WO2025216652A1 - Method and system for providing a wireless coverage area - Google Patents

Abstract

A method for providing an area of wireless coverage on cash-in-transit vehicle routes includes collecting data about established base stations, the building density and the terrain height in an area of radio frequency (RF) signal coverage of a local environment, training a machine learning model on the collected local environment coverage data to determine points in the local environment at which RF signal repeaters will be positioned, obtaining data about the route of a cash-in-transit vehicle, determining a target point in the local environment along the cash-in-transit vehicle route where the RF signal level is absent or below a set threshold value, determining a positioning point in the local environment for a radio repeater for providing an area of RF signal coverage encompassing said target point, generating a flight plan for an unmanned aerial vehicle (UAV) equipped with an RF signal repeater, and sending the UAV to the repeater positioning point. The technical result consists in increasing the accuracy of determining positioning points for RF signal repeaters.

Description

METHOD AND SYSTEM FOR PROVIDING RADIO COMMUNICATION COVERAGE

AREA OF TECHNOLOGY

[0001] This solution relates to the field of computer technology, in particular to the field of automated data processing for providing radio coverage along the routes of cash-in-transit vehicles using unmanned aerial vehicles (UAVs) with installed repeaters.

LEVEL OF TECHNOLOGY

[0002] For cash collection services, cash collection vehicles (CCTs) are used. They travel along specific routes to serve clients located in various locations within a given territory. A key issue is that given certain infrastructure conditions (development, interference, etc.), CCT routes can include areas without radio signal coverage, particularly cellular coverage. This can lead to a loss of operational control over the CCTs' movements.

[0003] To ensure radio signal coverage along ITS routes, UAVs equipped with radio signal repeaters can be used to compensate for the absence or weakness of a signal at desired points. An example of an approach for using UAVs is disclosed in patent application US 20180293897 A1 (T Mobile USA Inc, October 11, 2018). This known solution proposes, based on calculations of radio signal coverage, to generate signal transmission points to the UAV at algorithmically determined points.

[0004] A disadvantage of this approach is that it relies primarily on signal strength data within the coverage area and does not take into account the specific infrastructure parameters to identify points with insufficient signal strength and deploy UAVs there to improve coverage. Also, this approach is not applicable to ensuring communication while cash-in-transit vehicles are moving. ESSENCE OF THE INVENTION

[0005] The technical problem that the claimed invention is aimed at solving is the use of UAVs in areas where ITS routes pass to provide a radio signal coverage area.

[0006] The technical result is to provide a radio signal coverage area along the ITS routes.

[0007] Another technical result is an increase in the efficiency of determining points for placing radio signal repeaters in them to ensure coverage along ITS routes.

[0008] In a preferred embodiment, a method is claimed for providing a radio coverage area along the routes of cash-in-transit vehicles (CIT), performed using at least one computing device and comprising the steps of: collecting data on the radio signal coverage area of the terrain, including at least information on the installed base stations (BS), as well as the building density and the height of the relief; training a machine learning model based on the collected data on the coverage area of the terrain, during which the model is trained to determine points on the terrain for the placement of radio signal repeaters; receiving data on the route of movement of at least one CIT; determining at least one target point on the terrain along the route of the CIT, in which the radio signal level is absent or below a given threshold value; determining, using said machine learning model, a point on the terrain for the placement of a radio signal repeater providing a radio signal coverage area covering said target point; forming a flight mission for an unmanned aerial vehicle (UAV) with an installed radio signal repeater, containing at least the route of the UAV and the coordinates of the repeater placement point determined using a machine learning model; directing the UAV to the repeater placement point. [0009] In one of the particular examples of the implementation of the method, additionally, data on interference at radio frequencies in the coverage area is obtained.

[0010] In another particular example of the implementation of the method, the time of arrival of the ITS at the target point is calculated.

[0011] In another particular example of the implementation of the method, the flight mission additionally includes the time of arrival of the ITS at the target point.

[0012] In another particular example of the implementation of the method, the flight task is transmitted to the UAV, which ensures arrival at the location of the repeater by the time of arrival of the ITS.

[0013] In another particular example of the implementation of the method, when forming a flight mission, the proximity to the base stations installed in a given area is determined.

[0014] In another particular example of the implementation of the method, the UAV communicates wirelessly with the BS in the area where the repeater is located.

[0015] In another particular example of the implementation of the method, the UAV communicates via an atmospheric optical communication line.

[0016] In another particular example of the implementation of the method, the repeater on the UAV contains a rotating antenna.

[0017] In a preferred embodiment, a system for providing radio coverage along routes of cash-in-transit vehicles (CIT) is also claimed, comprising: a computing device configured to collect data on the radio signal coverage area of the terrain, including at least information on installed base stations (BS), as well as the building density and terrain height; to train a machine learning model based on the collected data on the coverage area of the terrain, during which the model is trained to determine points on the terrain for the placement of radio signal repeaters; to obtain data on the route of movement of at least one CIT; to determine at least one target point on the terrain along the route of the CIT, in which the radio signal level is absent or below a specified threshold value; determining, using said machine learning model, a point on the terrain for placing a radio signal repeater that provides a radio signal coverage area covering said target point; forming a flight mission for a UAV with an installed radio signal repeater, wherein the flight mission contains at least the route of the UAV and the coordinates of the repeater placement point determined using the machine learning model; transmitting the flight mission to the UAV;

An unmanned aerial vehicle (UAV) designed with the capability of receiving a flight mission from a computing device and moving to a specified repeater location.

DESCRIPTION OF DRAWINGS

[0018] Fig. 1 illustrates the general diagram of the claimed solution.

[0019] Fig. 2 illustrates a block diagram of the method.

[0020] Fig. 3 illustrates an example of calculating the power of base station signals.

[0021] Fig. 4 ...

IMPLEMENTATION OF THE INVENTION

[0022] Fig. 1 shows the general principle for implementing the claimed solution. To solve many technical and applied problems, it is necessary to optimize the transmission infrastructure (i.e., select/change the configuration/location of transmitters and antennas, etc.) to effectively achieve the target indicators. Such indicators are usually the signal coverage of a given territory under certain conditions (terrain, presence of buildings and structures, transport network topology, etc.). However, in addition to coverage, the target indicators may also be other characteristics - for example, the capacity or maximum network throughput in a given territory, etc. Technically, the problem is formulated as follows - under given conditions, taking into account the constraints, select the configuration of transmitters (repeaters) that most effectively ensures the achievement of the target indicators. Such problems arise both during the creation of the transmission infrastructure (for calculating/designing the initial configuration), and during operation in connection with changes in the conditions and/or requirements for signal coverage. [0023] As shown in Fig. 1, the information (10) about the radio signal coverage area of the area includes such data as: information about the installed base stations (BS) (11 - 13), the building density and the terrain height. Additionally, the BS type, power, equipment installed on the BS, the BS antenna directivity, etc. can be taken into account. Based on these parameters, the coverage area of the BS (11 - 13) by the signal can be determined.

[0024] The obtained information (10) is used on a selected computing device (20), for example, a PC or a server, to train a machine learning model (ML model). The ML model provides an assessment of target indicators (coverage quality, etc.) for a given configuration option (transmitter locations, transmitter types, etc.), and also allows for the determination of optimal points for the formation of stable radio signal coverage (implementation of an algorithm for searching for optimal coverage from given options).

[0025] Example input data for the ML model: init_signal_dbm = 40 dBm : outgoing signal power height = 20 m : antenna height buildings_rate_phil_phi2_rl_r2 = 0.7 : percentage of area covered by buildings for the ring sector at a distance from rl to r2 from the transmitter between angles phi 1 and phi2 from north ground_rate_phil_phi2_rl_r2 = 0.7 : percentage of terrain above the transmitter for the ring sector at a distance from rl to r2 from the transmitter between angles phi 1 and phi2 from north

}

Parameters phi 1, phi2, rl, r2 are usually configured by the system.

[0026] To improve the accuracy and speed of implementation of the proposed method, various heuristics and/or built-in mechanisms for pre-training the ML model and optimization module can be used. For example, the following heuristics can be used when selecting configuration options to exclude configurations with transmitter placement points that: - points located too close to each other, and there are no obstacles (mountains, buildings) between these points. The distance threshold at which points are excluded is calculated using heuristics.

- reached the top of the ranking, but have too little coverage within the task. The coverage threshold, starting from which points are excluded, is calculated using heuristics.

[0027] The result of the ML model’s operation is the determination of a point (32) to which a UAV (30) with an installed repeater is directed, in which it is necessary to organize a coverage zone (31) of a radio signal for the ITS (40) located at this point.

[0028] Let us consider in more detail the method (200) for providing a radio signal coverage area. In the first stage (201), data (10) is collected on the radio signal coverage area of the area, including such data as: information on installed base stations (11-13), building density, and terrain elevation. Additionally, the base station type, power, equipment installed on the base station, directionality, radio frequency interference data in the coverage area, etc. may be taken into account.

[0029] Next, at step (202), the ML model is trained based on the data obtained at step (201). As shown in Fig. 3, to calculate the signal level at point Bi, with the transmitter located at point A and with predetermined conditions (height of surrounding buildings, terrain, etc.), one of the known physical-mathematical models (hereinafter referred to as the FM model) for calculating the propagation of a radio signal is used. To calculate the signal level in the entire target coverage area, a radial grid with the origin of coordinates at the transmitter installation point is used. At each i-th node of the grid Bi, the signal level is calculated, and it is assumed that the signal around the node Bi within a radius R is considered equal to the signal at the node Bi. The signal around the node within a radius R is the same as at the node itself.

[0030] Since the calculations of the FM model even for one transmitter (repeater) take a lot of time and computational resources, it is possible to use a pre-trained ML model to approximate the assessment of target indicators for given configurations. [0031] The ML model is trained on synthetic data obtained by calculating target indicators (coverage) for different transmitter locations: Ci = f(propsi, 1 , where Ci is the coverage, propsi are the conditions of the corresponding transmitter location point, and li are the coordinates of the transmitter location (see definitions and calculation procedure below).

[0032] Calculation of features (terrain characteristics props;) The input features of the ML model are terrain statistics: the number of landscape areas above the transmitter's location (with coordinates li) in the first (2nd, 3rd, 4th) coordinate quadrant within a radius of rl to r2 relative to the location, and the number of buildings per unit area in these zones. Here, rl and r2 can have different values (configurable parameters).

[0033] Calculation of target (target variable)

The target variable of the ML model is calculated as the ratio of the area of the covered territory (with the transmitter located at coordinates li, based on the FM model calculations) to the maximum possible area under the given parameters—what the coverage from this point would be if there were no obstacles in the signal propagation path. Data for training the ML model is synthesized by simulating the installation of a transmitter (repeater) at a given point and calculating the coverage area in a radial grid based on the corresponding FM model of radio signal propagation.

[0034] Method for finding optimal coverage

The input of the ML model is:

- Points Ai with coordinates li that need to be ranked (which can be used to install the transmitter);

- Bi points/areas that need to be covered by the signal;

- Propsi conditions (relief, buildings, vegetation) for the location of Ai transmitter points.

[0035] At step (203), information is collected about the ITS routes, where zones and points are determined (step 204) in which the radio signal level is absent or weak enough, i.e. below the established threshold value, and does not allow the required level of communication with the ITS. Such a zone, as a rule, is outlined by geographic coordinates, which makes it possible, using the ML-model at step (205), to determine points for subsequent ranking in terms of selecting the optimal point for placing a repeater on a UAV (30). For the best repeater locations, coverage zones (31) are calculated using the above-mentioned ML-model, which calculates the coverage quality from possible UAV placement points.

[0036] When determining the point (32) for directing the UAV (30) to it, the proximity of the BS (11 - 13) is also taken into account, which is necessary to ensure communication between the BS and the UAV (30) repeater to ensure the required signal power and the formation of a coverage zone (31) of the radio signal. Communication between the UAV (30) and the BS can be organized according to wireless data transmission channel, for example, using an atmospheric optical communication line (FSO - free-space optics).

[0037] Additionally, a calculation of the time of arrival of the UAV (30) at a certain point (32) for placing a repeater can be performed, which can be calculated on the basis of the speed of movement of the ITS (40), the time of its expected arrival in an area with an absent or weak radio signal, road traffic and other information.

[0038] At step (206), a flight mission for the UAV (30) is generated and transmitted to it via the selected data transmission channel. The flight mission contains the geographic coordinates of the destination point (32) at which the UAV (30) with the repeater must be positioned, the route of the UAV, including the flight altitude and the trajectory. Additionally, the speed of the UAV (30) can be adjusted depending on the required time of arrival at the point (32).

[0039] Multiple UAVs may also be used, each positioned at a designated point to provide radio signal coverage. UAVs may alternate at the same point based on their battery charge levels. In this case, a backup flight mission is generated with a set time step required for the return of the first UAV, currently located at the point, to the charging station, and the direction of the second UAV to the point for deployment of a repeater, ensuring the required radio signal coverage.

[0040] Fig. 4 shows a general view of a computing device (400) with which the claimed solution can be implemented. In general, the computing device (400) comprises one or more processors (401) connected by a common information exchange bus, memory means such as RAM (402) and ROM (403), input/output interfaces (404), input/output devices (405), and a device for network interaction (406).

[0041] The processor (401) (or several processors, a multi-core processor) can be selected from a range of devices that are widely used at the present time, for example, from Intel™, AMD™, Apple™, Samsung Exynos™, MediaTEK™, Qualcomm Snapdragon™, etc. The processor must also include a graphic processor, for example, an NVIDIA or ATI GPU, which is also suitable for the full or partial implementation of the method (200, 300). In this case, the memory means may be the available memory capacity of the graphic card or graphic processor.

[0042] RAM (402) is a random access memory and is intended for storing machine-readable instructions executed by the processor (401) for execution necessary operations for logical data processing. RAM (402), as a rule, contains executable instructions of the operating system and corresponding software components (applications, software modules, etc.).

[0043] ROM (403) represents one or more permanent data storage devices, such as a hard disk drive (HDD), a solid state drive (SSD), flash memory (EEPROM, NAND, etc.), optical storage media (CD-R/RW, DVD-R/RW, BlueRay Disc, MD), etc.

[0044] To organize the operation of the components of the device (400) and to organize the operation of external connected devices, various types of I/O interfaces (404) are used. The selection of the corresponding interfaces depends on the specific design of the computing device, which may be, but are not limited to: PCI, AGP, PS/2, IrDa, FireWire, LPT, COM, SATA, IDE, Lightning, USB (2.0, 3.0, 3.1, micro, mini, type C), TRS/Audio jack (2.5, 3.5, 6.35), HDMI, DVI, VGA, Display Port, RJ45, RS232, etc.

[0045] To ensure user interaction with the computing device (400), various I/O information means (405) are used, for example, a keyboard, a display (monitor), a touch display, a touchpad, a joystick, a mouse, a light pen, a stylus, a touch panel, a trackball, speakers, a microphone, augmented reality means, optical sensors, a tablet, light indicators, a projector, a camera, biometric identification means (a retinal scanner, a fingerprint scanner, a voice recognition module), etc.

[0046] The network interaction means (406) ensures the transmission of data by the device (400) via an internal or external computer network, for example, an Intranet, the Internet, a LAN, etc. One or more means (406) may be, but are not limited to: an Ethernet card, a GSM modem, a GPRS modem, an LTE modem, a 5G modem, a satellite communication module, an NFC module, a Bluetooth and/or BLE module, a Wi-Fi module, etc.

[0047] Additionally, satellite navigation tools may also be used as part of the device (300), for example, GPS, GLONASS, BeiDou, Galileo.

[0048] The submitted application materials disclose preferred examples of the implementation of the technical solution and should not be interpreted as limiting other, particular examples of its implementation that do not go beyond the scope of the requested legal protection, which are obvious to specialists in the relevant field of technology.

Claims

FORMULA 1. A method for providing a radio coverage area along the routes of cash-in-transit vehicles (CIT), performed using at least one computing device and comprising the steps of: collecting data on the radio signal coverage area of the terrain, including at least information on the installed base stations (BS), as well as the building density and the height of the relief; training a machine learning model based on the collected data on the coverage area of the terrain, during which the model is trained to determine points on the terrain for the placement of radio signal repeaters; receiving data on the route of movement of at least one CIT; determining at least one target point on the terrain along the route of the CIT, in which the radio signal level is absent or below a specified threshold value; determining, using the said machine learning model, a point on the terrain for the placement of a radio signal repeater providing a radio signal coverage area covering the said target point; a flight mission is formed for an unmanned aerial vehicle (UAV) with an installed radio signal repeater, containing at least the route of the UAV and the coordinates of the repeater placement point determined using a machine learning model; the UAV is directed to the repeater placement point. 2. The method according to paragraph 1, characterized in that additionally, data on interference at radio frequencies in the coverage area is obtained. 3. The method according to paragraph 1, characterized in that the time of arrival of the ITS at the target point is calculated. 4. The method according to paragraph 3, characterized in that the flight mission additionally includes the time of arrival of the ITS at the target point. 5. The method according to paragraph 4, characterized in that the flight task is transmitted to the UAV, which ensures arrival at the location of the repeater by the time of arrival of the ITS. 6. The method according to paragraph 1, characterized in that when forming a flight mission, the proximity to the base stations installed in a given area is determined. 7. The method according to paragraph 1, characterized in that the UAV communicates wirelessly with the base station in the area where the repeater is located. 8. The method according to claim 8, characterized in that the UAV communicates via an atmospheric optical communication line. 9. The method according to claim 1, characterized in that the repeater on the UAV contains a rotating antenna. 10. A system for ensuring radio coverage along routes of cash-in-transit vehicles (CIT), comprising: a computing device configured to collect data on the area of radio signal coverage of the terrain, including at least information on installed base stations (BS), as well as building density and terrain height; to train a machine learning model based on the collected data on the area of coverage, during which the model is trained to determine points on the terrain for the placement of radio signal repeaters; receiving data on the route of movement of at least one CIT; determining at least one target point on the terrain along the route of the CIT, in which the radio signal level is absent or below a specified threshold; determining, using said machine learning model, the point on the terrain for the placement of a radio signal repeater providing a radio signal coverage area covering said target point; forming a flight mission for a UAV with an installed radio signal repeater, wherein the flight mission contains at least the route of movement of the UAV and the coordinates of the repeater placement point determined using a machine learning model; transmitting the flight mission to the UAV; A UAV capable of receiving a flight mission from a computing device and moving to a specified repeater location.