COMMUNICATION MANAGEMENT DEVICE, COMMUNICATION MANAGEMENT METHOD, AND COMMUNICATION MANAGEMENT SYSTEM

Abstract

The object is to improve the throughput of each of a plurality of communication terminals to be managed. [Solution] The communication management device 1 includes a generator 131 that generates pseudo-communication volume time series data similar to the time series data of the true communication volume, using the time series data of the communication volume of the selected communication terminal with the largest total communication volume for each time period as the time series data of the true communication volume, and a learning unit 13 that performs adversarial learning of a generative model having a discriminator 132 that distinguishes between the time series data of the pseudo-communication volume generated by the generator 131 and the time series data of the true communication volume, and a notification unit 16 that notifies a plurality of communication terminals 2 of the learned generator 131' constructed by the learning unit 13 as communication management information.

Description

[Technical field]

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

[0002] In recent years, with the increase in the number of communication terminals connected to mobile communication networks, there is a demand for more efficient data communication. For example, Patent Document 1 discloses a communication management system that collects information related to wireless communication such as the received signal strength of a communication terminal, judges the congestion level of a wireless line based on the information such as the throughput and received signal strength of the communication terminal, and determines a schedule for data communication between the communication terminal and the communication terminal according to the congestion level.

[0003] However, some IoT terminals and the like need to transmit data at a predetermined cycle, and therefore it may be difficult to avoid congestion during communication. Therefore, it is difficult to adopt the off-peak communication described in Patent Document 1 to an IoT terminal that needs to transmit data at a predetermined cycle. In addition, the communication management technology described in Patent Document 1 adjusts the communication volume over the entire mobile communication network. Therefore, it is also difficult to improve the throughput of each of the specific communication terminals selected as the management targets. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] International Publication No. 2016 / 079958 Summary of the Invention [Problem to be solved by the invention]

[0005] In conventional techniques, it has been difficult to improve the throughput of each of a plurality of communication terminals to be managed.

[0006] The present invention has been made to solve the above-mentioned problems, and has an object to improve the throughput of each of a plurality of communication terminals to be managed. [Means for solving the problem]

[0007] In order to solve the above-mentioned problems, the communication management device of the present invention includes a collection unit configured to collect time series data of communication volume for each time period of a plurality of communication terminals, each of which is identified by a subscriber identifier; a selection unit configured to select, based on the collected time series data of communication volume, time series data of communication volume of a communication terminal having the largest total communication volume for each time period; a generator that generates pseudo-communication volume time series data similar to the time series data of true communication volume, using the selected time series data of communication volume of the communication terminal having the largest total communication volume for each time period as time series data of true communication volume; a learning unit configured to perform adversarial learning of a generative model having a classifier that distinguishes between the time series data of pseudo-communication volume generated by the generator and the time series data of true communication volume; and a notification unit configured to notify the plurality of communication terminals of the learned generator constructed by the learning unit as communication management information.

[0008] In the communication management device according to the present invention, the plurality of communication terminals may be a plurality of communication terminals to which common identification information is assigned.

[0009] In addition, in the communication management device of the present invention, the collection unit may collect time series data of the communication volume for each time period of the multiple communication terminals to which the common identification information is assigned from a user plane function provided in a core network.

[0010] In the communication management device according to the present invention, the plurality of communication terminals may be a plurality of communication terminals located in the same communication area.

[0011] In the communication management device according to the present invention, the time series data of the pseudo communication volume may have a data distribution that has a minimum statistical distance from the data distribution of the time series data of the true communication volume.

[0012] In order to solve the above-mentioned problems, a communication management method according to the present invention includes a collection step of collecting time series data of communication volume for each time period of a plurality of communication terminals, each of which is identified by a subscriber identifier; a selection step of selecting, based on the collected time series data of communication volume, time series data of communication volume of a communication terminal having the largest total communication volume for each time period; a learning step of performing adversarial learning of a generative model having a generator that generates pseudo-communication volume time series data similar to the time series data of the true communication volume, using the selected time series data of communication volume of the communication terminal having the largest total communication volume for each time period as time series data of true communication volume, and a discriminator that discriminates between the time series data of pseudo-communication volume generated by the generator and the time series data of the true communication volume; and a notification step of notifying the plurality of communication terminals of the learned generator constructed in the learning step as communication management information.

[0013] In the communication management method according to the present invention, the plurality of communication terminals may be a plurality of communication terminals to which common identification information is assigned.

[0014] In addition, in the communication management method of the present invention, the collection step may collect time series data of the communication volume for each time period of the multiple communication terminals to which the common identification information is assigned from a user plane function provided in a core network.

[0015] In the communication management method according to the present invention, the plurality of communication terminals may be a plurality of communication terminals located in the same communication area.

[0016] In addition, the communication management method of the present invention may further include an acquisition step in which each of the multiple communication terminals acquires the learned generator of the communication management information notified in the notification step, a generation step in which, using the learned generator, a generation step in which pseudo-communication volume time series data similar to the time series data of the true communication volume is generated, and a communication step in which data transmission in each time period is controlled based on the generated pseudo-communication volume time series data.

[0017] In order to solve the above-mentioned problems, the communication management system of the present invention is a communication management system comprising the above-mentioned communication management device and the plurality of communication terminals, each of the plurality of communication terminals comprising an acquisition unit configured to acquire the learned generator of the communication management information notified from the communication management device, a generation unit configured to generate time series data of pseudo communication volume similar to the time series data of true communication volume using the learned generator, and a communication unit configured to control the transmission of data in each time zone based on the generated time series data of pseudo communication volume. Effect of the Invention

[0018] According to the present invention, the time series data of the communication volume of the selected communication terminal having the largest total communication volume for each time period is used as the time series data of the true communication volume, and adversarial learning of a generative model having a generator that generates time series data of pseudo communication volume similar to the time series data of the true communication volume, and a discriminator that discriminates between the time series data of the pseudo communication volume generated by the generator and the time series data of the true communication volume is performed. Therefore, the throughput of each of the multiple communication terminals to be managed can be improved. [Brief description of the drawings]

[0019] [Figure 1] FIG. 1 is a block diagram showing a configuration of a communication management system including a communication management device according to an embodiment of the present invention. [Diagram 2] FIG. 2 is a block diagram showing a configuration of a communication terminal according to the present embodiment. [Diagram 3]FIG. 3 is a diagram for explaining time-series data of communication volume collected by the communication management device according to the present embodiment. [Figure 4] FIG. 4 is a diagram for explaining the structure of the setting information table included in the communication management system according to the present embodiment. [Diagram 5] FIG. 5 is a block diagram showing a configuration of a learning unit included in the communication management device according to the present embodiment. [Figure 6] FIG. 6 is a diagram for explaining the learning unit included in the communication management device according to the present embodiment. [Figure 7] FIG. 7 is a diagram for explaining the learning unit included in the communication management device according to the present embodiment. [Figure 8] FIG. 8 is a block diagram showing a hardware configuration of the communication management device according to the present embodiment. [Figure 9] FIG. 9 is a block diagram showing a hardware configuration of the communication management device according to the present embodiment. [Figure 10] FIG. 10 is a sequence diagram showing an outline of the operation of the communication management system according to the present embodiment. [Figure 11] FIG. 11 is a sequence diagram showing an outline of the operation of the communication management system according to the present embodiment. [Figure 12] FIG. 12 is a flowchart showing the learning process performed by the communication management device according to the present embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0020] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Preferred embodiments of the present invention will now be described in detail with reference to FIGS.

[0021] [Communication management system configuration] First, there will be described an overview of a communication management system including a communication management device 1 according to an embodiment of the present invention and a communication terminal 2. Fig. 1 is a block diagram showing a configuration of a communication management system according to an embodiment of the present invention.

[0022] The communication management system according to the present embodiment is provided in, for example, a mobile communication network compatible with the 5G communication standard. The communication management system includes a communication management device 1, a communication terminal 2, a base station 3, a core network 4, and a data network 5. The communication management system manages the optimal data transmission timing of each of the multiple communication terminals 2 to be managed.

[0023] The communication terminal 2 is realized by a mobile communication terminal such as a smartphone, a tablet computer, or a laptop computer, or an IoT terminal using a 5G mobile communication network such as a smart meter, a wearable device, or an industrial sensor. The communication terminal 2 is equipped with a SIM 2a, and the contract profile of the SIM 2a stores the subscriber identification information of the user, and includes identifier information such as a subscriber identifier (IMSI: International Mobile Subscriber Identity) assigned to a mobile phone line contract, a telephone number (MSISDN: Mobile Subscriber International Subscriber Directory Number) of the subscriber user, and a SIM card number (ICCID: Integrated Circuit Card Identifier). The communication terminal 2 is uniquely identified by the IMSI.

[0024] The communication terminal 2 is also assigned a terminal IP address that uniquely identifies the terminal. The IP address is assigned to the communication terminal 2 via SMF 42 after a session is established. In this embodiment, there are multiple communication terminals 2, and the multiple communication terminals 2 that are in the same communication area 3A are assigned a group ID (common identification information). The group ID can be assigned to terminals that, among the multiple communication terminals 2 that are in the same communication area 3A, have in common certain attributes related to communication and services. The communication management process in this embodiment is performed for each of the multiple communication terminals 2 with the same group ID.

[0025] For example, if the communication terminal 2 is composed of industrial sensors, a common group ID can be assigned to multiple industrial sensors that have similar communication patterns and requirements, such as being used for similar purposes in equipment or the like in the same communication area 3A and needing to transmit a similar amount of data at regular intervals.

[0026] The base station 3 is configured as a wireless base station compatible with the 5G communication standard, and relays communication between the communication terminal 2 located in the communication area 3A and the core network 4. The base station 3 is connected to the core network 4 via a backhaul link. The base station 3 receives data from the communication terminal 2 using predefined wireless resources.

[0027] The core network 4 is connected to the communication management device 1 via a network NW such as a LAN, a WAN, or the Internet. The core network 4 includes an AMF (Access and Mobility Management Function) 40, a UDM (Unified Data Management) / UDR (Unified Data Repository) 41, a SMF (Session Management Function) 42, and a PCF (Policy Control Function) 43, which are nodes in the C-plane. The core network 4 also includes a plurality of UPFs (User Plane Functions) 44 in the U-plane. Functional nodes in the U-plane and C-plane other than those described above that the core network 4 includes are omitted from the illustration.

[0028] The AMF 40 is a node that provides a mobility control function and performs mobility control such as location registration, paging, and handover.

[0029] The UDM / UDR 41 manages subscriber profiles, performs authentication, and manages mobility. In this embodiment, the UDM / UDR 41 creates and stores a setting information table T2 in which the IMSIs, group IDs, and base station IDs of multiple communication terminals 2, and the communication paths of the UPF 44 set in data communication of the multiple communication terminals 2 are associated with each other, as shown in FIG. 4, in response to an instruction from the communication management device 1. The instruction from the communication management device 1 includes grouping information in which multiple IMSIs and group IDs of the management targets that are specified in advance are associated with each other. The value of the IP address of the UPF 44 in the setting information table T2 is registered after the communication paths are set by the SMF 42 and PCF 43 described later.

[0030] The UDM / UDR 41 can configure the setting information table T2 by adding a group ID field to the subscriber profile. The UDM / UDR 41 according to this embodiment has a communication interface 41a for communicating with the communication management device 1. The setting information table T2 managed by the UDM / UDR 41 is also synchronized with the communication management device 1, and the same contents are stored (first storage unit 14). The UDM / UDR 41 may be a device in which the UDM and UDR are arranged separately, in addition to the case where the UDM and UDR are configured as a single device.

[0031] The SMF 42 is a session management function that performs the establishment, modification, release, etc. of a PDU (Packet Data Unit) session between the communication terminal 2 and a data network such as the Internet. The SMF 42 sets an appropriate communication path for data communication between the communication terminal 2 and the UPF 44 based on a PCC (Policy and Charging Control) policy from the PCF 43.

[0032] The PCF 43 determines QoS and policies and provides them to the SMF 42. The PCF 43 applies PCC rules based on the specifications of 3GPP (registered trademark), and in response to an instruction from the communication management device 1, creates a PCC policy for setting a communication path of the UPF 44 with which the communication terminal 2 communicates.

[0033] The UPF 44 is a user plane function, and processes data between the base station 3 and a data network 5 such as the Internet. A plurality of UPFs 44 are provided in the core network 4. In this embodiment, the UPF 44 records time series data of communication volume for each time period of the communication terminal 2 in a memory. In this embodiment, the UPF 44 includes a communication interface 44a for communicating with the communication management device 1.

[0034] 3 is a diagram for explaining the time series data of the communication volume recorded by each UPF 44 and collected by the collection unit 11 of the communication management device 1 described later. As shown in table T1 in FIG. 3, each UPF 44 records a log of the time series data of the communication volume for each time period for each IMSI and group ID in the memory. i (i=1, 2, . . . , N) are time slots set for the communication management process of this embodiment.

[0035] In addition, the communication volume [bps] is i By setting a threshold value for the communication volume [bps] for each time period t, the data is converted into binary data. i If the communication volume [bps] for each exceeds the threshold (data communication is present), the value is "1", and if it does not exceed the threshold (no data communication), the value is "0". Note that the process of converting the time series data of communication volume into binary data by threshold processing of the communication volume [bps] may be configured to be performed by the collection unit 11 of the communication management device 1 instead of the UPF 44.

[0036] The data network 5 is an external network such as the Internet, a cloud network, etc. The communication terminal 2 performs data communication with the data network 5 via the base station 3 and the UPF 44 of the core network 4.

[0037] [Function block of communication management device] 1, the communication management device 1 includes a setting unit 10, a collecting unit 11, a selecting unit 12, a learning unit 13, a first storage unit 14, a second storage unit 15, and a notifying unit 16. The communication management device 1 learns a generative model by adversarial learning using the timing of data transmission of a communication terminal 2 having the best throughput among multiple communication terminals 2 as time-series data of true communication volume, and notifies the multiple communication terminals 2 under management of the learned generator constructed by learning as communication management information.

[0038] The setting unit 10 designates an IMSI and a group ID based on a location registration request signal from each communication terminal 2, and instructs the setting of the UPF 44 of each communication terminal 2. Specifically, the setting unit 10 transmits grouping information in which the IMSIs and group IDs of the management targets registered in advance are associated with each other to the UDM / UDR 41. Based on the grouping information from the setting unit 10, the UDM / UDR 41 creates a setting information table T2 (FIG. 4). Furthermore, the setting unit 10 instructs the setting of a user plane function for data communication of each communication terminal 2 based on the group ID associated with the IMSI included in the location registration request signal from each communication terminal 2.

[0039] The setting unit 10 requests the PCF 43 of the core network 4 to create a PCC policy by specifying the group ID, the IMSI, and the IP address of the communication management device 1. In response to the creation request, the PCF 43, the SMF 42, and the UDM / UDR 41 of the core network 4 cooperate to set an appropriate communication path of the UPF 44 for data communication of the communication terminal 2. When the communication path of the UPF 44 is set for data communication of the communication terminal 2, the setting information table T2 updated in the UDM / UDR 41 is synchronized with, for example, the first storage unit 14, and the updated setting information table T2 is stored in the first storage unit 14.

[0040] The collection unit 11 collects time series data of communication volume for each time period of a plurality of communication terminals 2, each of which is identified by an IMSI. More specifically, the collection unit 11 collects time series data of communication volume for each time period of a plurality of communication terminals 2 to which a group ID is assigned, from a UPF 44 included in the core network 4. The collection unit 11 collects time series data of communication volume for each time period of a plurality of communication terminals 2 for each group ID, via the network NW, from the UPF 44 related to the setting of a communication path for data communication of the communication terminals 2 by the setting unit 10. As shown in FIG. 3, the collection unit 11 collects time series data of communication volume for each time period of a plurality of communication terminals 2 for each group ID, from time periods t1, t2, ..., t N In the time series data (t i ,x i ) to collect.

[0041] The selection unit 12 selects the time series data of the communication amount of the communication terminal 2 having the largest total communication amount for each time period based on the collected time series data of the communication amount. More specifically, the selection unit 12 selects the time series data of the communication amount for each time period (t i ,x i ), for each IMSI with a common group ID, for each time period (t1 to t N ) communication volume (Σx i ) is selected. The communication terminal 2 with the largest total communication volume is the communication terminal 2 with the highest throughput among the multiple communication terminals 2 included in the group ID.

[0042] More specifically, the selection unit 12 can compare the total values ​​of communication volumes of all IMSIs having a common group ID, and select N pieces (N is a positive integer equal to or greater than 2) of time-series data of communication volumes in descending order of total value. The number of pieces of data to be selected can be a number necessary to obtain sufficient accuracy in adversarial learning by the learning unit 13 described below, such as the top 4%, for example.

[0043] The learning unit 13 performs adversarial learning of a generative model having a generator 131 that generates pseudo-communication volume time series data similar to the time series data of the true communication volume, using the time series data of the communication volume of the selected communication terminal 2 having the largest total communication volume for each time period as the time series data of the true communication volume, and a discriminator 132 that discriminates between the time series data of the pseudo-communication volume generated by the generator 131 and the time series data of the true communication volume.

[0044] 5, the learning unit 13 adversarially learns a GAN (Generative Adversarial Network) having a generator 131 and a discriminator 132. A trained generator 131′ is constructed by the learning of the learning unit 13.

[0045] 6 and 7 are diagrams showing schematic configurations of the neural network of the generator 131 and the discriminator 132 of the GAN used by the learning unit 13. As shown in FIG. 6, the generator 131 is configured of a neural network having an input layer, a hidden layer, and an output layer. The hidden layer can be configured of a fully connected layer and a deconvolution layer. The generator 131 is a model that generates time-series data of pseudo communication volume from random noise. For example, m samples of a Gaussian noise vector are randomly sampled and input to the input node of the generator 131 (z1 to z m The generator 131 performs a multiplication and accumulation operation on the input and weight parameters and performs threshold processing using an activation function to output G(z1) to G(z N ) to output.

[0046] The classifier 132 shown in Fig. 7 is configured as a neural network having an input layer, a hidden layer, and an output layer. The hidden layer can be configured as a convolutional layer, and the output layer can be configured as a fully connected layer. In the example of Fig. 7, time series data x1 to x2 of communication volume, which are N samples of training data, are N As described above, the time series data of the communication volume is expressed as binary data. Therefore, each input node of the input layer of the neural network constituting the classifier 132 is provided with a time period t iA communication amount value of 0 or 1 is input for each of the nodes. In the example of FIG. 5, time-series data of true communication amounts is input to the classifier 132 as training data 134.

[0047] The discriminator 132 outputs, for example, 1 or 0 after performing a product-sum operation of the input and weight parameters and threshold processing using an activation function. When the discriminator 132 discriminates that the training data related to the input time series data of true communication volume is correctly the time series data of true communication volume, it outputs an output y=1. On the other hand, when the discriminator 132 discriminates that the training data related to the input time series data of pseudo communication volume is correctly the time series data of pseudo communication volume, it outputs an output y=0. In this way, the discriminator 132 is a model that distinguishes the model distribution generated by the generator 131 from the data distribution of the training data, which is the true distribution. The time series data of the pseudo communication volume has a data distribution that has a minimum statistical distance from the data distribution of the time series data of true communication volume.

[0048] FIG. 5 is a block diagram for explaining the adversarial learning of GAN by the learning unit 13. The generator 131 of the GAN adopted by the learning unit 13 is represented as a function G, and the discriminator 132 is represented as a function D. Furthermore, the time series data of the true communication volume is represented as x, the predicted value output by the discriminator 132 is represented as y, and the correct label is represented as t. The correct label t is set to 1 for the time series data of the true communication volume, and 0 for the time series data of the pseudo communication volume generated by the generator 131. At this time, the discriminator 132 calculates the cross entropy E CE It can be expressed as:

[0049]

number

[0050] The first term in the brace of the above equation (1) represents t n lny n In the above, the predicted value y n is the correct label for the time series data of the true traffic volume, t n = 1. On the other hand, the second term in the braces represents (1-t n)ln(1-y n ), the predicted value y n is the time series data of the pseudo traffic volume and the correct label value to be identified (1-t n ) = 0. In this way, the cross entropy E CE is maximized when the predicted value matches the correct label value.

[0051] Here, the generator 131 constituting the GAN has parameters w G ,θ G and function G(w G ,θ G ) The discriminator 132 also uses the parameter w D ,θ D and function D(w D ,θ D ) The cross entropy E CE The objective function E of the GAN including the generator 131 and the discriminator 132 based on the above can be expressed by the following equation (2).

number

[0052] The first term of the above formula (2) represents E D(x)=1 lnD(w D ,θ D ) is the expected value at which the discriminator 132 discriminates the time series data of the true traffic volume as the time series data of the true traffic volume. D(x)=0 ln(1-D(G(w G ,θ G ),w D ,θ D)) is an expected value at which the discriminator 132 discriminates the time series data of the pseudo communication volume generated by the generator 131 as time series data of the pseudo communication volume. In GAN learning, the generator 131 and the discriminator 132 are adversarially trained by min-max optimization of the objective function E. Therefore, the generator 131 is trained so as to generate time series data of the pseudo communication volume that deceives the discriminator 132, and the discriminator 132 is trained so as to discriminate the time series data of the pseudo communication volume generated by the generator 131 as time series data of the pseudo communication volume.

[0053] In learning by the classifier 132, when time series data of true communication volume is given, the classifier 132 maximizes the first term of the objective function E in the above formula (2) by outputting an output close to y = 1. On the other hand, when time series data of pseudo communication volume is given, the classifier 132 learns to maximize the second term of the objective function E by outputting an output close to y = 0.

[0054] In the learning of the generator 131, D(G(w G ,θ G ),w D ,θ D )(D(G(z)) in Figure 5) is close to 1. G ,θ G ) (G(z) in FIG. 5 ) to minimize the objective function E. The learning unit 13 uses a learning procedure in which the parameters of the generator 131 and the classifier 132 are updated alternately. The learning procedure of the generator 131 and the classifier 132 by the learning unit 13 will be described in detail later.

[0055] When the objective function E of the GAN is optimized, the learning unit 13 stores the trained generator 131′ in the second storage unit 15.

[0056] The first storage unit 14 stores a setting information table T2 (FIG. 4) in which the IP address, IMSI, group ID, and base station ID of the UPF 44 related to the setting of the communication path by the setting unit 10 are associated with each other. The first storage unit 14 can synchronize with the setting information table T2 created and updated by the UDM / UDR 41. Alternatively, the first storage unit 14 may be configured to periodically acquire the setting information table T2 created and updated by the UDM / UDR 41, or to refer to and reflect the updated setting information table T2.

[0057] The second storage unit 15 stores the trained generator 131′ constructed by the learning unit 13. Since the trained generator 131′ is a generator constructed for each group ID, the trained generator 131′ is associated with a group ID.

[0058] The notification unit 16 notifies the plurality of communication terminals 2 of the trained generator 131' constructed by the learning unit 13 as communication management information. More specifically, the notification unit 16 notifies the plurality of communication terminals 2 having the same group ID of the trained generator 131' constructed for each group ID via the network NW.

[0059] [Communication terminal function block] Next, functional blocks of the communication terminal 2 according to the present embodiment will be described with reference to Fig. 2. Note that the multiple communication terminals 2 are configured with the same functional blocks.

[0060] The third storage unit 20 stores the learned generator 131′ notified by the notification unit 16 of the communication management device 1 as communication management information.

[0061] The acquisition unit 21 acquires the learned generator 131′ of the communication management information notified from the communication management device 1. Specifically, the acquisition unit 21 reads out the learned generator 131′ from the third storage unit 20.

[0062] The generation unit 22 uses the learned generator 131′ to generate time series data of pseudo communication volume similar to the time series data of the true communication volume. The generated time series data of pseudo communication volume is information indicating the data transmission timing very similar to the data transmission timing of the communication terminal 2 having the best throughput among the group IDs. For example, the time series data of pseudo communication volume (t i ,x i ) for each time period (t1, t2, t3, t4, . . . , t N ), (x1,x2,x3,x4,...,x N )=(0,1,1,0,...,1). In this case, the data transmission timing is indicated as "0" in time period t1, which means no data is transmitted, and "1" in time period t2, which means data is transmitted,....

[0063] The communication unit 23 controls the transmission of data in each time period based on the time series data of the generated pseudo communication volume. For example, the communication unit 23 can control, for example, in a "0" time period t1 in which data is not transmitted, to transmit data with a communication volume that does not exceed the threshold value, in addition to cases in which data is not transmitted, taking into consideration the threshold value used in converting the time series data of the communication volume into a binary representation. On the other hand, in a "1" time period t2 in which data is transmitted, data can be transmitted with a communication volume that exceeds the threshold value. The communication unit 23 can control communication, for example, by a grant-free method in which data is transmitted at a determined timing without requiring additional permission from the base station 3.

[0064] [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.

[0065] 8, the communication management device 1 can be realized by, for example, a computer including a processor 102, a main memory device 103, a communication interface 104, an auxiliary memory device 105, and an input / output I / O 106, which are connected via a bus 101, and a program that controls these hardware resources. The communication management device 1 can also include a display device 107 connected via the bus 101.

[0066] The processor 102 is realized by a CPU, a GPU, an FPGA, an ASIC, or the like.

[0067] 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 implement the various functions of the communication management device 1, such as the setting unit 10, the collecting unit 11, the selecting unit 12, the learning unit 13, and the notifying unit 16 shown in FIG.

[0068] The communication interface 104 is an interface circuit for connecting the communication management device 1 to various external electronic devices via a network.

[0069] 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.

[0070] The auxiliary storage device 105 has a program storage area for storing the GAN learning program and communication management program executed by the communication management device 1. The auxiliary storage device 105 also has an area for storing grouping information in which a group ID and an IMSI are associated with each other. The auxiliary storage device 105 realizes the first storage unit 14 and the second storage unit 15 described in FIG. 1. Furthermore, the auxiliary storage device 105 may have, for example, a backup area for backing up the above-mentioned data and programs.

[0071] 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.

[0072] The display device 107 is configured by an organic EL display, a liquid crystal display, or the like.

[0073] [Hardware configuration of communication terminal] Next, an example of a hardware configuration for realizing the communication terminal 2 having the above-mentioned functions will be described with reference to FIG.

[0074] 9, the communication terminal 2 can be realized by a computer including a processor 202, a main memory device 203, a communication interface 204, an auxiliary memory device 205, and an input / output I / O 206, which are connected via a bus 201, and a program that controls these hardware resources. Furthermore, the communication terminal 2 can include a display device 207 connected via the bus 201.

[0075] The main memory device 203 stores in advance programs for the processor 202 to perform various controls and calculations. The processor 202 and the main memory device 203 realize the functions of the communication terminal 2, such as the acquisition unit 21, the generation unit 22, and the communication unit 23 shown in FIG.

[0076] The auxiliary storage device 205 has a program storage area for storing the computation program of the trained generator 131′ executed by the communication terminal 2. It also has a program storage area for storing the communication program executed by the communication terminal 2. The auxiliary storage device 205 realizes the third storage unit 20 described in FIG. 2. Furthermore, it may have, for example, a backup area for backing up the above-mentioned data, programs, and the like.

[0077] [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 sequence diagrams of FIGS. 10 and 11 and the flowchart of FIG.

[0078] 10 is a sequence diagram showing grouping of communication terminals 2 by the communication management system and setting of communication paths for data communication. First, the communication management device 1 transmits grouping information associated with a group ID and an IMSI to the UDM / UDR 41 (step S100). The grouping information is stored in advance in the communication management device 1. Next, the UDM / UDR 41 creates a setting information table T2 (FIG. 4) based on the received grouping information (step S101). In step S101, the values ​​of "group ID" and "IMSI" in the setting information table T2 are registered, and there are no entries yet for the values ​​of the other items.

[0079] Thereafter, the communication terminal 2 present in the communication area 3A transmits a location registration request signal from the base station 3 to the core network 4 (step S102). The location registration request signal includes the IMSI of the communication terminal 2 and the base station ID of the present base station 3. When the location registration request signal is received by the UDM / UDR 41 via the AMF 40, the UDM / UDR 41 associates a group ID with the base station ID and IMSI included in the received location registration request signal based on the information in the setting information table T2 (FIG. 4) created in step S101, and further transfers the location registration request signal to the communication management device 1 (step S103). Note that in step S103, the value of the base station ID in the setting information table T2 is set.

[0080] Next, the setting unit 10 of the communication management device 1 requests the PCF 43 to create a PCC policy by specifying the IMSI, base station ID, group ID, and further the IP address of the device itself, contained in the location registration request signal received in step S103 (step S104). Then, the PCF 43 creates a PCC policy based on the specified requirements (step S105). The PCF 43 creates a PCC policy including information on which UPF 44 the data communication of the communication terminal 2 will pass through. The PCC policy specifies the optimal UPF 44 as a communication path for data communication from the communication terminal 2 to the data network 5.

[0081] Next, the PCF 43 transmits the created PCC policy to the SMF 42 (step S106). After that, the SMF 42 transmits data communication path setting information related to the user plane function, such as setting of a communication path specified by the PCC policy, to the UPF 44 specified by the PCC policy (step S107). Next, the UPF 44 registers the received data communication path setting information in a memory (step S108).

[0082] Next, the UPF 44 transmits an ACK to the SMF 42 to notify it of the IP address of the UPF 44 (step S109). Furthermore, the SMF 42 transmits an ACK to the communications management device 1 to notify it of the IP address of the UPF 44 (step S110). After that, the communications management device 1 notifies the UDM / UDR 41 of the IP address of the UPF 44, and transmits an ACK to the communications terminal 2 (step S111). At that time, the IP address of the UPF 44 that communicates with the communications terminal 2 is set in the setting information table T2. The setting information table T2 updated by the UDM / UDR 41 is also stored in the first storage unit 14 of the communications management device 1. Further after that, a communications path for data communications between the communications terminal 2 and the UPF 44 is established (step S112). The communications terminal 2 performs data communications with the data network 5.

[0083] After that, the UPF 44 records a log of communication amounts for each time period of the multiple communication terminals 2 (step S113). The log of communication amounts recorded in the UPF 44 is time series data (t i ,x i ). After that, the communication management device 1 executes the communication management process (step S114).

[0084] Next, the communication management process (step S114) described in Fig. 10 will be described in more detail with reference to the sequence in Fig. 11. First, the collection unit 11 of the communication management device collects time series data of communication volume of IMSIs (communication terminals 2) having a common group ID from the UPF 44 (step S1). The collection unit 11 refers to the setting information table T2 stored in the first storage unit 14, and identifies, for example, the IP address "IP11" of the UPF 44 with which IMSI_1 to IMSI_N of the group ID "1" communicate, and collects time series data of communication volume from the UPF 44 of the identified IP address "IP11" (table T1 in Fig. 3).

[0085] Next, the selection unit 12 of the communication management device 1 selects the time series data of the communication volume of the communication terminal 2 having the largest total communication volume for each time period based on the collected time series data of the communication volume (step S2). In step S2, the selection unit 12 selects the time series data of the communication volume for each time period (t i ,x i ), for each IMSI with a common group ID, for each time period (t1 to t N ) communication volume (Σx i ) is the largest, and the time series data of the communication volume of the communication terminal 2 having the best throughput is selected.

[0086] In step S2, the time series data of the N communication volumes with the highest throughput is obtained. For example, the total communication volumes of all IMSIs can be compared, and N pieces of data can be collected in descending order of the largest value. The time series data of communication volumes selected in step S2 is used as training data in adversarial learning, i.e., time series data of true communication volumes.

[0087] Next, the learning unit 13 of the communication management device 1 performs a learning process of a GAN including a generator 131 and a discriminator 132 (step S3). More specifically, in step S3, the learning unit 13 performs adversarial learning of a generative model having a generator 131 that generates time series data of pseudo communication volume similar to the time series data of the true communication volume, using the time series data of the communication volume of the communication terminal 2 having the largest total communication volume for each time period selected in step S2 as time series data of the true communication volume, and a discriminator 132 that discriminates between the time series data of the pseudo communication volume generated by the generator 131 and the time series data of the true communication volume (step S3).

[0088] 12 is a flowchart showing a GAN learning process by the learning unit 13 included in the communication management device 1. First, the learning unit 13 acquires time series data of true communication volume to be used as training data (step S50). In step S50, a set of N pieces of time series data of true communication volume is acquired. The time series data of true communication volume indicates the timing of data transmission of a communication terminal 2 having a high throughput among multiple communication terminals 2 having a common group ID.

[0089] Here, as shown in the GAN learning process by the learning unit 13 in FIG. 5, the time-series data of the true communication volume acquired in step S50 is used as training data 134 to be input when the classifier 132 is trained.

[0090] Next, the learning unit 13 inputs the time series data of the true communication volume to the discriminator 132 as training data 134, and adjusts the parameter w of the discriminator 132 so as to discriminate the time series data of the true communication volume from the time series data of the true communication volume (y=1). D ,θ D (Step S51). In Step S51, the learning unit 13 can cause the classifier 132 to learn the time series data of the true communication volume by using, for example, an error backpropagation method. By Step S51, the classifier 132 capable of discriminating the time series data of the true communication volume from the time series data of the true communication volume is constructed in advance.

[0091] Next, the learning unit 13 generates Gaussian noise 130 and provides a random vector of the generated Gaussian noise 130 as an input to the generator 131 (step S52). Next, the generator 131 generates a random vector of the generated Gaussian noise 130 based on the input z and the weighting parameter w G ,θ G Then, a product-sum operation and a threshold process using an activation function are performed to generate time series data G(z) of pseudo communication volume (step S53).

[0092] Next, the classifier 132 is trained. The classifier 132 is trained by using the parameter w D ,θ D First, the learning unit 13 inputs the training data 134 of the time series data of the true communication volume collected in step S50 to the discriminator 132, and uses the backpropagation method or the like to maximize the objective function E of the above formula (2). D ,θ D (Step S54). Note that the label of the training data 134 is set to 1 (time series data of the true communication volume).

[0093] Next, the learning unit 13 provides the time series data of the pseudo communication volume generated by the generator 131 in step S53 to the discriminator 132, and calculates the parameter w by using the backpropagation method or the like so that the objective function E in the above formula (2) is maximized. D ,θ D (Step S55). That is, in steps S54 and S55, in order to maximize the objective function E in the above formula (2), the first term is updated as D(w D ,θ D )=1 is output, and the second term is D(G(w G ,θ G ),w D ,θ D )=0. In addition, in the training data 134, the label is set to 0 (time series data of pseudo communication volume).

[0094] The learning of the classifier 132 in steps S54 and S55 corresponds to the dashed arrow ("Training") shown in FIG. 5, in which a classifier error is calculated in block 135 of the objective function E based on the output 133 from the classifier 132, and then the error is backpropagated to the classifier 132.

[0095] Next, the generator 131 is trained. In the training of the generator 131, the parameters of the discriminator 132 are fixed. The training unit 13 trains the generator 131 so that time-series data of pseudo communication volume is generated when random Gaussian noise 130 is given to the generator 131. Specifically, in order to minimize the objective function E of the above formula (2), the training unit 13 calculates an error and trains the parameter w by using an error backpropagation method or the like. G ,θ G is updated (step S56).

[0096] The learning in step S56 corresponds to the dashed arrow indicating backpropagation of error to the generator 131 shown in Fig. 5. That is, step S56 corresponds to the dashed arrow ("training") in which the time-series data of the pseudo communication volume generated by the generator 131 in Fig. 5 is input to the discriminator 132, a generator error is calculated from the output 133 in the block 135 of the objective function E, and the error is further backpropagated to the generator 131.

[0097] Thereafter, until the value of the objective function E reaches a Nash equilibrium and converges (step S57: NO), the learning of the discriminator 132 and the generator 131 from step S53 to step S56 is repeated. On the other hand, if the value of the objective function E has converged (step S57: YES), the processing from step S51 to step S57 is repeated using the remaining N-1 pieces of time series data of true communication volumes among the N pieces of time series data of true communication volumes until the learning of the generator 131 and the discriminator 132 is performed (step S58: NO).

[0098] Thereafter, when the generator 131 and the discriminator 132 are trained using the remaining N-1 pieces of time-series data of true communication volume (step S58: YES), the training unit 13 stores the trained generator 131' in the second storage unit 15 (step S4). The trained generator 131' is constructed by the above process.

[0099] Next, returning to FIG. 11, the notification unit 16 notifies the multiple communication terminals 2 having the same group ID via the network NW of the learned generator 131' constructed for each group ID as communication management information (step S5). Then, the acquisition unit 21 of the communication terminal 2 acquires the learned generator 131' (step S6). Next, the generation unit 22 of the communication terminal 2 uses the learned generator 131' to generate time series data of pseudo communication volume similar to time series data of true communication volume (step S7). Then, the communication unit 23 of the communication terminal 2 controls the timing of data transmission of its own terminal based on the time series data of the pseudo communication volume generated in step S7, and transmits data (step S8).

[0100] Similarly, the processes from step S6 to step S8 are performed for each of the other communication terminals 2 (IMSI_2 to IMSI_N) to be managed that have the same group ID (group 1). Similarly, the processes from step S1 to step S8 are performed for the communication management process for the communication terminals 2 that have different group IDs.

[0101] As described above, the communication management device 1 according to the present embodiment selects time-series data of communication volume of a communication terminal 2 with high throughput as true data in adversarial learning, and learns a generator 131 that generates time-series data of pseudo communication volume similar to the data transmission timing of the communication terminal 2 with high throughput by learning GAN. Then, the learned generator 131' is notified to the multiple communication terminals 2 as communication management information. Therefore, it is possible to improve the throughput of each of the multiple communication terminals 2 to be managed.

[0102] Furthermore, the communication management device 1 according to the present embodiment groups a plurality of communication terminals 2 to be managed in advance, and learns the optimal data transmission timing for each group. Therefore, it is possible to improve the throughput of each of the communication terminals 2 that need to perform data communication even during periods when the communication band is tight.

[0103] In the above embodiment, a communication management system that complies with 5G has been exemplified, but the communication management system may also be one that complies with 4G / LTE, 6G, etc.

[0104] In addition, in the embodiment described above, the case where GAN is used as the generative model is described, but the generative model is not limited to GAN. For example, VAE (Variational Autoencoder), Autoregressive Models, Energy-Based Models, Transformer-Based Generative Models, etc. can be used.

[0105] The above describes the embodiments of the communication management device, communication management method, and communication management system 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 can be made within the scope of the invention described in the claims. [Explanation of symbols]

[0106] 1...communication management device, 10...setting unit, 11...collection unit, 12...selection unit, 13...learning unit, 14...first memory unit, 15...second memory unit, 16...notification unit, 2...communication terminal, 2a...SIM, 3...base station, 4...core network, 40...AMF, 41...UDM / UDR, 42...SMF, 43...PCF, 44...UPF, 5...data network, 101, 201...bus, 102, 202...processor, 103, 203...main memory device, 41a, 44a, 104, 204...communication interface, 105, 205...auxiliary memory device, 106, 206...input / output I / O, 107, 207...display device, 130...noise, 131...generator, 132...discriminator, 131'...trained generator, 133...output, 134...training data, 135...block of objective function E, T1...table, NW...network.

Claims

1. A collection unit configured to collect time series data of communication volume for each time period of a plurality of communication terminals each identified by a subscriber identifier; A selection unit configured to select, based on the collected time series data of the communication volume, the time series data of the communication volume of a communication terminal having the largest total communication volume for each time period; a learning unit configured to perform adversarial learning of a generative model having a generator that generates pseudo-communication volume time series data similar to the time series data of the true communication volume, using the time series data of the communication volume of the selected communication terminal having the largest total of the communication volume for each time period as the time series data of the true communication volume, and a classifier that distinguishes between the pseudo-communication volume time series data generated by the generator and the time series data of the true communication volume; a notification unit configured to notify the plurality of communication terminals of the trained generator constructed by the learning unit as communication management information; A communication management device comprising:

2. 2. The communication management device according to claim 1, The plurality of communication terminals are a plurality of communication terminals to which common identification information is assigned. A communication management device comprising:

3. 3. The communication management device according to claim 2, The collection unit collects, from a user plane function of a core network, time series data of the communication volume for each time period of the plurality of communication terminals to which the common identification information is assigned. A communication management device comprising:

4. 2. The communication management device according to claim 1, The plurality of communication terminals are a plurality of communication terminals located in the same communication area. A communication management device comprising:

5. 2. The communication management device according to claim 1, The time series data of the pseudo communication volume has a data distribution that has a minimum statistical distance from the data distribution of the time series data of the true communication volume. A communication management device comprising:

6. A collection step of collecting time series data of communication volume for each time period of a plurality of communication terminals each identified by a subscriber identifier; A selection step of selecting, based on the collected time series data of the communication volume, the time series data of the communication volume of a communication terminal having the largest total communication volume for each time period; a learning step of performing adversarial learning of a generative model having a generator that generates pseudo-communication volume time series data similar to the time series data of the true communication volume, using the time series data of the selected communication terminal having the largest total communication volume for each time period as the time series data of the true communication volume, and a classifier that distinguishes between the pseudo-communication volume time series data generated by the generator and the time series data of the true communication volume; a notification step of notifying the plurality of communication terminals of the trained generator constructed in the learning step as communication management information; A communication management method comprising:

7. 7. The communication management method according to claim 6, The plurality of communication terminals are a plurality of communication terminals to which common identification information is assigned. A communication management method comprising:

8. 8. The communication management method according to claim 7, The collecting step collects, from a user plane function of a core network, time series data of the communication amounts of the plurality of communication terminals to which the common identification information is assigned for each of the time periods. A communication management method comprising:

9. 7. The communication management method according to claim 6, The plurality of communication terminals are a plurality of communication terminals located in the same communication area. A communication management method comprising:

10. 7. The communication management method according to claim 6, Furthermore, each of the plurality of communication terminals an acquisition step of acquiring the learned generator of the communication management information notified in the notification step; A generating step of generating time series data of pseudo communication volume similar to the time series data of true communication volume by using the trained generator; A communication step of controlling data transmission in each time period based on the generated time series data of the pseudo communication volume. A communication management method comprising:

11. A communication management device according to any one of claims 1 to 5, The plurality of communication terminals; A communication management system comprising: Each of the plurality of communication terminals an acquisition unit configured to acquire the learned generator of the communication management information notified from the communication management device; A generation unit configured to generate time series data of pseudo communication volume similar to the time series data of true communication volume by using the trained generator; a communication unit configured to control transmission of data in each time period based on the generated time series data of the pseudo communication volume; A communication management system comprising:

Images