Communication control device and communication control method

Abstract

A communication control device (100) comprises: an acquisition unit (111) that acquires first reference information, which includes information pertaining to the location of, the movement speed of, and an application currently in use on a target terminal device, and second reference information, which includes information pertaining to communication load and / or communication quality in each of one or more cells; and a determination unit (112) that executes a determination process for referring to the first reference information and the second reference information to determine a switching destination edge server to which the target terminal device should connect and a switching method that should be used in said switching.

Description

Communication control device and communication control method

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

[0002] In the field of wireless access network technology, research is underway on a technology called Multi-access Edge Computing (MEC), which includes multiple edge servers. In addition, research is underway on several methods that can be applied to connection and switching methods to MEC servers (edge ​​servers) in the MEC technology (for example, Non-Patent Documents 1 to 3).

[0003] 3GPP TS 23.501 v18.4.0 (2023-12)3GPP TS 23.503 v18.4.0 (2023-12)3GPP TS 23.548 v18.4.0 (2023-12)

[0004] Generally, the preferred method of switching to an edge server may differ depending on the location and usage status of the terminal device, but conventional techniques have had problems in this regard.

[0005] In order to solve the above problem, a communication control device of one embodiment includes an acquisition unit that acquires first reference information including information regarding the location, movement speed, and application in use of a target terminal device, and second reference information including information regarding at least one of the communication load and communication quality in each of one or more cells, and a decision unit that executes a decision process by referring to the first reference information and the second reference information to determine the edge server to which the target terminal device should be switched and the switching method to be used in the switching.

[0006] In order to solve the above problem, a communication control device of one embodiment includes: an acquisition unit that acquires learning data that includes at least first reference information including information on the location, movement speed, and application in use of a terminal device; second reference information including information on at least one of the communication load and communication quality in each of one or more cells; and a correct answer label regarding the edge server to which the terminal device should be switched and the switching method to be used in the switching; and a learning unit that learns a prediction model that predicts the edge server to which the terminal device should be connected and the switching method to be used in the switching from the first reference information for inference and the second reference information for inference, by referring to the learning data acquired by the acquisition unit.

[0007] In order to solve the above problem, a communication control method of one embodiment is a communication control method executed by a computer, and includes an acquisition step of acquiring first reference information including information regarding the location, movement speed, and application in use of a target terminal device, and second reference information including information regarding at least one of the communication load and communication quality in each of one or more cells, and a determination step of executing a determination process that refers to the first reference information and the second reference information to determine the edge server to which the target terminal device should be switched and the switching method to be used in the switching.

[0008] In order to solve the above problem, a communication control method according to one embodiment is a communication control method executed by a computer, and includes: an acquisition step of acquiring learning data including at least first reference information including information on the location, moving speed, and application in use of a terminal device; second reference information including information on at least one of the communication load and communication quality in each of one or more cells; and a correct answer label related to the edge server to which the terminal device should be connected and the switching method to be used in the switching; and a learning step of learning a prediction model that predicts the edge server to which the terminal device should be connected and the switching method to be used in the switching from the first reference information for inference and the second reference information for inference, by referring to the learning data acquired by the acquisition unit.

[0009] The communication control device according to each aspect of the present invention may be realized by a computer. In this case, the program for the communication control device that realizes the communication control device on a computer by causing the computer to operate as each part (software element) of the communication control device, and the computer-readable recording medium on which the program is recorded, also fall within the scope of the present invention.

[0010] According to the configurations according to the aspects of the present invention, a method for switching to an edge server can be suitably determined.

[0011] Fig. 1 is a block diagram showing a configuration example of a communication system according to an embodiment; Fig. 2 is a flow diagram showing a flow of a communication control method according to an embodiment; Fig. 3 is a block diagram showing another configuration example of a communication system according to an embodiment; Fig. 4 is a diagram for explaining a prediction model according to an embodiment; Fig. 5 is a diagram for explaining an effect of a communication system according to an embodiment;

[0012] [Embodiment 1] Hereinafter, the configuration of a communication system (also referred to as a communication control system) 1 according to this embodiment will be described with reference to FIG. 1. FIG. 1 is a block diagram showing the configuration of the communication system 1 according to this embodiment. As shown in FIG. 1, the communication system 1 according to this embodiment includes a communication control device 100, an MEC server 200, a base station 300, and a terminal device 400. Here, as shown in FIG. 1, a plurality of MEC servers 200 are included in the communication system 1, and each may be referred to by being assigned a branch number, such as MEC server 200-1 and MEC server 200-2. Similarly, as shown in FIG. 1, a plurality of base stations 300 are included in the communication system 1, and each may be referred to by being assigned a branch number, such as base station 300-1 and base station 300-2.

[0013] In the example shown in FIG. 1 , the communication control device 100 is communicably connected to an MEC server 200-1 and an MEC server 200-2, respectively. The MEC server 200-1 and the MEC server 200-2 are communicably connected to a base station 300-1 and a base station 300-2, respectively. In this embodiment, the MEC server 200-1 and the MEC server 200-2 may be referred to as a first MEC server and a second MEC server, respectively. The base station 300-1 and the base station 300-2 may be referred to as a first base station and a second base station, respectively. Note that, in the example shown in FIG. 1 , only one terminal device 400 is illustrated, but this does not limit the present embodiment, and the communication system 1 may be configured to include multiple terminal devices 400. As an example, the terminal devices are identified from each other in the communication system 1 by terminal IDs.

[0014] (Base Station) The base station 300 performs wireless communication via radio waves with one or more terminal devices (mobile terminal devices, UEs (User Equipment)) 400. As an example, the base station 300 performs various processes, such as: managing one or more cells within the area in which the base station 300 can communicate; establishing communication with terminal devices located in each cell; exchanging data (uplink and downlink); and issuing handover instructions between cells or between base stations to terminal devices. Here, the management of a cell by the base station 300 includes monitoring the communication load in the cell; and monitoring the communication quality in the cell. Here, the base station 300 can be configured to monitor, as an example, at least one of the following indicators of communication load: the cell throughput in the cell; the number of connected users in the cell; and the number of active users in the cell, but this does not limit the present embodiment. Furthermore, as an example, the base station 300 can be configured to monitor at least one of the following as indicators of communication quality: SS-RSRP (Synchronization Signal - Reference Signal Received Power) of the terminal device in the cell; SS-RSRQ (Synchronization Signal - Reference Signal Received Quality) of the terminal device in the cell; RSSI (Received Signal Strength Indicator) of the terminal device in the cell; and SS-SIR (Synchronization Signal - Signal to Interference Ratio) of the terminal device in the cell, but this does not limit the present embodiment.

[0015] As an example, the base station 300 is configured to be able to perform at least processing conforming to the 4G or 5G standard, and may also be referred to as an eNB or a gNB. However, this does not limit the present embodiment. Although not shown in FIG. 1 , the communication system 1 may include a core network that provides data to the base station 300, acquires data from the base station 300, and executes processing by referring to the acquired data.

[0016] Further, as an example, the base station 300 provides the communication control device 100 with the following information (also referred to as second reference information) regarding at least one of the communication load and communication quality in each of one or more cells (C1, C2, C3, ...).

[0017] (MEC Server) The MEC (Multi-access Edge Computing) servers 200 are servers (edge ​​servers) for edge computing that are distributed in plurality in the communication system 1. As an example, the plurality of MEC servers 200 included in the communication system 1 include: a first MEC server connected to a first base station group covering a first area (region) among the plurality of base stations included in the communication system 1; and a second MEC server connected to a second base station group covering a second area (region) among the plurality of base stations included in the communication system 1. In the example shown in FIG. 1 , the MEC server 200-1 is connected to the base station 300-1 that manages the cells C1 and C2 that cover the first area (region), and the MEC server 200-2 is connected to the base station 300-2 that manages the cells C3 and C4 that cover the second area (region).

[0018] The specific processing performed by the MEC server 200 is not limited to this embodiment, but examples include providing data to various applications executed by the target terminal device 400, obtaining data from the applications, and performing processing using the obtained data.

[0019] (Terminal Device) As an example, the terminal device 400 is located in one or more cells that cover the communication area provided by the communication system 1, and communicates with the base station 300 that manages the cell. Furthermore, based on instructions from the base station 300, the terminal device 400 executes processing related to cell switching (handover) and base station switching (handover).

[0020] Furthermore, the terminal device 400 provides the communication control device 100 via the base station 300 with the following information (also referred to as first reference information) regarding the location, moving speed, and application in use of the terminal device 400.

[0021] The term "movement speed" includes at least one of the direction of movement and the speed of movement. The terminal device 400 may be configured to provide position information about the terminal device 400 at each of a plurality of points in time as "information about the movement speed." The communication control device 100 can identify the position and movement speed of the terminal device 400 by referring to the position information about the terminal device 400 at each of the plurality of points in time.

[0022] Furthermore, the terminal device 400 may be configured to provide at least one of the following information as the "information related to the application in use": - Information identifying the application in use (such as an app ID) - Information related to the processing load of the application in use.

[0023] 1, the communication control device 100 includes a control unit 110, a storage unit 120, and a communication unit 130. Each unit included in the communication control device 100 may be implemented in a single device, or may be distributed across multiple devices.

[0024] (Communication Unit 130) The communication unit 130 transmits and receives data to and from devices external to the communication control device 100. As an example, the communication unit 130: - receives the first reference information described above from the terminal device 400 via the base station 300; - receives the second reference information described above from the base station 300. The communication unit 130 also: - transmits MEC server switching control information MCI to the MEC server 200; - transmits base station switching control information NCI to the base station 300; and - transmits cell switching control information CCI to the base station 300. Here, the MEC server switching control information MCI includes, as an example, information indicating: - the destination MEC server to which the target terminal device 400 should be connected; and - the switching method to be used in the switching. The base station switching control information NCI includes, as an example, information indicating the destination base station to which the target terminal device 400 should be connected. The cell switching control information CCI also includes, for example, information indicating the base station to which the target terminal device 400 should be switched.

[0025] (Storage unit 120) The storage unit 120 stores various types of information referenced by the control unit 110 and various types of information derived by the control unit 110. As an example, as shown in FIG. 1 , the storage unit 120 stores the following: First reference information RI1 Second reference information RI2 People flow data HFI Prediction model PM etc. Here, as described above, the first reference information RI1 includes information on the location, movement speed, and applications in use of the target terminal device 400, and is, for example, information acquired from a base station via the communication unit 130. When there are multiple terminal devices, the first reference information RI1 stores, for example, information on the location, movement speed, and applications in use of each terminal device in association with the terminal ID of the terminal device.

[0026] As described above, the second reference information RI2 is information relating to at least one of the communication load and communication quality in each cell, and is, for example, information acquired from each base station via the communication unit 130. For example, the second reference information RI2 stores at least one of the communication load and communication quality for each cell in association with the cell ID of the cell.

[0027] The people flow data HFI is data indicating the flow of people in a target area including the location of the target terminal device 400, and is acquired from an external server, for example. The people flow data stored in the storage unit 120 may be data for each time of day and each day of the week, for example. The communication control device 100 may also be configured to sequentially acquire the latest people flow data for the target area and store it in the storage unit 120. The people flow data includes, for example, position information for buildings, roads, routes, etc. in the target area, and data indicating the movement of people (movement of vehicles) on the buildings, roads, routes, etc.

[0028] The first reference information RI1 and the second reference information RI2 described above are not only referred to in the determination process by the determination unit 112, but also referred to in the learning process of the prediction model PM by the learning unit 114. When referred to in the determination process by the determination unit 112, they are referred to as "first reference information RI1 for inference" or "second reference information RI2 for inference," etc., and when referred to in the learning process by the learning unit 114, they are referred to as "first reference information RI1 for learning" or "second reference information RI2 for learning," etc. As an example, a process may be performed in which the learning unit 114 refers to the past first reference information RI1 and second reference information RI2 for learning, and the determination unit 112 refers to the more recent first reference information RI1 and second reference information RI2 for inference.

[0029] The prediction model PM is a model used in the decision process of the switching decision unit 112, which will be described later. The storage unit 120 stores, as the prediction model PM, a plurality of parameters that define the prediction model PM. The prediction model PM is trained (machine learned) by the learning unit 114, which will be described later, as an example. Furthermore, the prediction model PM is configured as, for example, a convolutional neural network (CNN) and a recurrent neural network (RNN), or a combination of these, but this does not limit the present embodiment. Details of the processing by the prediction model PM will be described later.

[0030] (Control Unit 110 ) As shown in FIG. 1 , the control unit 110 includes an acquisition unit 111 , a determination unit 112 , a switching execution unit 113 , and a learning unit 114 .

[0031] (Acquisition unit 111) The acquisition unit 111 acquires first reference information RI1 including information on the location, movement speed, and applications in use of the target terminal device 400, and second reference information RI2 including information on at least one of the communication load and communication quality in each of one or more cells (C1, C2, ...). The acquisition unit 111 may acquire the first reference information RI1 and the second reference information RI2 via the communication unit 130, or may be configured to acquire this information stored in the storage unit 120.

[0032] (Determining unit 112) The determining unit 112 executes a determination process to determine the edge server (MEC servers 200-1, 200-2, ...) to which the target terminal device 400 should be connected and the switching method to be used in the switching, by referring to the first reference information RI1 and the second reference information RI2 acquired by the acquiring unit 111. According to the above configuration, it is possible to suitably determine the edge server (MEC servers 200-1, 200-2, ...) to which the target terminal device 400 should be connected and the switching method to be used in the switching.

[0033] Here, specific examples of edge server (MEC server) switching methods are not limited to this embodiment, but include, for example: ULCL (Uplink Classifier) ​​(also called BP: Branching Point) URSP (UE Route Selection Policy) (also called PRA: Presence Reporting Area) SSC (Session and Service Continuity) mode 2 SSC (Session and Service Continuity) mode 3 EASDF (Edge Application Service Discovery Function) and the like.

[0034] ULCL is a technology that branches (session breakout) traffic from the UE at the I-UPF, and has the advantage that there is only one destination (PDU session) from the UE's perspective (no special measures are required on the terminal side (UE side)).

[0035] URSP is almost the same as LADN, but it is a technology in which the network side instructs the UE to create a PDU session to the Local-DN, and distributes policies (URSP Rules) to the UE via the PCF on the C-Plane.

[0036] SSC mode 2 is a technology that switches PDU sessions via a UPF distributed at a closer location. When switching PDU sessions, the old PDU session is disconnected and a new PDU session is established. In SSC mode 2, the UE's IP address is changed, but no action is required on the terminal side (UE side). However, action is required on the core network side. The user experience of SSC mode 2 is that there is a temporary interruption, but the delay then decreases.

[0037] SSC mode 3 is also a technology that switches PDU sessions via a UPF distributed at a closer location, but when switching PDU sessions, the new PDU session is connected, traffic is switched, and then the old PDU session is disconnected. In SSC mode 3, the UE's IP address is changed, but the terminal side (UE side) also needs to make adjustments. The core network side also needs to make adjustments. The user experience of SSC mode 3 is that there is no interruption and delays are reduced.

[0038] EASDF is a technology that acts as a DNS resolver, mediating queries to the appropriate DNS based on UE location information, etc., and assisting in the resolution of the FQDN of the MEC (EAS) in the local DN.

[0039] As an example, the determination unit 112 executes the above-described determination process using a prediction model PM. Here, the prediction model PM is a trained model trained using training data including at least the following: first reference information RI1 (first reference information RI1 for learning) including information on the location, moving speed, and applications in use of the target terminal device 400, and second reference information RI2 (second reference information RI2 for learning) including information on at least one of the communication load and communication quality in each of one or more cells (C1, C2, ...), and a ground truth label regarding the edge server to which the target terminal device 400 should be connected and the switching method to be used in the switching.

[0040] 4 is a diagram illustrating the prediction process by the prediction model PM. As shown in FIG. 4, the prediction model PM receives, as an example, the first reference information RI1 and the second reference information RI2 described above, and is configured to output the following: destination (switching destination) cell designation information CII; destination (switching destination) MEC designation information MII; and connection method (switching method) designation information SMI. The determination unit 112 refers to the output information to determine the destination edge server (MEC server 200-1, 200-2, ...) to which the target terminal device 400 should be connected and the switching method to be used in the switching. More specifically, the determination unit 112: - determines the MEC server indicated by the connection destination (switching destination) MEC specification information MII as the switching destination edge server (MEC server 200-1, 200-2, ...) to which the target terminal device 400 should connect; and - determines the switching method indicated by the connection method (switching method) specification information SMI as the switching method to be used in the above-mentioned switching.

[0041] The determination process by the determination unit 112 also includes a process of referring to the above-described first reference information RI1 and second reference information RI2 to determine a switchover destination cell in which the target terminal device 400 should be located. As an example, the determination unit 112 determines a cell indicated by the connection destination (switchover destination) cell designation information CII output by the above-described prediction model PM as the switchover destination cell in which the target terminal device 400 should be located.

[0042] The prediction model PM may also be configured to receive people flow data HFI as input, and the prediction model PM may further refer to the people flow data HFI to output the various specified information (CII, MII, SMI) described above. The determination unit 112 may then use this output as the output of the determination process. In other words, the acquisition unit 111 may further acquire people flow data HFI related to a target area including the location of the target terminal device 400, and the determination unit 112 may further refer to the people flow data HFI to execute the determination process. By having the prediction model PM further refer to the people flow data HFI, the determination process by the determination unit 112 can be more optimal.

[0043] In addition, the prediction model PM may be configured to: - refer to the people flow data HFI only during learning, and not during inference, or - refer to the people flow data HFI both during learning and inference.

[0044] As an example, the prediction model PM may be configured to output the various types of specified information (CII, MII, SMI) described above by referring to the people flow data HFI that is acquired sequentially.

[0045] (Switching Execution Unit 113) The switching execution unit 113 switches at least one of the cell, base station, and MEC server to which the target terminal device 400 should be connected, according to the result of the determination process by the determination unit 112. As an example, the switching execution unit 113 instructs the target terminal device 400 and the associated base station to perform handover to the cell indicated by the cell designation information CII of the connection destination (switching destination).

[0046] The switching execution unit 113 also instructs the target terminal device 400 and the related MEC server to perform handover to the MEC server indicated by the connection destination (switching destination) MEC specification information MII. The switching execution unit 113 also instructs the target terminal device 400 and the related MEC server to use the switching method indicated by the connection method (switching method) specification information SMI in switching the MEC server.

[0047] (Learning Unit 114) The learning unit 114 trains the learning model PM. As an example, the learning unit 114 trains the learning model PM using training data including at least: the first reference information RI1 for learning, the second reference information RI2 for learning, and a correct label for the edge server to which the target terminal device 400 should be connected and the switching method to be used in the switching. As an example, the learning unit 114 inputs the first reference information RI1 for learning and the second reference information RI2 for learning to the prediction model PM, and trains the prediction model PM by updating one or more parameters of the prediction model PM so as to reduce the difference between the output of the prediction model PM and the correct label.

[0048] The learning unit 114 may be configured to subsequently acquire correct labels corresponding to the first reference information RI1 and the second reference information RI2 that have been used for inference, and re-learn the learning model PM using the correct labels. Furthermore, such re-learning may be repeated. This configuration allows the prediction model PM to perform more accurate predictions, thereby making the determination process by the determination unit 112 more suitable.

[0049] As described above, the communication control device 100 uses, as an example, a machine-learned prediction model PM to control the edge server to which the target terminal device 400 should be switched and the switching method to be used in the switching, and is also called a RAN Intelligent Controller (RIC). However, this name does not limit the present embodiment.

[0050] (Processing Flow by Communication Control Device 100) The processing flow by the communication control device 100 will be described below with reference to Fig. 3. Fig. 3 is a flow chart showing the processing flow by the communication control device 100.

[0051] (Step S11) In step S11, the acquiring unit 111 acquires the first reference information RI1 and the second reference information RI2. Details of the first reference information RI1 and the second reference information RI2 have been described above, and therefore will not be described here.

[0052] (Step S12) In step S12, the determination unit 112 executes a determination process to determine the edge server (MEC server 200-1, 200-2, ...) to which the target terminal device 400 should be connected and the switching method to be used in the switching, by referring to the first reference information RI1 and the second reference information RI2 acquired by the acquisition unit 111 in step S11. Specific examples of the determination process by the determination unit 112 have been described above, and therefore will not be described here.

[0053] (Step S13) In step S13, the switching execution unit 113 switches at least one of the cell, the base station, and the MEC server to which the target terminal device 400 should be connected, in accordance with the result of the determination process by the determination unit 112. Specific examples of the process by the switching execution unit 113 have been described above, and therefore will not be described here.

[0054] (Additional Notes Regarding Communication System 1) The communication control device 100 may be configured to execute only the learning phase of the prediction model PM without executing the inference phase using the prediction model PM. In such a configuration, the communication control device 100 may be configured without the above-described determination unit 112 and switching execution unit 113, and such a configuration is also included in the configuration described in this embodiment.

[0055] (Another Configuration Example of Communication System) Next, another configuration example of the communication system according to this embodiment will be described. FIG. 4 is a block diagram showing the configuration of a communication system (also referred to as a communication control system 2) 2 according to this embodiment. As shown in FIG. 4, the communication system 2 includes a server group 500, a first MEC server group 600-1, a second MEC server group 600-2, and a terminal device 400. Note that the communication system 2 may be configured to include a plurality of terminal devices 400. As an example, the respective terminal devices are identified from each other in the communication system 2 by terminal IDs.

[0056] (Server group 500) The server group 500 is composed of one or more server groups that play the roles of a core network and a data center in the communication system 2. As an example, as shown in Fig. 4, the server group 500 includes a core network 510 and a model learning unit 520. As an example, the core network 510 has various functions that a core network for configuring a communication system compliant with the 4G or 5G standard has.

[0057] The model learning unit 520 has, for example, the same configuration as the above-described learning unit 114. For example, the model learning unit 520 learns a prediction model PM using learning data including, for each of the multiple terminal devices 400: the above-described first reference information RI1; the above-described second reference information RI2; the above-described people flow data HFI; and a correct answer label for the edge server to which each of the target terminal devices 400 should be switched and the switching method to be used in the switching. The prediction model PM learned by the learning unit 520 is supplied to the first MEC 600-1, the second MEC 600-2, ... as an initial model.

[0058] (First MEC 600-1) The first MEC 600-1 is realized by one or more physical servers or virtual servers for realizing multiple functions described below, and is also referred to as the first MEC server 600-1. As an example, the first MEC 600-1 includes a UPF 610-1, an application management unit 620-1, a communication control device 100-1, and a gNB 630-1, as shown in FIG.

[0059] (UPF (User Plane Function)) The UPF 610-1 is, for example, a network function (NF) that executes various processes related to U-Plane communication in the 5G standard.

[0060] (Application Management Unit) The application management unit 620-1, for example, provides data to various applications executed by the target terminal device 400, acquires data from the applications, and executes processing by referring to the acquired data.

[0061] (Communication control device) The communication control device 100-1, as an example, has the same functions as the above-described communication control device 100. However, while in the communication system 1, the communication control device 100 was realized in a form separate from the MEC server 200, in the communication system 2 according to this example, the communication control device 100-1 is implemented as part of the first MEC 600-1. The various processes executed by the communication control device 100-1 are the same as those of the communication control device 100, and therefore description thereof will be omitted here.

[0062] (gNB) The gNB 630-1 is, for example, a base station that performs various processes compliant with the 5G standard. The gNB 630-1 has, for example, the same functions as the base station 300 described above. However, in the communication system 1, the base station 300 was realized in a form separate from the MEC server 200, but in the communication system 2 according to this example, the base station 300 is implemented as part of the first MEC 600-1.

[0063] (Second MEC 600-2) As an example, the second MEC 600-2 includes a UPF 610-2, an application management unit 620-2, a communication control device 100-2, and a gNB 630-2, similar to the first MEC 600-1, as shown in Figure 4. The configuration of each unit has been described in the first MEC 600-1, so description thereof will be omitted here.

[0064] The communication system 2 configured as above also includes: an acquisition unit (acquisition unit 111 provided in each of the communication control devices 100-1, 100-2, ...) that acquires first reference information RI1 including information on the location, movement speed, and application in use of a target terminal device, and second reference information RI2 including information on at least one of the communication load and communication quality in each of one or a plurality of cells; and a decision unit (decision unit 112 provided in each of the communication control devices 100-1, 100-2, ...) that executes a decision process to determine a switching destination edge server (first MEC 600-1, second MEC 600-2, ...) to which the target terminal device 400 should be connected and a switching method to be used in the switching, by referring to the first reference information RI1 and the second reference information RI2. Therefore, it is possible to suitably determine the edge server (first MEC 600-1, second MEC 600-2, ...) to which the target terminal device 400 should be connected and the switching method to be used in the switching.

[0065] (Explanation of Effects of Communication Systems 1 and 2) Examples of effects of the above-described communication systems 1 and 2 will be described below with reference to Fig. 5. Fig. 5 is a diagram for explaining examples of effects of the communication systems 1 and 2 according to this embodiment.

[0066] In Fig. 5, a first terminal device UE1 is moving along a route P1, and a second terminal device UE2 is moving along a route P2. Here, route P1 is, for example, a general road or a conventional railroad line. Route P2 is, for example, a highway or a Shinkansen. Also, symbols MR1, MR2, and MR3 in Fig. 5 indicate areas covered by MEC1, MEC2, and MEC3, respectively.

[0067] As a comparative example, if the configurations according to this embodiment are not adopted, both UE1 and UE2 will switch between MECs after moving to the next MEC area.

[0068] On the other hand, the determination unit 112 according to this embodiment refers to the first reference information RI1, the second reference information RI2, and the people flow data HFI to determine the edge servers (MEC1, MEC2, MEC3) to which the target terminal devices UE1 and UE2 should be connected and the switching method to be used in the switching, so that the next destination can be predicted and data linkage between MECs can be performed smoothly. Therefore, even lower latency can be expected and the user experience can be improved without changing the communication standard itself.

[0069] [Example of implementation using software] The functions of the communication control devices 100, 100-1, and 100-2 (hereinafter referred to as "devices") can be realized by a program that causes a computer to function as the device, and a program that causes a computer to function as each control block of the device (particularly each part included in the control unit 110).

[0070] In this case, the device includes a computer having at least one control device (e.g., a processor) and at least one storage device (e.g., a memory) as hardware for executing the program. The functions described in each of the above embodiments are realized by executing the program using the control device and storage device.

[0071] The program may be non-transitory and may be recorded on one or more computer-readable recording media. The recording media may or may not be included in the device. In the latter case, the program may be supplied to the device via any wired or wireless transmission medium.

[0072] Furthermore, some or all of the functions of the control blocks can be realized by logic circuits. For example, an integrated circuit in which a logic circuit that functions as each of the control blocks is formed is also included in the scope of the present invention. In addition, the functions of the control blocks can also be realized by, for example, a quantum computer.

[0073] (Additional Note) The configuration described in this specification can also be expressed as follows.

[0074] (Supplementary Note 1) A communication control device comprising: an acquisition unit that acquires first reference information including information on the location, movement speed, and applications in use of a target terminal device, and second reference information including information on at least one of the communication load and communication quality in each of one or more cells; and a decision unit that executes a decision process by referring to the first reference information and the second reference information to determine an edge server to which the target terminal device should be switched and a switching method to be used in the switching.

[0075] (Supplementary Note 2) The communication control device according to Supplementary Note 1, wherein the determination unit executes the determination process using a trained model trained using training data including at least the first reference information for learning, the second reference information for learning, and a correct answer label for an edge server to which a terminal device should be connected and a switching method to be used in the switching.

[0076] (Supplementary Note 3) The communication control device according to Supplementary Note 1 or 2, wherein the determination process includes a process of determining a switching destination cell in which the target terminal device should be located, by referring to the first reference information and the second reference information.

[0077] (Supplementary Note 4) The communication control device according to any one of Supplementary Notes 1 to 3, wherein the acquisition unit further acquires people flow data relating to a target area including a location where the target terminal device is located, and the determination unit further refers to the people flow data to execute the determination process.

[0078] (Supplementary Note 5) A communication control device comprising: an acquisition unit that acquires learning data including at least first reference information including information on a location, a moving speed, and an application in use of a terminal device; second reference information including information on at least one of a communication load and a communication quality in each of one or a plurality of cells; and a correct answer label related to an edge server to which the terminal device should be switched and a switching method to be used in the switching; and a learning unit that learns a prediction model that predicts the edge server to which the terminal device should be connected and the switching method to be used in the switching, from the first reference information for inference and the second reference information for inference, by referring to the learning data acquired by the acquisition unit.

[0079] (Supplementary Note 6) A communication control method executed by a computer, comprising: an acquisition step of acquiring first reference information including information on the location, movement speed, and application in use of a target terminal device, and second reference information including information on at least one of the communication load and communication quality in each of one or more cells; and a determination step of executing a determination process by referring to the first reference information and the second reference information to determine an edge server to which the target terminal device should be switched and a switching method to be used in the switching.

[0080] (Supplementary Note 7) A communication control method executed by a computer, comprising: an acquisition step of acquiring learning data including at least first reference information including information on a terminal device's location, moving speed, and application in use; second reference information including information on at least one of a communication load and a communication quality in each of one or a plurality of cells; and a correct answer label for an edge server to which the terminal device should be switched and a switching method to be used in the switching; and a learning step of learning a prediction model that predicts the edge server to which the terminal device should be connected and the switching method to be used in the switching, from the first reference information for inference and the second reference information for inference, by referring to the learning data acquired by the acquisition unit.

[0081] The present invention is not limited to the above-described embodiments, and various modifications are possible within the scope of the claims. Embodiments obtained by appropriately combining the technical means disclosed in different embodiments are also included in the technical scope of the present invention. Furthermore, new technical features can be formed by combining the technical means disclosed in each embodiment.

[0082] 1, 2 ... Communication system 100, 100-1, 100-2 ... Communication control device 110 ... Control unit 111 ... Acquisition unit 112 ... Determination unit 113 ... Switching execution unit 114 ... Learning unit 200-1, 200-2 ... MEC server 600-1 ... First MEC (MEC server) 600-2 ... Second MEC (MEC server) 300-1, 300-2 ... Base station 630-1, 630-2 ... gNB (base station)

Claims

1. A communication control device comprising: an acquisition unit that acquires first reference information including information regarding the location, movement speed, and applications in use of a target terminal device, and second reference information including information regarding at least one of the communication load and communication quality in each of one or more cells; and a decision unit that executes a decision process by referring to the first reference information and the second reference information to determine the edge server to which the target terminal device should be switched and the switching method to be used in the switching.

2. The communication control device according to claim 1, wherein the determination unit executes the determination process using a trained model trained using training data including at least the first reference information for learning, the second reference information for learning, and a correct answer label for the edge server to which the terminal device should be connected and the switching method to be used in the switching.

3. The communication control device according to claim 1 or 2, wherein the determination process includes a process of determining a switching destination cell in which the target terminal device should be located by referring to the first reference information and the second reference information.

4. A communication control device as described in any one of claims 1 to 3, wherein the acquisition unit further acquires people flow data relating to a target area including the location of the target terminal device, and the determination unit further refers to the people flow data to execute the determination process.

5. A communication control device comprising: an acquisition unit that acquires learning data including at least first reference information including information on the location, movement speed, and applications in use of a terminal device; second reference information including information on at least one of the communication load and communication quality in each of one or more cells; and a correct answer label for the edge server to which the terminal device should be switched and the switching method to be used in the switching; and a learning unit that learns a prediction model that predicts the edge server to which the terminal device should be connected and the switching method to be used in the switching from the first reference information for inference and the second reference information for inference, by referring to the learning data acquired by the acquisition unit.

6. A communication control method executed by a computer, comprising: an acquisition step of acquiring first reference information including information on the location, movement speed, and application in use of a target terminal device, and second reference information including information on at least one of the communication load and communication quality in each of one or more cells; and a determination step of executing a determination process that refers to the first reference information and the second reference information to determine the edge server to which the target terminal device should be switched and the switching method to be used in the switching.

7. A communication control method executed by a computer, comprising: an acquisition step of acquiring learning data including at least: first reference information including information on the location, movement speed, and applications in use of a terminal device; second reference information including information on at least one of the communication load and communication quality in each of one or more cells; and a correct answer label for the edge server to which the terminal device should be switched and the switching method to be used in the switching; and a learning step of learning a prediction model that predicts the edge server to which the terminal device should be connected and the switching method to be used in the switching, from the first reference information for inference and the second reference information for inference, by referring to the learning data acquired in the acquisition step.

Images