Wireless quality prediction method and wireless communication system

Abstract

In order to provide a wireless quality prediction method which can easily adapt to a change in wireless quality even when the transmission environment has changed, this wireless communication system performs: an acquisition process for acquiring the current position of a user terminal, an estimated position of the user terminal after a prescribed time has elapsed, and an actual measurement value of received power of the user terminal at the current position; a first prediction process for using a received power predictor to predict a first predicted value, which is the predicted value of the received power at the current position, and a second predicted value, which is the predicted value of the received power at the estimated position; a correction process for finding, on the basis of the result of comparing the actual measurement value of the received power and the first predicted value, a third predicted value which is obtained by the correcting the second predicted value; and a second prediction process for using a wireless quality predictor and the third predicted value to predict the wireless quality of the user terminal at the estimated position.

Description

[Technical Field]

[0001] The present invention relates to a wireless quality prediction method and a wireless communication system. [Background technology]

[0002] A method is being considered in which radio wave measurements in a wireless communication area are taken in advance to create a wireless quality distribution (heat map), and handover control is based on the created wireless quality distribution. [Prior art documents] [Non-patent literature]

[0003] [Non-Patent Document 1] Konishi et al., "Effects of Automatic Optimization by Self-Organizing Networks (SON) Technology for LTE / LTE-Advanced Systems," IEICE Transactions on Network Engineering, Vol. J97-B, No. 8, pp. 599-610 Summary of the Invention [Problem to be solved by the invention]

[0004] However, with the conventional method, if the propagation environment changes (for example, a new building is constructed) after the wireless quality distribution is created, it is difficult to respond to the change in the wireless quality distribution.

[0005] The embodiments of the present invention have been made in consideration of the above problems, and provide a wireless quality prediction method that can easily respond to changes in wireless quality even when the propagation environment changes. [Means for solving the problem]

[0006] In order to solve the above problem, a wireless quality prediction method according to an embodiment of the present invention includes an acquisition process in which a wireless communication system acquires the current location of a user terminal, an estimated location of the user terminal after a predetermined time has elapsed, and an actual measured value of received power of the user terminal at the current location; a first prediction process in which a received power predictor is used to predict a first predicted value that is a predicted value of received power at the current location and a second predicted value that is a predicted value of received power at the estimated location; a correction process in which a third predicted value is obtained by correcting the second predicted value based on a comparison result between the actual measured value of received power and the first predicted value; and a second prediction process in which a wireless quality predictor and the third predicted value are used to predict the wireless quality of the user terminal at the estimated location. [Effects of the Invention]

[0007] According to an embodiment of the present invention, it is possible to provide a wireless quality prediction method that can easily adapt to changes in wireless quality even when the propagation environment changes. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a diagram illustrating an example of a system configuration of a wireless communication system according to an embodiment of the present invention. [Figure 2] FIG. 10 is a diagram illustrating an example of a predictor of received power according to the present embodiment. [Figure 3] FIG. 10 is a diagram illustrating an example of a predictor of wireless quality according to the present embodiment. [Figure 4] 10 is a flowchart illustrating an example of a wireless quality prediction process according to the present embodiment. [Figure 5] FIG. 2 is a diagram illustrating a first prediction process according to the present embodiment. [Figure 6] FIG. 10 is a diagram for explaining a correction process according to the present embodiment. [Figure 7] FIG. 10 is a diagram illustrating a second prediction process according to the present embodiment. [Figure 8] FIG. 10 is a sequence diagram illustrating an example of processing in the wireless communication system according to the present embodiment. [Figure 9]FIG. 2 is a diagram illustrating an example of a hardware configuration of a prediction device according to the present embodiment. [Figure 10] FIG. 2 is a diagram illustrating an example of a hardware configuration of a user terminal according to the present embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. The embodiment described below is merely an example, and the embodiment to which the present invention is applied is not limited to the following embodiment.

[0010] <System configuration> 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, for example, a user terminal 100, which is a wireless station used by a user, and a prediction device 10 that can communicate with the user terminal 100.

[0011] The prediction device 10 is, for example, an information processing device having a computer configuration or a system including multiple computers. The prediction device 10 executes a wireless quality prediction process to predict wireless quality at an estimated position based on the current position of the user terminal 100, an estimated position of the user terminal 100 after a predetermined time has elapsed, and an actual measurement value of the received power of the user terminal 100 at the current position.

[0012] The user terminal 100 is a radio station that connects to a radio base station 2 among multiple radio base stations 2 that has better radio quality than the other radio base stations 2 by a predetermined radio communication such as 5G (5th Generation) or LTE (Long Term Evolution). The user terminal 100 can communicate with the prediction device 10 via the radio base station 2 or the like, queries the prediction device 10 about the radio quality at the estimated location, and performs communication control such as handover based on the predicted value of the radio quality at the estimated location notified by the prediction device 10.

[0013] <Functional configuration> (Functional configuration of the prediction device) The prediction device 10 implements, for example, an acquisition unit 11, a first prediction unit 12, a correction unit 13, a second prediction unit 14, a notification unit 15, a received power predictor 21, and a wireless quality predictor 22 by executing a predetermined program on a computer included in the prediction device 10. Note that each of the above functional configurations is not limited to a physical machine (computer) and may be implemented by, for example, a program executed by a virtual machine on a cloud. Furthermore, each of the above functional configurations may be distributed and arranged on separate physical machines or virtual machines. Furthermore, at least a portion of each of the above functional configurations may be implemented by hardware.

[0014] The acquisition unit 11 executes an acquisition process to acquire the current location of the user terminal 100, the estimated location of the user terminal 100 after a predetermined time has elapsed, and the actual measured value of the received power of the user terminal 100 at the current location. For example, the acquisition unit 11 acquires the current location of the user terminal 100, the estimated location, and the actual measured value of the received power included in an inquiry sent by the user terminal 100.

[0015] The first prediction unit 12 uses a received power predictor 21 to perform a first prediction process to predict a predicted value of received power at the current location of the user terminal 100 (hereinafter referred to as the first predicted value P1) and a predicted value of received power at the estimated location (hereinafter referred to as the second predicted value P2).

[0016] 2 is a diagram for explaining the received power predictor 21 according to this embodiment. The received power predictor 21 is a computer, a storage unit, a device, or the like having a first neural network 201 that has been trained in advance to predict the received power at the current position using the current position (e.g., latitude and longitude) as a feature.

[0017] The first prediction unit 12 inputs the current location of the user terminal 100 acquired by the acquisition unit 11 into the trained first neural network 201 included in the received power predictor 21, thereby obtaining a first predicted value P1 of the received power at the current location of the user terminal 100. Similarly, the first prediction unit 12 inputs the estimated location of the user terminal 100 acquired by the acquisition unit 11 into the trained first neural network 201 included in the received power predictor 21, thereby obtaining a second predicted value P2 of the received power at the estimated location of the user terminal 100.

[0018] 1, the functional configuration of the prediction device 10 will be further described. The correction unit 13 obtains a third predicted value P3 by correcting the second predicted value P2 based on a comparison result between the actual measured value of received power acquired by the acquisition unit 11 and the actual measured value of received power predicted by the first prediction unit 12. For example, the correction unit 13 calculates the third predicted value P3 using the following equation (1): P3 = (measured received power value - P1) + P2 (1) However, the present invention is not limited to this, and the correction unit may calculate the third predicted value P3 using another formula such as the following formula (2). P3 = (measured received power value / P1) × P2 (2) In short, when the propagation environment changes and the actual measured value of the received power at the current location changes from the first predicted value, the correction unit 13 is required to correct the second predicted value and obtain the third predicted value, assuming that the received power at the estimated location also changes in a similar manner.

[0019] Therefore, it is desirable to set the predetermined time (n seconds) for calculating the estimated position of the user terminal 100 to a sufficiently short time so that the distance between the current position and the estimated position of the user terminal 100 is not too great. Furthermore, it is desirable that n in this predetermined time (n seconds) be a setting value that can be changed by an administrator or the like.

[0020] The second prediction unit 14 performs a second prediction process to predict the wireless quality (e.g., throughput) of the user terminal 100 at the estimated position using the wireless quality predictor 22 and the third predicted value P3 corrected by the correction unit 13.

[0021] 3 is a diagram illustrating the wireless quality predictor 22 according to this embodiment. The wireless quality predictor 22 is a computer, a storage unit, a device, or the like having a second neural network 301 that has been trained in advance to predict wireless quality such as throughput using a plurality of pieces of information including the current location and received power as feature quantities. Note that the plurality of pieces of information may include, for example, time information such as time and time zone, or calendar information such as weekdays, weekends, and holidays.

[0022] The second prediction unit 14 inputs a plurality of pieces of information, including the estimated position of the user terminal 100 after a predetermined time has elapsed, acquired by the acquisition unit 11, and the third predicted value P3 corrected by the correction unit 13, to the trained second neural network 301 of the wireless quality predictor 22. This allows the second prediction unit 14 to obtain a predicted value of wireless quality, such as throughput, at the estimated position of the user terminal 100. Note that the predicted value of wireless quality is not limited to throughput, and may be other wireless quality values, such as an error rate or a retransmission rate.

[0023] 1, the functional configuration of the prediction device 10 will be further described. The notification unit 15 notifies the user terminal 100 of the predicted value of the wireless quality at the estimated position of the user terminal 100, which is predicted by the second prediction unit 14.

[0024] 1 is an example. For example, the received power predictor 21 or the wireless quality predictor 22 may be realized by a computer or the like external to the prediction device 10. The trained first neural network 201 included in the received power predictor 21 may be included in the first prediction unit 12. Similarly, the trained second neural network 301 included in the wireless quality predictor 22 may be included in the second prediction unit 14.

[0025] (User terminal functional configuration) The user terminal 100 implements, for example, a wireless communication unit 101, a position acquisition unit 102, a calculation unit 103, a received power acquisition unit 104, an inquiry unit 105, a storage unit 106, an information receiving unit 107, and a communication control unit 108 by causing a computer included in the user terminal 100 to execute a predetermined program. Note that at least a part of the above functional configurations may be implemented by hardware.

[0026] The wireless communication unit 101 performs predetermined wireless communication with one or more wireless base stations 2 under the control of the communication control unit 108. The location acquisition unit 102 acquires the current location of the user terminal 100, for example, by using a GPS (Global Positioning System) device or the like.

[0027] The calculation unit 103 executes a calculation process to calculate an estimated position of the user terminal 100 after a predetermined time (n seconds) has elapsed, based on, for example, the current position of the user terminal 100 acquired by the position acquisition unit 102 and the movement of the user terminal 100 measured by sensors such as an acceleration sensor and an angle sensor. Alternatively, the calculation unit 103 may store a history of the current position of the user terminal 100 acquired by the position acquisition unit 102 in the storage unit 106, and estimate the estimated position of the user terminal 100 after a predetermined time (n seconds) has elapsed based on this history. Note that in this embodiment, the method by which the calculation unit 103 estimates the estimated position of the user terminal 100 after a predetermined time has elapsed may be any method.

[0028] The received power acquisition unit 104 executes a received power acquisition process to acquire the actual measured value of the received power of the radio waves received by the wireless communication unit 101 from the wireless base station 2 from the wireless communication unit 101, the communication control unit 108, or the like.

[0029] The query unit 105 executes a query process to transmit a query including the current location of the user terminal 100, the estimated location of the user terminal 100 after a predetermined time has elapsed, and the actual measured value of the received power at the current location to the prediction device 10. The storage unit 106 stores various information or data, such as a history of the current location of the user terminal 100.

[0030] The information receiving unit 107 executes an information receiving process to receive a predicted value of communication quality at the estimated location notified from the prediction device 10 in response to an inquiry by the inquiry unit 105. The communication control unit 108 executes a communication control process to perform call control of wireless communication by the wireless communication unit 101. For example, the communication control unit 108 determines whether or not to perform a handover based on the predicted value of communication quality at the estimated location received by the information receiving unit 107, and if a handover is to be performed, controls the wireless communication unit 101 to perform the handover.

[0031] Note that the system configuration and functional configuration of the wireless communication system 1 shown in Fig. 1 are merely examples. For example, the first prediction unit 12, the correction unit 13, the second prediction unit 14, the received power predictor 21, and the wireless quality predictor 22, etc., included in the prediction device 10 in Fig. 1 may be included in the user terminal 100. In this case, the acquisition unit 11, the notification unit 15, the inquiry unit 105, the information receiving unit 107, etc., shown in Fig. 1 are not required.

[0032] <Processing flow> Next, the processing flow of the wireless quality prediction method according to this embodiment will be described.

[0033] (Wireless quality prediction processing) Fig. 4 is a flowchart showing an example of a wireless quality prediction process according to this embodiment. This process shows an example of a wireless quality prediction process executed by the wireless communication system 1. This process is executed, for example, by the prediction device 10 of Fig. 1. Also, as described above, if the user terminal 100 has the first prediction unit 12, the correction unit 13, the second prediction unit 14, the received power predictor 21, and the wireless quality predictor 22, etc., the process of Fig. 4 may be executed by the user terminal 100. Here, the following description will be given assuming that the prediction device 10 executes the wireless quality prediction process shown in Fig. 4.

[0034] In step S401, the acquisition unit 11 acquires the current location of the user terminal 100, the estimated location of the user terminal 100 after a predetermined time has elapsed, and the actual measured value of the received power of the user terminal 100 at the current location. For example, when the acquisition unit 11 receives an inquiry from the user terminal 100, it acquires the current location, the estimated location, and the actual measured value of the received power of the user terminal 100 included in the inquiry.

[0035] In steps S402 and S403, the first prediction unit 12 performs a first prediction process to predict a first predicted value P1 of the received power at the current location of the user terminal 100 and a second predicted value P2 of the received power at the estimated location of the user terminal 100 after a predetermined time has elapsed.

[0036] 5 is a diagram for explaining the first prediction process according to this embodiment. In the following description, the current location of the user terminal 100 is referred to as the "current location," and the estimated location of the user terminal 100 after a predetermined time (n seconds) is referred to as the "estimated location." The predetermined time of n seconds is a setting value set by an administrator, designer, or the like, and is set in advance so as to obtain good prediction results.

[0037] The first prediction unit 12 inputs the current position (e.g., latitude and longitude) acquired by the acquisition unit 11 into the trained first neural network 201 included in the received power predictor 21 described in Fig. 2, and sets the output received power as a first predicted value P1 of the received power at the current position. Similarly, the first prediction unit 12 inputs the estimated position (e.g., latitude and longitude) acquired by the acquisition unit 11 into the trained first neural network 201 included in the received power predictor 21 described in Fig. 2, and sets the output received power as a second predicted value P2 of the received power at the estimated position.

[0038] In step S404 of FIG. 4, the correction unit 13 obtains a third predicted value P3 by correcting the second predicted value P2 based on the comparison result between the actual measured value of the received power at the current location acquired by the acquisition unit 11 and the first predicted value P1 of the received power at the current location.

[0039] 6 is a diagram for explaining the correction process according to this embodiment. The correction unit 13 compares the actual measurement value of the received power at the current position acquired by the acquisition unit 11 with the first predicted value P1 predicted by the first prediction unit 12, corrects the second predicted value P2 based on the comparison result, and obtains the third predicted value P3. For example, the correction unit 13 calculates the third predicted value P3 using the above-mentioned formula (1) or formula (2), etc.

[0040] For example, suppose that after the first neural network 201 described in FIG. 2 is trained by machine learning, a new building or the like is constructed, causing a decrease in the received power at the current location. In this case, since the estimated location n seconds later is sufficiently close to the current location, it is conceivable that the received power will also decrease at the estimated location due to the influence of the same building. Therefore, the correction unit 13 calculates, for example, the difference between the actually measured value of the received power at the current location and the first predicted value P1, and adds or subtracts the calculated difference to or from the second predicted value P2 to obtain a third predicted value P3 of the received power at the estimated location that takes into account the influence of the newly constructed building.

[0041] In step S405 of FIG. 4, the correction unit 13 uses the third predicted value P3 corrected to execute a second prediction process for predicting the throughput (an example of wireless quality) of the user terminal 100 at the estimated position.

[0042] 7 is a diagram for explaining the second prediction process according to this embodiment. The second prediction unit 14 inputs a plurality of pieces of information, including the estimated position acquired by the acquisition unit 11 and the third predicted value P3 corrected by the correction unit 13, to the trained second neural network 301 included in the wireless quality predictor 22 described in FIG. 3. The second prediction unit 14 also sets the throughput output by the trained second neural network 301 as the predicted value of the wireless quality at the estimated position.

[0043] The predicted value of the wireless quality of the estimated position predicted by the second prediction unit 14 is notified to the user terminal 100 or the like by the notification unit 15, for example.

[0044] By the above process, the prediction device 10 can provide a wireless quality prediction method that can easily respond to changes in wireless quality even when the propagation environment changes. (Processing of wireless communication systems) Fig. 8 is a sequence diagram showing an example of processing in the wireless communication system according to this embodiment. This processing shows an example of processing in the entire wireless communication system corresponding to the wireless quality prediction processing described in Fig. 4. At the start of the processing shown in Fig. 8, it is assumed that the user terminal 100 is connected to any wireless base station 2 via predetermined wireless communication and is able to communicate with the prediction device 10.

[0045] In step S801, the location acquisition unit 102 of the user terminal 100 acquires the current location of the user terminal 100 using, for example, a GPS device. In step S802, the calculation unit 103 of the user terminal 100 calculates an estimated position of the user terminal 100 after a predetermined time (n seconds) has elapsed, for example, from the current position of the user terminal 100 and the movement of the user terminal 100 measured by a sensor.

[0046] In step S803, the received power acquisition unit 104 of the user terminal 100 acquires the actual measured value of the received power of the radio waves received by the wireless communication unit 101 from the wireless base station 2 from the wireless communication unit 101, the communication control unit 108, or the like.

[0047] In step S804, the inquiry unit 105 of the user terminal 100 transmits an inquiry including the current location of the user terminal 100, the estimated location, and the actual measurement of the received power to the prediction device 10.

[0048] In step S805, upon receiving the inquiry from the user terminal 100, the prediction device 10 executes the wireless quality prediction process described with reference to FIG.

[0049] In step S806, the notification unit 15 of the prediction device 10 notifies the user terminal 100 of the predicted value of the wireless quality at the estimated position.

[0050] In step S807, the communication control unit 108 of the user terminal 100 controls handover and the like of the user terminal 100 based on the predicted value of wireless quality at the estimated position received by the information receiving unit 107.

[0051] <Hardware configuration example> (Hardware configuration of the prediction device) Fig. 9 is a diagram illustrating an example of the hardware configuration of the prediction device 10 according to this embodiment. The prediction device 10 has, for example, the configuration of a computer 900 as shown in Fig. 9. 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.

[0052] The processor 901 is, for example, an arithmetic unit such as a CPU (Central Processing Unit) that executes predetermined programs to realize various functions. The memory 902 is a storage medium readable by the computer 900, and includes, for example, a RAM (Random Access Memory) and a ROM (Read Only Memory). The storage device 903 is a computer-readable storage medium, and may include, for example, a HDD (Hard Disk Drive), an SSD (Solid State Drive), various optical disks, and magneto-optical disks.

[0053] The communication device 904 includes one or more pieces of hardware (communication devices) for communicating with other devices via a wireless or wired network. The input device 905 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that receives input from the outside. The output device 906 is an output device (e.g., a display, a speaker, an LED lamp, etc.) that outputs to the outside. Note that the input device 905 and the output device 906 may be integrated into one device (e.g., an input / output device such as a touch panel display).

[0054] The bus B is commonly connected to the above components and transmits, for example, address signals, data signals, and various control signals. 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).

[0055] (Hardware configuration of user terminal) 10 is a diagram showing an example of the hardware configuration of a user terminal according to this embodiment. The user terminal 100 includes a GPS device 1001, a sensor 1002, and the like in addition to the hardware configuration of the computer 900 described in FIG.

[0056] The GPS device 1001 is a positioning device that receives positioning signals transmitted by GPS satellites and outputs location information indicating the current location of the user terminal 100. The sensor 1002 is a detection device that detects the movement of the user terminal 100, such as an acceleration sensor or angle sensor.

[0057] (supplement) The prediction device 10 in this embodiment is not limited to being realized by a dedicated device, but may also be realized by a general-purpose computer. In this case, a program for realizing this function may be recorded on a computer-readable recording medium, and the program recorded on this recording medium may be read into a computer system and executed to realize the function. Note that the term "computer system" here includes hardware such as an OS and peripheral devices.

[0058] Additionally, "computer-readable recording media" includes various storage devices such as portable media such as flexible disks, optical magnetic disks, ROMs, and CD-ROMs, as well as hard disks built into computer systems. Furthermore, "computer-readable recording media" may also include devices that dynamically store programs for a short period of time, such as communication lines when transmitting programs via networks such as the Internet or communication lines such as telephone lines, and devices that store programs for a certain period of time, such as volatile memory within computer systems that serve as servers or clients in such cases.

[0059] Furthermore, the above program may be one that realizes part of the above-mentioned functions, or may be one that can realize the above-mentioned functions in combination with a program already recorded in a computer system, or may be one that is realized using hardware such as a PLD (Programmable Logic Device) or FPGA (Field Programmable Gate Array).

[0060] <Effects of the embodiment> According to this embodiment, it is possible to provide a wireless quality prediction method that can easily respond to changes in wireless quality even when the propagation environment changes.

[0061] For example, in conventional technology, if machine learning is performed to predict wireless quality at each location and then the propagation environment changes, the accuracy of the wireless quality prediction may decrease.

[0062] On the other hand, in this embodiment, the prediction device 10 predicts a first predicted value P1 of the received power at the current location and a second predicted value P2 of the received power at an estimated location after a predetermined time has elapsed, using a received power predictor 21. Furthermore, the prediction device 10 corrects the second predicted value P2 using a comparison result (difference or ratio) between the actually measured value of the received power at the current location and the first predicted value P1, and estimates the wireless quality at the estimated location using the corrected third predicted value P3.

[0063] Therefore, for example, even if the propagation environment changes and the wireless quality changes after the first neural network 201 of the received power predictor 21 described in FIG. 2 is trained by machine learning, it is possible to suppress a decrease in the prediction accuracy of the wireless quality.

[0064] <Summary of the embodiment> This specification discloses at least the following wireless communication methods and wireless communication systems. (Section 1) The wireless communication system an acquisition process for acquiring a current location of a user terminal, an estimated location of the user terminal after a predetermined time has elapsed, and an actual measurement value of the received power of the user terminal at the current location; a first prediction process for predicting a first predicted value, which is a predicted value of the received power at the current position, and a second predicted value, which is a predicted value of the received power at the estimated position, using a received power predictor; a correction process for correcting the second predicted value to obtain a third predicted value based on a comparison result between the actual measured value of the received power and the first predicted value; a second prediction process for predicting the wireless quality of the user terminal at the estimated location using a wireless quality predictor and the third predicted value; A wireless quality prediction method for performing the above. (Section 2) 2. The wireless quality prediction method according to claim 1, wherein the received power predictor has a first neural network that has been trained in advance to predict received power using a current location as a feature. (Section 3) 3. The wireless quality prediction method according to claim 1 or 2, wherein the wireless quality predictor has a second neural network that has been trained in advance to predict the wireless quality using a plurality of pieces of information including a current location and received power as features. (Section 4) 4. The wireless quality prediction method according to claim 1, wherein the correction unit calculates the third predicted value by adding or subtracting a difference between the actual measured value of the received power and the first predicted value to or from the second predicted value. (Section 5) A wireless communication system including a user terminal and a prediction device capable of communicating with the user terminal, The prediction device includes: an acquisition unit that acquires, from the user terminal, a current location of the user terminal, an estimated location of the user terminal after a predetermined time has elapsed, and an actual measurement value of the received power of the user terminal at the current location; a first prediction unit that predicts a first predicted value that is a predicted value of the received power at the current position and a second predicted value that is a predicted value of the received power at the estimated position using a received power predictor; a correction unit that obtains a third predicted value by correcting the second predicted value based on a comparison result between the actual measured value of the received power and the first predicted value; a second prediction unit that predicts the wireless quality of the user terminal at the estimated location using a wireless quality predictor and the third predicted value; a notification unit that notifies the user terminal of a predicted value of wireless quality of the user terminal at the estimated location; A wireless communication system comprising: (Section 6) The user terminal an inquiry unit that transmits an inquiry to the prediction device, the inquiry including a current location of the user terminal, an estimated location of the user terminal after a predetermined time has elapsed, and an actual measurement value of the received power of the user terminal at the current location; a communication control unit that controls handover of the user terminal based on a predicted value of wireless quality of the user terminal at the estimated position notified by the prediction device; 6. The wireless communication system of claim 5, comprising:

[0065] Although the present embodiment has been described above, the present invention is not limited to such a specific embodiment, and various modifications and changes are possible within the scope of the gist of the present invention described in the claims. [Explanation of symbols]

[0066] 1. Wireless communication systems 10 Prediction Device 11 Acquisition Department 12 First Prediction Section 13 Correction unit 14 Second Prediction Section 15 Notification Department 21 Received power predictor 22 Wireless Quality Predictor 100 user terminals 105 Inquiry Department 108 Communication control unit 201 The First Neural Network 301 Second Neural Network

Claims

1. The wireless communication system an acquisition process for acquiring a current location of a user terminal, an estimated location of the user terminal after a predetermined time has elapsed, and an actual measurement value of the received power of the user terminal at the current location; a first prediction process for predicting a first predicted value, which is a predicted value of the received power at the current position, and a second predicted value, which is a predicted value of the received power at the estimated position, using a received power predictor; a correction process for correcting the second predicted value to obtain a third predicted value based on a comparison result between the actual measured value of the received power and the first predicted value; a second prediction process for predicting the wireless quality of the user terminal at the estimated location using a wireless quality predictor and the third predicted value; A wireless quality prediction method for performing the above.

2. 2. The wireless quality prediction method according to claim 1, wherein the predictor of the received power has a first neural network that has been trained in advance to predict the received power using a current location as a feature.

3. 3. The wireless quality prediction method according to claim 1, wherein the wireless quality predictor has a second neural network that is trained in advance to predict the wireless quality using a plurality of pieces of information including a current location and a received power as feature quantities.

4. 4. The wireless quality prediction method according to claim 1, wherein the correction process calculates the third predicted value by adding or subtracting a difference between the actual measured value of the received power and the first predicted value to or from the second predicted value.

5. A wireless communication system including a user terminal and a prediction device capable of communicating with the user terminal, The prediction device includes: an acquisition unit configured to acquire, from the user terminal, a current location of the user terminal, an estimated location of the user terminal after a predetermined time has elapsed, and an actual measurement value of received power of the user terminal at the current location; a first prediction unit configured to predict, using a received power predictor, a first predicted value that is a predicted value of received power at the current position and a second predicted value that is a predicted value of received power at the estimated position; a correction unit configured to obtain a third predicted value by correcting the second predicted value based on a comparison result between the actual measured value of the received power and the first predicted value; a second prediction unit configured to predict a radio quality of the user terminal at the estimated location using a radio quality predictor and the third predicted value; a notification unit configured to notify the user terminal of a predicted value of wireless quality of the user terminal at the estimated location; A wireless communication system comprising:

6. The user terminal an inquiry unit configured to send an inquiry to the prediction device, the inquiry including a current location of the user terminal, an estimated location of the user terminal after a predetermined time has elapsed, and an actual measurement value of the received power of the user terminal at the current location; a communication control unit configured to control handover of the user terminal based on a predicted value of wireless quality of the user terminal at the estimated location notified by the prediction device; and 6. The wireless communication system of claim 5, comprising:

Images