A low-altitude economy unmanned aerial vehicle communication optimization method based on machine learning

Abstract

The present application relates to the field of unmanned aerial vehicle communication, and particularly relates to a low-altitude economic unmanned aerial vehicle communication optimization method based on machine learning, comprising: establishing an actual effective communication range through a communication attenuation gradient, obtaining a multi-layer communication projection area of an unmanned aerial vehicle under a map model information unit plane projection; covering other communication units and user units according to the effective projection area, receiving path intention information of other unmanned aerial vehicles under the communication projection area, and being a relay communication unit with the unmanned aerial vehicles in the effective communication range. The present application sets a low-altitude linkage communication mode, links the unmanned aerial vehicle groups, forms a chain connection of the unmanned aerial vehicles in a region, and expands the overall network chain to a certain width according to the intention paths of multiple different unmanned aerial vehicles on the basis of the original path planning, thereby enhancing the overall chain signal coverage and further enhancing the optimal communication distance of the unmanned aerial vehicles.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of unmanned aerial vehicle communication, in particular to a low-altitude economic unmanned aerial vehicle communication optimization method based on machine learning. BACKGROUND

[0002] Low-altitude economy is a comprehensive economic form relying on low-altitude airspace, driven by various manned and unmanned aerial vehicles, and radiating related fields to develop in an integrated manner. Among them, the application of unmanned aerial vehicles, especially unmanned aerial vehicles, is becoming an unstoppable trend.

[0003] The existing unmanned aerial vehicle algorithm generally involves optimization design under current communication. However, as a dynamic mobile device, unmanned aerial vehicles are inherently unstable in communication coverage. Whether the user's location or the unmanned aerial vehicle's location, and the way of automatic connection through the cellular network, will all challenge the communication strength of the unmanned aerial vehicle. In the face of low-altitude economic conditions, how to transmit stable signals within the low-altitude range is also a trend that unmanned aerial vehicles need to develop, especially in areas where the signal is not good enough. Too many and dense buildings will result in more corner situations. Relying solely on real-time unmanned aerial vehicle path algorithms to avoid obstacles obviously puts a heavy load on the overall system of the unmanned aerial vehicle. As the last line of defense mechanism, it is clear that a pre-positioned communication optimization method is needed to reduce the collision phenomenon in the air. SUMMARY

[0004] The technical problem to be solved by the present application is to overcome the defects of the prior art and provide a low-altitude economic unmanned aerial vehicle communication optimization method based on machine learning.

[0005] To solve the above technical problems, the present application provides the following technical solutions:

[0006] In the first aspect of the present application, a low-altitude economic unmanned aerial vehicle communication optimization method based on machine learning is provided, comprising:

[0007] An actual effective communication range is established by a communication attenuation gradient, and a multi-layer communication projection area of the unmanned aerial vehicle under the planar projection of the map model information unit is obtained;

[0008] According to the effective projection area, other communication units and user units are covered, and the path intention information of other unmanned aerial vehicles is received under the communication projection area, and the unmanned aerial vehicles in the effective communication range are mutual relay communication units;

[0009] A best signal path planning is established based on a machine learning algorithm, the signal sources in the environment are divided into fixed and variable quantities, and the signal source positioning information is continuously iterated and updated.

[0010] As a preferred technical solution of the present application, the machine learning algorithm comprises a UAV path planning algorithm and a particle swarm algorithm, wherein the particle swarm algorithm is used to calculate information of a change amount communication source, the change amount communication source comprising a UAV relay unit, a mobile communication source and an unstable signal source, and the particle swarm algorithm comprises the following steps:

[0011] A. Initialization: generating an initial communication particle swarm, assigning a random initial position and signal speed to each particle, and dynamically collecting the change degree of the signal;

[0012] B. Calculate the adaptive range of the signal source: by establishing an optimal communication range, the communication of a single particle is expanded to the default area, and the position entering the optimal communication range during movement is re-marked as the actual effective communication range;

[0013] C. Update the path intention-based information: build a link network of the change amount signal source, change the original UAV path based on the actual state of the link network, wherein the edges of the link network tend to shrink inward, and the inside of the link network tends to expand outward.

[0014] As a preferred technical solution of the present application, the fixed amount comprises a user signal source, a base station signal source and a satellite communication signal, and the UAV further comprises a map model information unit and a system communication module.

[0015] As a preferred technical solution of the present application, the map model information unit further comprises an airborne radar, wherein the map model information unit comprises buildings, geographical position heights and aerial part new objects, and the aerial part new objects are identified by the airborne radar.

[0016] The map model information unit is marked with a communication range value in different height intervals, and the reduction of the communication range value is based on the obstruction of the buildings and the aerial part new objects.

[0017] In a second aspect of the present application, a low-altitude economic UAV communication optimization system based on machine learning is provided, comprising a user terminal system, the user terminal system being linked with a system communication module of a UAV, and the user terminal system comprising:

[0018] A communication module for communicating with a single UAV and linking a plurality of UAVs with the same task;

[0019] A terminal module for connecting to a server terminal and connecting to a link network through the connection to the server terminal, the server terminal being used to access or disconnect the UAVs of the link network in the same area;

[0020] A communication optimization module for updating the actual communicable distance of the UAV.

[0021] In a third aspect of the present application, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method for optimizing the communication network topology of UAVs according to any one of claims 1 to 4, or the functions of the system according to claim 5 when the computer program is executed.

[0022] In a fourth aspect of the present application, a non-transitory computer-readable storage medium is provided, having a computer program stored thereon, wherein the computer program implements the steps of the method for optimizing the communication network topology of UAVs according to any one of claims 1 to 4, or the functions of the system according to claim 5 when executed by a processor.

[0023] Compared with the prior art, the present application has the following advantages:

[0024] 1: The present application enables the UAV group to be linked to each other by setting up a low-altitude linkage communication mode, forming a chain connection of UAVs in the region, and expanding the overall network chain to a certain extent based on the original path planning according to the intended paths of multiple different UAVs, thereby enhancing the overall chain signal coverage and further enhancing the optimal communication distance of the UAVs.

[0025] 2: The present application further designs an overall communication system based on the above method, which can generate a chain relay effect in the region according to a fixed signal source after establishing a cloud network in a single server, and based on the airborne wireless module and communication module carried by the UAV itself, the communication module can also serve as a signal relay network in the range in movement based on the signal enhancement module, and be overall controlled by the server. BRIEF DESCRIPTION OF DRAWINGS

[0026] The accompanying drawings are included to provide a further understanding of the present application, and constitute a part of the specification, illustrate the present application, and are used together with the embodiments to explain the present application, and do not constitute a limitation on the present application. In the drawings:

[0027] Fig. 1 is a schematic diagram of the UAV communication optimization process of the present application;

[0028] Fig. 2 is a schematic diagram of the UAV communication optimization system of the present application. DETAILED DESCRIPTION

[0029] The preferred embodiments of the present application will be described below with reference to the accompanying drawings, and it should be understood that the preferred embodiments described herein are only used to illustrate and explain the present application, and do not constitute a limitation on the present application.

[0030] Example 1

[0031] As Figs. 1-2As shown, the present application provides a low-altitude economic unmanned aerial vehicle communication optimization method based on machine learning, comprising:

[0032] The actual effective communication range is established by the communication attenuation gradient, and the multi-layer communication projection area of the unmanned aerial vehicle under the planar projection of the map model information unit is obtained;

[0033] According to the effective projection area, other communication units and user units are covered, and the path intention information of other unmanned aerial vehicles is received under the communication projection area, and the unmanned aerial vehicles in the effective communication range are mutual relay communication units;

[0034] The best signal path planning is established based on the machine learning algorithm, the signal sources in the environment are divided into fixed and variable amounts, and the signal source positioning information is continuously iterated and updated.

[0035] The machine learning algorithm includes an unmanned aerial vehicle path planning algorithm and a particle swarm algorithm, wherein the particle swarm algorithm is used to calculate the information received by the variable amount communication source, the variable amount communication source includes an unmanned aerial vehicle relay unit, a mobile communication source and an unstable signal source, and the particle swarm algorithm includes the following steps:

[0036] A, initialization: generating initial communication particle swarm, assigning random initial position and signal speed to each particle, and dynamically collecting the change degree of the signal;

[0037] B, calculate the adaptive range of the signal source: by establishing the best communication range, when a single particle communication expands the default area, and the position entering the best communication range is re-marked as the actual effective communication range;

[0038] v i+1 =ω*v i +c1*rand()*(pbest i -x i )+c2*rand()*(gbest i -x i )

[0039] Wherein, i=1, 2, …, n, n represents the total number of particle swarm; v i represents the current particle speed, v i+1 indicates the particle speed of the next iteration; the function rand() is used to generate a random number between 0 and 1, x i represents the current position coordinates of the particle. Learning factors c1 and c2 are usually assigned fixed values; if v i exceeds the allowed value V max , v i is set to V max; pbesti represents the best position of the particle individual, and gbesti represents the global optimal position of the entire particle group;

[0040] For the inertia factor ω, when the UAV accesses the link network based on the communication module, the data sent by other UAVs is used as the basis for calculation.

[0041] C, update the path intention based message: build a link network of change signal source, change the original UAV path by the actual state of the link network, where the edge of the link network tends to shrink inward, and the inside of the link network tends to expand outward;

[0042] The Fratar model is used to calculate the trend flight distribution matrix in different flight routes in each region in the future, as shown in the following formula:

[0043]

[0044] In the formula,

[0045] Q ij The flight distribution amount from region i to region j in the future prediction period i;

[0046] Q 0ij The current departure amount of the existing flight from region i to region j;

[0047] G j The growth multiple of the flight distribution intention amount in region j;

[0048] F i The growth multiple of the flight distribution occurrence amount in region i;

[0049] n - the total number of regional flight intervals;

[0050] Q aj The characteristic time flight distribution intention amount in region j;

[0051] Q 0aj The current flight distribution formation amount in region j;

[0052] Q pi The characteristic time flight distribution intention amount in region i;

[0053] Q 0pi The current traffic formation amount in region i;

[0054] L i The position coefficient of region i to all region j;

[0055] L j The position coefficient of region j to all region i;

[0056] According to the above prediction, when the flight distribution in the region is less, the route planning can be directly based on the signal source generated by the fixed amount to achieve the best communication optimization effect, for example, when there is only one unmanned aerial vehicle in the region, the multi-hop wireless network deployment optimization based on the particle swarm algorithm can be directly used;

[0057] Therefore, under normal circumstances, when the flight units in the region are more crowded, the flight equipment performs path planning to obtain better flight strategies to complete the optimization of communication. In order to ensure the best optimization of the route, the flight path of the target location can be directly calculated based on the above formula, and the link network is distributed to each different unmanned aerial vehicle through the target path in time sequence. When the same path is crowded, the unmanned aerial vehicle passing through the path location is preferentially ensured to have the best communication height, so that the unmanned aerial vehicle continuously forms a continuous communication line strip around it when passing through, and then other flight lines can be added around the communication line strip to form an expansion of the link network through the range signal relay generated by the communication line strip. For example, when there are unmanned aerial vehicles passing through at different heights on one side of a building, the unmanned aerial vehicle at this height is preferentially ensured to continuously pass through and form a signal relay point, and then a flight path is set on the other side of the building to allow other unmanned aerial vehicles to pass through synchronously with the unmanned aerial vehicle passing through to form a new passing line.

[0058] The fixed amount includes user signal sources, base station signal sources, and satellite communication signals, and the unmanned aerial vehicle further includes a map model information unit and a system communication module.

[0059] The map model information unit further includes an airborne radar, wherein the map model information unit includes buildings, geographical location heights, and air part new objects, and the air part new objects are identified by the airborne radar;

[0060] The map model information unit is marked with a communication range value in different height intervals, and the reduction of the communication range value is based on the obstruction of the buildings and the air part new objects.

[0061] In another embodiment, the present application provides a low-altitude economic unmanned aerial vehicle communication optimization system based on machine learning, which comprises a user terminal system, the user terminal system is linked with a system communication module of an unmanned aerial vehicle, and the user terminal system comprises:

[0062] A communication module is used for communication with a single unmanned aerial vehicle and links a plurality of unmanned aerial vehicles with the same task;

[0063] A terminal module is used for connecting to a server terminal and connecting to a link network through the connection to the server terminal, and the server terminal is used for accessing or disconnecting the unmanned aerial vehicles of the link network in the same region;

[0064] The communication optimization module is configured to update an actual communicable distance of the UAV.

[0065] In another embodiment, the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the functions of the method embodiments or other corresponding system embodiments when executing the computer program, which will not be repeated here.

[0066] In another embodiment, a non-transitory computer-readable storage medium is provided, and the computer program is stored on the medium, and the computer program is executed by the processor to implement the functions of the method embodiments or other corresponding system embodiments, which will not be repeated here.

[0067] Finally, it should be noted that: the above only for the preferred embodiments of the present application, and not for limiting the present application, although the foregoing embodiments of the present application have been described in detail, for those skilled in the art, it still can be modified to the technical scheme recorded in the foregoing embodiments, or equivalent replacement of some technical features. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A communication optimization method for low-altitude economic unmanned aerial vehicles (UAVs) based on machine learning, characterized in that, include: The actual effective communication range is established by the communication attenuation gradient, and the multi-layer communication projection area of ​​the UAV under the plane projection of the information unit of the map model is obtained. It covers other communication units and user units based on the effective projection area, and receives path intention information of other UAVs within the communication projection area, and serves as a relay communication unit with UAVs within the effective communication range. The optimal signal path planning is established based on machine learning algorithms. Signal sources in the environment are divided into fixed quantities and variable quantities, and the signal source location information is continuously updated iteratively.

2. The communication optimization method for low-altitude economic unmanned aerial vehicles based on machine learning according to claim 1, characterized in that, The machine learning algorithm includes a UAV path planning algorithm and a particle swarm optimization algorithm. The particle swarm optimization algorithm is used to calculate the information received from changing communication sources, including UAV relay units, mobile communication sources, and unstable signal sources. The particle swarm optimization algorithm includes the following steps: A. Initialization: Generate an initial communication particle swarm, assign a random initial position and signal velocity to each particle, and dynamically acquire the degree of signal change. B. Calculate the adaptive range of the signal source: By establishing the optimal communication range, the communication of a single particle extends the default area, and the position that enters the optimal communication range when moving is remarked as the actual effective communication range. C. Update path intent-based messages: Construct a link network of variable signal sources, and change the original UAV path based on the actual state of the link network. The edges of the link network tend to contract inward, while the inner side of the link network tends to expand outward.

3. The method for optimizing communication of low-altitude economic unmanned aerial vehicles based on machine learning according to claim 2, characterized in that, The fixed quantities include user signal sources, base station signal sources, and satellite communication signals. The UAV also includes a map model information unit and a system communication module.

4. The method for optimizing communication of low-altitude economic unmanned aerial vehicles based on machine learning according to claim 3, characterized in that, The map model information unit also includes airborne radar. The map model information unit includes buildings, geographical location heights, and newly added objects in the air. The newly added objects in the air are identified by airborne radar. The map model information units are marked with communication range values ​​at different height intervals. The reduction of communication range values ​​is based on the obstruction settings of buildings and newly added objects in the air.

5. A machine learning-based communication optimization system for low-altitude economic unmanned aerial vehicles (UAVs) according to claim 1, comprising a user terminal system, characterized in that, The user terminal system is linked to the system communication module of the UAV, and the user terminal system includes: A communication module for communicating with a single drone and linking multiple drones performing the same task; The terminal module is used to connect to the server terminal and connect to the network via the server terminal. The server terminal is used to connect or disconnect drones in the same area of ​​the network. The communication optimization module is used to update the actual communication range of the drone.

6. An electronic device, characterized in that, The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the UAV communication network topology optimization method as described in any one of claims 1 to 4, or the functions of the system as described in claim 5.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the UAV communication network topology optimization method as described in any one of claims 1 to 4, or the functions of the system as described in claim 5.

Images