Information processing device, method for controlling information processing device, and program for controlling information processing device

Abstract

This information processing device (RAN Intelligent Controller (RIC)) comprises: a change acquisition unit that acquires environment information including information relating to a future change in environment in a coverage area of a base station; a quality information acquisition unit that acquires an actual measurement value of communication quality between the base station and a communication terminal; a first calculation unit that predicts the communication quality between the base station and the communication terminal when a parameter value pertaining to the base station is set to the base station in the environment after the change, and calculates a parameter value that brings the difference between the prediction value of the communication quality and the actual measurement value of the communication quality in the environment before the change close to zero; and a learning unit that learns a correspondence relationship between the predicted value, the parameter value, the environment information, and the actual measurement value of the communication quality when the parameter value calculated by the first calculation unit is set to the base station in the environment after the change, and generates a learning model that outputs a parameter value for bringing the difference between the predicted value and the measured value close to zero when prescribed environment information is inputted. The first calculation unit calculates the parameter value using the learning model.

Description

Information processing device, control method for information processing device, and control program for information processing device

[0001] The present invention relates to an information processing device, a control method for an information processing device, and a control program for an information processing device.

[0002] Conventionally, there has been a problem of providing a wireless quality estimation system that estimates wireless quality taking into account environmental information that changes over time, and that takes into account future quality degradation and determines by when preventive measures against quality degradation should be implemented (for example, Patent Document 1).

[0003] WO 2009 / 119786

[0004] Considering the effect that environmental changes have on communication quality, the setting parameter values ​​of base stations are changed, but it is required to quickly and accurately reset the parameter values.

[0005] An information processing device according to one embodiment of the present invention includes a change acquisition unit that acquires environmental information relating to the environment, including information relating to future environmental changes in the coverage area of ​​the base station; a quality information acquisition unit that acquires actual measured values ​​of communication quality between the base station and the communication terminal from a communication terminal connected to the base station; a first calculation unit that calculates parameter values ​​of the base station, which are parameter values ​​that predict the communication quality between the base station and the communication terminal when the parameter values ​​are set in the base station in a changed environment, and calculates parameter values ​​that bring the difference between the predicted value of communication quality and the actual measured value of communication quality in the environment before the change closer to zero; and a learning unit that learns the correspondence between the actual measured value of communication quality when the parameter values ​​calculated by the first calculation unit are set in the base station in a changed environment, acquired from the quality information acquisition unit, the predicted value, the parameter value, and environmental information, and generates a learning model that outputs parameter values ​​that bring the difference between the predicted value and the actual measured value closer to zero when specified environmental information is input, and the first calculation unit calculates the parameter values ​​using the learning model.

[0006] In an information processing device according to one embodiment of the present invention, the device further includes a collection unit that collects various types of information acquired from a plurality of information acquisition devices installed in the environment, and a second calculation unit that reflects the various types of information in a digital twin of an environment constructed in a virtual space by simulating a real space in which a base station and a communication terminal exist, and predicts communication quality in the changed environment using a plurality of parameter values ​​of the base station on the digital twin, and the first calculation unit may use the parameter values ​​calculated by the second calculation unit to train the learning model.

[0007] In an information processing device according to one embodiment of the present invention, the change acquisition unit acquires information relating to a building under construction in the coverage area as environmental information, and the first calculation unit calculates parameter values ​​when the shape of the building under construction changes as the environment after the change.

[0008] In an information processing device according to one embodiment of the present invention, the change acquisition unit may acquire, as environmental information, a plurality of images of the coverage area taken in chronological order, and the first calculation unit may calculate a parameter value based on the changes extracted from the plurality of images as the environment after the change.

[0009] In an information processing device according to one embodiment of the present invention, the first calculation unit may calculate parameter values ​​of other base stations adjacent to the base station in addition to the parameter values ​​of the base station in order to bring the communication quality of a communication terminal present in the coverage area of ​​the base station closer to the actual measured value in the environment before the change.

[0010] A control method for an information processing device according to one embodiment of the present invention includes a change acquisition step of acquiring environmental information related to the environment, including information regarding future environmental changes in the coverage area of ​​the base station; a quality information acquisition step of acquiring actual measured values ​​of communication quality between the base station and the communication terminal from a communication terminal connected to the base station; a first calculation step of calculating parameter values ​​of the base station, which are parameter values ​​of the base station, predicting the communication quality between the base station and the communication terminal connected to the base station when the parameter values ​​are set to the base station in a changed environment, and calculating parameter values ​​that bring the difference between the predicted value of communication quality and the actual measured value of communication quality in the environment before the change closer to zero; a learning step of learning the correspondence between the actual measured value of communication quality when the parameter values ​​calculated in the first calculation step are set to the base station in the changed environment, acquired in the quality information acquisition step, the predicted value, the parameter value, and environmental information, and generating a learning model that outputs parameter values ​​that bring the difference between the predicted value and the actual measured value closer to zero when specified environmental information is input; and a step of calculating parameter values ​​using the learning model.

[0011] A control program for an information processing device according to one embodiment of the present invention causes the information processing device to function as: a change acquisition function that acquires environmental information related to the environment, including information about future environmental changes in the coverage area of ​​the base station; a quality information acquisition function that acquires, from a communication terminal connected to the base station, an actual measured value of communication quality between the base station and the communication terminal; a first calculation function that predicts, as a parameter value of the base station, the communication quality between the base station and a communication terminal connected to the base station when the parameter value is set in the base station in a changed environment, and calculates a parameter value that brings the difference between the predicted value of communication quality and the actual measured value of communication quality in the environment before the change closer to zero; a learning function that learns the correspondence between the actual measured value of communication quality when the parameter value calculated by the first calculation function is set in the base station in a changed environment, acquired by the quality information acquisition function, the predicted value, the parameter value, and environmental information, and generates a learning model that outputs a parameter value that brings the difference between the predicted value and the actual measured value closer to zero when specified environmental information is input; and a function that calculates the parameter value using the learning model.

[0012] When changing the setting parameter values ​​of a base station, taking into consideration the effect of environmental changes on communication quality, it is possible to quickly and accurately reset the parameter values.

[0013] FIG. 1 is a schematic diagram of an information processing system configuration according to an embodiment of the present invention. FIG. 2 is an example of a functional block diagram of an information processing device according to an embodiment of the present invention. FIG. 3 is an example of a data flow in an information processing system according to an embodiment of the present invention. FIG. 4 is an example of a data flow in an information processing system according to an embodiment of the present invention. FIGS. 5(a) to 5(c) are schematic diagrams for explaining an information processing system according to an embodiment of the present invention. FIG. 6 is a flowchart showing an example of the operation of an information processing device according to an embodiment of the present invention.

[0014] Hereinafter, an embodiment of the invention according to the present disclosure (also referred to as the present invention) will be described using the drawings. Note that the drawings are merely examples, and the present invention is not limited to those shown in the drawings. For example, the numbers of information processing devices, communication terminals, and base stations, functional block diagrams, flowcharts, and data flows shown in the drawings are merely examples, and the present invention is not limited to these.

[0015] <System Configuration> Fig. 1 is a diagram showing an example configuration of an information processing system according to an embodiment of the present invention. The information processing system 600 includes a plurality of communication terminals UE, a radio access network RAN ​​(Radio Access Network) 400, and a core network CN. The RAN 400 includes a base station 200 and an information processing device 100. Note that this embodiment assumes a 5G (fifth generation) mobile communication system, and the RAN 400 may be a RAN to which specifications defined by the industry association O-RAN Alliance (Open Radio Access Network Alliance) are applied. Furthermore, the base station 200 may include a radio unit (RU), a distribution unit (DU), and a central unit (CU). Note that the CU / DU may be implemented by a virtual RAN (vRAN), which implements each function using software on general-purpose hardware.

[0016] The information processing device 100 may be implemented with a RAN Intelligent Controller (RIC), which is defined as a logical node in O-RAN that designs and configures base station parameters and automates and optimizes operation. The information processing device 100 and the base station 200 are communicably connected via a network. Note that the base station 200 may have the functions of the information processing device 100.

[0017] <Information Processing Apparatus> Next, the hardware configuration and functional configuration of the information processing apparatus 100 will be described with reference to Fig. 2. (1) Hardware Configuration of Information Processing Apparatus The information processing apparatus 100 includes a control unit 110, a communication unit 120, an input / output unit 130, and a storage unit 170.

[0018] The control unit 110 is typically a processor, including a central processing unit (CPU), a microprocessing unit (MPU), a graphics processing unit (GPU), a microprocessor, etc., and is realized by a logic circuit (hardware) or a dedicated circuit formed in an integrated circuit (IC (Integrated Circuit) chip, LSI (Large Scale Integration)), etc. The control unit 110 reads out a program (software) stored in the storage unit 170 and executes the code and instructions included in the program, thereby performing the functions and methods described in each embodiment.

[0019] The storage unit 170 stores various programs and various data required for the operation of the information processing device 100. The storage unit 170 may include, for example, a hard disk drive (HDD), a solid state drive (SSD), a flash memory, etc. The storage unit 170 may also include memory (random access memory (RAM), read only memory (ROM), etc.) that provides a working area for the control unit 110.

[0020] The communication unit 120 is implemented as hardware such as a network adapter, communication software, or a combination of these. The communication unit 120 transmits and receives various types of data to and from the base station 200.

[0021] The input / output unit 130 includes an input device that accepts various operations from an administrator or the like on the information processing device 100, and an output unit that outputs processing results processed by the information processing device 100. The input device may include, for example, a keyboard and a microphone, and the output device may include, for example, a display and a speaker.

[0022] (2) Functional Configuration of Information Processing Apparatus The information processing apparatus 100 includes, as functions realized by the control unit 110, a change acquisition unit 111, a quality information acquisition unit 112, a prediction unit 113, a first calculation unit 114, a learning unit 115, a second calculation unit 117, and a collection unit 116. Note that, among the functional units shown in FIG. 2 , functional units that are not essential for the embodiments described hereinafter may be omitted. Furthermore, the functions or processes of the functional units may be realized by machine learning (ML) or artificial intelligence (AI) to the extent feasible.

[0023] First Embodiment The processing of each functional unit of the information processing device 100 in the first embodiment will be described with reference to the data flow diagram of FIG. 3 . First, the change acquisition unit 111 acquires environmental information related to the environment, including information regarding future environmental changes in the coverage area of ​​each base station 200. Future environmental changes in the coverage area relate to the appearance or disappearance of factors that may affect radio wave propagation and throughput within the coverage area, such as the construction or demolition of obstacles such as buildings or houses, the construction of facilities that attract people, and changes in the terrain. The environmental information may include, for example, 3D (three-dimensional) terrain information (data 11) of the area within the coverage area, 3D building information (data 12) obtainable from existing services, images capturing daily changes (data 13), and development plans (data 14) by local governments or developers in the area within the coverage area. Images may be obtained, for example, from fixed cameras installed within the area or management cameras installed on buildings under construction. The development plan may also include information about the structure of the building to be constructed, including the height and materials, and the construction schedule. This environmental information is stored in a predetermined storage 15. Note that the environmental information is not limited to the information described above.

[0024] The quality information acquisition unit 112 acquires communication quality (data 10) between the base station 200 and the communication terminal UE, measured by the communication terminal UE connected to the base station 200. The communication quality may be, for example, radio wave attenuation information, received signal power, signal-to-noise ratio (SNR), signal-to-interference plus noise ratio (SINR), received signal strength indicator (RSSI), reference signal received quality (RARQ), packet error rate, number of arriving bits, bit error rate (BER), packet arrival delay time, average traffic capacity, number of call disconnections, etc. The acquired actual measurement value of the communication quality is also stored in the storage 15. Note that the quality information acquisition unit 112 also acquires location information of the communication terminal UE that transmitted the communication quality in order to determine the distribution status of the communication quality in the coverage area.

[0025] The prediction unit 113 predicts (simulates) the communication quality between the base station 200 and the communication terminal UE when the environment in the coverage area changes. The prediction by the prediction unit 113 may be performed using, for example, an existing radio wave propagation simulator. The radio wave propagation simulator analyzes radio wave propagation in a 3D model of the coverage area environment generated on a computer (in a digital space) using techniques such as the ray tracing method, the FDTD method, the method of moments, and the finite element method. The prediction unit 113 can simulate and predict communication quality when, for example, the height of a building under construction increases.

[0026] The first calculation unit 114 calculates parameter values ​​for the base station 200 that bring the difference between the predicted value of communication quality between the base station 200 and the communication terminal UE, predicted by the prediction unit 113, when the parameter values ​​are set in the base station 200 in the changed environment and the actual measured value of communication quality in the environment before the change closer to zero. Here, the parameter values ​​for the base station 200 may be transmission power, handover parameters, antenna tilt angle, antenna azimuth angle, antenna beam width, transmission gain, etc. In order to prevent a decrease in communication quality due to a change in the environment, the first calculation unit 114 calculates parameter values ​​(data 17) for the base station 200 that bring the predicted value of communication quality due to the change in the environment closer to the actual measured value of communication quality before the change. That is, the calculation of the parameter values ​​by the first calculation unit 114 and the prediction (simulation) of communication quality by the prediction unit 113 when the calculated parameter values ​​are set in the base station 200 may be repeated until the predicted value satisfies a predetermined condition (step 16). As described above, the predetermined condition may be that the difference between the predicted value by the prediction unit 113 and the actual measured value of the environment before the change is close to or equal to zero. It is preferable that the communication quality does not change across the entire coverage area before and after the change in the environment. However, for example, a priority may be assigned to each predetermined section, and the communication quality of a section with a higher priority may be prioritized. The priority may be set, for example, according to the location of a crowded area such as a train station or a facility where an event is held, or according to a time period when there are many people or when there are few people.

[0027] The learning unit 115 learns the correspondence between the actual measurement value (data 20), the predicted value (data 19), the parameter value (data 17), and the environmental information (data 11-14) of communication quality when the parameter value calculated by the first calculation unit 114 is set in the base station 200 in the changed environment acquired from the quality information acquisition unit 112, and generates a learning model that outputs parameter values ​​that bring the difference (data 22) between the predicted value and the actual measurement value closer to zero when predetermined environmental information is input (step 23). That is, the learning by the learning unit 115 may be machine learning with teacher data. However, the learning by the learning unit 115 is not limited to this and may be deep learning. The learning unit 115 may repeat the above learning each time the parameter value of the base station 200 is reset, thereby improving the accuracy of the learning model.

[0028] As described above, according to one embodiment of the present invention, the effects of environmental changes are simulated in advance, and parameter values ​​for the base station are set to counteract the effects. Then, the differences between the predicted values ​​obtained by the simulation and the actual values ​​measured when the parameter values ​​are actually set in the base station, the set parameter values, and environmental information are learned, so that parameter values ​​for counteracting environmental changes can be calculated more accurately and quickly.

[0029] The environment information also includes information about buildings under construction in the coverage area, and the first calculation unit 114 calculates parameter values ​​for a changed environment when the shape of the buildings under construction changes, thereby making it possible to set appropriate parameter values ​​that take into account radio wave interference caused by the buildings under construction.

[0030] The environmental information also includes multiple images of the coverage area captured in time series, and the first calculation unit 114 calculates parameter values ​​based on changes extracted from the multiple images as the changed environment. This makes it possible to accurately determine changes in the environment and set parameter values ​​that take the changes in the environment into greater consideration.

[0031] Second Embodiment Next, the processing of each functional unit of the information processing device 100 in the second embodiment will be described with reference to the data flow diagram of FIG. 4 . FIG. 4 illustrates an example of a data flow according to the second embodiment, in which the process 30 indicated by the dashed line is added to the data flow of FIG. 3 . Returning to FIG. 2 , the collection unit 116 collects various information acquired from multiple information acquisition devices installed in the environment within the coverage area of ​​the base station 200. The information acquisition devices are various Internet of Things (IoT) devices installed in the area, such as a motion sensor, a temperature sensor, a rainfall sensor, a humidity sensor, and a wind speed / wind direction sensor. The second calculation unit 117 reflects the various collected information in a digital twin of an environment constructed in a virtual space by simulating the real space in which the base station 200 and the communication terminal UE exist, and predicts communication quality in the digital twin using parameter values ​​of various base stations (data 31 in FIG. 4 ) in the changed environment (step 32 in FIG. 4 ). The learning unit 115 may use the predicted value (data 33) and the parameter value at that time (data 31) to train the learning model.

[0032] In this way, according to one embodiment of the present invention, weather and people flow in the real world can be reflected in the digital twin in real time, and the impact that may have on communication quality can be simulated. As a result, parameter values ​​to be set for base stations can be calculated more quickly.

[0033] Third Embodiment Next, a third embodiment will be described with reference to FIG. 5 . The first calculation unit 114 may calculate parameter values ​​of other base stations adjacent to the base station 200 in addition to the parameter values ​​of the base station 200, in order to bring the communication quality of a communication terminal UE present in the coverage area of ​​the base station 200 closer to the actual measured value in the environment before the change. For example, as shown in FIG. 5( a), assume that the coverage areas of the base stations 200A to 200C are areas A1 to A3, respectively. Then, as shown in FIG. 5( b), assume that due to an environmental change, the coverage area of ​​the base station 200A changes to area A1', and the direction of the base station 200B can no longer be covered. In this case, the first calculation unit 114 may also calculate parameter values ​​for the base stations 200B and 200C using the above-described process. By changing the parameter values, the beam direction, coverage area, and transmission power of the antennas of the base stations 200B and 200C may be changed, and mutual complementation by the areas A1' to A3' may be realized as shown in FIG. 5(c).

[0034] As described above, according to one embodiment of the present invention, parameter values ​​are changed for surrounding base stations as well, making it possible to more flexibly respond to changes in communication quality due to changes in the environment.

[0035] <Control Flow of Information Processing Device> The control flow of the information processing device 100 described above will be described with reference to Figures 3 to 6. First, the change acquisition unit 111 acquires environmental information related to the environment, including information about future environmental changes in the coverage area of ​​the base station 200 (step S11). The quality information acquisition unit 112 acquires an actual measurement value of communication quality between the base station 200 and the communication terminal UE from the communication terminal UE connected to the base station 200 (step S12). The first calculation unit 114 predicts the communication quality between the base station 200 and the communication terminal UE when the parameter values ​​of the base station 200 are set in the base station 200 in the changed environment, and calculates parameter values ​​that bring the difference between the predicted value of communication quality and the actual measurement value of communication quality in the environment before the change closer to zero (step S13). The learning unit 115 learns the correspondence relationships between the actual measurement value of communication quality when the calculated parameter value is set in the base station 200 in the changed environment, the predicted value, the parameter value, and the environmental information, and generates a learning model that outputs parameter values ​​that bring the difference between the predicted value and the actual measurement value closer to zero when predetermined environmental information is input (step S14). The first calculation unit 114 calculates the parameter value using the learning model (step S15).

[0036] While the present invention has been described based on the drawings and examples, it should be noted that those skilled in the art would easily be able to make various modifications and alterations based on the present disclosure. Therefore, it should be noted that these modifications and alterations are within the scope of the present invention. For example, the functions included in each component, step, etc. can be rearranged so as not to cause logical inconsistencies, and multiple components, steps, etc. can be combined or divided into one. Furthermore, the configurations described in the above embodiments may be appropriately combined. For example, each component described as being included in the information processing device 100 may be realized in a distributed manner by multiple information processing devices. Furthermore, the processing described above as being performed by the information processing device 100 may be performed by the base station 200.

[0037] Furthermore, although the above description has been given using a 5G mobile communication system as an example, the present invention is not limited to this and may also be applied to mobile communication systems such as 4G (fourth generation), 6G (sixth generation), and LTE.

[0038] Furthermore, in the above description, the parameter values ​​of an existing base station are changed, but the present invention is not limited to this, and parameter values ​​may be calculated when a new base station is installed.

[0039] The programs of the embodiments of the present disclosure may be provided in a state stored in a storage medium readable by an information processing device. The storage medium may store the programs in a "non-transitory tangible medium." The programs include, for example, software programs and control programs. When the functional units of the information processing device 100 are realized by software, the information processing device 100 functions as a change acquisition unit 111, a quality information acquisition unit 112, a prediction unit 113, a first calculation unit 114, a learning unit 115, a second calculation unit 117, and a collection unit 116 by the processor executing the programs loaded into the memory.

[0040] The storage medium may, where appropriate, comprise one or more semiconductor-based or other integrated circuits (ICs) (e.g., field programmable gate arrays (FPGAs), application specific ICs (ASICs), etc.), hard disk drives (HDDs), hybrid hard drives (HHDs), optical disks, optical disk drives (ODDs), magneto-optical disks, magneto-optical drives, floppy diskettes, floppy disk drives (FDDs), magnetic tapes, solid state drives (SSDs), RAM drives, secure digital cards or drives, any other suitable storage media, or any suitable combination of two or more of these. The storage medium may, where appropriate, be volatile, non-volatile, or a combination of volatile and non-volatile.

[0041] Furthermore, the program of the present disclosure may be provided to the information processing device 100 via any transmission medium (such as a communication network or broadcast waves) capable of transmitting the program.

[0042] Furthermore, each embodiment of the present disclosure may be realized in the form of a data signal embedded in a carrier wave, in which the program is embodied by electronic transmission. Note that the program of the present disclosure may be implemented using, for example, a scripting language such as JavaScript (registered trademark) or Python, or the C language, Go language, Swift, Koltin, Java (registered trademark), or the like.

[0043] According to each aspect of the present disclosure described above, a certain level of communication quality is maintained regardless of changes in the environment, thereby contributing to the achievement of Goal 11 of the Sustainable Development Goals (SDGs), "Sustainable cities and communities."

[0044] REFERENCE SIGNS LIST 100 Information processing device 110 Control unit 111 Change acquisition unit 112 Quality information acquisition unit 113 Prediction unit 114 First calculation unit 115 Learning unit 116 Collection unit 117 Second calculation unit 120 Communication unit 130 Input / output unit 170 Storage unit 200 Base station 400 RAN 600 Information processing system UE Communication terminal CN Core network

Claims

1. An information processing device comprising: a change acquisition unit that acquires environmental information related to the environment, including information about future environmental changes in the coverage area of ​​a base station; a quality information acquisition unit that acquires from a communication terminal connected to the base station an actual measured value of communication quality between the base station and the communication terminal; a first calculation unit that predicts parameter values ​​of the base station, the parameter values ​​being set in the base station in the changed environment, and calculates parameter values ​​that make the difference between the predicted value of communication quality and the actual measured value of communication quality in the environment before the change approach zero; and a learning unit that learns the correspondence between the actual measured value of communication quality when the parameter values ​​calculated by the first calculation unit are set in the base station in the changed environment, acquired from the quality information acquisition unit, the predicted value, the parameter value, and the environmental information, and generates a learning model that outputs parameter values ​​that make the difference between the predicted value and the actual measured value approach zero when specified environmental information is input, wherein the first calculation unit calculates the parameter values ​​using the learning model.

2. The information processing device according to claim 1, further comprising a collection unit that collects various types of information acquired from a plurality of information acquisition devices installed in the environment, and a second calculation unit that reflects the various types of information in a digital twin of the environment constructed in a virtual space by simulating the real space in which the base station and the communication terminal exist, and predicts communication quality in the changed environment using a plurality of parameter values ​​of the base station on the digital twin, and the first calculation unit uses the parameter values ​​calculated by the second calculation unit to train the learning model.

3. The information processing device described in claim 1, wherein the change acquisition unit acquires information about a building under construction in the coverage area as the environmental information, and the first calculation unit calculates the parameter value when the shape of the building under construction changes as the environment after the change.

4. The information processing device described in claim 1, wherein the change acquisition unit acquires multiple images of the coverage area taken in time series as the environmental information, and the first calculation unit calculates the parameter value based on the changes extracted from the multiple images as the environment after the change.

5. The information processing device according to claim 1, wherein the first calculation unit calculates parameter values ​​of other base stations adjacent to the base station in addition to the parameter values ​​of the base station in order to bring the communication quality of communication terminals present in the coverage area of ​​the base station closer to the actual measured value in the environment before the change.

6. A control method for an information processing device that causes an information processing device to execute the following steps: a change acquisition step of acquiring environmental information related to the environment, including information about future environmental changes in the coverage area of ​​the base station; a quality information acquisition step of acquiring, from a communication terminal connected to the base station, an actual measurement value of communication quality between the base station and the communication terminal; a first calculation step of calculating parameter values ​​of the base station, the parameter values ​​being parameter values ​​of the base station, that predict the communication quality between the base station and the communication terminal when the parameter values ​​are set in the base station in the environment after the change, and parameter values ​​that make the difference between the predicted value of communication quality and the actual measurement value of communication quality in the environment before the change approach zero; a learning step of learning the correspondence between the actual measurement value of communication quality when the parameter values ​​calculated in the first calculation step are set in the base station in the environment after the change, acquired in the quality information acquisition step, the predicted value, the parameter value, and the environmental information, and generating a learning model that outputs parameter values ​​that make the difference between the predicted value and the actual measurement value approach zero when specified environmental information is input.

7. A control program for an information processing device that causes an information processing device to function as: a change acquisition function that acquires environmental information related to the environment, including information about future environmental changes in the coverage area of ​​a base station; a quality information acquisition function that acquires, from a communication terminal connected to the base station, an actual measured value of communication quality between the base station and the communication terminal; a first calculation function that predicts parameter values ​​of the base station, which are parameter values ​​of the base station, when the parameter values ​​are set in the base station in the environment after the change, and calculates parameter values ​​that make the difference between the predicted value of communication quality and the actual measured value of communication quality in the environment before the change approach zero; a learning function that learns the correspondence between the actual measured value of communication quality when the parameter values ​​calculated by the first calculation function are set in the base station in the environment after the change, acquired by the quality information acquisition function, the predicted value, the parameter value, and the environmental information, and generates a learning model that outputs parameter values ​​that make the difference between the predicted value and the actual measured value approach zero when specified environmental information is input; and a function that calculates the parameter values ​​using the learning model.

Images