High-speed rail NGBR data transmission method, device, equipment, base station and system

Abstract

The disclosed embodiment provides a high-speed rail NGBR data transmission method, which is applied to the operation and management of OM equipment, including: obtaining prediction data for each 5G‑R base station along the target high-speed rail, and inputting a trained unlicensed frequency band NR‑U service prediction network to obtain the NR‑U service start time and duration predicted for the NR‑U device; the NR‑U device is an available NR‑U device installed in the 5G‑R base station for carrying NR‑U services; according to the predicted NR‑U service start time, controlling the NR‑U service of the NR‑U device to start for NGBR data transmission; and according to the predicted NR‑U service duration, controlling the NR‑U service of the NR‑U device to close. The problem that the existing 5G network and 5G‑R private network are not suitable for carrying NGBR services for a large number of users is solved.

Description

Technical Field

[0001] The present disclosure relates to the field of railway wireless communication technology, and in particular to a high-speed railway NGBR data transmission method, device, equipment, base station and system. Background Art

[0002] With the continuous construction and development of my country's high-speed rail, intelligence and automation have become the development direction of high-speed rail technology, giving rise to the high-speed rail's further demand for the quality of wireless network communication along the line. 5G technology's high speed, low latency and multi-connection capabilities can not only improve passengers' travel experience, but also provide strong support for the intelligence and automation of high-speed rail, and will become an important communication system for carrying high-speed rail mobile data services in the future.

[0003] In terms of service types and transmission resource occupation, the service types in the fifth generation mobile communication technology (5G) network are divided into non-guaranteed bit rate service (NGBR) and guaranteed bit rate service (GBR). Although both NGBR and GBR services may occupy major network resources in different scenarios, in many real-world scenarios, since a large number of daily Internet activities (such as video streaming, large file downloads, Internet browsing, emails, and social media, etc.) are mainly based on NGBR, NGBR services are often the main resource consumers.

[0004] In terms of signal coverage and transmission, the operator's 5G network is widely distributed in densely populated areas, which can solve the business information transmission problem of high-speed rail and its passengers to a certain extent. However, except for some key lines, the 5G signal coverage along the high-speed rail is not perfect. For sparsely populated areas, the operator network rarely optimizes its coverage in a targeted manner. This results in the high-speed rail 5G communication quality not being able to meet the needs of various services. Therefore, it is difficult to improve the high-speed rail user experience by relying on the operator network.

[0005] In terms of railway private networks, the railway mobile communication system (GSM-R, Global System Mobile for Railway) currently used by railways can meet the global coverage requirements of wireless signals, but is not suitable for NGBR services that carry a large number of users; the railway mobile communication system based on 5G technology (5G-R, 5G-Railway) also has the problem of frequency band application and the limitation of relatively narrow bandwidth. Therefore, solving the global coverage and large bandwidth transmission of 5G signals along the high-speed railway is a major industry pain point in the field of high-speed railway mobile communications.

[0006] It can be seen that in the application scenario of high-speed rail, neither the 5G network nor the 5G-R private network is suitable for NGBR services that carry a large number of users. Summary of the invention

[0007] The disclosed embodiments provide a high-speed rail NGBR data transmission method, apparatus, device, base station and system to solve the problem that the existing 5G network and 5G-R private network are not suitable for carrying NGBR services for a large number of users.

[0008] Based on the above problems, in the first aspect, a high-speed rail NGBR data transmission method is provided, which is applied to operation and management OM equipment, including:

[0009] For each 5G-R base station along the target high-speed railway, obtain prediction data and input the trained unlicensed frequency band NR-U service prediction network to obtain the predicted NR-U service start time and duration for the NR-U device; the NR-U device is an available NR-U device installed in the 5G-R base station for carrying the NR-U service;

[0010] The prediction data includes: the average start time and duration of the historical 5G-R service of the 5G-R base station, the current weather information, and the designed arrival time and actual arrival time of the trains along the target high-speed railway line within a preset period from now on;

[0011] According to the predicted NR-U service start time, controlling the NR-U service of the NR-U device to start, so as to perform NGBR data transmission; and

[0012] According to the predicted NR-U service duration, control the NR-U service of the NR-U device to close.

[0013] In combination with the first aspect, in any possible implementation manner, the NR-U service prediction network is trained in the following manner: obtaining training data and true data; for each 5G-R base station along the target high-speed railway line, the training data includes the following data counted within a preset historical time period: the 5G-R service start time and duration of the 5G-R base station, weather information, and the designed arrival time and actual arrival time of trains along the target high-speed railway line; using the training data as the input of the NR-U service prediction network to be trained, and using the NR-U service start time and duration of the 5G-R base station within the preset historical time period as true data, to train the NR-U service prediction network.

[0014] In combination with the first aspect, in any possible implementation, the available NR-U devices are determined in the following manner: a preset channel modeling technology is used to perform channel modeling on the area covered by each NR-U device along the target high-speed railway based on the following information: terrain, topography, base station location, antenna height, and transmission power, and the network coverage of the area is predicted; the network includes: public network and / or wifi; for each NR-U device, if the coverage range of the network does not overlap with the coverage range of the NR-U device to a preset overlap threshold, the NR-U device is determined as an available NR-U device.

[0015] In combination with the first aspect, in any possible implementation, the method also includes: for any station along the target high-speed railway line, when any train enters the station, the predicted business data corresponding to the train predicted for the relevant NR-U device is updated according to the actual entry information of the train; the predicted business data includes: the start time and / or duration of the NR-U service; the entry information includes at least one of the following: entry time, carriage length; the relevant NR-U equipment includes: the NR-U equipment of the station and / or each NR-U equipment that the train will pass through subsequently.

[0016] In combination with the first aspect, in any possible implementation, based on the actual entry information of the train, the predicted business data row corresponding to the train predicted for the relevant NR-U device is updated, including: determining the train delay and the delay time interval based on the actual entry time of the train; superimposing the delay time interval to the business start time corresponding to the train predicted for the relevant NR-U device, and updating the business start time.

[0017] In combination with the first aspect, in any possible implementation, the method also includes: determining the NR-U service end time of any 5G-R base station along the target high-speed railway line that is equipped with an available NR-U device; wherein the NR-U service end time is determined based on the predicted NR-U service start time and duration of the NR-U service of the NR-U device; if it is determined that the NR-U service has ended according to the NR-U service end time, and it is detected that the 5G-R service is continuing, and it is obtained that a train has temporarily stopped within the coverage area of ​​the 5G-R base station, then the NR-U service is reopened and the temporary parking time interval is determined; the temporary parking time interval is superimposed on the service start time corresponding to the train predicted for the relevant NR-U device, and the service start time is updated; the relevant NR-U devices include: the NR-U device of the station and / or each NR-U device that the train will pass through subsequently; the temporary parking time interval is superimposed on the service duration corresponding to the train predicted for the NR-U device, and the service duration is updated.

[0018] In combination with the first aspect, in any possible implementation, controlling the NR-U service of the NR-U device to be turned off includes: determining whether the current NR-U service of the NR-U device satisfies: the no NR-U service time exceeds the first preset time, and the number of times the NR-U device is turned off within the second preset time does not reach the preset number of times; if satisfied, turning off the NR-U device; otherwise, turning off the radio frequency channel of the NR-U device; controlling the NR-U service of the NR-U device to be turned on includes: determining whether the NR-U service was turned off by turning off the NR-U device last time; if so, turning on the NR-U device; otherwise, turning on the radio frequency channel of the NR-U device.

[0019] In combination with the first aspect, in any possible implementation, in the NR-U service transmission architecture, the listen-before-talk LBT detection adopts a detection method based on the load device LBE; and / or the prediction data also includes current delay information, then the training data also includes delay information of trains along the target high-speed railway line.

[0020] In a second aspect, a high-speed rail NGBR data transmission device is provided, which is applied to OM equipment, including:

[0021] An acquisition module is used to acquire prediction data for each 5G-R base station along the target high-speed railway, and input the trained unlicensed frequency band NR-U service prediction network to obtain the predicted NR-U service start time and duration for the NR-U device; the NR-U device is an available NR-U device installed in the 5G-R base station for carrying the NR-U service;

[0022] The prediction data includes: the average start time and duration of the historical 5G-R service of the 5G-R base station, the current weather information, and the designed arrival time and actual arrival time of the trains along the target high-speed railway line within a preset period from now on;

[0023] a service activation module, configured to control activation of an NR-U service of the NR-U device according to the predicted NR-U service start time, so as to perform NGBR data transmission; and

[0024] The service shutdown module is used to control the NR-U service shutdown of the NR-U device according to the predicted NR-U service duration.

[0025] In a third aspect, an operation management device is provided, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor and the memory communicate through the bus, and when the machine-readable instructions are executed by the processor, the steps of the high-speed rail NGBR data transmission method as described in any one of claims 1 to 8 are performed.

[0026] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the high-speed rail NGBR data transmission method as described in the first aspect or in combination with any possible embodiment of the first aspect are executed.

[0027] In a fifth aspect, a base station is provided, comprising: a 5G-R base station or NR-U device equipped with an NR-U device; the NR-U device is used to start the NR-U service for NGBR data transmission when receiving a service start indication sent by an OM device; and to close the NR-U service when receiving a service shutdown indication sent by the OM device; wherein the service start indication is determined by the OM device according to the predicted service start time of the NR-U device; the service shutdown indication is determined by the OM device according to the predicted service start time and duration of the NR-U device; the OM device predicts the service start time and duration of the NR-U device by inputting the prediction data into a trained NR-U service prediction network; the prediction data includes: the historical average 5G-R service start time and duration of the 5G-R base station where the NR-U device is located, current weather information, and the designed arrival time and actual arrival time of the trains along the target high-speed railway line within a preset period from the current time.

[0028] In the sixth aspect, a high-speed rail NGBR data transmission system is provided, comprising: an operation management device as described in the third aspect, and at least one 5G-R base station or NR-U device as described in the fifth aspect.

[0029] The beneficial effects of the embodiments of the present disclosure include:

[0030] The high-speed rail NGBR data transmission method, device, equipment, base station and system provided by the embodiments of the present disclosure pre-install NR-U equipment at the 5G-R base station along the target high-speed rail line, and transmit NGBR data through the NR-U equipment; further, in order to save energy, the OM equipment pre-trains the NR-U service prediction network, predicts the service start time and service duration of each available NR-U device along the target high-speed rail line, and controls the corresponding NR-U equipment to be turned on and off according to the predicted service start time and service duration. It not only solves the problem that the existing 5G network and 5G-R private network are not suitable for NGBR services that carry a large number of users, but also turns on the NR-U equipment when there is business, and turns off the NR-U equipment when there is no business, further saving energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 A flowchart of a high-speed rail NGBR data transmission method provided in an embodiment of the present disclosure;

[0032] Figure 2a to Figure 2b A schematic diagram of 5G-R and 5G service types provided for an embodiment of the present disclosure;

[0033] Figure 3 A schematic diagram of a traditional NR-U transmission architecture provided in an embodiment of the present disclosure;

[0034] Figure 4 A schematic diagram of predicting the start time and duration of an NR-U service by using a neural network provided in an embodiment of the present disclosure;

[0035] Figure 5 A schematic diagram of the start-up time and service duration of the NR-U device installed in the 5G-R base station obtained according to the prediction result of the NR-U service prediction network provided in an embodiment of the present disclosure;

[0036] Figure 6 A schematic diagram of the coverage of the public network or WiFi, 5G-R and NR-U near a high-speed railway station obtained by modeling and simulation based on ray tracing technology according to an embodiment of the present disclosure;

[0037] Figure 7 A schematic diagram of train delay processing provided in an embodiment of the present disclosure;

[0038] Figure 8 A schematic diagram of a temporary train stop process provided by an embodiment of the present disclosure;

[0039] Fig. 9 A schematic diagram of the FBE and LBE detection methods provided in the embodiments of the present disclosure;

[0040] Fig.10A schematic diagram of the NR-U transmission architecture for high-speed rail scenarios provided in an embodiment of the present disclosure;

[0041] Fig.11 A schematic diagram of the structure of a high-speed rail NGBR data transmission device provided in an embodiment of the present disclosure;

[0042] Fig.12 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0043] The embodiments of the present disclosure provide a high-speed rail NGBR data transmission method, device, equipment, base station and system. The preferred embodiments of the present disclosure are described below in conjunction with the drawings of the specification. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present disclosure, and are not used to limit the present disclosure. In addition, the embodiments and features in the embodiments of the present application can be combined with each other if there is no conflict.

[0044] The present disclosure provides a high-speed rail NGBR data transmission method, which is applied to an operation management (OM) device side, such as Figure 1 As shown, including:

[0045] S101. For each 5G-R base station along the target high-speed railway, obtain prediction data and input the trained NR-U service prediction network to obtain the predicted NR-U service start time and duration for the NR-U device; the NR-U device is an available NR-U device installed in the 5G-R base station for carrying the NR-U service;

[0046] The forecast data includes: the average start time and duration of the historical 5G-R service of the 5G-R base station, the weather information of the day, the designed arrival time and actual arrival time of the trains along the target high-speed railway line on the day;

[0047] S102. According to the predicted NR-U service start time, control the NR-U service of the NR-U device to start, so as to perform NGBR data transmission;

[0048] S103. According to the predicted NR-U service duration, control the NR-U service of the NR-U device to close.

[0049] In related technologies, due to insufficient coverage of public network operators (e.g. 5G), the bandwidth of 5G-R private network is relatively narrow, and the 5G-R system mainly provides services for trains and is not suitable for traditional mobile phone users. Figure 2a and Figure 2bThe service types of 5G-R and 5G are listed separately. The service of 5G-R is operation control and operation maintenance, including train personnel communication, emergency communication, dispatching communication, etc. The main service of 5G is mobile Internet and Internet of Things service, mainly including daily voice calls, video playback, audio playback, etc. In sparsely populated areas, although there are abundant spectrum resources available, they are rarely used effectively to meet the transmission needs of a large number of NGBR services;

[0050] 3GPP proposed the Licensed Assisted Access (LAA) technology for 4G in Release 13, and proposed the New Radio Unlicensed (NR-U) technology for 5G in the subsequent Release 16. NR-U is designed to allow 5G technology to operate on unlicensed frequency bands in order to share spectrum resources with existing wireless networks and provide wider coverage and higher flexibility. Compared with the unlicensed spectrum technology of 4G, the application scenarios and methods of 5G's unlicensed spectrum technology are also more diverse, such as: Carrier Aggregation (CA), Dual Connectivity (DC), Standalone (SA), etc. At present, solutions combining NR-U technology are rare in the field of high-speed rail communications. Considering the rich unlicensed frequency band spectrum resources in sparsely populated areas, NR-U technology will be very helpful for the transmission of 5G communication NGBR services in the above areas.

[0051] Furthermore, as mentioned above, NR-U uses 5G technology to transmit on unlicensed frequency bands, which can enhance coverage and improve user experience. Unlicensed spectrum resources are abundant, covering low-frequency bands of 2.4GHz (globally, bandwidth 100MHz (2.4-2.5GHz)), 3.5GHz (United States), medium-low frequency bands of 5GHz (globally, bandwidth 200MHz (5.15-5.35GHz)), 6GHz (United States and Europe), etc. Among them, the 2.4GHz band is similar to the 5G-R band (2.1GHz) and is at the same level as the 5G-R coverage range. Therefore, NR-U equipment can be installed on the base station of the high-speed rail 5G-R network without the need to add a new base station (NR-U equipment is also called NR-U base station), reducing deployment costs. Traditional NR-U transmission architecture such as Figure 3As shown. The traditional NR-U transmission architecture includes 7 parts: S301. Determine whether the current service is NGBR service based on the user's bearer (Radio Bear). If so, it can be transmitted through NR-U. S302. Listen Before Talk (LBT) detection is a detection mechanism unique to unlicensed frequency bands. The LBT of the NR-U disclosed in the present invention can choose to be based on the load device (LBE, Load Based Equipment), and determine whether to schedule based on the detection results. If the current detection channel is "idle", scheduling can be performed. If the current detection is "busy", no scheduling is performed. This will be explained later. Steps S303 to S307 are basically the same as the 5G processing. S303, media access control (MAC) scheduling, packet assembly after scheduling, S304 physical layer (PHY) processing, S305 air interface transmission, S306 to S307 process the feedback results. If the feedback is negative acknowledgment (NACK) and not hybrid automatic repeat request response (HARQ ACK), retransmission is required.

[0052] Therefore, in the disclosed embodiment, NR-U devices are installed for the 5G-R base stations along the target high-speed railway. In view of the need for NR-U to seize resources with other unlicensed frequency band technologies, the power of the signal is detected to determine whether the unlicensed frequency band can be used for transmission, which requires consideration of the additional energy consumption of NR-U. Therefore, it is necessary to combine the regularity of the movement of the high-speed railway itself and conduct research on the base stations along the high-speed railway, including but not limited to the intelligent activation and deactivation of the NR-U function and the detection scheme of LBE.

[0053] In order to realize the intelligent activation and deactivation of the NR-U function, the present disclosure pre-trains the NR-U service prediction network for predicting the service start time and service duration of the NR-U device. The executor of the embodiment of the present disclosure may be an OM device, and the OM device may be any host device with an OM system installed. The OM device can manage at least one 5G-R base station and the NR-U device installed thereon, and can be set as needed during implementation. During implementation, the prediction data may be obtained by the OM device, and the trained NR-U service prediction network may be input to predict the service start time and service duration of the managed NR-U device. The prediction frequency is set according to the busyness of different railway lines. Predictions may be made every day as needed, or once at intervals. There is no restriction here.

[0054] During implementation, the OM device can collect data in units of 5G-R base stations, including: train information (time information, delay information, temporary parking information, etc.), station information (designed arrival time of the train, actual arrival time), weather information, etc. The OM device can obtain the arrival information of the train on the target high-speed rail line through the network (the station is all stations before the 5G-R base station in the direction of the train), that is, the designed arrival time and actual arrival time of the train, as well as weather information and delay information. Since the NR-U device and the 5G-R base station are located at the same location, for each NR-U site location, the OM device can count the time from the arrival of the train (the station is a station before the 5G-R base station in the direction of the train) to the time when the 5G-R base station generates the service (that is, the service start time), and the service duration of the 5G-R base station. After a certain period of statistics, the OM device can build an AI prediction model training set in units of base stations. The neural network model is used to predict the NR-U service start time and the corresponding service duration.

[0055] It can be seen that the neural network model constructed to implement the NR-U service prediction network can take the following parameters as independent variables: 5G-R service start time and duration, weather information, train design arrival time and actual arrival time; the start time and duration of NR-U service are used as dependent variables. The neural network model adopted can be any existing network model, such as: Auto-Regression and Moving Average Model (ARMA), Convolutional Neural Networks (CNN), etc., which are not limited here. Therefore, in the prediction process, for each 5G-R base station, the prediction data may include: the historical 5G-R service start time and duration of the 5G-R base station, the current weather information, and the target high-speed rail line train design arrival time and actual arrival time within the preset period from now on. Among them, the preset period can be set according to the prediction frequency, for example, it can be one day; the historical 5G-R service start time and duration of the 5G-R base station can be taken as the average of the values ​​taken within a period of time.

[0056] Figure 4 Schematic diagram of predicting the start time and duration of NR-U service through neural network, as shown in Figure 4As shown, the independent variable is used as the input of the neural network model, and for each 5G-R base station, the service conditions fi(T) corresponding to the NR-U device corresponding to the 5G-R base station in different time periods T are obtained, that is, the predicted start time and duration of the NR-U service. According to the start time of the NR-U service, the NR-U service can be controlled to be turned on (that is, the NR-U device is turned on or the Radio channel of the NR-U device is turned on), and according to the predicted duration of the NR-U service, the NR-U service can be controlled to be turned off (that is, the NR-U device is turned off or the Radio channel of the NR-U device is turned off). In this way, the 5G-R base station can be turned on all day, and the start time of the NR-U service and the duration of the NR-U service can be predicted through the neural network model. Compared with the traditional NR-U transmission architecture, the NR-U transmission architecture for high-speed rail scenarios not only solves the transmission problem of NGBR data, but also saves energy by intelligently controlling the opening and closing of the NR-U service.

[0057] Table 1 is an example of a train passing a 5G-R base station in one day. According to the train information, the specific time when the train departs from a certain station can be known, thereby obtaining the relevant information in Table 1.

[0058] Table 1 Examples of trains passing by 5G-R base stations in one day

[0059]

[0060]

[0061] Figure 5 This is a schematic diagram of the start-up time and service duration of the NR-U equipment installed in the 5G-R base station obtained based on the prediction results of the NR-U service prediction network. Figure 5 As shown, the horizontal axis represents the start-up time of the NR-U device, and the vertical axis represents the duration of the NR-U service. The horizontal axis can also represent the predicted corresponding time (for example, 0 to 24 hours a day), and the vertical axis represents the NR-U service volume corresponding to different times, so that the effective use time curve corresponding to the 5G-R base station prediction can be obtained. Since it takes some time to turn on the NR-U device, the start-up time of the NR-U device is usually earlier than the arrival time of the NR-U service. In addition, when the OM device uses the NR-U service prediction network, the collected weather, delay information, etc. can be used as training data for subsequent AI models to continuously improve the model training. The NR-U device startup here can refer to the NR-U device startup or the NR-U device Radio channel startup.

[0062] In another embodiment of the present disclosure, a training method for an NR-U service prediction network is provided. The NR-U service prediction network is trained in the following manner:

[0063] Step 1: Obtain training data and true value data;

[0064] Step 2: For each 5G-R base station along the target high-speed railway, the training data includes the following data collected during a preset historical period: the start time and duration of the 5G-R service of the 5G-R base station, weather information, and the designed arrival time and actual arrival time of trains along the target high-speed railway;

[0065] Step 3: Use the training data as the input of the NR-U service prediction network to be trained, and use the service start time and duration corresponding to the NR-U equipment installed on the 5G-R base station within the preset historical time period as the true value data to train the NR-U service prediction network.

[0066] In the disclosed embodiment, the executor of the training method of the NR-U service prediction network can be an OM device or other devices, and there is no limitation here. For true value data, since the 5G-R base station and the NR-U device are co-located, the time when the train services of the two arrive at the base station and the duration of the train services are the same. Therefore, it can be assumed that the train arrival time and service duration of the 5G-R base station are the same as those of the NR-U device, and the train arrival time and service duration of the 5G-R base station are used as the start time and service duration of the NR-U service. Alternatively, in the data collection stage, the NR-U device is turned on throughout the day to collect the start time and service duration of the NR-U service as the true value data.

[0067] During training, the training data can be labeled according to the correspondence between the true value data and the training data, and a loss function can be constructed to compare the prediction results obtained each time with the corresponding true value data. According to the comparison results, the parameters in the NR-U service prediction network are updated until the training is completed. The specific process will not be repeated here.

[0068] In another embodiment of the present disclosure, a method for determining an available NR-U device is provided, and the available NR-U device can be determined in the following manner:

[0069] Step 1: Use the preset channel modeling technology to perform channel modeling on the area covered by each NR-U device along the target high-speed railway based on the following information: topography, landform, base station location, antenna height and transmission power, and predict the network coverage of the above area; the above network includes: public network and / or wireless fidelity (wifi);

[0070] Step 2: For each NR-U device, if the coverage of the above network and the coverage of the NR-U device do not overlap to a preset overlap threshold, the NR-U device is determined as an available NR-U device.

[0071] In the disclosed embodiment, considering the coverage of stations in sparsely populated areas and the deployment of base stations on lines in sparsely populated areas, it is necessary to consider the problems of blind spots, overlapping or redundant coverage to avoid incomplete coverage or waste of resources. The OM device can perform coverage prediction based on deterministic channel modeling, that is, using a preset channel modeling technology, based on information such as terrain, topography, base station location, antenna height, and transmission power, channel modeling is performed on the area near the target high-speed rail line (for example: the area covered by each NR-U device), and the network coverage of the area is predicted. According to the coverage situation, it is determined whether the NR-U base station is to be dismantled or deactivated. The preset channel modeling technology includes but is not limited to ray tracing technology, etc. The network here includes a public network and / or WiFi. The public network may include successive generations of cellular networks (4G, 5G, etc.). When the coverage range of the NR-U device overlaps with the coverage range of the public network or WiFi, and the overlapping range does not reach the preset overlapping threshold, it is determined that the NR-U device is available. On the contrary, when the overlapping range reaches the preset overlapping threshold, the corresponding NR-U device can be shut down or dismantled.

[0072] In addition, the step of determining available NR-U devices may not need to be performed before each prediction, but may be performed at longer time intervals to re-evaluate new available NR-U devices and shut down or dismantle new unavailable NR-U devices.

[0073] Figure 6 The following is a schematic diagram of the coverage of public network or WiFi, 5G-R and NR-U near the high-speed railway station obtained by ray tracing technology modeling and simulation. Figure 6 As shown, in order to avoid overlapping and redundant coverage and further save resources and energy, when the public network 4G cell 0 and 5G-R and NR-U cell 1 appear, the NR-U equipment of 5G-R and NR-U cell 1 can be removed or shut down; when the public network 5G cell 1, Wi-Fi and 5G-R and NR-U cell 2 appear, the NR-U equipment of 5G-R and NR-U cell 2 can be removed or shut down; when the situation of 5G-R and NR-U cell 3 appears, the NR-U equipment can be retained.

[0074] In another embodiment provided by the present disclosure, the method further includes the following steps:

[0075] For any station along the target high-speed railway line, when any train enters the station, the predicted business data corresponding to the train predicted for the relevant NR-U equipment is updated according to the actual entry information of the train; the predicted business data includes: the start time and / or duration of the NR-U service; the entry information includes at least one of the following: entry time, carriage length; the relevant NR-U equipment includes: the NR-U equipment of the station and / or each NR-U equipment that the train will pass through subsequently.

[0076] In this embodiment, in order to make the prediction data more accurate, the prediction data can be corrected and updated each time the train enters the station. Due to the influence of factors such as weather, the actual train entry time may be different from the designed entry time, and because the length of the train carriage may be different each time, the duration of the service each time the train passes may be different. In addition, changes in the actual entry time may affect the predicted service data of each NR-U device that the train passes later. Each time a train enters the station, the predicted service data corresponding to the NR-U device of the station and / or each NR-U device that the train will pass later can be updated using information such as the actual entry time of the train. The specific NR-U device that needs to be updated, as well as the start time or duration of the service of the corresponding NR-U device to be updated, can be determined based on the actual updated data.

[0077] In another embodiment provided by the present disclosure, when a train is delayed, this step can also be implemented as follows:

[0078] Step 1: Determine the train delay and the delay time interval according to the actual arrival time of the train;

[0079] Step 2: Add the determined delay time interval to the service start time corresponding to the train predicted by the above-mentioned relevant NR-U equipment, and update the service start time.

[0080] In this embodiment, when a train enters a station, the OM device can obtain train delay information and use the delay information to update the opening and closing time of the corresponding NR-U device. Figure 7 As shown, when the train enters station N, the OM device updates the predicted service data (NR-U service start and duration). If the train is determined to be delayed, the delay time interval (for example, the train is delayed by 30 minutes) is respectively associated with the relevant NR-U equipment ( Figure 7 The NR-U device at station N and the NR-U devices 1 to 3 that will be passed later are included in the forecasted NR-U service opening time to obtain the updated service opening time, thereby obtaining the updated service closing time based on the service duration. For trains that are not delayed, the delay time interval can be set to 0.

[0081] In another embodiment provided by the present disclosure, when a train stops temporarily, the following steps may be performed:

[0082] Step 1: For any 5G-R base station along the target high-speed railway line that is equipped with an available NR-U device, determine the NR-U service end time of the NR-U device; wherein the NR-U service end time is determined according to the predicted NR-U service start time and duration of the NR-U device;

[0083] Step 2: If the NR-U service is determined to have ended according to the NR-U service end time, and the 5G-R service is detected to be ongoing, and it is obtained that a train has temporarily stopped within the coverage area of ​​the 5G-R base station, the NR-U service is restarted and the temporary stop time interval is determined;

[0084] Step 3: superimpose the temporary stop time interval to the service start time corresponding to the train predicted for the relevant NR-U equipment, and update the service start time; the relevant NR-U equipment includes: the NR-U equipment of the station and / or each NR-U equipment that the train will pass through later; and

[0085] Step 4: Add the temporary stop time interval to the service duration corresponding to the train predicted by the NR-U device, and update the service duration.

[0086] In this embodiment, if a temporary stop occurs, when the OM device collects the end time of 5G-R and NR-U services, if it finds that the predicted end time of NR-U service has arrived, while the 5G-R service is still ongoing, and the OM device obtains the temporary stop information, it is determined that a train has stopped temporarily. At this time, the NR-U service can be reopened and the predicted service information of the relevant NR-U devices can be updated. Figure 8 As shown, a train temporarily stops within the coverage of NR-U device 1, the NR-U service is restarted, and the temporary stop time interval (for example, temporary stop for 30 minutes) is determined, and the relevant NR-U devices are respectively ( Figure 8 The NR-U device 1 where the temporary stop is located, and the NR-U devices 2 to 3 that will be passed later), the predicted NR-U service opening time is superimposed to obtain the updated service opening time, and thus the updated service closing time is obtained based on the service duration. In addition, the temporary stop time interval is superimposed to the service duration corresponding to the train predicted for the NR-U device 1, and the service duration is updated.

[0087] Whether a delay or a temporary stop occurs, the OM device can collect the current weather conditions, delay data, temporary stop data, and updated forecast business data for subsequent training and improvement of the NR-U business forecast network.

[0088] In another embodiment provided by the present disclosure, an implementation method for closing the NR-U service is provided, and the closing of the NR-U service is controlled in the following manner:

[0089] Step 1: Determine whether the current NR-U service of the NR-U device satisfies: the time without NR-U service exceeds the first preset time, and the number of shutdown times of the NR-U device does not reach the preset number within the second preset time;

[0090] Step 2: If the conditions are met, turn off the NR-U device; otherwise, turn off the RF channel of the NR-U device.

[0091] In this embodiment, two solutions can be considered for turning on and off the NR-U device:

[0092] Solution 1: NR-U turns on and off the entire station (including baseband and RF channels). This method is more energy-efficient, but it takes more time (minutes) to turn on and off the base station. The radio channel here refers to the RF channel, which generally includes devices such as power amplifiers.

[0093] Solution 2: Only turn on and off the Radio channel. Since the energy consumption of 5G is mainly on the Radio, and the signal power detection module of NR-U is also on the Radio, the time to start and close the Radio channel is shorter than the time to turn on and off the base station for the entire station (in seconds). The advantage of this method is that it is more flexible.

[0094] Under the premise of considering the startup time of the NR-U device, the OM device can decide to turn on or off the NR-U device. Since there are two ways to turn on and off the base station, the present disclosure determines it by setting a threshold. For example: Threshold 1: refers to the NR-U device having no business time exceeding the first preset time (for example: three minutes); Threshold 2: refers to the NR-U device being turned off a preset number of times (for example: 5 times) within the second preset time (for example: 30 minutes). The OM device determines whether the NR-U device is turned off for the entire station or only the Radio is turned off based on the above threshold value. Because the time for turning on the entire station is longer than the time for turning on the Radio, generally at the minute level, when the NR-U device can be turned off within the obtained time period for less than the first preset time (for example: three minutes), or the frequency of turning off within the second preset time (for example: 30 minutes) exceeds the preset number of times (for example 5 times), only the Radio channel of the NR-U device is turned off to save energy, otherwise the NR-U device is turned off to save energy, avoiding continuous high-frequency switching of the NR-U device.

[0095] In addition, the opening and closing of the NR-U device or the Radio channel of the NR-U device will be completed according to the activation and deactivation of the cell configured by the OM device, or the activation and deactivation of the Radio channel.

[0096] In another embodiment provided by the present disclosure, an implementation method for enabling the NR-U service is provided accordingly, and the NR-U service enabling of the NR-U device is controlled in the following manner:

[0097] Step 1: Determine whether the NR-U service was shut down by shutting down the NR-U device last time;

[0098] Step 2: If yes, turn on the NR-U device; otherwise, turn on the RF channel of the NR-U device.

[0099] In this embodiment, the opening mode corresponds to the closing mode. If the NR-U service was closed by closing the NR-U device last time, the NR-U device needs to be opened at the beginning, otherwise the RF channel of the NR-U device is opened. In short, according to the predicted effective use time curve of the NR-U device, combined with the NR-U startup time as the advance amount, the opening and closing of the NR-U device can be effectively controlled by the OM device while taking into account energy saving.

[0100] In another embodiment provided in the present disclosure, in the NR-U service transmission architecture, LBT detection adopts a detection method based on a load device (LBE, Load Based Equipment).

[0101] In this embodiment, there are two detection methods for NR-U. One is based on the frame device (FBE, Frame based Equipment). The characteristic of this detection method is that it is suitable for scenarios without other access technologies and uses fixed-duration detection. The other is based on the load device LBE. The characteristic of this detection method is that it does not rely on the external environment and uses random detection with a non-fixed-length contention window. When a conflict occurs in the use channel or the channel quality is poor, the detection time will be increased. Since there are Wi-Fi devices on the train, which belong to other access technologies, the present disclosure uses a detection method based on LBE. The schematic diagram of FBE and LBE is shown in the figure. Fig. 9 As shown. Clear Channel Assessment (CCA) characterizes the detection time of FBE. When the detection result within the CCA time is "idle", data transmission can be carried out, otherwise, it cannot be transmitted within the maximum transmission time. The fixed frame time of FBE includes the maximum channel occupancy time and the detection time. The LBE detection time is composed of CCA and Enhanced Clear Channel Assessment (ECCA). When the detection results within the CCA and ECCA time are both "idle", data transmission can be carried out, otherwise, CCA and ECCA detections need to be performed again until both are detected as "idle". LBE only limits the maximum channel occupancy time.

[0102] The NR-U transmission architecture for high-speed rail scenarios provided by the embodiments of the present disclosure is as follows: Fig.10 As shown. Fig.10As shown, in step S1001, the OM device performs coverage prediction based on channel modeling, determines available NR-U cells, and removes or deactivates unavailable cells; in step 1002, the OM device collects data to train the constructed NR-U service prediction network, and inputs the prediction data into the trained NR-U service prediction network to predict the service start time and duration of each NR-U device; in step S1003, the NR-U device is turned on or off according to the predicted start time and duration; in step S1004, the OM device turns on the NR-U device; in step S1005, the OM device turns off the NR-U device; steps S1006 to S1012 are basically the same as the traditional NR-U transmission architecture, which will not be repeated here. It should be noted that in the new NR-U transmission architecture provided in the embodiment of the present disclosure, the model training steps in steps S1001 and 1002 do not need to be executed every time data is transmitted, and can be selected for execution according to actual conditions, which will not be repeated here.

[0103] In another embodiment provided by the present disclosure, the prediction data also includes current delay information, and the training data also includes delay information of trains along the target high-speed railway line.

[0104] In this embodiment, the train delay time can be added as an independent variable in the NR-U service prediction network. Accordingly, the training data of the delay information of the trains along the target high-speed railway line can be added during the training process.

[0105] Correspondingly, the NR-U device installed in each 5G-R base station can receive the service activation indication sent by the OM device and activate the NR-U service for NGBR data transmission; and receive the service shutdown indication sent by the OM device and shut down the NR-U service.

[0106] Based on the same disclosed concept, the embodiments of the present disclosure also provide a high-speed rail NGBR data transmission method, device, equipment, base station and system. Since the principles of the problems solved by these devices and equipment are similar to those of the aforementioned high-speed rail NGBR data transmission method, the implementation of the devices and equipment can refer to the implementation of the aforementioned method, and the repeated parts will not be repeated.

[0107] The present disclosure provides a high-speed rail NGBR data transmission device, which is applied to OM equipment, such as Fig.11 As shown, including:

[0108] The acquisition module 1101 is used to acquire prediction data for each 5G-R base station along the target high-speed railway, and input the trained unlicensed frequency band NR-U service prediction network to obtain the NR-U service start time and duration predicted for the NR-U device; the NR-U device is an available NR-U device installed in the 5G-R base station for carrying the NR-U service;

[0109] The prediction data includes: the average start time and duration of the historical 5G-R service of the 5G-R base station, the current weather information, and the designed arrival time and actual arrival time of the trains along the target high-speed railway line within a preset period from now on;

[0110] A service start module 1102, configured to control the start of the NR-U service of the NR-U device according to the predicted NR-U service start time, so as to perform NGBR data transmission; and

[0111] The service shutdown module 1103 is used to control the NR-U service shutdown of the NR-U device according to the predicted NR-U service duration.

[0112] In another embodiment provided by the present disclosure, the above-mentioned device also includes: a training module 1104; the training module 1104 trains the NR-U service prediction network in the following manner: obtaining training data and true value data; for each 5G-R base station along the target high-speed railway line, the training data includes the following data counted within a preset historical time period: the 5G-R service start time and duration of the 5G-R base station, weather information, and the designed arrival time and actual arrival time of trains along the target high-speed railway line; using the training data as the input of the NR-U service prediction network to be trained, and using the service start time and duration corresponding to the NR-U device installed on the 5G-R base station within the preset historical time period as the true value data, to train the NR-U service prediction network.

[0113] In another embodiment provided by the present disclosure, the above-mentioned apparatus also includes: an available NR-U device determination module 1105; the NR-U device determination module 1105 determines the available NR-U devices in the following manner: using a preset channel modeling technology, channel modeling is performed on the area covered by each NR-U device along the target high-speed railway based on the following information: terrain, topography, base station location, antenna height and transmission power, and the network coverage of the area is predicted; the network includes: public network and / or wifi; for each NR-U device, if the coverage range of the network does not overlap with the coverage range of the NR-U device to a preset overlap threshold, the NR-U device is determined as an available NR-U device.

[0114] In another embodiment provided by the present disclosure, the above-mentioned device also includes: an update module 1106, which is used to update the predicted business data corresponding to the train predicted for the relevant NR-U device according to the actual entry information of the train at any station along the target high-speed railway line when any train enters the station; the predicted business data includes: the start time and / or duration of the NR-U service; the entry information includes at least one of the following: entry time, carriage length; the relevant NR-U equipment includes: the NR-U equipment of the station and / or each NR-U equipment that the train will pass through subsequently.

[0115] In another embodiment provided by the present disclosure, the update module 1106 is used to determine the delay of the train and the delay time interval based on the actual entry time of the train; the delay time interval is superimposed on the service start time corresponding to the train predicted for the relevant NR-U device, and the service start time is updated.

[0116] In another embodiment provided by the present disclosure, the update module 1106 is used to determine the NR-U service end time of the NR-U device for any 5G-R base station along the target high-speed railway line that is equipped with an available NR-U device; wherein the NR-U service end time is determined based on the predicted NR-U service start time and duration of the NR-U device; if it is determined that the NR-U service has ended based on the NR-U service end time, and it is detected that the 5G-R service is continuing, and it is obtained that a train has temporarily stopped within the coverage area of ​​the 5G-R base station, then the NR-U service is reopened and the temporary parking time interval is determined; the temporary parking time interval is superimposed on the service start time corresponding to the train predicted for the relevant NR-U device, and the service start time is updated; the relevant NR-U devices include: the station NR-U device and / or each NR-U device that the train will pass through subsequently; the temporary parking time interval is superimposed on the service duration corresponding to the train predicted for the NR-U device, and the service duration is updated.

[0117] In another embodiment provided by the present disclosure, the service shutdown module 1103 is used to determine whether the current NR-U service of the NR-U device meets the following requirements: the no NR-U service time exceeds the first preset time, and the number of times the NR-U device is shut down within the second preset time does not reach the preset number; if so, shut down the NR-U device; otherwise, shut down the radio frequency channel of the NR-U device;

[0118] In another embodiment provided by the present disclosure, the service startup module 1102 is used to determine whether the NR-U service was shut down by shutting down the NR-U device last time; if so, the NR-U device is turned on; otherwise, the radio frequency channel of the NR-U device is turned on.

[0119] In another embodiment provided in the present disclosure, in the NR-U transmission architecture, the listen-before-talk LBT detection adopts a detection method based on the load device LBE; and / or the prediction data also includes current delay information, then the training data also includes delay information of trains along the target high-speed railway line.

[0120] An embodiment of the present disclosure provides an operation management device, including: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor communicates with the memory through the bus, and when the machine-readable instructions are executed by the processor, the steps of the high-speed rail NGBR data transmission method as described in any of the above embodiments are performed.

[0121] An embodiment of the present disclosure provides a base station, including: a 5G-R base station or NR-U device equipped with an NR-U device; the NR-U device is used to start the NR-U service for NGBR data transmission when receiving a service start indication sent by an OM device; and to close the NR-U service when receiving a service shutdown indication sent by the OM device; wherein the service start indication is determined by the OM device according to the predicted service start time of the NR-U device; the service shutdown indication is determined by the OM device according to the predicted service start time and duration of the NR-U device; the OM device predicts the service start time and duration of the NR-U device by inputting the prediction data into a trained NR-U service prediction network; the prediction data includes: the historical average 5G-R service start time and duration of the 5G-R base station where the NR-U device is located, current weather information, and the designed arrival time and actual arrival time of the trains along the target high-speed railway line within a preset period from the current time.

[0122] Reference Fig.12 As shown, it is a schematic diagram of the structure of the electronic device 1200 provided in the embodiment of the present application, including a processor 1201, a memory 1202, and a bus 1203. Among them, the memory 1202 is used to store execution instructions, including a memory 12021 and an external memory 12022; the memory 12021 here is also called an internal memory, which is used to temporarily store the operation data in the processor 1201, and the data exchanged with the external memory 12022 such as a hard disk. The processor 1201 exchanges data with the external memory 12022 through the memory 12021. When the electronic device 1200 is running, the processor 1201 communicates with the memory 1202 through the bus 1203, so that the processor 1201 executes the following instructions:

[0123] For each 5G-R base station along the target high-speed railway, prediction data is obtained, and a trained unlicensed frequency band NR-U service prediction network is input to obtain the predicted NR-U service start time and duration for the NR-U device; the NR-U device is an available NR-U device installed on the 5G-R base station for carrying the NR-U service; the prediction data includes: the average of the historical 5G-R service start time and duration of the 5G-R base station, the current weather information, and the designed arrival time and actual arrival time of the trains along the target high-speed railway within a preset period from now on; according to the predicted NR-U service start time, the NR-U service of the NR-U device is controlled to be turned on for NGBR data transmission; and according to the predicted NR-U service duration, the NR-U service of the NR-U device is controlled to be turned off; or

[0124] When receiving a service start indication sent by the OM device, the NR-U service is started for NGBR data transmission; when receiving a service shutdown indication sent by the OM device, the NR-U service is closed; wherein, the service start indication is determined by the OM device according to the predicted service start time of the NR-U device; the service shutdown indication is determined by the OM device according to the predicted service start time and duration of the NR-U device; the OM device predicts the service start time and duration of the NR-U device by inputting the prediction data into a trained NR-U service prediction network; the prediction data includes: the historical average 5G-R service start time and duration of the 5G-R base station where the NR-U device is located, current weather information, and the designed arrival time and actual arrival time of the trains along the target high-speed railway line within a preset period from the current time.

[0125] The embodiment of the present disclosure provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the high-speed rail NGBR data transmission method as described in any of the above embodiments are executed. The storage medium can be a volatile or non-volatile computer-readable storage medium.

[0126] An embodiment of the present disclosure provides a high-speed rail NGBR data transmission system, including: the above-mentioned operation management device, and at least one of the above-mentioned 5G-R base station or NR-U device.

[0127] The present invention deploys NR-U devices in areas with insufficient public network or WiFi coverage through wireless coverage prediction, and uses unlicensed frequency bands with rich spectrum resources to enhance the transmission of NGBR services for high-speed rail users, increase cell coverage, improve user throughput, and enhance user experience. At the same time, with the increasing number of 5G NR-U devices, equipment energy consumption will be a key pain point, especially for high-speed rail scenarios with a large number of sparsely populated areas. This application applies AI technology to NR-U device deployment and opening and closing stations, performs energy-saving judgments on deployed NR-U devices, combines the autoregressive moving average model to predict high-speed rail train information and business conditions, and then judges the timing of turning on and off NR-U devices to save energy.

[0128] Through the description of the above implementation methods, those skilled in the art can clearly understand that the embodiments of the present disclosure can be implemented by hardware, or by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present disclosure.

[0129] Those skilled in the art can understand that the drawings are only schematic diagrams of a preferred embodiment, and the modules or processes in the drawings are not necessarily required for implementing the present disclosure.

[0130] Those skilled in the art can understand that the modules in the device in the embodiment can be distributed in the device in the embodiment according to the description of the embodiment, or can be changed accordingly and located in one or more devices different from the present embodiment. The modules in the above embodiment can be combined into one module, or can be further divided into multiple sub-modules.

[0131] The serial numbers of the above-mentioned embodiments of the present disclosure are only for description and do not represent the advantages or disadvantages of the embodiments.

[0132] Obviously, those skilled in the art can make various changes and modifications to the present disclosure without departing from the spirit and scope of the present disclosure. Thus, if these modifications and variations of the present disclosure fall within the scope of the claims of the present disclosure and their equivalents, the present disclosure is also intended to include these modifications and variations.

Claims

1. A high-speed rail non-guaranteed bit rate service NGBR data transmission method, applied to operation and management OM equipment, characterized in that: include: For each 5G-R base station along the target high-speed railway, obtain prediction data and input the trained unlicensed band NR-U service prediction network to obtain the predicted NR-U service start time and duration for the NR-U device; The NR-U device is an available NR-U device installed in the 5G-R base station for carrying NR-U services; The prediction data includes: the average start time and duration of the historical 5G-R service of the 5G-R base station, the current weather information, and the designed arrival time and actual arrival time of the trains along the target high-speed railway line within a preset period from now on; According to the predicted NR-U service start time, controlling the NR-U service of the NR-U device to start, so as to perform NGBR data transmission; and Controlling closing of the NR-U service of the NR-U device according to the predicted NR-U service duration; For any 5G-R base station along the target high-speed railway line that is equipped with an available NR-U device, determine the NR-U service end time of the NR-U device; wherein the NR-U service end time is determined according to the predicted NR-U service start time and duration of the NR-U device; If it is determined that the NR-U service has ended according to the NR-U service end time, and it is detected that the 5G-R service is continuing, and it is obtained that a train has temporarily stopped within the coverage area of ​​the 5G-R base station, the NR-U service is restarted and the temporary stop time interval is determined; Adding the temporary stop time interval to the service start time corresponding to the train predicted for the relevant NR-U equipment, and updating the service start time; the relevant NR-U equipment includes: each NR-U equipment that the train will pass through later; The temporary stop time interval is superimposed on the service duration corresponding to the train predicted for the NR-U device, and the service duration is updated.

2. The method according to claim 1, characterized in that The NR-U service prediction network is trained in the following manner: Get training data and true value data; For each 5G-R base station along the target high-speed railway, the training data includes the following data counted within a preset historical time period: the start time and duration of the 5G-R service of the 5G-R base station, weather information, and the designed arrival time and actual arrival time of the trains along the target high-speed railway; The training data is used as the input of the NR-U service prediction network to be trained, and the service start time and duration corresponding to the NR-U device installed in the 5G-R base station within the preset historical time period are used as true value data to train the NR-U service prediction network.

3. The method according to claim 1, characterized in that Use the following method to determine the available NR-U devices: Using preset channel modeling technology, channel modeling is performed on the area covered by each NR-U device along the target high-speed railway based on the following information: topography, landform, base station location, antenna height and transmission power, and the network coverage of the area is predicted; the network includes: public network and / or wifi; For each NR-U device, if the coverage of the network and the coverage of the NR-U device do not overlap to a preset overlap threshold, the NR-U device is determined as an available NR-U device.

4. The method according to any one of claims 1 to 3, characterized in that: Also includes: For any station along the target high-speed railway line, when any train enters the station, the predicted service data corresponding to the train predicted for the relevant NR-U equipment is updated according to the actual entry information of the train; The predicted service data includes: the start time and / or duration of the NR-U service; the entry information includes at least one of the following: entry time, carriage length; the related NR-U equipment includes: the NR-U equipment of the station and / or each NR-U equipment that the train will pass through subsequently.

5. The method according to claim 4, characterized in that According to the actual station entry information of the train, the predicted service data rows corresponding to the train predicted for the relevant NR-U equipment are updated, including: Determine the train delay and the delay time interval according to the actual arrival time of the train; The delay time interval is superimposed on the business start time corresponding to the train predicted for the relevant NR-U device, and the business start time is updated.

6. The method according to any one of claims 1 to 3, characterized in that: Controlling the NR-U service of the NR-U device to be closed includes: Determine whether the current NR-U service of the NR-U device satisfies: the no NR-U service time exceeds a first preset time, and the number of times the NR-U device is turned off does not reach a preset number of times within a second preset time; If the conditions are met, the NR-U device is turned off; otherwise, the radio frequency channel of the NR-U device is turned off; Controlling the NR-U service activation of the NR-U device includes: Determining whether the NR-U service was shut down by shutting down the NR-U device last time; If so, turn on the NR-U device; otherwise, turn on the RF channel of the NR-U device.

7. The method according to claim 6, characterized in that In the NR-U service transmission architecture, the listen-before-talk LBT detection adopts a detection method based on the load device LBE; and / or The prediction data also includes current delay information, and the training data also includes delay information of trains along the target high-speed railway line.

8. A high-speed rail NGBR data transmission device, applied to OM equipment, characterized in that: include: The acquisition module is used to obtain the prediction data for each 5G-R base station along the target high-speed railway, and input the trained unlicensed frequency band NR-U service prediction network to obtain the predicted NR-U service start time and duration for the NR-U device; The NR-U device is an available NR-U device installed in the 5G-R base station for carrying NR-U services; The prediction data includes: the average start time and duration of the historical 5G-R service of the 5G-R base station, the current weather information, and the designed arrival time and actual arrival time of the trains along the target high-speed railway line within a preset period from now on; a service activation module, configured to control activation of an NR-U service of the NR-U device according to the predicted NR-U service start time, so as to perform NGBR data transmission; and A service closing module, configured to control closing of an NR-U service of the NR-U device according to a predicted NR-U service duration; An update module is used to determine the NR-U service end time of any 5G-R base station along the target high-speed railway line that is equipped with an available NR-U device; wherein the NR-U service end time is determined based on the predicted NR-U service start time and duration of the NR-U service of the NR-U device; if it is determined that the NR-U service has ended based on the NR-U service end time, and it is detected that the 5G-R service is continuing, and it is obtained that a train has temporarily stopped within the coverage area of ​​the 5G-R base station, then the NR-U service is reopened and the temporary parking time interval is determined; the temporary parking time interval is superimposed on the service start time corresponding to the train predicted for the relevant NR-U device, and the service start time is updated; the relevant NR-U device includes: each NR-U device that the train will pass through subsequently; the temporary parking time interval is superimposed on the service duration corresponding to the train predicted for the NR-U device, and the service duration is updated.

9. An operation management device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor. When the computer device is running, the processor and the memory communicate via the bus. When the machine-readable instructions are executed by the processor, the steps of the high-speed rail NGBR data transmission method as described in any one of claims 1 to 7 are performed.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, executes the steps of the high-speed rail NGBR data transmission method as described in any one of claims 1 to 7.

11. A base station, characterized in that: include: 5G-R base station or NR-U equipment installed with NR-U equipment; The NR-U device is configured to enable the NR-U service for NGBR data transmission upon receiving a service enable indication sent by the OM device; and disable the NR-U service upon receiving a service disable indication sent by the OM device; Among them, the service start indication is determined by the OM device according to the predicted service start time of the NR-U device; the service close indication is determined by the OM device according to the predicted service start time and duration of the NR-U device; the OM device predicts the service start time and duration of the NR-U device by inputting the prediction data into the trained NR-U service prediction network; the prediction data includes: the historical mean 5G-R service start time and duration of the 5G-R base station where the NR-U device is located, the current weather information, and the designed arrival time and actual arrival time of the target high-speed rail line trains within the preset period from now on; The NR-U device is also used to reopen the NR-U service in the event of a temporary stop of the train; and / or update the service start time.

12. A high-speed rail NGBR data transmission system, characterized in that: include: An operation management device as described in claim 10, and at least one 5G-R base station or NR-U device as described in claim 11.

Images