Radio communication device, prediction device, and communication control system

Abstract

To provide a radio communication device, a prediction device, and a communication control system, that predicts a throughput when performing a radio communication in a railway vehicle to be moved.SOLUTION: A radio communication device 140 provided to a railway vehicle to be moved, includes: an in-vehicle communication part 142 that receives the number of persons who operates a communication terminal in the railway vehicle; an acquisition part 143 that acquires train information indicating a speed of the railway vehicle and a position of the railway vehicle, a reference signal reception power, and a signal-to-interference noise ratio; a storage part 141 that stores a table information or a learned model for predicting a throughput; and a prediction part 144 that predicts the throughput when performing a radio communication in the railway vehicle by using the number of persons, the train information, the reference signal reception power, the signal-to-interference noise ratio, the table information, or the learned model.SELECTED DRAWING: Figure 4

Description

Technical Field

[0001] The present disclosure relates to a wireless communication device, a prediction device, and a communication control system.

Background Art

[0002] Wireless communication technology is widely known. In wireless communication, throughput is important. Technologies related to throughput have been proposed (see Patent Document 1). The evaluation device of Patent Document 1 estimates the throughput at the evaluation point.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the above technology, the throughput at the evaluation point is estimated. That is, the throughput at a fixed location is estimated. There may be a case where it is desired to know the throughput when performing wireless communication in a moving railway vehicle. In the above technology, the throughput at a fixed location is estimated. Therefore, the above technology cannot be used. Thus, it is a problem of how to predict the throughput when performing wireless communication in a moving railway vehicle.

[0005] An object of the present disclosure is to predict the throughput when performing wireless communication in a moving railway vehicle.

Means for Solving the Problems

[0006] A wireless communication device according to an aspect of the present disclosure is provided. The wireless communication device is provided in a moving railway vehicle. The wireless communication device includes a vehicle interior communication unit that receives the number of people operating a communication terminal within the railway vehicle, an acquisition unit that acquires train information indicating the speed and position of the railway vehicle, a reference signal reception power, and a signal-to-interference-plus-noise ratio, a storage unit that stores table information or a learned model for predicting throughput, and a prediction unit that predicts the throughput when performing wireless communication in the railway vehicle using the number of people, the train information, the reference signal reception power, the signal-to-interference-plus-noise ratio, and the table information or the learned model.

Advantages of the Invention

[0007] According to the present disclosure, it is possible to predict the throughput when performing wireless communication in a moving railway vehicle.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Best Mode for Carrying Out the Invention

[0009] Hereinafter, embodiments will be described with reference to the drawings. The following embodiments are merely examples, and various modifications are possible within the scope of the present disclosure.

[0010] Embodiment 1. FIG. 1 is a diagram showing the communication system of Embodiment 1. The communication system includes a railway vehicle 100 and a collection server 200. The railway vehicle 100 and the collection server 200 communicate via an access point 10 and the Internet 11. The access point 10 may be a base station.

[0011] The railway vehicle 100 is moving. The railway vehicle 100 transmits images to the collection server 200 via the access point 10 and the Internet 11. The railway vehicle 100 includes a camera 110, an image processing device 120, a train information management device 130, and a wireless communication device 140. For example, the camera 110, the image processing device 120, the train information management device 130, and the wireless communication device 140 are connected by a network such as Ethernet (registered trademark).

[0012] The camera 110 photographs inside or outside the railway vehicle 100. The image processing device 120 will be described later. The train information management device 130 stores train information. The train information will be described later. The wireless communication device 140 will be described later.

[0013] Also, there is a person inside the railway vehicle 100. A communication terminal operated by the person can be connected to the Internet 11 via the wireless communication device 140.

[0014] Next, the hardware of the image processing device 120, the train information management device 130, and the wireless communication device 140 will be described. FIG. 2 is a diagram showing the hardware of the wireless communication device according to Embodiment 1. The wireless communication device 140 includes a processor 1401, a volatile memory device 1402, and a non-volatile memory device 1403.

[0015] The processor 1401 controls the entire wireless communication device 140. For example, the processor 1401 is a CPU (Central Processing Unit), an FPGA (Field Programmable Gate Array), or the like. The processor 1401 may be a multi-processor. Further, the wireless communication device 140 may include a processing circuit.

[0016] The volatile memory device 1402 is the main memory device of the wireless communication device 140. For example, the volatile memory device 1402 is a RAM (Random Access Memory). The non-volatile memory device 1403 is the auxiliary storage device of the wireless communication device 140. For example, the non-volatile memory device 1403 is an HDD (Hard Disk Drive) or an SSD (Solid State Drive).

[0017] Similar to the wireless communication device 140, the image processing device 120 and the train information management device 130 include a processor, a volatile memory device, and a non-volatile memory device. Further, the image processing device 120 and the train information management device 130 may include a processing circuit.

[0018] Next, the functions of the image processing device 120 will be described. FIG. 3 is a block diagram showing the functions of the image processing device according to Embodiment 1. The image processing device 120 includes an acquisition unit 121, an estimation unit 122, an in-vehicle communication unit 123, and a determination unit 124.

[0019] Part or all of the acquisition unit 121, the estimation unit 122, the in-vehicle communication unit 123, and the determination unit 124 may be realized by a processing circuit included in the image processing device 120. Further, part or all of the acquisition unit 121, the estimation unit 122, the in-vehicle communication unit 123, and the determination unit 124 may be realized as modules of a program executed by a processor included in the image processing device 120. The functions of the acquisition unit 121, the estimation unit 122, the in-vehicle communication unit 123, and the determination unit 124 will be described later.

[0020] Next, the functions of the wireless communication device 140 will be described. FIG. 4 is a block diagram showing the functions of the wireless communication device according to the first embodiment. The wireless communication device 140 includes a storage unit 141, an in-vehicle communication unit 142, an acquisition unit 143, a prediction unit 144, and an out-vehicle communication unit 145.

[0021] The storage unit 141 may be realized as a storage area secured in the volatile storage device 1402 or the non-volatile storage device 1403. Part or all of the in-vehicle communication unit 142, the acquisition unit 143, the prediction unit 144, and the out-vehicle communication unit 145 may be realized by a processing circuit. Further, part or all of the in-vehicle communication unit 142, the acquisition unit 143, the prediction unit 144, and the out-vehicle communication unit 145 may be realized as modules of a program executed by the processor 1401.

[0022] The storage unit 141 stores a reference signal received power (RSRP) and a signal-to-interference-plus-noise ratio (SINR). Note that the reference signal received power is a value measured by the wireless communication device 140. The measurement may be performed by the out-vehicle communication unit 145. Further, for example, the signal-to-interference-plus-noise ratio is a value calculated based on the reference signal received power. The calculation may be performed by the out-vehicle communication unit 145.

[0023] In addition, the storage unit 141 stores table information or a learned model. The table information will be described later. The learned model is used when predicting throughput, as will be described later.

[0024] The functions of the in-vehicle communication unit 142, the acquisition unit 143, the prediction unit 144, and the out-vehicle communication unit 145 will be described later.

[0025] Next, the processes executed by the railway vehicle 100 will be described using a sequence diagram. FIG. 5 is a sequence diagram showing an example of the processes executed by the railway vehicle according to the first embodiment. (Step ST101) The camera 110 transmits an image to the image processing device 120. The camera 110 may transmit a video to the image processing device 120. The image or the video includes a person operating a communication terminal within the railway vehicle 100. For example, the communication terminal is a smartphone, a tablet terminal, or the like. Upon transmission by the camera 110, the acquisition unit 121 of the image processing device 120 acquires the image or the video.

[0026] (Step ST102) The estimation unit 122 of the image processing device 120 estimates the number of people operating a communication terminal within the railway vehicle 100 using the image or the video. Specifically, the estimation unit 122 estimates the number of people using image recognition technology. For example, the estimation unit 122 estimates the number of people using a learned model.

[0027] (Step ST103) The in-vehicle communication unit 123 of the image processing device 120 transmits the number of people to the wireless communication device 140. As a result, the in-vehicle communication unit 142 of the wireless communication device 140 receives the number of people.

[0028] (Step ST104) The acquisition unit 143 of the wireless communication device 140 acquires train information from the train information management device 130. The train information indicates the speed and the position of the railway vehicle 100. Specifically, the train information indicates the current speed of the railway vehicle 100 and the current position of the railway vehicle 100.

[0029] Here, the train information may be stored in the storage unit 141. When the train information is stored in the storage unit 141, the acquisition unit 143 acquires the train information from the storage unit 141. Further, the acquisition unit 143 may acquire the speed of the railway vehicle 100 from a speed sensor. The acquisition unit 143 may acquire the position of the railway vehicle 100 from a GPS (Global Positioning System) sensor or the like.

[0030] (Step ST105) The acquisition unit 143 of the wireless communication device 140 acquires the reference signal reception power and the signal-to-interference-plus-noise ratio. For example, the acquisition unit 143 acquires the reference signal reception power and the signal-to-interference-plus-noise ratio from the storage unit 141. The acquisition unit 143 may acquire the reference signal reception power and the signal-to-interference-plus-noise ratio from the outside-vehicle communication unit 145.

[0031] (Step ST106) The prediction unit 144 of the wireless communication device 140 may predict the throughput when performing wireless communication in the railway vehicle 100 by using the number of people, the train information, the reference signal reception power, the signal-to-interference-plus-noise ratio, and the learned model. Specifically, the prediction unit 144 of the wireless communication device 140 predicts the throughput in the network between the wireless communication device 140 and the collection server 200 by using the number of people, the train information, the reference signal reception power, the signal-to-interference-plus-noise ratio, and the learned model. Specifically, when the prediction unit 144 inputs the number of people, the train information, the reference signal reception power, and the signal-to-interference-plus-noise ratio into the learned model, the learned model outputs the throughput.

[0032] The prediction unit 144 of the wireless communication device 140 may predict the throughput when performing wireless communication in the railway vehicle 100 by using the number of people, the train information, the reference signal reception power, the signal-to-interference-plus-noise ratio, and the table information. Here, the table information will be described. The table information is information for predicting the throughput. Specifically, the table information is information indicating the correspondence relationship between the number of people, the train information, the reference signal reception power, the signal-to-interference-plus-noise ratio, and the throughput.

[0033] (Step ST107) The in-vehicle communication unit 142 of the wireless communication device 140 transmits the throughput to the image processing device 120. Thereby, the in-vehicle communication unit 123 of the image processing device 120 receives the throughput.

[0034] (Step ST108) The determination unit 124 of the image processing apparatus 120 determines the bit rate when transmitting the video to the collection server 200 based on the throughput. Specifically, the determination unit 124 determines the bit rate while keeping the frame rate constant and considering factors such as the resolution and compression ratio. For example, in a situation where the frame rate and compression ratio are fixed, the bit rate is determined by setting the resolution so that the bit rate does not exceed the value obtained by subtracting a margin from the throughput value.

[0035] (Step ST109) The in-vehicle communication unit 123 of the image processing apparatus 120 transmits the video to the wireless communication device 140 at the determined bit rate. Note that the video may be a video inside the railway vehicle 100 or a video outside the railway vehicle 100. Also, the video may be a video stored in the image processing apparatus 120 or a video acquired from the camera 110 after Step ST108. By the transmission of the image processing apparatus 120, the in-vehicle communication unit 142 of the wireless communication device 140 receives the video.

[0036] (Step ST110) The out-of-vehicle communication unit 145 of the wireless communication device 140 transmits the video to the collection server 200.

[0037] Here, the learning method for generating the learned model for predicting throughput is not limited. For example, the learned model may be generated by learning at any time during the operation of the railway vehicle 100. For example, the learning method is supervised learning. Also, the learning data is the number of people operating the communication terminal within the railway vehicle 100, train information, reference signal reception power, and signal-to-interference-plus-noise ratio. At least one condition among time, day, day of the week, weather, and temperature may be added to the learning data. Explain the utilization phase when the learned model is learned using the said condition. The acquisition unit 143 acquires environment information indicating at least one of time, day, day of the week, weather, and temperature. Specifically, the environment information is information indicating at least one of the current time, day, day of the week, weather, and temperature. For example, the acquisition unit 143 acquires the environment information from the storage unit 141 or an external device. Note that the external device is a device existing outside the wireless communication device 140. For example, the external device is a cloud server. The diagram of the external device is omitted. The prediction unit 144 predicts the throughput using the environment information, the number of people, the train information, the reference signal reception power, the signal-to-interference-plus-noise ratio, and the table information or the learned model. Note that the table information is information indicating the correspondence between the environment information, the number of people, the train information, the reference signal reception power, the signal-to-interference-plus-noise ratio, and the throughput. By the processing of the wireless communication device 140, the wireless communication device 140 can predict the throughput corresponding to the communication that changes according to time, day, day of the week, weather, temperature, etc.

[0038] According to the first embodiment, the wireless communication device 140 can predict the throughput when performing wireless communication in the moving railway vehicle 100.

[0039] Also, the image processing device 120 determines the bitrate when transmitting the video to the collection server 200 based on the throughput. Then, the image processing device 120 transmits the video to the collection server 200 at the determined bitrate via the wireless communication device 140. Thereby, the video is received by the collection server 200 without interruption.

[0040] Embodiment 2 Next, Embodiment 2 will be described. In Embodiment 2, matters different from Embodiment 1 will be mainly described. And in Embodiment 2, the description of matters common to Embodiment 1 will be omitted.

[0041] In Embodiment 1, the case where the wireless communication device 140 predicts the throughput was described. In Embodiment 2, the case where a server existing outside the railway vehicle predicts the throughput will be described.

[0042] FIG. 6 is a diagram showing the communication system of Embodiment 2. The communication system includes a railway vehicle 100a, a collection server 200, and a prediction server 300. The railway vehicle 100a, the collection server 200, and the prediction server 300 communicate via an access point 10 and the Internet 11.

[0043] The railway vehicle 100a has a wireless communication device 140a. The wireless communication device 140a has a storage unit 141, an in-vehicle communication unit 142, an acquisition unit 143, and an out-of-vehicle communication unit 145. That is, the wireless communication device 140a does not have a prediction unit 144. Also, the storage unit 141 does not store table information or a learned model.

[0044] Next, the functions of the prediction server 300 will be described. FIG. 7 is a block diagram showing the functions of the prediction server of Embodiment 2. The prediction server 300 is also referred to as a prediction device. The prediction server 300 has a storage unit 310, a communication unit 320, an acquisition unit 330, and a prediction unit 340. The storage unit 310 may be realized as a storage area secured in a volatile storage device or a non-volatile storage device included in the prediction server 300. Part or all of the communication unit 320, the acquisition unit 330, and the prediction unit 340 may be realized by a processing circuit included in the prediction server 300. Also, part or all of the communication unit 320, the acquisition unit 330, and the prediction unit 340 may be realized as modules of a program executed by a processor included in the prediction server 300.

[0045] The storage unit 310 may store table information or a learned model. As will be described later, the learned model is used when predicting throughput. The functions of the communication unit 320, the acquisition unit 330, and the prediction unit 340 will be described later.

[0046] Next, the processing executed in the communication system will be described using a sequence diagram. FIG. 8 is a sequence diagram (Part 1) showing an example of the processing executed in the communication system according to Embodiment 2. Note that in FIG. 8, the collection server 200 is omitted. (Step ST111) The camera 110 transmits an image to the image processing device 120. The camera 110 may transmit a video to the image processing device 120. The image or the video includes a person operating a communication terminal inside the railway vehicle 100a. Upon transmission by the camera 110, the acquisition unit 121 of the image processing device 120 acquires the image or the video.

[0047] (Step ST112) The estimation unit 122 of the image processing device 120 estimates the number of people operating a communication terminal inside the railway vehicle 100a using the image or the video. (Step ST113) The in-vehicle communication unit 123 of the image processing device 120 transmits the number of people to the wireless communication device 140. As a result, the in-vehicle communication unit 142 of the wireless communication device 140a receives the number of people.

[0048] (Step ST114) The acquisition unit 143 of the wireless communication device 140a acquires train information from the train information management device 130. Here, the train information may be stored in the storage unit 141. When the train information is stored in the storage unit 141, the acquisition unit 143 acquires the train information from the storage unit 141. Further, the acquisition unit 143 may acquire the speed of the railway vehicle 100a from a speed sensor. The acquisition unit 143 may acquire the position of the railway vehicle 100a from a GPS sensor or the like.

[0049] (Step ST115) The acquisition unit 143 of the wireless communication device 140a acquires the reference signal reception power and the signal-to-interference-plus-noise ratio. For example, the acquisition unit 143 acquires the reference signal reception power and the signal-to-interference-plus-noise ratio from the storage unit 141. The acquisition unit 143 may acquire the reference signal reception power and the signal-to-interference-plus-noise ratio from the vehicle exterior communication unit 145.

[0050] (Step ST116) The vehicle exterior communication unit 145 of the wireless communication device 140a transmits the number of people, the train information, the reference signal reception power, and the signal-to-interference-plus-noise ratio to the prediction server 300. As a result, the communication unit 320 of the prediction server 300 receives the number of people, the train information, the reference signal reception power, and the signal-to-interference-plus-noise ratio from the railway vehicle 100a.

[0051] (Step ST117) The acquisition unit 330 of the prediction server 300 acquires table information or a learned model from the storage unit 310. The acquisition unit 330 may acquire table information or a learned model from an external device. (Step ST118) The prediction unit 340 of the prediction server 300 predicts the throughput when performing wireless communication in the railway vehicle 100a using the number of people, the train information, the reference signal reception power, the signal-to-interference-plus-noise ratio, and the table information or the learned model. (Step ST119) The communication unit 320 of the prediction server 300 transmits the throughput to the image processing device 120 via the wireless communication device 140a. As a result, the in-vehicle communication unit 123 of the image processing device 120 receives the throughput.

[0052] FIG. 9 is a sequence diagram (part 2) showing an example of processing executed in the communication system according to the second embodiment. In FIG. 9, the prediction server 300 is omitted. (Step ST121) The determination unit 124 of the image processing device 120 determines the bit rate when transmitting the video to the collection server 200 based on the throughput.

[0053] (Step ST122) The in-vehicle communication unit 123 of the image processing apparatus 120 transmits the video to the wireless communication apparatus 140a at the determined bit rate. Note that the video may be a video inside the railway vehicle 100a or a video outside the railway vehicle 100a. Also, the video may be a video stored in the image processing apparatus 120 or a video acquired from the camera 110 after step ST121. Upon transmission by the image processing apparatus 120, the in-vehicle communication unit 142 of the wireless communication apparatus 140a receives the video.

[0054] (Step ST123) The out-of-vehicle communication unit 145 of the wireless communication apparatus 140a transmits the video to the collection server 200.

[0055] According to Embodiment 2, the prediction server 300 can predict the throughput when performing wireless communication in the moving railway vehicle 100a.

[0056] Also, the wireless communication apparatus 140a does not predict the throughput. Therefore, the wireless communication apparatus 140a can be realized with an inexpensive device. Thus, according to Embodiment 2, the cost of the communication system can be suppressed.

[0057] The prediction server 300 may execute the following processing. The acquisition unit 330 acquires environment information indicating at least one of time, date, day of the week, weather, and temperature. For example, the acquisition unit 330 acquires the environment information from the storage unit 310 or an external device. The prediction unit 340 predicts the throughput using the environment information, the number of people, the train information, the reference signal reception power, the signal-to-interference-plus-noise ratio, and the table information or the learned model. Thereby, the prediction server 300 can predict the throughput corresponding to the communication that changes depending on time, date, day of the week, weather, temperature, etc.

[0058] Here, a system including the image processing device 120 and the wireless communication device 140 or the wireless communication device 140a may be referred to as a communication control system. A part of the functions of the image processing device 120 may be realized by the wireless communication device 140 or the wireless communication device 140a. For example, the estimation unit 122 is realized by the wireless communication device 140 or the wireless communication device 140a. Also, a part of the functions of the wireless communication device 140 or the wireless communication device 140a may be realized by the image processing device 120. For example, the prediction unit 144 is realized by the image processing device 120. Also, the table information or the learned model may be stored in the storage area of the image processing device 120 or may be stored in the storage unit 141. Further, the in-vehicle communication unit 123, the in-vehicle communication unit 142, or the out-of-vehicle communication unit 145 may be referred to as a communication unit.

[0059] The features in each of the embodiments described above can be appropriately combined with each other.

Description of Reference Numerals

[0060] 10 Access Point, 11 Internet, 100 Railway Vehicle, 100a Railway Vehicle, 110 Camera, 120 Image Processing Device, 121 Acquisition Unit, 122 Estimation Unit, 123 In-Vehicle Communication Unit, 124 Decision Unit, 130 Train Information Management Device, 140 Wireless Communication Device, 140a Wireless Communication Device, 141 Storage Unit, 142 In-Vehicle Communication Unit, 143 Acquisition Unit, 144 Prediction Unit, 145 Out-of-Vehicle Communication Unit, 200 Collection Server, 300 Prediction Server, 310 Storage Unit, 320 Communication Unit, 330 Acquisition Unit, 340 Prediction Unit, 1401 Processor, 1402 Volatile Memory Device, 1403 Non-Volatile Memory Device.

Claims

1. A wireless communication device provided in a moving railway vehicle, comprising: an in-vehicle communication unit that receives the number of people operating communication terminals within the railway vehicle; an acquisition unit that acquires train information indicating the speed and position of the railway vehicle, reference signal reception power, and signal-to-interference-plus-noise ratio; a storage unit that stores table information or a learned model for predicting throughput; a prediction unit that predicts the throughput when performing wireless communication in the railway vehicle by using the number of people, the train information, the reference signal reception power, the signal-to-interference-plus-noise ratio, and the table information or the learned model; A wireless communication device having the above components.

2. The acquisition unit acquires environment information indicating at least one of time, date, day of the week, weather, and temperature, and the prediction unit predicts the throughput by using the environment information, the number of people, the train information, the reference signal reception power, the signal-to-interference-plus-noise ratio, and the table information or the learned model. The wireless communication device according to Claim 1.

3. A prediction device that communicates with a moving railway vehicle, comprising: a communication unit that receives from the railway vehicle the number of people operating communication terminals within the railway vehicle, train information indicating the speed and position of the railway vehicle, reference signal reception power, and signal-to-interference-plus-noise ratio; an acquisition unit that acquires table information or a learned model for predicting throughput; a prediction unit that predicts the throughput when performing wireless communication in the railway vehicle by using the number of people, the train information, the reference signal reception power, the signal-to-interference-plus-noise ratio, and the table information or the learned model; A prediction device having the above components.

4. The acquisition unit acquires environment information indicating at least one of time, date, day of the week, weather, and temperature, and the prediction unit predicts the throughput by using the environment information, the number of people, the train information, the reference signal reception power, the signal-to-interference-plus-noise ratio, and the table information or the learned model. The prediction device according to Claim 3.

5. A communication control system including a plurality of devices provided in a moving railway vehicle, comprising: an acquisition unit that acquires an image including a person operating a communication terminal within the railway vehicle, train information indicating the speed and position of the railway vehicle, reference signal reception power, and signal-to-interference-plus-noise ratio; An estimation unit that estimates the number of people operating communication terminals inside the railway vehicle using the image; A storage unit that stores table information or a learned model for predicting throughput; A prediction unit that predicts the throughput when performing wireless communication in the railway vehicle using the number of people, the train information, the reference signal reception power, the signal-to-interference-plus-noise ratio, and the table information or the learned model; A communication control system comprising the above.

6. The acquisition unit acquires environment information indicating at least one of time, date, day of the week, weather, and temperature; The prediction unit predicts the throughput using the environment information, the number of people, the train information, the reference signal reception power, the signal-to-interference-plus-noise ratio, and the table information or the learned model; The communication control system according to claim 5.

7. A determination unit that determines the bit rate when transmitting video based on the throughput; A communication unit that transmits video inside the railway vehicle or video outside the railway vehicle to the outside of the railway vehicle at the bit rate; Further comprising: The communication control system according to claim 5 or 6.

Images