 2 via SMF42 after the session is established. In this embodiment, there are N user terminals 2 (where N is a positive integer greater than or equal to 2). User terminals 2-1, 2-2, ..., 2-N are each located in the communication area of ​​a different base station 3. Each user terminal 2 accesses a specific cloud 5 from a designated UPF44 via the base station 3 in which it is located. In this embodiment, multiple user terminals 2 are pre-grouped based on predetermined attributes and assigned a group ID (group identifier). The predetermined attributes can be defined by arbitrary criteria, such as multiple user terminals 2 managed by the same organization or QoS requirements.

[0024] User terminal 2 transmits a location registration request signal to the core network 4 via base station 3 when moving within the communication area, as a periodic location update, and when powered on. The location registration request signal transmitted by user terminal 2 includes the IMSI.

[0025] Base station 3 is a wireless base station compatible with the 5G system and relays communication between user terminals 2 located in the communication area and the core network 4. Base station 3 is connected to the core network 4 via a network such as a backhaul link. There are N base stations 3 (where N is an integer of 2 or more). Hereinafter, when base stations 3-1, 3-2, ..., 3-N are not distinguished from each other, they will be collectively referred to as "base station 3". Base station 3 is uniquely identified by its base station ID. The base station ID also allows for the determination of the geographical location of base station 3. That is, the base station ID and location information consisting of the latitude, longitude, and altitude of the location where base station 3 is installed are associated and stored in the auxiliary storage device 105 of the communication control device 1 described later.

[0026] The core network 4 is connected to the communication control device 1 via a network NW such as a LAN, WAN, or the Internet. The core network 4 includes nodes within the C-plane, namely AMF (Access and Mobility Management Function) 40, UDM (Unified Data Management) / UDR (Unified Data Repository) 41, SMF (Session Management Function) 42, and PCF (Policy Control Function) 43. The core network 4 also includes multiple UPF (User Plane Function) 44 within the U-plane. Functional nodes within the U-plane and C-plane that are included in the core network 4 other than those mentioned above are not shown in the diagram.

[0027] The AMF40 is an access and mobility management device that manages the registration and wireless connection of user terminals 2 that have moved to each communication area.

[0028] The UDM / UDR41 manages subscriber profiles, performs authentication, and manages mobility. In this embodiment, the UDM / UDR41 stores a group ID assigned to each IMSI in the subscriber profile. The UDM / UDR41 is equipped with a communication interface 41a for communicating with the communication control device 1.

[0029] Furthermore, in response to instructions from the communication control device 1, the UDM / UDR41 creates and stores a configuration information table T1, as shown in Figure 2, which associates the IMSI, group ID, base station ID, UPF44 communication path set in the data communication of the user terminals 2, and the destination cloud 5 with each other. The instructions from the communication control device 1 include grouping information that associates multiple IMSIs and group IDs of the controlled targets specified in advance. The IP address value of the UPF44 in the configuration information table T1 is registered after the communication path is set by the SMF42 and PCF43 described later. The IP address of the cloud 5 is registered when a predicted value is obtained by the calculation unit 13 of the communication control device 1 described later.

[0030] The UDM / UDR41 can configure the configuration information table T1 by adding a group ID field to the subscriber profile. The configuration information table T1 managed by the UDM / UDR41 is also synchronized with the communication control device 1, and the same contents are stored in the second storage unit 15. In this embodiment, the UDM / UDR41 is shown as an example where the UDM and UDR are configured as a single device, but the UDM / UDR41 may also be a device in which the UDM and UDR are arranged separately.

[0031] SMF42 is a session management function that establishes, modifies, and releases PDU (Packet Data Unit) sessions between user terminal 2 and data networks such as the Internet. Based on the PCC (Policy and Charging Control) policy from PCF43, SMF42 sets the appropriate communication path for data communication between user terminal 2 and UPF44.

[0032] PCF43 determines QoS and policies and provides them to SMF42. PCF43 applies PCC rules according to the 3GPP (registered trademark) specification and creates PCC policies for configuring the communication path of UPF44 through which user terminal 2 communicates, in response to instructions from communication control device 1.

[0033] The UPF44 is a user plane function that processes packets between base station 3 and data networks such as the internet. The UPF44 functions as a gateway between the core network 4 and external data networks. Multiple UPF44s are provided in the core network 4. As shown in Figure 1, each of UPF_1 to UPF_N is directly connected to each of base stations 3-1, 3-2, ..., 3-N, forming a so-called full-mesh connection. In this embodiment, each UPF44 transmits packets from user terminals 2 to cloud 5 via a data network such as the internet. Each UPF44 also forwards packets transmitted from cloud 5 to user terminals 2. As shown in Figure 1, each UPF44 connects to one cloud 5. In this embodiment, multiple user terminals 2 belonging to the same group ID communicate with the most suitable UPF44 from UPF_1 to UPF_N, which is specified according to the cloud 5 associated with the specific location to which they connect. Each UPF44 has an IP address, which allows for unique identification of the UPF44.

[0034] Cloud 5 provides a designated website or web application. Cloud 5 is a cloud hub, which is a geographical location or area where the physical equipment constituting the website is located. Cloud 5 can be an edge server such as a server, data center, or MEC server. In this embodiment, multiple user terminals 2 having the same group ID can connect to multiple Cloud 5s, which are data final processing nodes providing the same website or application.

[0035] Multiple clouds 5 are geographically dispersed and located at different distances from each other. Furthermore, the distance from each base station 3 to each of the clouds 5 differs for each cloud 5. For example, the cloud 5 closest in physical distance from base station 3-1 is "Cloud 1-1," and the cloud 5 furthest away is "Cloud 1-N." Multiple user terminals 2 access the same cloud 5 from their respective base stations 3 via the same designated UPF 44. Each cloud 5 can be uniquely identified by its IP address, and location information is associated with the IP address and stored in the auxiliary storage device 105 of the communication control device 1, as described later.

[0036] [Functional blocks of the communication control device] As shown in Figure 1, the communication control device 1 comprises an acquisition unit 10, a learning unit 11, a first storage unit 12 (storage unit), a calculation unit 13, a communication control unit 14, and a second storage unit 15. The communication control device 1 learns the relationship between combinations of multiple base stations 3 where multiple user terminals 2 are located and network configuration information related to the connected cloud 5, which suppresses delays in data communication with the multiple user terminals 2.

[0037] The acquisition unit 10 acquires information about the multiple base stations 3 in which each of the multiple user terminals 2 is located, based on the location registration request signals transmitted by each of the multiple user terminals 2 when they are in the area of ​​the multiple base stations 3. The acquisition unit 10 also acquires information about the multiple base stations 3 by associating the group ID associated with the location registration request signals transmitted by the multiple user terminals 2 with the information about the multiple base stations 3. The base station ID is used as the information about the base stations 3. The base station ID is added to the location registration request signal transmitted by the user terminal 2 in the core network 4 when the location registration request signal transmitted by the user terminal 2 passes through the core network 4. As mentioned above, the location registration request signal is transmitted when the user terminal 2 crosses the communication area of ​​each base station 3 or at regular intervals.

[0038] The base station ID acquired by the acquisition unit 10 indicates information about the base station 3 where multiple user terminals 2 with the same group ID are located at the same time. The base station ID for each user terminal 2 acquired by the acquisition unit 10 is used as an unknown input when the calculation unit 13 (described later) performs calculations on the trained machine learning model. In addition, the base station ID acquired by the acquisition unit 10 can be used as part of the training data when the learning unit 11 trains the machine learning model.

[0039] The learning unit 11 learns, using a machine learning model, the relationship between the combination of multiple base stations 3 to which each of the multiple user terminals 2 is located, and the network configuration information of the destination cloud 5, which is one of the multiple clouds 5 that the multiple user terminals 2 can connect to, and which suppresses communication delays with the multiple user terminals 2. The learning unit 11 can train the machine learning model through supervised learning.

[0040] The communication delays targeted are, in particular, the overall transmission delay of data communication between multiple user terminals 2. In other words, the transmission delay of data communication at the group ID level is the target of suppression. Transmission delays include delays caused by the physical distance between endpoints when viewed from multiple base stations 3 where multiple user terminals 2 are located. Specifically, the transmission delay in user plane data transfer from multiple base stations 3 to the cloud 5 can be targeted for suppression. In this case, by selecting the cloud 5 that is the shortest or most optimally located physical distance from each of the base stations 3 where multiple user terminals 2 are located as the connection destination, the transmission delay of data communication for the entire group will be suppressed.

[0041] The network configuration information includes information about the cloud 5 located at the shortest physical distance from the base stations 3, among multiple clouds 5 located at geographically different locations for each of the multiple user terminals 2. In other words, the network configuration information identifies the destination cloud 5, and the information about the identified cloud 5 allows for the setting of the optimal UPF44 for the data communication of each of the multiple user terminals 2. For example, among clouds 1 to N, if cloud 1 is identified as the destination, the optimal UPF_1 for connecting to cloud 1 is identified.

[0042] Specifically, as network configuration information, a DNN (Data Network Name) identifier that can identify information about the destination cloud 5 and the routing destination UPF44 can be used. Note that when optimizing the physical distance from multiple base stations 3 to a specific cloud 5, the distance from a single user terminal 2 is not necessarily the shortest distance. The network configuration information identifies the cloud 5 that is closer to the base stations 3, i.e., the optimal distance.

[0043] Figure 3 shows the structure of a neural network model adopted as an example of a machine learning model used by the learning unit 11. The neural network model comprises an input layer x, a hidden layer h, and an output layer y. The learning unit 11 provides the base station IDs of the base stations 3 where multiple user terminals 2 (IMSI) with the same group ID are located to the input layer of the neural network model, applies an activation function to the weighted sum of the inputs, and passes the output determined by thresholding to the output layer. The output node of the output layer outputs a model prediction of network configuration information regarding the cloud 5 to which the multiple user terminals 2 are connected, for each combination of base station IDs of the base stations 3 where the multiple user terminals 2 are located.

[0044] The learning unit 11 introduces an objective function and learns the parameters of the neural network model so that the predicted values ​​of network configuration information from the neural network model for combinations of base stations 3 where multiple user terminals 2 are located become the values ​​of the network configuration information for the correct labels. The learning unit 11 adjusts the weight parameters of the neural network related to the machine learning model so that the objective function is minimized, i.e., becomes 0. The learning unit 11 can optimize the objective function using methods such as backpropagation.

[0045] Specifically, the learning unit 11 can predict the destination cloud 5 as a classification, and train the neural network to output the cloud 5 with the correct label with high probability, using the optimal cloud 5 as the ground truth. In this case, cross-entropy loss is used as the objective function. Alternatively, the learning unit 11 can introduce an objective function that minimizes the squared error, which is the distance error between multiple base station IDs and the corresponding cloud 5, as a regression problem. When treated as a regression problem, the actual distance between the locations of multiple base stations 3 and the location of cloud 5 is used as the ground truth label, and the model is trained to minimize the squared error between this and the predicted distance output by the model.

[0046] The first memory unit 12 stores the trained machine learning model constructed by the learning unit 11. The first memory unit 12 stores the trained machine learning model while associating it with a group ID.

[0047] The calculation unit 13 provides information on multiple base stations 3 where each of the multiple user terminals 2 is located as unknown input to a pre-trained machine learning model, performs calculations on the pre-trained machine learning model, and outputs network configuration information for the destination cloud 5 that suppresses communication delays with the multiple user terminals 2, among the multiple clouds 5 of the final data processing nodes to which the multiple user terminals 2 can connect.

[0048] The calculation unit 13 uses the base station IDs of multiple base stations 3, which are attached to the location registration request signals transmitted by multiple user terminals 2 and acquired by the acquisition unit 10, as unknown inputs. That is, the base station IDs for each IMSI of the same group ID are given as unknown inputs to the trained machine learning model corresponding to the group ID stored in the first storage unit 12. The calculation unit 13 can output a DNN identifier as network configuration information. The IP address of the destination cloud 5 indicated by the network configuration information output by the calculation unit 13 is registered in the configuration information table T1.

[0049] The communication control unit 14 instructs the core network 4 to configure the data communication path between each of the multiple user terminals 2 and the connected cloud 5, based on the network configuration information output by the calculation unit 13. More specifically, the communication control unit 14 specifies the IMSIs of the multiple user terminals 2 having the same group ID and instructs the core network 4 to configure a common UPF44 for each of the multiple user terminals 2. If the calculation unit 13 outputs a DNN identifier as network configuration information, it can obtain the identification information of the connected cloud 5 associated with the output DNN identifier by referring to the information stored in the auxiliary storage device 105.

[0050] The communication control unit 14 specifies the destination cloud 5 identified by the DNN identifier for each user terminal 2 with the same group ID, and instructs the UPF44 settings of each user terminal 2. In detail, the communication control unit 14 refers to table T1 shown in Figure 2 when it receives a location registration request signal from the user terminal 2 via the core network 4. The location registration request signal includes the IMSI of the user terminal 2, as mentioned above.

[0051] The communication control unit 14 requests the creation of a PCC policy from the PCF43 of the core network 4, specifying the group ID, IMSI, the IP address of the communication control device 1, and the destination cloud 5. In response to the creation request, the PCF43, SMF42, and UDM / UDR41 of the core network 4 cooperate to set the appropriate communication path for UPF44 for the data communication of the user terminal 2. Once the UPF44 communication path is set for the data communication of the user terminal 2, as explained in Figure 2, the IP addresses of the UPF44 related to the communication path setting are stored for each IMSI in the table T1 of the second storage unit 15.

[0052] The second storage unit 15 stores a configuration information table T1 that associates the IMSI, group ID, base station ID, UPF44 communication path set in the data communication of multiple user terminals 2, and the destination cloud 5 with each other. Of the configuration information table T1, the identification information of the destination cloud 5 ("cloud IP address") is identified and stored by the DNN identifier output from the arithmetic unit 13. In addition, the identification information of UPF44 ("UPF IP address") is stored in accordance with the setting of UPF44 according to the instructions of the core network 4 of the communication control unit 14.

[0053] [Hardware configuration of the communication control unit] Next, an example of a hardware configuration for realizing the communication control device 1 having the functions described above will be explained using Figure 4.

[0054] As shown in Figure 4, the communication control device 1 can be implemented, for example, by a computer equipped with a processor 102, main memory 103, communication interface 104, auxiliary storage 105, and input / output I / O 106 connected via a bus 101, and a program to control these hardware resources. Furthermore, the communication control device 1 may include a display device 107 connected via the bus 101.

[0055] Processor 102 is implemented using CPUs, GPUs, FPGAs, ASICs, etc.

[0056] The main memory 103 contains pre-stored programs for the processor 102 to perform various controls and calculations. The processor 102 and the main memory 103 work together to realize the various functions of the communication control device 1, such as the acquisition unit 10, learning unit 11, calculation unit 13, and communication control unit 14 shown in Figure 1.

[0057] The communication interface 104 is an interface circuit for networking the communication control device 1 with various external electronic devices.

[0058] The auxiliary storage device 105 consists of a read / write storage medium and a drive device for reading and writing various information such as programs and data to the storage medium. The auxiliary storage device 105 can use semiconductor memory such as a hard disk or flash memory as the storage medium.

[0059] The auxiliary storage device 105 has a program storage area for storing the communication control program executed by the communication control device 1. It also has a program storage area for storing the machine learning program executed by the communication control device 1. Furthermore, the auxiliary storage device 105 has an area for storing information associated with the DNN identifier, the identification information of the cloud 5, and the identification information of the UPF 44. Furthermore, the auxiliary storage device 105 has an area for storing grouping information associated with the IMSI and group ID of multiple user terminals 2. Furthermore, the auxiliary storage device 105 has an area for storing location information associated with the base station ID, the identification information of the UPF 44, and the identification information of the cloud 5. The auxiliary storage device 105 realizes the first storage unit 12 and the second storage unit 15 described in Figure 1. Furthermore, it may have, for example, a backup area for backing up the above-mentioned data and programs.

[0060] The I / O106 is an input / output device that accepts signals from external devices and outputs signals to external devices.

[0061] The display device 107 is composed of an organic EL display, a liquid crystal display, and the like. The display device 107 can display configuration information for Cloud 5 and UPF44, which are connected to each group ID.

[0062] [Operation of the communication control system] Next, the operation of the communication control system equipped with the communication control device 1 having the above-described configuration will be explained with reference to the sequence in Figure 5. Figure 5 shows the processing of the communication control system related to inference after the machine learning model trained by the learning unit 11 of the communication control device 1 has been constructed.

[0063] First, the communication control device 1 transmits grouping information, which includes the group ID and IMSI, to the UDM / UDR 41 (step S100). The grouping information is stored in the communication control device 1 in advance. Next, the UDM / UDR 41 creates a configuration information table T1 (Figure 2) based on the received grouping information (step S101). In step S101, the values ​​for "group ID" and "IMSI" in the configuration information table T1 are registered, while the values ​​for the other items are not yet entered. The configuration information table T1 is also stored in the second storage unit 15 of the communication control device 1.

[0064] Subsequently, multiple user terminals 2 of group ID "1" transmit location registration request signals to the core network 4 via the base station 3 where each terminal is located (step S102). The location registration request signal includes the IMSI of the user terminal 2 and the base station ID of the base station 3 where it is located. When the UDM / UDR 41 receives the location registration request signal via the AMF 40, the UDM / UDR 41 refers to the grouping information in the configuration information table T1 (Figure 2) created in step S101, associates the group ID with the base station ID and IMSI included in the received location registration request signal, and then forwards the location registration request signal to the communication control device 1 (step S103). Note that in step S103, the value of the base station ID in the configuration information table T1 is set.

[0065] Next, the calculation unit 13 of the communication control device 1 reads the trained machine learning model associated with the group ID received in step S103 from the first storage unit 12 and performs calculation processing (step S104). In step S104, the calculation of the trained machine learning model is performed using the base station ID of the IMSI with the same group ID, which was acquired by the acquisition unit 10 of the communication control device 1 in step S103, as an unknown input. The calculation processing in step S104 outputs the optimal network configuration information, i.e., the DNN identifier. The IP address of the destination cloud 5, identified by the DNN identifier, is registered in the configuration information table T1 (Figure 2).

[0066] Subsequently, the communication control unit 14 of the communication control device 1 requests the PCF43 to create a PCC policy, specifying the IP address of Cloud 5 associated with the DNN identifier output in step S104, as well as the group ID, IMSI, and the IP address of the communication control device 1 (step S105). In the example in Figure 5, Cloud_2 is specified. Next, the PCF43 creates a PCC policy based on the specified requirements (step S106). The PCF43 creates a PCC policy that includes information on which UPF44 the data communication of user terminal 2 will pass through. The PCC policy specifies the optimal UPF44 as the communication path for data communication from user terminal 2 to Cloud_2 with the same group ID.

[0067] Next, PCF43 sends the created PCC policy to SMF42 (step S107). Then, SMF42 sends data communication path configuration information related to user plane functions such as setting communication paths defined in the PCC policy to UPF44, which is specified by the PCC policy (step S108). In the example in Figure 5, UPF_2 is configured. Next, UPF44 (UPF_2) registers the received data communication path configuration information in memory (step S109).

[0068] Next, UPF44 (UPF_2) sends an ACK to SMF42, notifying it of UPF_2's IP address (step S110). Furthermore, SMF42 sends an ACK to the communication control device 1, notifying it of UPF_2's IP address (step S111). Subsequently, the communication control device 1 notifies UDM / UDR41 of UPF_2's IP address and also sends an ACK to user terminal 2 (step S112). At this time, the IP address of UPF_2 communicating with user terminal 2 is set in the configuration information table T1 (Figure 2). The configuration information table T1 updated by UDM / UDR41 is also stored in the second storage unit 15 of the communication control device 1. After that, a data communication path is established between user terminal 2, UPF44 (UPF_2), and cloud 5 (cloud_2) (step S113). The processes from step S102 to step S113 are also performed for other user terminals 2 belonging to the same group ID "1".

[0069] Through the above process, multiple user terminals 2 with the same group ID can connect to the same cloud_2 and perform data communication via the transfer route that minimizes data communication delays overall.

[0070] Next, the operation of the communication control device 1 having the above-described configuration will be explained with reference to the flowcharts in Figures 6 and 7. Figure 6 is a flowchart of the learning process by the communication control device 1. Figure 7 is a flowchart of the calculation process by the communication control device 1.

[0071] As shown in Figure 6, first, the learning unit 11 prepares training data (step S1). Specifically, the base station IDs of the base stations 3 where each of the multiple user terminals 2 with the same group ID are located, which are acquired by the acquisition unit 10, can be used as training data. The set of base station ID combinations for each IMSI is pre-assigned a DNN identifier as the correct label. Alternatively, the identification information of the cloud 5 may be provided as the correct label.

[0072] Next, the learning unit 11 trains a machine learning model using the training data prepared in step S1 (step S2). More specifically, the learning unit 11 uses a machine learning model to learn the relationship between the combination of base station IDs of multiple base stations 3 where each of the multiple user terminals 2 is located, and the network configuration information of the destination cloud 5 that suppresses delays in data communication with the multiple user terminals 2.

[0073] Subsequently, the first memory unit 12 associates the group ID with the trained machine learning model constructed in step S2 and stores it (step S3).

[0074] Next, as shown in Figure 7, the acquisition unit 10 acquires the base station ID of the base station 3 where multiple user terminals 2 with a common group ID are located (step S10). Step S10 corresponds to step S103 described in Figure 5. In other words, in step S10, the base station ID of the base station 3 where each user terminal 2 is located is acquired, triggered by location registration request signals transmitted by multiple user terminals 2 with the same group ID.

[0075] Next, the arithmetic unit 13 reads the trained machine learning model corresponding to the group ID obtained in step S10 from the first storage unit 12, and performs calculations on the trained machine learning model using the combination of base station IDs obtained in step S10 as an unknown input, and outputs network configuration information for the destination cloud 5 that suppresses the transmission delay of data communication for the entire group (step S11). In step S11, the DNN identifier indicating the cloud 5 that is physically closer from the multiple base stations 3 is output. Step S11 corresponds to step S104 explained in Figure 5.

[0076] Subsequently, the communication control unit 14, based on the network configuration information output in step S11, specifies each of the multiple user terminals 2 having the same group ID and instructs the core network 4 to configure UPF44 for the multiple user terminals 2 (step S12). Step S12 corresponds to step S105 described in Figure 5.

[0077] As described above, the communication control device 1 according to this embodiment learns, using a machine learning model, the combination of base stations 3 where multiple user terminals 2 are located, and network configuration information regarding the destination cloud 5 that can suppress the transmission delay of data communication with the multiple user terminals 2, and the learned network configuration information is stored in a database in advance. Therefore, the communication delay of multiple user terminals 2 can be suppressed with a simpler configuration.

[0078] Furthermore, according to the communication control device 1 of this embodiment, multiple user terminals 2 are grouped together, and the optimal cloud 5 to connect to is selected on a group basis. Therefore, by selecting the cloud 5 that is physically close to the group as the connection destination for each group of multiple user terminals 2, the transmission delay of data communication for the entire group can be suppressed more efficiently with a simpler configuration.

[0079] Furthermore, according to the communication control device 1 of this embodiment, a location registration request signal transmitted by a base station 3 where multiple user terminals 2 are located triggers the acquisition of a base station ID, calculation of a trained machine learning model, and the creation of a PCC policy. Therefore, it is possible to suppress the delay of communication between multiple user terminals 2 with a simpler configuration.

[0080] In the embodiment described, the machine learning model used by the learning unit 11 was exemplified as a multilayer neural network. However, other machine learning models such as multilayer perceptrons, decision tree-based models such as random forests, gradient boosting-based decision trees such as XGBoost and LightGBM, k-nearest neighbors, support vector machines, and linear regression can also be used.

[0081] Furthermore, in the embodiment described, the input layer of the multilayer neural network used by the learning unit 11 was described as being input to the base station ID of the base station 3 where multiple user terminals 2 with the same group ID are located. However, if a model can be constructed that outputs information about the destination cloud 5 in order to suppress the transmission delay of data communication across multiple user terminals 2, the features input to the input layer can be not only the base station ID for each IMSI, but also values ​​such as the number of hops in the path considering the logical distance, network delays such as the number of relay nodes and switching processing time, and QoS requirements such as bandwidth and reliability.

[0082] Although embodiments of the communication control device and communication control method of the present invention have been described above, the present invention is not limited to the embodiments described above, and various modifications that a person skilled in the art can envision are possible within the scope of the invention described in the claims. [Explanation of Symbols]

[0083] 1...Communication control unit, 10...Acquisition unit, 11...Learning unit, 12...First memory unit, 13...Calculation unit, 14...Communication control unit, 15...Second memory unit, 2...User terminal, 3...Base station, 4...Core network, 40...AMF, 41...UDM / UDR, 42...SMF, 43...PCF, 44...UPF, 5...Cloud, 101...Bus, 102...Processor, 103...Main memory, 41a, 104...Communication interface, 105...Auxiliary memory, 106...Input / output I / O, 107...Display device, NW...Network.

Claims

1. A calculation unit configured to provide a trained machine learning model with information on multiple base stations in which each of multiple user terminals is located as unknown input, perform calculations on the trained machine learning model, and output network configuration information regarding a data processing device to which the multiple user terminals can connect, which is one of multiple data processing nodes that are final data processing nodes that the multiple user terminals can connect to, and which suppresses the delay of communication with the multiple user terminals. A communication control unit is configured to instruct the core network to configure the data communication path between each of the plurality of user terminals and the connected data processing device, based on the network configuration information output by the calculation unit. A communication control device equipped with the following features.

2. In the communication control device according to claim 1, Furthermore, the learning unit is configured to learn, using a machine learning model, the relationship between the combination of the multiple base stations in which each of the multiple user terminals is located and the network configuration information relating to the data processing device to which the multiple user terminals can connect, which suppresses the delay of the communication with the multiple user terminals. A storage unit configured to store the trained machine learning model constructed by the learning unit, Equipped with, The calculation unit reads the trained machine learning model stored in the memory unit and performs calculations. A communication control device characterized by the following:

3. In the communication control device according to claim 2, Furthermore, the system includes an acquisition unit configured to acquire information about the base stations where each of the multiple user terminals is located, based on a location registration request signal transmitted by each of the multiple user terminals when it is in the area of ​​the multiple base stations. The calculation unit uses the information of the multiple base stations acquired by the acquisition unit as the unknown input. A communication control device characterized by the following:

4. In the communication control device according to claim 3, The location registration request signal is associated with a group identifier of the group to which the plurality of user terminals belong. The acquisition unit acquires the group identifier associated with the location registration request signal and the information of the multiple base stations in association with it. The memory unit stores the group identifier associated with the trained machine learning model, The communication control unit specifies the plurality of user terminals having the group identifier and instructs the core network to set up the data communication path between each of the plurality of user terminals and the data processing device to which it is connected. A communication control device characterized by the following:

5. In the communication control device according to claim 1, The network configuration information includes information on the data processing device to which each of the multiple user terminals is connected, which is located at a position that is physically closer to the multiple base stations than the multiple data processing devices. Based on the information from the data processing device to which the connection is made, a common user plane function can be configured for the data communication of each of the multiple user terminals. A communication control device characterized by the following:

6. A calculation step in which information of multiple base stations in which each of multiple user terminals is located is provided as unknown input to a trained machine learning model, the trained machine learning model performs calculations, and outputs network configuration information for a data processing device that is a destination data processing node that suppresses communication delay with the multiple user terminals, among multiple data processing devices that are data final processing nodes to which the multiple user terminals can connect. A communication control step instructs the core network to configure a data communication path between each of the multiple user terminals and the connected data processing device, based on the network configuration information output in the calculation step. A communication control method comprising the following:

7. In the communication control method described in claim 6, Furthermore, a learning step is performed using a machine learning model to learn the relationship between the combination of the multiple base stations in which each of the multiple user terminals is located and the network configuration information relating to the data processing device to which the multiple user terminals can connect, which suppresses the delay of the communication with the multiple user terminals. A storage step in which the trained machine learning model constructed in the learning step is stored in a memory unit. Equipped with, The calculation step involves reading the trained machine learning model stored in the memory unit and performing calculations. A communication control method characterized by the following:

8. In the communication control method described in claim 7, Furthermore, the system includes an acquisition step in which each of the multiple user terminals obtains information about the multiple base stations in which each of the multiple user terminals is located, based on a location registration request signal transmitted by each of the multiple user terminals when it is in the area of ​​the multiple base stations. The calculation step uses the information of the multiple base stations acquired in the acquisition step as the unknown input. A communication control method characterized by the following:

9. In the communication control method described in claim 8, The location registration request signal is associated with a group identifier of the group to which the plurality of user terminals belong. The acquisition step involves associating the group identifier associated with the location registration request signal with the information of the multiple base stations, The memory step involves associating the group identifier with the trained machine learning model and storing it in the memory unit. The communication control step specifies the plurality of user terminals having the group identifier and instructs the core network to set up the data communication path between each of the plurality of user terminals and the data processing device to which it is connected. A communication control method characterized by the following:

10. In the communication control method described in claim 6, The network configuration information includes information on the data processing device to which each of the multiple user terminals is connected, which is located at a position that is physically closer to the multiple base stations than the multiple data processing devices. Based on the information from the data processing device to which the connection is made, a common user plane function can be configured for the data communication of each of the multiple user terminals. A communication control method characterized by the following:

Images