WO2023233484A1

WO2023233484A1 - Wireless quality prediction device, wireless quality prediction method, and program

Info

Publication number: WO2023233484A1
Application number: PCT/JP2022/021991
Authority: WO
Inventors: 尚希澁谷; 憲一河村; 元晴佐々木; 貴庸守山
Original assignee: 日本電信電話株式会社
Priority date: 2022-05-30
Filing date: 2022-05-30
Publication date: 2023-12-07

Abstract

In order to make it possible to predict the wireless quality of a wireless terminal after the elapse of a predetermined time without creating a wireless quality distribution, this wireless quality prediction device, which predicts the wireless quality between a wireless base station and a wireless terminal that performs wireless communication with the wireless base station, comprises: a reception power learner configured to predict a predicted value of the reception power of the wireless terminal after the elapse of a predetermined time, on the basis of the terminal position of the wireless terminal and an estimated value of the terminal state after the elapse of the predetermined time; a wireless quality learner configured to predict a predicted value of the wireless quality after the elapse of the predetermined time, on the basis of information about the wireless base station, information about the wireless communication, information about the wireless terminal, and the predicted value of the reception power; and a notification unit configured to notify the wireless terminal of the predicted value of the wireless quality after the elapse of the predetermined time.

Description

Wireless quality prediction device, wireless quality prediction method, and program

The present invention relates to a radio quality prediction device, a radio quality prediction method, and a program.

A method is being considered in which radio wave measurement results in a wireless communication area are measured in advance to create a wireless quality distribution (heat map), and handover control is based on the created wireless quality distribution (for example, see Non-Patent Document 1).

In order to create a wireless quality distribution, it is necessary to measure wireless quality, such as throughput, for each prediction area. However, measuring throughput uses a large amount of communication bandwidth and interferes with other communications, making it difficult to create a wireless quality distribution.

The embodiments of the present invention have been made in view of the above-mentioned problems, and make it possible to predict the wireless quality of a wireless terminal after a predetermined period of time has elapsed without creating a wireless quality distribution.

In order to solve the above problems, a wireless quality prediction device according to an embodiment of the present invention is a wireless quality prediction device that predicts wireless quality between a wireless base station and a wireless terminal that performs wireless communication with the wireless base station. and configured to predict a predicted value of received power of the wireless terminal after the predetermined time has elapsed, based on estimated values of the terminal position and terminal state of the wireless terminal after the elapse of the predetermined time. The wireless quality after the predetermined time has elapsed based on the received power learning device, information on the wireless base station, information on the wireless communication, information on the wireless terminal, and the predicted value of the received power. a wireless quality learning device configured to predict a predicted value of the wireless quality, and a notification unit configured to notify the wireless terminal of the predicted value of the wireless quality after the predetermined time has elapsed. .

According to the embodiments of the present invention, it becomes possible to predict the wireless quality of a wireless terminal after a predetermined time has elapsed without creating a wireless quality distribution.

1 is a diagram illustrating an example of a system configuration of a wireless communication system according to an embodiment. FIG. 3 is a diagram for explaining a received power learning device according to the present embodiment. FIG. 3 is a diagram for explaining learning of the received power learning device according to the present embodiment. FIG. 2 is a diagram for explaining a wireless quality learning device according to the present embodiment. FIG. 3 is a diagram for explaining learning by the wireless quality learning device according to the present embodiment. 7 is a flowchart illustrating an example of wireless quality prediction processing according to the present embodiment. FIG. 2 is a diagram (1) for explaining wireless quality prediction processing according to the present embodiment. FIG. 2 is a diagram (2) for explaining wireless quality prediction processing according to the present embodiment. 1 is a diagram illustrating an example of the hardware configuration of a radio quality prediction device and a radio base station according to the present embodiment. FIG. 2 is a diagram illustrating an example of the hardware configuration of a wireless terminal according to the present embodiment.

Hereinafter, an embodiment of the present invention (this embodiment) will be described with reference to the drawings. The embodiments described below are merely examples, and the embodiments to which the present invention is applied are not limited to the following embodiments.

<System configuration>
FIG. 1 is a diagram showing an example of the system configuration of a wireless communication system according to this embodiment. The wireless communication system 1 includes a wireless base station 10, a wireless terminal 20 that performs wireless communication with the wireless base station 10, a wireless quality prediction device 100 that predicts wireless quality between the wireless base station 10 and the wireless terminal 20, including.

The wireless base station 10 provides wireless communication services, such as 5G (5th Generation) and LTE (Long Term Evolution), to wireless terminals 20 within the communication area of the wireless base station 10. The wireless terminal 20 can perform wireless communication with the wireless base station 10 within the communication area of the wireless base station 10.

The wireless quality prediction device 100 predicts the wireless quality between the wireless base station 10 and the wireless terminal 20, and provides the wireless terminal 20 with a predicted value of the predicted wireless quality. For example, the wireless quality prediction device 100 predicts the throughput (an example of wireless quality) of the wireless terminal 20 after a predetermined time (n seconds) has elapsed, and notifies the wireless terminal 20 of the predicted value of the predicted throughput. .

The wireless terminal 20 controls, for example, handover of the wireless terminal 20 based on the notified predicted throughput value.

(About the assignment)
In LTE, for example, the received power strength Ms of the connected cell s is compared with the received power strength Mn of the adjacent cell n, and handover is executed to switch the connected cell. As the switching condition, for example, Mn+HO _offset,s,n >Ms is set, and when this switching condition continues for a certain period of time (TTT: Time to Trigger) or more, the handover process is executed. Here, HO _offset,s,n is an offset value uniquely set between cell s and cell n.

However, in this method, handover is determined after the wireless quality has deteriorated, so there is a problem that, for example, if the wireless quality suddenly deteriorates, the communication quality will temporarily deteriorate.

Therefore, a method is being considered in which radio wave measurement results in a wireless communication area are measured in advance, a wireless quality distribution (heat map) is created, and handover control is based on the created wireless quality distribution (for example, Non-Patent Document 1) .

However, in order to create a wireless quality distribution, it is necessary to measure wireless quality, such as throughput, for each prediction area. However, measuring throughput uses a large amount of communication bandwidth and interferes with other communications, making it difficult to create a wireless quality distribution.

Therefore, the present embodiment provides a wireless quality prediction device and a wireless quality prediction method that can predict the wireless quality of a wireless terminal after a predetermined time has elapsed without creating a wireless quality distribution.

<Functional configuration>
(Functional configuration of wireless quality prediction device)
The wireless quality prediction device 100 includes one or more computers, and by executing a predetermined program on the one or more computers, for example, a received power learning device 101, a wireless quality learning device 102, a notification unit 103, and an MCS conversion unit 104, etc. Note that at least some of the above functional configurations may be realized by hardware.

The reception power learning device 101 calculates the reception power of the wireless terminal 20 after a predetermined time has elapsed based on the estimated value of the terminal position and terminal state of the wireless terminal 20 after the elapse of a predetermined time (for example, n seconds). Execute received power prediction processing to predict a predicted power value. Further, the received power learning device 101 notifies the wireless quality learning device 102 of the predicted value of the received power after n seconds.

Here, the terminal location is location information (eg, latitude, longitude, etc.) indicating the location of the wireless terminal 20. Further, the terminal state is information such as the orientation and speed of the wireless terminal 20 acquired by a device such as an acceleration sensor, a gyro sensor, or an IMU (Inertial Measurement Unit) included in the wireless terminal 20. Even for the same wireless terminal 20, reception power differs depending on direction or speed, so it is desirable to use terminal state information when predicting reception power. Note that the terminal state may be determined using only the direction of the wireless terminal 20 or only the speed of the wireless terminal 20.

After a predetermined period of time ( A wireless quality prediction process is executed to predict a predicted value of wireless quality after (n seconds).

Here, the information on the wireless base station includes information such as the manufacturer, type, communication standard, and number of wireless terminals 20 connected to the wireless base station 10, for example. Processing time (delay) varies depending on the manufacturer, type, etc. of the wireless base station 10. Furthermore, the number of connected wireless terminals 20 also affects wireless quality (for example, throughput). Therefore, it is desirable to use information on wireless base stations when predicting wireless quality. However, at least part of the information on the wireless base station may be omitted. The wireless communication information includes, for example, information such as a wireless communication MCS (Modulation and Coding Scheme) or a maximum throughput value. MCS indicates a combination of a data modulation method and a channel coding rate, and normally, the larger the MCS number, the larger the transport block size, and higher throughput can be achieved.

The information on the wireless terminal includes, for example, information such as the type of the wireless terminal 20 (chip set manufacturer or model name, etc.) and the form of the wireless terminal 20 (for example, robot, vehicle, smartphone, wearable terminal, etc.). . Wireless quality (for example, throughput) may vary depending on the chip set manufacturer, model name, etc. Furthermore, there are differences in the received power measured depending on the shape of the wireless terminal 20 and the like. Therefore, it is desirable to use information on wireless base stations when predicting wireless quality. However, at least part of the information on the wireless terminal may be omitted.

The wireless quality of the wireless terminal 20 predicted by the wireless quality learning device 102 includes, for example, the throughput of wireless communication between the wireless base station 10 and the wireless terminal 20. Although the wireless quality of the wireless terminal 20 may be an index other than throughput, the following description will be made assuming that the wireless quality of the wireless terminal 20 is throughput.

The notification unit 103 notifies the wireless terminal 20, via the wireless base station 10, of the predicted value of the throughput of the wireless terminal 20 after n seconds, which is predicted by the wireless quality learning device 102.

The MCS conversion unit 104 executes, for example, an MCS conversion process that converts the MCS notified from the wireless base station 10 into a maximum throughput value of wireless communication. For example, the MCS conversion unit 104 has correspondence information in which a plurality of MCSs and a maximum throughput value corresponding to each MCS are stored in association with each other, and uses this correspondence information to convert the MCS into the maximum throughput value. Furthermore, the MCS conversion unit 104 notifies the wireless quality learning device 102 of the wireless base station information received from the wireless base station 10 and the converted maximum throughput. Note that the wireless base station 10 may have the function of the MCS conversion unit 104.

(Functional configuration of wireless terminal)
The wireless terminal 20 has, for example, a communication control unit 21, a position acquisition unit 22, a status acquisition unit 23, a terminal information transmission unit 24, a terminal control unit 25, etc., by a computer included in the wireless terminal 20 executing a predetermined program. has been realized. Note that at least some of the above functional configurations may be realized by hardware.

The communication control unit 21 executes communication control processing to control wireless communication with the wireless base station 10. For example, the communication control unit 21 determines a CQI (Channel Quality Indicator) value indicating the downlink radio channel state from the reception level of the pilot signal received by the antenna 27, and transmits the determined CQI value to the radio base station 10. Notice. Further, the communication control unit 21 performs wireless communication with the wireless base station 10 via the antenna 27 based on the MCS notified from the wireless base station 10.

The position acquisition unit 22 acquires the current position (terminal position) of the wireless terminal 20 using, for example, a positioning device such as a GPS (Global Positioning System) device included in the wireless terminal 20. Further, the position acquisition unit 22, for example, based on the acquired current position of the wireless terminal 20 and the movement of the wireless terminal 20 measured by a device such as an acceleration sensor, a gyro sensor, or an IMU included in the wireless terminal 20, The position of the wireless terminal 20 (terminal position) after a predetermined period of time (n seconds) is estimated. As an example, the position acquisition unit 22 uses a machine learning model or the like that has been learned in advance using the current position of the wireless terminal 20 and the movement of the wireless terminal 20 as feature quantities, and the position of the wireless terminal 20 n seconds later as training data. Then, the terminal position of the wireless terminal 20 n seconds later may be estimated.

The status acquisition unit 23 acquires the terminal status (direction, speed, etc.) of the wireless terminal 20 based on sensor data acquired by, for example, an acceleration sensor, a gyro sensor, an IMU, etc. included in the wireless terminal 20. Further, the state acquisition unit 23 estimates the state (terminal state) of the wireless terminal 20 after a predetermined time (n seconds) has passed, based on sensor data acquired by an acceleration sensor, a gyro sensor, an IMU, or the like. . For example, the state acquisition unit 23 uses past sensor data of the wireless terminal 20 as a feature quantity and a machine learning model learned in advance using the current terminal state of the wireless terminal 20 as teacher data to determine whether the wireless terminal n seconds later Twenty terminal states may be estimated.

The terminal information transmitting unit 24 transmits information such as wireless terminal information, received power, interference wave information (SINR), and the terminal position and terminal status after a predetermined period of time (n seconds) to the wireless base station. 10 to the wireless quality prediction device 100. Here, the interference wave information (SINR) deteriorates due to the influence of interference waves in radio section 2, and if this value is low, for example, an increase in the error rate or a waiting time (delay) occurs, resulting in a decrease in throughput. do. Therefore, it is desirable to use interference wave information (SINR) measured by the wireless terminal 20 when predicting wireless quality. However, the interference wave information (SINR) is optional and not essential.

The information on the wireless terminal is stored in advance by, for example, the terminal information transmitter 24 or the terminal controller 25. The received power and interference wave information are acquired by the terminal information transmitter 24 from the communication controller 21 or the like, for example. The position acquisition unit 22 and the status acquisition unit 23 estimate the terminal position and terminal state after n seconds.

The terminal control unit 25 controls the entire wireless terminal 20. For example, the terminal control unit 25 controls handover, etc., based on the throughput of the wireless terminal 20 after a predetermined time (n seconds), which is notified from the wireless quality prediction device 100.

Further, if the wireless terminal 20 is a wireless terminal that holds movement route information and has a movement function such as a robot or a vehicle that moves along a predetermined path, the terminal control unit 25 controls the movement of the wireless terminal 20. Control. In this case, the terminal control unit 25 changes the movement route of the wireless terminal 20 based on the throughput of the wireless terminal 20 after a predetermined period of time (n seconds) has passed, which is notified from the wireless quality prediction device 100. Good too.

(Functional configuration of wireless base station)
The wireless base station 10 implements, for example, a communication control unit 11, a transmitting/receiving unit 12, etc. by a computer included in the wireless base station 10 executing a predetermined program. Note that at least some of the above functional configurations may be realized by hardware.

The communication control unit 11 executes communication control processing to control wireless communication with the wireless terminal 20. For example, the communication control unit 11 determines the MCS based on the CQI value received from the wireless terminal 20, and notifies the wireless terminal 20 of the determined MCS. Furthermore, the communication control unit 11 performs wireless communication with the wireless terminal 20 via the antenna 13 based on the determined MCS.

The transmitting/receiving unit 12 notifies the wireless quality prediction device 100 of, for example, information on the wireless base station and the MCS determined by the communication control unit 11. Further, the transmitting/receiving unit 12 receives from the wireless quality predicting device 100 the predicted value of the throughput after n seconds, which the wireless quality predicting device 100 reports to the wireless terminal 20 , and transfers it to the wireless terminal 20 .

(About the received power learning device)
FIG. 2 is a diagram for explaining the received power learning device according to the present embodiment. The received power learning device 101 is a first learning device that has learned to predict the received power of a wireless terminal based on current data or past data acquired from one or more wireless terminals connected to the wireless base station 10. It has a neural network 201.

For example, the first neural network 201 uses the current terminal position and terminal status of one or more wireless terminals that perform wireless communication with the wireless base station 10, and the received power of the wireless terminal a predetermined time ago as feature quantities. , is learned in advance using the current received power of the terminal as training data.

The received power learning device 101 inputs into the first neural network 201 the estimated values of the terminal position and terminal state of the wireless terminal 20 after a predetermined period of time, the current received power of the wireless terminal 20, etc. Then, a predicted value of the received power of the wireless terminal 20 after a predetermined time has elapsed is predicted.

Preferably, the received power learning device 101 learns the current location and terminal status of one or more wireless terminals that perform wireless communication with the wireless base station 10, as well as the current received power of the wireless terminal and the past state of the wireless terminal a predetermined time ago. The first neural network 201 is periodically trained using received power and the like.

FIG. 3 is a diagram for explaining learning by the received power learning device 101 according to the present embodiment. In FIG. 3, it is assumed that a wireless terminal 20-1 within the communication area 301 of the wireless base station 10-1 is performing wireless communication with the wireless base station 10-1. In this case, the wireless terminal 20-1 successively measures the received power received from the wireless base station 10-1, as well as the terminal position and terminal status of the wireless terminal 20-1, and The measurement results are transmitted to the wireless quality prediction device 100. Further, the received power learning device 101 learns the first neural network 201 corresponding to the wireless base station 10-1 based on the received measurement results.

Similarly, it is assumed that the wireless terminals 20-2 and 20-3 within the communication area 302 of the wireless base station 10-2 are communicating wirelessly with the wireless base station 10-2. In this case, the wireless terminals 20-2 and 20-3 sequentially measure the received power received from the wireless base station 10-2, the terminal position and the terminal status of their own terminals, and transmit the information via the wireless base station 10-2. , transmits the measurement results to the wireless quality prediction device 100. Further, the received power learning device 101 learns the first neural network 201 corresponding to the wireless base station 10-2 based on the received measurement results.

As another example, as shown in FIG. It may also be a neural network trained to predict the received power of.

In this way, the received power learning device 101 predicts the received power of the wireless terminal 20 after a predetermined time has elapsed based on the estimated value of the terminal position and terminal state of the wireless terminal 20 after the elapse of a predetermined time. Configured to predict values.

(About wireless quality learning device)
FIG. 4 is a diagram for explaining the wireless quality learning device according to the present embodiment. The wireless quality learning device 102 uses wireless base station information, wireless communication information, wireless terminal information, interference wave information of the wireless terminal 20, received power of the wireless terminal, etc. as feature quantities, and uses It has a second neural network 401 trained in advance to predict quality.

For example, as shown in FIG. 4, the second neural network 401 uses wireless base station information, maximum throughput (or MCS), wireless terminal information, received power of the wireless terminal 20, etc. as feature quantities, and It has been trained to predict a throughput of 20.

Preferably, the feature amount further includes interference wave information of the wireless terminal 20. As the interference wave information of the wireless terminal 20, for example, SINR (Signal-to-Noise Ratio) measured by the wireless terminal 20 can be used. Note that the interference wave information of the wireless terminal 20 may be information other than SINR.

The wireless quality learning device 102 provides the second neural network 401 with, for example, information on the wireless base station, maximum throughput, information on the wireless terminal, SINR measured by the wireless terminal 20, and information after a predetermined period of time has elapsed. A predicted value of received power of the wireless terminal 20, etc. is input. Thereby, the wireless quality learning device 102 can obtain from the second neural network 401 a predicted value of the throughput of the wireless terminal 20 after a predetermined period of time has elapsed.

Preferably, the wireless quality learning device 102 trains the second neural network 401 in advance so as not to depend on the communication area and location information provided by the wireless base station 10.

FIG. 5 is a diagram for explaining learning by the wireless quality learning device according to the present embodiment. In order to increase versatility, the wireless quality learning device 102 learns the second neural network 401 by utilizing not only the communication area of the wireless base station 10 to be predicted, but also data from other communication areas. is desirable.

For example, as shown in FIG. 5, the wireless quality learning device 102 uses information such as received power, SINR, and information of wireless terminals in areas A to C provided by a plurality of wireless base stations 10-1 to 10-3. , wireless base station information, and learning data such as MCS (or maximum throughput). Furthermore, the wireless quality learning device 102 trains the second neural network 401 using learning data acquired from various areas and various wireless terminals. Note that the wireless quality learning device 102 according to this embodiment does not require the work of measuring throughput and creating a wireless quality distribution (heat map) during learning.

<Processing flow>
Next, a process flow of the wireless quality prediction method according to the present embodiment will be described.

FIG. 6 is a flowchart illustrating an example of wireless quality prediction processing according to the present embodiment. In this process, when the wireless base station 10 and the wireless terminal 20 are performing wireless communication, the wireless quality prediction device 100 calculates a predicted value of the throughput of the wireless terminal 20 after a predetermined time (n seconds) has elapsed. A specific example of a wireless quality prediction process for predicting is shown.

In step S601, the wireless terminal 20 acquires the received power, SINR, terminal position, and terminal state of the wireless terminal 20. For example, the terminal information transmitter 24 of the wireless terminal 20 acquires the received power and SINR (an example of interference wave information) of the wireless terminal 20 from the communication controller 21 or the terminal controller 25. Further, the position acquisition unit 22 of the wireless terminal 20 acquires the terminal position of the wireless terminal 20 from a GPS device included in the wireless terminal 20 or the like. Further, the status acquisition unit 23 of the wireless terminal 20 acquires the terminal status (direction, speed, etc.) of the wireless terminal 20 based on sensor data from an acceleration sensor, a gyro sensor, an IMU, or the like included in the wireless terminal 20.

In step 602, the wireless terminal 20 determines the terminal position n seconds later based on the current terminal position, terminal state, and sensor data such as an acceleration sensor, a gyro sensor, or an IMU, as shown in FIG. 7, for example. and estimate (or calculate) the estimated value of the terminal state. For example, the position acquisition unit 22 of the wireless terminal 20 estimates the estimated value of the terminal position n seconds later based on the acquired current terminal position and sensor data. Furthermore, the state acquisition unit 23 of the wireless terminal 20 estimates an estimated value of the terminal state after n seconds based on the acquired current terminal state and sensor data.

In step S603, the terminal information transmitting unit 24 of the wireless terminal 20 transmits wireless terminal information, received power, SINR, estimated value of the terminal position and terminal state after n seconds, etc. via the wireless base station 10. It is transmitted to the received power learning device 101 of the quality prediction device 100. Among the information transmitted by the wireless terminal 20, information such as the received power and estimated values of the terminal position and terminal state after n seconds are input to the received power learning device 101, as shown in FIG. Furthermore, information on the wireless terminal and information such as SINR is input to the wireless quality learning device 102, as shown in FIG.

In step S604, the transmitting/receiving unit 12 of the wireless base station 10 transmits (notifies) information on the wireless base station and information such as MCS to the wireless quality prediction device 100, for example, in parallel with the processing in steps S601 to S601. do. As a result, for example, as shown in FIG. 8, information on the radio base station transmitted by the radio base station 10 and information such as MCS are input to the MCS conversion unit 104 of the radio quality prediction device 100. Note that the information on the wireless base station includes, for example, information such as the communication standard of the wireless base station 10, the manufacturer, or the number of wireless terminals connected to the wireless base station 10.

In step S605, the MCS conversion unit 104 of the wireless quality prediction device 100 converts the MCS into a maximum throughput value using the above-mentioned correspondence information, and uses the converted maximum throughput value together with the wireless base station information to determine the wireless quality. The learning device 102 is notified.

In step S606, the received power learning device 101 of the wireless quality prediction device 100 inputs the input received power, the terminal position and terminal state after n seconds, etc. to the first neural network 201, and The predicted value of the received power n seconds after is predicted. Further, the received power learning device 101 notifies the wireless quality learning device 102 of the predicted value of the received power after n seconds.

Through each of the above processes, for example, as shown in FIG. Information such as the predicted value of the received power of the wireless terminal 20 is input.

In step S607, the wireless quality learning device 102 inputs the wireless terminal information, SINR, wireless base station information, maximum throughput, received power predicted value, etc. to the second neural network 401, and Predict future throughput estimates.

In step S608, the notification unit 103 of the wireless quality prediction device 100 sends the predicted value of the throughput of the wireless terminal 20 after n seconds, predicted by the wireless quality learning device 102, to the wireless terminal 20 via the wireless base station 10. Notify (send).

In step S609, the terminal control unit 25 of the wireless terminal 20 makes a determination, for example, about handover control or route change control, based on the predicted value of throughput after n seconds received from the wireless quality prediction device 100.

In step S610, the terminal control unit 25 executes control such as handover control or route change control according to the determination result.

Through the process shown in FIG. 6, the wireless terminal 20 can predict the throughput of the wireless terminal 20 after a predetermined time has elapsed (n seconds later), so for example, if the throughput deteriorates after n seconds, handover etc. can be performed at an earlier timing. processing can be started. Note that the predetermined time (n seconds) is determined by the administrator who manages the wireless communication system 1 or the designer who designed the wireless quality, depending on the system requirements, prediction accuracy, etc., as a set value or setting range. Set.

<Hardware configuration example>
(Hardware configuration of prediction device)
FIG. 9 is a diagram illustrating an example of the hardware configuration of a radio quality prediction device and a radio base station according to this embodiment. The wireless quality prediction device 100 and the wireless base station include, for example, the configuration of a computer 900 as shown in FIG. In the example of FIG. 9, the computer 900 includes a processor 901, a memory 902, a storage device 903, a communication device 904, an input device 905, an output device 906, a bus B, and the like.

The processor 901 is, for example, an arithmetic device such as a CPU (Central Processing Unit) that implements various functions by executing a predetermined program. The memory 902 is a storage medium readable by the computer 900, and includes, for example, RAM (Random Access Memory), ROM (Read Only Memory), and the like. The storage device 903 is a computer-readable storage medium, and may include, for example, an HDD (Hard Disk Drive), an SSD (Solid State Drive), various optical disks, magneto-optical disks, and the like.

The communication device 904 includes one or more hardware (communication devices) for communicating with other devices via a wireless or wired network. The input device 905 is an input device (eg, keyboard, mouse, microphone, switch, button, sensor, etc.) that accepts input from the outside. The output device 906 is an output device (for example, a display, a speaker, an LED lamp, etc.) that performs output to the outside. Note that the input device 905 and the output device 906 may have an integrated configuration (for example, an input/output device such as a touch panel display).

Bus B is commonly connected to each of the above components, and transmits, for example, address signals, data signals, and various control signals. Note that the processor 901 is not limited to a CPU, and may be, for example, a DSP (Digital Signal Processor), a PLD (Programmable Logic Device), or an FPGA (Field Programmable Gate Array).

(Hardware configuration of wireless terminal)
FIG. 10 is a diagram showing an example of the hardware configuration of the wireless terminal according to this embodiment. In addition to the hardware configuration of the computer 900 described in FIG. 9, the wireless terminal 20 includes a GPS device 1001, a sensor 1002, and the like.

The GPS device 1001 is a positioning device that receives positioning signals transmitted by GPS satellites and outputs position information indicating the current position of the wireless terminal 20. Note that the GPS device 1001 may be a positioning device other than GPS. The sensor 1002 is a device that detects the movement or posture of the wireless terminal 20, such as an acceleration sensor, a gyro sensor, or an IMU.

(supplement)
The radio quality prediction device 100, the radio terminal 20, and the radio base station 10 in this embodiment are not limited to being implemented by dedicated devices, but may be implemented by a general-purpose computer. In that case, a program for realizing this function may be recorded on a computer-readable recording medium, and the program recorded on the recording medium may be read into a computer system and executed. Note that the "computer system" herein includes hardware such as an OS (Operating System) and peripheral devices.

Furthermore, the term "computer-readable recording medium" includes various storage devices such as flexible disks, magneto-optical disks, ROMs, CD-ROMs, and other portable media, and hard disks built into computer systems. Furthermore, a "computer-readable recording medium" refers to a storage medium that dynamically stores a program for a short period of time, such as a communication line when transmitting a program via a network such as the Internet or a communication line such as a telephone line. It may also include a device that retains a program for a certain period of time, such as a volatile memory inside a computer system that is a server or client in that case.

Further, the above-mentioned program may be one for realizing a part of the above-mentioned functions, and further may be one that can realize the above-mentioned functions in combination with a program already recorded in the computer system. It may be realized using hardware such as a PLD (Programmable Logic Device) or an FPGA (Field Programmable Gate Array).

<Effects of embodiment>
According to this embodiment, the wireless quality of the wireless terminal 20 after a predetermined period of time can be predicted without creating a wireless quality distribution. Thereby, the wireless terminal 20 can start handover before the wireless quality deteriorates, so that it is possible to reduce temporary deterioration of communication quality due to sudden wireless quality deterioration, for example.

Furthermore, the wireless quality learning device 102 according to this embodiment eliminates the need to measure throughput and create a wireless quality distribution (heat map) for each prediction area.

<Summary of embodiments>
This specification discloses at least a radio quality prediction device, a radio quality prediction method, and a program described in the following sections.
(Section 1)
A wireless quality prediction device that predicts wireless quality between a wireless base station and a wireless terminal that performs wireless communication with the wireless base station,
Received power configured to predict a predicted value of received power of the wireless terminal after the predetermined time has elapsed, based on estimated values of the terminal position and terminal state of the wireless terminal after the elapse of the predetermined time. learning device and
The configuration is configured to predict the predicted value of the wireless quality after the predetermined time has elapsed based on the wireless base station information, the wireless communication information, the wireless terminal information, and the received power predicted value. wireless quality learning device,
a notification unit configured to notify the wireless terminal of the predicted value of the wireless quality after the predetermined time has elapsed;
A wireless quality prediction device having:
(Section 2)
The received power learning device is
The current terminal position and terminal state of another wireless terminal that performs wireless communication with the wireless base station, and the past received power of the other wireless terminal before a predetermined time are used as feature quantities, and the current terminal status of the other wireless terminal is has a first neural network that has learned in advance the received power of
The estimated value of the terminal position and terminal state of the wireless terminal after the elapse of the predetermined time period, and the received power of the wireless terminal are input into the first neural network, and the Predicting the predicted value of the received power of a wireless terminal,
The radio quality prediction device according to item 1.
(Section 3)
The received power learning device is configured to learn the current terminal position and terminal state of another wireless terminal that performs wireless communication with the wireless base station, the current received power of the other wireless terminal, and the predetermined time of the wireless terminal. 3. The wireless quality prediction device according to claim 2, wherein the first neural network is periodically trained using previous received power.
(Section 4)
The wireless quality learning device is
Information on the wireless base station, information on the wireless communication, information on other wireless terminals that perform wireless communication with the wireless base station, interference wave information on the other wireless terminals, and received power of the other wireless terminals. a second neural network trained in advance to predict the communication quality of the wireless communication;
The second neural network includes information on the wireless base station, information on the wireless communication, information on the wireless terminal, interference wave information measured by the wireless terminal, and information on the wireless terminal after the predetermined time has elapsed. inputting a predicted value of received power and predicting a predicted value of the radio quality after the predetermined time has elapsed;
The wireless quality prediction device according to any one of items 1 to 3.
(Section 5)
The wireless quality includes a throughput value of the wireless communication,
The wireless communication information includes a maximum throughput value of the wireless communication,
The interference wave information of the wireless terminal includes an SINR value of the wireless communication measured by the wireless terminal,
The terminal state of the wireless terminal includes the direction or speed of the wireless terminal,
The radio quality prediction device according to item 1.
(Section 6)
A wireless quality prediction method for predicting wireless quality between a wireless base station and a wireless terminal that performs wireless communication with the wireless base station, the method comprising:
A received power learning device predicts a predicted value of received power of the wireless terminal after the predetermined time has elapsed, based on estimated values of the terminal position and terminal state of the wireless terminal after the elapse of the predetermined time. processing and
A wireless quality learning device predicts the wireless quality after the predetermined time has elapsed based on the wireless base station information, the wireless communication information, the wireless terminal information, and the predicted value of the received power. The process of predicting the value,
a process in which a notification unit notifies the wireless terminal of the predicted value of the wireless quality after the predetermined time has elapsed;
A wireless quality prediction method, including:
(Section 7)
A computer that predicts wireless quality between a wireless base station and a wireless terminal that performs wireless communication with the wireless base station,
Received power configured to predict a predicted value of received power of the wireless terminal after the predetermined time has elapsed, based on estimated values of the terminal position and terminal state of the wireless terminal after the elapse of the predetermined time. learning device and
The configuration is configured to predict the predicted value of the wireless quality after the predetermined time has elapsed based on the wireless base station information, the wireless communication information, the wireless terminal information, and the received power predicted value. wireless quality learning device,
a notification unit configured to notify the wireless terminal of the predicted value of the wireless quality after the predetermined time has elapsed;
A program that functions as

Although the present embodiment has been described above, the present invention is not limited to such specific embodiment, and various modifications and changes can be made within the scope of the gist of the present invention as described in the claims. It is.

1 Wireless Communication System 10 Wireless Base Station 20 Wireless Terminal 100 Wireless Quality Prediction Device 101 Received Power Learning Device 102 Wireless Quality Learning Device 103 Notification Unit 201 First Neural Network 401 Second Neural Network 900 Computer

Claims

A wireless quality prediction device that predicts wireless quality between a wireless base station and a wireless terminal that performs wireless communication with the wireless base station,
Received power configured to predict a predicted value of received power of the wireless terminal after the predetermined time has elapsed, based on estimated values of the terminal position and terminal state of the wireless terminal after the elapse of the predetermined time. learning device and
The configuration is configured to predict the predicted value of the wireless quality after the predetermined time has elapsed based on the wireless base station information, the wireless communication information, the wireless terminal information, and the received power predicted value. wireless quality learning device,
a notification unit configured to notify the wireless terminal of the predicted value of the wireless quality after the predetermined time has elapsed;
A wireless quality prediction device having:
The received power learning device is
The current terminal position and terminal state of another wireless terminal that performs wireless communication with the wireless base station, and the past received power of the other wireless terminal before a predetermined time are used as feature quantities, and the current terminal status of the other wireless terminal is has a first neural network that has learned in advance the received power of
The estimated value of the terminal position and terminal state of the wireless terminal after the elapse of the predetermined time period, and the received power of the wireless terminal are input into the first neural network, and the Predicting the predicted value of the received power of a wireless terminal,
The radio quality prediction device according to claim 1.
The received power learning device is configured to learn the current terminal position and terminal state of another wireless terminal that performs wireless communication with the wireless base station, the current received power of the other wireless terminal, and the predetermined time of the wireless terminal. The radio quality prediction device according to claim 2, wherein the first neural network is periodically learned using previous past received power.
The wireless quality learning device is
Information on the wireless base station, information on the wireless communication, information on other wireless terminals that perform wireless communication with the wireless base station, interference wave information on the other wireless terminals, and received power of the other wireless terminals. a second neural network trained in advance to predict the communication quality of the wireless communication;
The second neural network includes information on the wireless base station, information on the wireless communication, information on the wireless terminal, interference wave information measured by the wireless terminal, and information on the wireless terminal after the predetermined time has elapsed. inputting a predicted value of received power and predicting a predicted value of the radio quality after the predetermined time has elapsed;
The radio quality prediction device according to any one of claims 1 to 3.
The wireless quality includes a throughput value of the wireless communication,
The wireless communication information includes a maximum throughput value of the wireless communication,
The interference wave information of the wireless terminal includes an SINR value of the wireless communication measured by the wireless terminal,
The terminal state of the wireless terminal includes the direction or speed of the wireless terminal,
The radio quality prediction device according to claim 1.
A wireless quality prediction method for predicting wireless quality between a wireless base station and a wireless terminal that performs wireless communication with the wireless base station, the method comprising:
A received power learning device predicts a predicted value of received power of the wireless terminal after the predetermined time has elapsed, based on estimated values of the terminal position and terminal state of the wireless terminal after the elapse of the predetermined time. processing and
A wireless quality learning device predicts the wireless quality after the predetermined time has elapsed based on the wireless base station information, the wireless communication information, the wireless terminal information, and the predicted value of the received power. The process of predicting the value,
a process in which a notification unit notifies the wireless terminal of the predicted value of the wireless quality after the predetermined time has elapsed;
A wireless quality prediction method, including:
A computer that predicts wireless quality between a wireless base station and a wireless terminal that performs wireless communication with the wireless base station,
Received power configured to predict a predicted value of received power of the wireless terminal after the predetermined time has elapsed, based on estimated values of the terminal position and terminal state of the wireless terminal after the elapse of the predetermined time. learning device and
The configuration is configured to predict the predicted value of the wireless quality after the predetermined time has elapsed based on the wireless base station information, the wireless communication information, the wireless terminal information, and the received power predicted value. wireless quality learning device,
a notification unit configured to notify the wireless terminal of the predicted value of the wireless quality after the predetermined time has elapsed;
A program that functions as