WO2024089820A1 - 情報配信装置、予測システム、情報配信方法、及びプログラム - Google Patents

情報配信装置、予測システム、情報配信方法、及びプログラム Download PDF

Info

Publication number
WO2024089820A1
WO2024089820A1 PCT/JP2022/039992 JP2022039992W WO2024089820A1 WO 2024089820 A1 WO2024089820 A1 WO 2024089820A1 JP 2022039992 W JP2022039992 W JP 2022039992W WO 2024089820 A1 WO2024089820 A1 WO 2024089820A1
Authority
WO
WIPO (PCT)
Prior art keywords
model
terminal
unit
information distribution
communication quality
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/JP2022/039992
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
尚希 澁谷
憲一 河村
元晴 佐々木
貴庸 守山
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
NTT Inc
Original Assignee
Nippon Telegraph and Telephone Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Nippon Telegraph and Telephone Corp filed Critical Nippon Telegraph and Telephone Corp
Priority to JP2024552599A priority Critical patent/JPWO2024089820A1/ja
Priority to PCT/JP2022/039992 priority patent/WO2024089820A1/ja
Publication of WO2024089820A1 publication Critical patent/WO2024089820A1/ja
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/10—Scheduling measurement reports ; Arrangements for measurement reports
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/06—Selective distribution of broadcast services, e.g. multimedia broadcast multicast service [MBMS]; Services to user groups; One-way selective calling services
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management

Definitions

  • the present invention relates to technology for predicting wireless communication quality.
  • wireless communication In applications such as remote control or remote monitoring of vehicles, robots, and other mobile objects, it is common to use wireless communication to perform remote communication between a server at a center and a terminal installed on the mobile object at the site. Furthermore, since mobile objects are mobile, high availability of wireless communication quality is required for remote communication for safety reasons. It is considered effective to estimate (predict) whether the wireless communication quality can be used stably at the mobile object's destination, and if there is a risk, to perform processing such as switching the line in advance or lowering the video transmission rate to prevent momentary interruptions in the video. Therefore, it is important to predict the communication quality at the destination.
  • Non-Patent Document 1 An example of a technology for predicting wireless communication quality at a destination is disclosed in Non-Patent Document 1.
  • the technology disclosed in Non-Patent Document 1 uses machine learning to learn a model (which may be called a learner) that calculates a predicted value of wireless communication quality at the terminal's position from past quality information. By using this model, it is possible to predict wireless communication quality at the terminal's future position.
  • a model which may be called a learner
  • a terminal sends a query containing a desired location, etc. to a server equipped with a trained model, receives a predicted value of wireless communication quality from the server, and uses the predicted value to control network switching, etc.
  • the model exists on the server side, so if communication between the terminal and the server is interrupted, the terminal cannot receive notification of the predicted values used for control.
  • the present invention has been made in consideration of the above points, and aims to provide a technology that makes it possible to calculate a predicted value at a terminal without obtaining the predicted value from a server equipped with a model for predicting communication quality.
  • a generation unit that generates a model for predicting communication quality in a terminal; and a distribution unit that distributes the model to the terminal.
  • the disclosed technology provides a technology that allows a terminal to calculate a predicted value without obtaining the predicted value from a server that has a model for predicting communication quality.
  • FIG. 1 is a diagram for explaining a problem.
  • FIG. 1 is a diagram for explaining an overview of an embodiment.
  • FIG. 1 is a diagram showing an apparatus configuration according to a first embodiment. 4 is a flowchart for explaining an operation example of the first embodiment.
  • FIG. 13 is a diagram showing an apparatus configuration according to a second embodiment. 13 is a flowchart for explaining an operation example of the second embodiment.
  • FIG. 2 illustrates an example of a hardware configuration of the apparatus.
  • communication quality is assumed to refer to quality in wireless communication, but the technology according to the present invention can also be applied to the communication quality of wired communication rather than wireless.
  • the technology according to the present invention can be applied in an environment in which devices that allow terminals to connect to a network via wired communication are installed in various locations (positions).
  • communication quality is assumed to be the quality of communication when a terminal performs wireless communication. Also, “communication quality” may be referred to as “quality.”
  • terminal is assumed to be mobile.
  • a “terminal” may be a smartphone carried by a person, or a communication device mounted on a mobile object such as a drone, automobile, or robot, or the mobile object itself such as a drone, automobile, or robot may be called a "terminal.”
  • the "communication quality” used below may be any of received power, throughput, delay, jitter, and packet loss, or may be a quality other than these.
  • a terminal can transmit an inquiry including a future location and the like to a communication quality prediction server having a trained model, and can receive a predicted value of communication quality at the future location from the communication quality prediction server.
  • FIG. 2 shows an example of the overall configuration of a prediction system in this embodiment. An outline of this embodiment will be described with reference to Fig. 2.
  • this prediction system includes an information distribution device 100 and a terminal 200.
  • the information distribution device 100 and the terminal 200 can communicate with each other via a network including a wireless section.
  • the information distribution device 100 may be a communication quality prediction server.
  • the terminal 200 moves within a target area where it is expected that communication quality prediction will be performed.
  • the terminal 200 transmits communication quality (e.g., throughput, received power, etc.) and location information of the location where it was measured as collected data to the information distribution device 100.
  • the information distribution device 100 acquires communication quality measured at various points by multiple terminals.
  • the information distribution device 100 uses machine learning to learn a model for predicting communication quality in a target area based on data collected from the terminal 200.
  • the learned model is stored in a model DB.
  • This model is, for example, a neural network model, and in this case, the model DB stores functions, weight parameters, etc. as the model.
  • the data used for machine learning is not limited to data collected from the terminal 200.
  • Data collected from a base station (such as an AP) may also be used as the data used for machine learning.
  • the information distribution device 100 may perform propagation estimation in the target area, for example by a ray tracing method, by referring to a DB (database) that stores information on buildings and the like in the target area, and store the propagation estimation results (e.g., received power at each point, propagation loss at each point) in the model DB.
  • a DB database
  • the propagation estimation results are a type of model for predicting communication quality, and the propagation estimation results may also be called a "model.”
  • the information distribution device 100 distributes (transmits) the model to the terminal 200.
  • the terminal 200 uses the model received from the information distribution device 100 to calculate a predicted value of communication quality at a desired position (e.g., a predicted future position).
  • the predicted value is used, for example, to control line switching, etc.
  • the above model may be a model based on machine learning, a model based on propagation estimation, or both a model based on machine learning and a model based on propagation estimation.
  • the model may also be distributed to multiple terminals simultaneously. Collected data may also be notified to the information distribution device 100 from multiple terminals.
  • Example 1 Device configuration example 3 shows an example of the configuration of the information distribution device 100 and the terminal 200 in the first embodiment.
  • the information distribution device 100 includes an information acquisition unit 110, a learning unit 120, a model DB 130, a distribution unit 160, a propagation estimation unit 150, and a propagation estimation information DB 140.
  • any of the "information acquisition unit 110, learning unit 120" and the “propagation estimation unit 150, propagation estimation information DB 140" may not be included.
  • both the learning unit 120 and the propagation estimation unit 150 may be referred to as a "generation unit.”
  • the terminal 200 includes a communication quality acquisition unit 210, a position acquisition unit 220, an information notification unit 240, an input information generation unit 250, a receiving unit 260, a model DB 270, a prediction unit 280, a control determination unit 290, a control unit 300, and a log DB 310.
  • the communication quality acquisition unit 210 is a functional unit that acquires communication quality (e.g., throughput, received power, etc.) in the terminal 200.
  • the position acquisition unit 220 is, for example, a GNSS receiver, and acquires position information of the terminal 200.
  • the terminal 200 may also be equipped with various sensors. Environmental condition information acquired by the sensors (e.g., temperature, humidity, information on surrounding objects and buildings, etc.) may be notified to the information distribution device 100 by the information notification unit 240.
  • Example 1 Operation example
  • the communication quality acquisition unit 210 in the terminal 200 acquires communication quality (e.g., throughput, received power).
  • the location acquisition unit 220 acquires location information of the terminal 200.
  • the information notification unit 240 notifies the information distribution device 100 of data (information) including the acquired communication quality and location information as data for learning. This notification is performed, for example, periodically.
  • the information acquisition unit 110 in the information distribution device 100 acquires the information notified from the terminal 200.
  • the learning unit 120 performs learning by machine learning using information notified from the terminal 200 side. For example, the learning unit 120 learns a neural network model that inputs location information and outputs (predicts) communication quality.
  • the learned model is stored in the model DB 130.
  • the data stored here as the learned model is, for example, a neural network function and weight parameters.
  • the propagation estimation unit 150 may use information stored in the propagation estimation information DB 140 to perform propagation estimation for the target area, and store the propagation estimation results in the model DB 130. As described above, the propagation estimation results may be called a "model.”
  • the propagation estimation information DB 140 stores information on buildings, base stations, etc. in the target area, and the propagation estimation unit 150 performs propagation estimation using, for example, a ray tracing method.
  • the propagation estimation result is, for example, the received power at each position in the target area.
  • environmental state information received from the terminal 200 may be used.
  • the distribution unit 160 in the information distribution device 100 acquires the model from the model DB 130, and distributes (transmits) the model to the terminal 200.
  • the timing of distribution may be periodic, may be the timing when a distribution request is received from the terminal 200, may be any timing when communication with the terminal 200 is possible, or may be any timing other than the above.
  • the model to be distributed may be a model that has been trained by machine learning, may be a propagation estimation result, or may be both.
  • the receiver 260 in the terminal 200 receives the model distributed from the distributor 160.
  • the model is stored in the model DB 270.
  • the predictor 280 reads out the model from the model DB 270 and holds it.
  • the prediction unit 280 of the terminal 200 uses the model to predict communication quality.
  • the predicted value is notified to the control determination unit 290.
  • the input information generating unit 250 predicts the future location of the terminal 200 based on the location information acquired by the location acquiring unit 220, and inputs the information on the future location to the predicting unit 280.
  • the predicting unit 280 uses the model to acquire a predicted value of the communication quality at the future location.
  • a predicted value of throughput is obtained as an example of communication quality.
  • the model used is a propagation estimation result, a predicted value of received power is obtained as an example of communication quality.
  • the throughput may be estimated from the received power.
  • prediction process by the prediction unit 280 may be performed in response to an inquiry from the control determination unit 290, or at other times (for example, when an updated model is received).
  • control determination unit 290 executes control determination, and the control unit 300 performs control. For example, when the control determination unit 290 grasps that the quality of the current line will deteriorate based on a predicted value, it determines that line switching is necessary, and instructs the control unit 300 to switch the line. The control unit 300 executes control to switch the line used by the terminal 200.
  • the control decision unit 290 may be provided in a server or the like external to the terminal 200. In this case, information is exchanged between the control decision unit 290 and the prediction unit 280/control unit 300 via a network.
  • ⁇ S106> When the prediction unit 280 of the terminal 200 predicts communication quality using a model, a log is stored in the log DB 310. In addition, the position acquisition unit 220 and the communication quality acquisition unit 210 continuously acquire the position and communication quality. The position and communication quality are also stored in the log DB 310 as logs.
  • the information notification unit 240 reads the log from the log DB 310 and transmits the log as feedback to the information distribution device 100.
  • the information distribution device 100 can use the log to re-learn the model.
  • the log may contain a predicted value of communication quality obtained using a model from a predicted future location, and actual measurement results at that location.
  • the learning unit 120 in the information distribution device 100 can re-learn the model to more accurately predict communication quality.
  • steps S103 to S106 are repeated. Steps S101 to S106 may also be repeated.
  • Example 2 Next, a description will be given of Example 2.
  • a model that is a target of ensemble learning or the like is a model that is learned by machine learning.
  • a learning unit 320 is also provided in the terminal 200.
  • the terminal 200 can measure communication quality/location at any time or at any timing, and can also learn a model.
  • the model created by the terminal 200 (or each of the multiple terminals) is notified to the information distribution device 100 periodically or at any timing.
  • the information distribution device 100 for example, generates one model by ensemble learning using multiple models received from the multiple terminals 200, thereby improving the prediction accuracy of the model.
  • Example 2 Device configuration example 5 shows an example of the configuration of the information distribution device 100 and the terminal 200 in the embodiment 2.
  • the configuration of the information distribution device 100 is the same as that in the embodiment 1 (FIG. 3).
  • the configuration of the terminal 200 is the same as that in the embodiment 1 (FIG. 3), except that a learning unit 320 is added.
  • Example 1 Operation example
  • the configuration in the second embodiment can also perform the operations described in the first embodiment, but here, an operation of performing ensemble learning using multiple models acquired from multiple terminals will be described.
  • the information distribution device 100 may perform ensemble learning using a model (the model described in the first embodiment) generated (learned) from location information and communication quality data received from one or more terminals, and multiple models received from multiple terminals, which will be described below.
  • the distribution unit 160 in the information distribution device 100 acquires a model from the model DB 130, and distributes (transmits) the model to the terminal 200.
  • the timing of distribution may be periodic, may be when a distribution request is received from the terminal 200, may be any timing when communication with the terminal 200 is possible, or may be any other timing.
  • the receiving unit 260 in the terminal 200 receives the model distributed from the distribution unit 160.
  • the model is stored in the model DB 270.
  • the prediction unit 280 reads out the model from the model DB 270 and stores it.
  • the prediction unit 280 of the terminal 200 executes prediction of communication quality using the model.
  • the predicted value is notified to the control determination unit 290.
  • the input information generation unit 250 predicts a future position of the terminal 200 based on the position information acquired from the position acquisition unit 220, and inputs the information of the future position to the prediction unit 280.
  • the prediction unit 280 acquires a predicted value of communication quality at the future position using the model. Control is performed based on the predicted value in the same manner as in the first embodiment.
  • the log is stored in the log DB 310.
  • the position acquisition unit 220 and the communication quality acquisition unit 210 continuously acquire the position and communication quality. These are also stored as logs in the log DB 310.
  • the above log includes, for example, a predicted value of communication quality obtained from a predicted future location using a model, and actual measurement results at that location. Note that the log may include the location and measurement results without including a predicted value.
  • the information notification unit 240 notifies the information distribution device 100 of the model learned by the learning unit 320 and the log read from the log DB 310 periodically or at any timing.
  • the information acquisition unit 110 in the information distribution device 100 acquires the model and log notified from the terminal 200 and stores them in a storage unit such as a memory.
  • the learning unit 120 of the information distribution device 100 generates one model from the multiple models by performing ensemble learning using the multiple models and multiple logs received from the multiple terminals 200.
  • the generated model is stored in the model DB 130.
  • the processes of S201 to S205 are executed repeatedly.
  • the information distribution device 100 and the terminal 200 described in this embodiment can both be realized, for example, by causing a computer to execute a program.
  • This computer may be a physical computer or a virtual machine on the cloud.
  • the information distribution device 100 and the terminal 200 are collectively referred to as "devices.”
  • the device can be realized by using hardware resources such as a CPU and memory built into a computer to execute a program corresponding to the processing performed by the device.
  • the program can be recorded on a computer-readable recording medium (such as a portable memory) and then stored or distributed.
  • the program can also be provided via a network such as the Internet or email.
  • FIG. 7 is a diagram showing an example of the hardware configuration of the computer.
  • the computer in FIG. 7 has a drive device 1000, an auxiliary storage device 1002, a memory device 1003, a CPU 1004, an interface device 1005, a display device 1006, an input device 1007, an output device 1008, etc., all of which are interconnected by a bus BS.
  • the computer may further include a GPU.
  • the program that realizes the processing on the computer is provided by a recording medium 1001, such as a CD-ROM or a memory card.
  • a recording medium 1001 storing the program is set in the drive device 1000, the program is installed from the recording medium 1001 via the drive device 1000 into the auxiliary storage device 1002.
  • the program does not necessarily have to be installed from the recording medium 1001, but may be downloaded from another computer via a network.
  • the auxiliary storage device 1002 stores the installed program as well as necessary files, data, etc.
  • the memory device 1003 When an instruction to start a program is received, the memory device 1003 reads out and stores the program from the auxiliary storage device 1002.
  • the CPU 1004 realizes the functions related to the device in accordance with the program stored in the memory device 1003.
  • the interface device 1005 is used as an interface for connecting to a network, etc.
  • the display device 1006 displays a GUI (Graphical User Interface) based on a program, etc.
  • the input device 1007 is composed of a keyboard and mouse, buttons, a touch panel, etc., and is used to input various operational instructions.
  • the output device 1008 outputs the results of calculations.
  • the terminal can predict communication quality and continue controlling the terminal using the predicted value.
  • Additional Notes Memory, at least one processor coupled to the memory; Including, The processor, generating a model for predicting communication quality at a terminal; An information distribution device that distributes the model to the terminal.
  • the processor receiving data including location information and communication quality from one or more terminals; The information distribution device according to claim 1, further comprising: learning the model using the data.
  • Additional Note 3) 3. The information distribution device according to claim 1, wherein the processor learns the model using a plurality of models received from a plurality of terminals.
  • the processor Acquire a propagation estimation result by performing a propagation estimation in a target area; The information distribution device according to any one of appendixes 1 to 3, wherein the propagation estimation result is distributed to the terminal as the model.
  • An information distribution method executed by an information distribution device comprising: generating a model for predicting communication quality at a terminal; and distributing the model to the terminal.
  • a non-transitory storage medium storing a program for causing a computer to function as each unit in the information distribution device according to any one of claims 1 to 4.
  • Information distribution device 110 Information acquisition unit 120 Learning unit 130 Model DB 140 Propagation estimation information DB 150 Propagation Estimation Unit 160 Distribution Unit 200 Terminal 210 Communication Quality Acquisition Unit 220 Position Acquisition Unit 240 Information Notification Unit 250 Input Information Generation Unit 260 Reception Unit 270 Model DB 280 Prediction unit 290 Control decision unit 300 Control unit 310 Log DB 320 Learning unit 1000 Drive device 1001 Recording medium 1002 Auxiliary storage device 1003 Memory device 1004 CPU 1005 Interface device 1006 Display device 1007 Input device 1008 Output device

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Multimedia (AREA)
  • Mobile Radio Communication Systems (AREA)
PCT/JP2022/039992 2022-10-26 2022-10-26 情報配信装置、予測システム、情報配信方法、及びプログラム Ceased WO2024089820A1 (ja)

Priority Applications (2)

Application Number Priority Date Filing Date Title
JP2024552599A JPWO2024089820A1 (https=) 2022-10-26 2022-10-26
PCT/JP2022/039992 WO2024089820A1 (ja) 2022-10-26 2022-10-26 情報配信装置、予測システム、情報配信方法、及びプログラム

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2022/039992 WO2024089820A1 (ja) 2022-10-26 2022-10-26 情報配信装置、予測システム、情報配信方法、及びプログラム

Publications (1)

Publication Number Publication Date
WO2024089820A1 true WO2024089820A1 (ja) 2024-05-02

Family

ID=90830285

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2022/039992 Ceased WO2024089820A1 (ja) 2022-10-26 2022-10-26 情報配信装置、予測システム、情報配信方法、及びプログラム

Country Status (2)

Country Link
JP (1) JPWO2024089820A1 (https=)
WO (1) WO2024089820A1 (https=)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009278421A (ja) * 2008-05-15 2009-11-26 Nec Corp 無線品質劣化予測システム
WO2020217458A1 (ja) * 2019-04-26 2020-10-29 日本電信電話株式会社 通信システム及び端末
WO2021107831A1 (en) * 2019-11-28 2021-06-03 Telefonaktiebolaget Lm Ericsson (Publ) Performing a handover procedure

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009278421A (ja) * 2008-05-15 2009-11-26 Nec Corp 無線品質劣化予測システム
WO2020217458A1 (ja) * 2019-04-26 2020-10-29 日本電信電話株式会社 通信システム及び端末
WO2021107831A1 (en) * 2019-11-28 2021-06-03 Telefonaktiebolaget Lm Ericsson (Publ) Performing a handover procedure

Also Published As

Publication number Publication date
JPWO2024089820A1 (https=) 2024-05-02

Similar Documents

Publication Publication Date Title
US20240015196A1 (en) Low latency wireless communication system for teleoperated vehicle environments
Zhang et al. Computation offloading and service caching in heterogeneous MEC wireless networks
US11748326B2 (en) Data flow control device and data flow control method
Khatib et al. Designing a 6G testbed for location: Use cases, challenges, enablers and requirements
US20260010845A1 (en) Systems and methods of assigning microtasks of workflows to teleoperators
JP7729400B2 (ja) 無線品質予測方法、及び無線通信システム
WO2022024197A1 (ja) 通信システム、接続先制御方法、制御装置、及びプログラム
CN116981547A (zh) 机器人控制方法和机器人控制系统
JP7568073B2 (ja) 通信制御システム、通信制御方法、及びプログラム
WO2024089820A1 (ja) 情報配信装置、予測システム、情報配信方法、及びプログラム
JP7841613B2 (ja) 推定装置、学習装置、推定方法、学習方法、及びプログラム
WO2024150327A1 (ja) 予測装置、学習装置、予測システム、予測方法、及びプログラム
Peng et al. Punctual cloud: Achieving punctuality for time-critical cloud control systems
CN117938231A (zh) Leo卫星网络的卫星切换方法、系统、电子设备及存储介质
JP7111159B2 (ja) 情報共有装置、情報共有方法および情報共有プログラム
CN116647851A (zh) 用于网络性能确定的方法、装置和计算机程序产品
JP7779385B2 (ja) 無線品質予測システム、無線品質予測装置、無線品質予測方法、及びプログラム
KR20170106152A (ko) 실내 위치 추정을 위한 서버의 동작 방법
WO2025150115A1 (ja) 無線通信装置及び無線通信方法
WO2022219753A1 (ja) 制御システム、制御方法、及びプログラム
JP6544184B2 (ja) データ通信制御方法、情報処理装置、プログラム及びデータ通信制御システム
Pathirana et al. Robust extended Kalman filter based technique for location management in PCS networks
JP7568074B2 (ja) 通信制御システム、通信制御方法、及びプログラム
CN117555815B (zh) 参数预测方法、模型训练方法和相关装置
JP7372058B2 (ja) 交通流予測支援装置、交通流予測支援方法、及び交通流予測支援プログラム

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22963469

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2024552599

Country of ref document: JP

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 22963469

Country of ref document: EP

Kind code of ref document: A1