Air base station dynamic deployment method and device based on connection service and medium

Abstract

The invention provides an air base station dynamic deployment method and device based on continuing service and a medium, and relates to the technical field of wireless communication. The air base station dynamic deployment method based on the continuation service comprises the following steps: determining the dispatching time, the service time and the deployment position of an unmanned aerial vehicle in an unmanned aerial vehicle unit; each unmanned aerial vehicle in the unmanned aerial vehicle unit is used for alternately providing air base station service for a target area so as to ensure the continuity of the base station service; sending the corresponding dispatch time, service time and deployment position to the unmanned aerial vehicle; the drone is configured to take off based on the dispatch time, hover based on the deployment location, and provide a base station service over the air based on the service time. A deployment strategy is designed for each unmanned aerial vehicle, the deployment strategy comprises dispatching time, service time and a deployment position, and continuous supply of base station services in a target area is realized by adopting alternate continuous work of a plurality of unmanned aerial vehicles in a time sequence. Compared with an existing unmanned aerial vehicle mooring scheme, due to the fact that physical constraint is avoided, maneuverability is higher.

Description

Technical Field

[0001] The present invention relates to the field of wireless communication technologies, and particularly to a method, device, and medium for dynamically deploying an aerial base station based on continuous service. Background Art

[0002] With the continuous rise of the applications of AI technologies such as large models and autonomous driving, people's dependence on communication rate and communication coverage continues to increase. As a typical aerial base station solution, an unmanned aerial vehicle (UAV) base station has gradually come into the industry's view. The UAV base station can provide a powerful supplement when ground infrastructure is difficult to meet service requirements, and is particularly suitable for special scenarios such as complex terrains, post-disaster reconstructions, and traffic surges caused by emergencies.

[0003] Due to the limitation of the current battery energy storage capacity of UAVs, the UAV base station cannot be continuously deployed for a long time. Its effective operation time is only about 70%, and the remaining 30% of the time requires battery charging or replacement. The tethered UAV solution can, to a certain extent, alleviate the impact of the battery energy storage capacity limitation on the continuous deployment of the UAV base station. However, its mobility is physically restricted, with a slow moving speed and unable to complete deployment tasks outside the restricted space. Therefore, there is an urgent need for a UAV deployment solution with strong mobility and capable of providing continuous base station services. Summary of the Invention

[0004] The present invention provides a method, device, and medium for dynamically deploying an aerial base station based on continuous service, aiming to solve the defect of poor mobility in the existing tethered UAV solution, and realizing the ability to provide continuous base station services without affecting the mobility of the UAV.

[0005] The present invention provides a method for dynamically deploying an aerial base station based on continuous service, including the following steps.

[0006] Determine the dispatch time, service time, and deployment location of the UAVs in the UAV fleet; each UAV in the UAV fleet is used to rotate and provide aerial base station services to a target area to ensure the continuity of the base station services in the target area; Send the corresponding dispatch time, service time, and deployment location to the UAVs; the UAVs are configured to take off based on the dispatch time, hover based on the deployment location, and provide base station services in the air based on the service time.

[0007] According to the method for dynamically deploying an aerial base station based on continuous service provided by the present invention, determining the deployment location of the UAVs includes: Obtain the deployment location of the previous UAV; Collect the positions of the users in the target area at the target moment to obtain user position information; the target moment is a certain moment before the end of the service of the previous UAV; Based on the user location information and the deployment location of the previous drone, determine the deployment location of the next drone with the goal of maximizing the transmission data volume of the next drone; the previous drone and the next drone are two adjacent drones in time sequence, the previous drone is the replaced drone, and the next drone is the drone that replaces the previous drone.

[0008] According to a method for dynamically deploying an aerial base station based on consecutive services provided by the present invention, the method for determining the target time includes: Determine the service end time of the previous drone according to the dispatch time and service time of the previous drone; Determine the flight time of the next drone according to the deployment location fluctuation range; Determine the target time according to the service end time of the previous drone and the flight time of the next drone.

[0009] According to a method for dynamically deploying an aerial base station based on consecutive services provided by the present invention, based on the user location information and the deployment location of the previous drone, determine the deployment location of the next drone with the goal of maximizing the transmission data volume of the next drone, including: Input the user location information and the deployment location of the previous drone into the deployment decision model to obtain the deployment location of the next drone; wherein, the deployment decision model is a reinforcement learning model, and the reward function of the reinforcement learning model is constructed based on the total transmission data volume during the drone service time.

[0010] According to a method for dynamically deploying an aerial base station based on consecutive services provided by the present invention, the training method of the deployment decision model includes: Obtain the historical location information of users in the target area during the target time period; Construct a reward function; the reward function is the total transmission data volume of the drone during the target time period, and the total transmission data volume is determined based on the historical location information; Construct the action space of the drone; the action space is expressed as , where respectively represent moving forward a set distance, moving backward a set distance, moving right a set distance, moving left a set distance, and hovering; Based on the user historical location information at the start time of the target time period, the reward function, and the action space, use the reinforcement learning algorithm based on value distribution to determine the deployment decision model.

[0011] According to a method for dynamically deploying an aerial base station based on consecutive services provided by the present invention, determining the deployment location of the drone further includes: Collect the location information of users in the target area; Based on the location information of users, with the goal that the distance between the drone and each user does not exceed a set threshold, determine the deployment location of the first drone.

[0012] According to a method for dynamically deploying an aerial base station based on continuous service provided by the present invention, determining the dispatch time of the drone includes: Obtain the deployment location of the next drone; Determine the flight time of the next drone according to the deployment location; Determine the dispatch time of the next drone according to the dispatch time of the previous drone, the service time of the previous drone, and the flight time of the next drone; the previous drone and the next drone are two adjacent drones in time sequence, the previous drone is the replaced drone, and the next drone is the drone that replaces the previous drone.

[0013] According to a method for dynamically deploying an aerial base station based on continuous service provided by the present invention, determining the service time of the drone includes: Determine the service time of the drone according to the battery energy of the drone, the flight energy consumption, the basic energy consumption, and the service energy consumption per unit time of the drone; the basic energy consumption is the energy consumption other than the flight energy consumption and the service energy consumption.

[0014] The present invention also provides a device for dynamically deploying an aerial base station based on continuous service, including the following modules: A dispatch strategy determination module, configured to determine the dispatch time, service time, and deployment location of the drones in the drone group; each drone in the drone group is used to rotate to provide aerial base station services for the target area to ensure the continuity of the base station services.

[0015] A dispatch strategy sending module, configured to send the corresponding dispatch time, service time, and deployment location to the drone; the drone is configured to take off based on the dispatch time, hover based on the deployment location, and provide base station services in the air based on the service time.

[0016] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the program, it implements the method for dynamically deploying an aerial base station based on continuous service as described in any one of the above.

[0017] The present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the method for dynamically deploying an aerial base station based on continuous service as described in any one of the above.

[0018] The present invention also provides a computer program product, including a computer program which, when executed by a processor, implements the method for dynamically deploying an aerial base station based on continuous service as described in any one of the above.

[0019] The method, device and medium for dynamically deploying an aerial base station based on continuous service provided by the present invention realize continuous supply of base station services for a target area by designing deployment strategies for each unmanned aerial vehicle (UAV), including dispatch time, service time and deployment location, and adopting the rotation and connection of multiple UAVs in time sequence. Compared with the existing tethered UAV solution, it has stronger mobility because it is not subject to physical constraints. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0021] Figure 1 It is a schematic flowchart of the method for dynamically deploying an aerial base station based on continuous service provided by an embodiment of the present invention.

[0022] Figure 2 It is a schematic structural diagram of the device for dynamically deploying an aerial base station based on continuous service provided by an embodiment of the present invention.

[0023] Figure 3 It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] To make the objectives, technical solutions and advantages of the present invention clearer, the following will clearly and completely describe the technical solutions in the present invention with reference to the accompanying drawings in the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments of the present invention belong to the scope of protection of the present invention.

[0025] The following combines Figures 1-3 to describe the method, device and medium for dynamically deploying an aerial base station based on continuous service of the present invention.

[0026] Figure 1 It is a schematic flowchart of the method for dynamically deploying an aerial base station based on continuous service provided by an embodiment of the present invention. As Figure 1 shown, the method includes the following: Step 101: Determine the dispatch time, service time, and deployment location of the drones in the drone group; each drone in the drone group is used to rotate to provide in-air base station services for the target area to ensure the continuity of the base station services.

[0027] Step 102: Send the corresponding dispatch time, service time, and deployment location to the drones; the drones are configured to take off based on the dispatch time, hover based on the deployment location, and provide base station services in the air based on the service time.

[0028] In the embodiment of the present invention, multiple drones take turns to provide in-air base station services for the target area, achieving the continuity of the base station services in the target area in the time domain. It should be noted that the target area described in the embodiment of the present invention can be covered by only one drone base station. Due to the limited battery energy storage capacity of the drone, continuous services cannot be provided in the time domain. Therefore, the method of alternating work of multiple drones is adopted to achieve continuous services for the target area. If a certain area cannot be completely covered by one drone, then through the method of area division, the area can be divided into multiple sub-areas that can be covered by a single drone (which will be introduced later), and each sub-area is the target area described in the embodiment of the present invention.

[0029] In the embodiment of the present invention, in order to achieve the continuity of the base station services in the target area in the time domain, a successive dispatch strategy is designed for each drone. Each drone corresponds to its own dispatch strategy, and the dispatch strategy includes the dispatch time, service time, and deployment location.

[0030] In some embodiments of the present invention, in order to maximize the energy efficiency of the drones, the deployment location of the drones is determined based on the maximization of the total amount of transmitted data of the drones, and at the same time, the mobility of the users in the target area is considered.

[0031] The specific method for determining the deployment location of the drones is as follows: Obtain the deployment location of the previous drone; collect the positions of the users in the target area at the target moment to obtain user position information; the target moment is a certain moment before the end of the service of the previous drone; based on the user position information and the deployment location of the previous drone, with the goal of maximizing the transmitted data volume of the next drone, determine the deployment location of the next drone.

[0032] It should be noted that the previous drone and the next drone are two drones adjacent in time sequence. The previous drone is the drone to be replaced, and the next drone is the drone that replaces the previous drone. For example, in a drone fleet with five drones A, B, C, D, and E, they are dispatched in the service order of A - B - C - D - E - A... for communication services. For drones A and B, drone A is the previous drone and drone B is the next drone. For drones B and C, drone B is the previous drone and drone C is the next drone. For drones E and A, drone E is the previous drone and drone A is the next drone.

[0033] Taking drones A and B as an example, when determining the deployment location of drone B, it is necessary to determine the deployment location of drone B with the goal of maximizing the transmission data volume of drone B based on the deployment location of drone A that is currently providing base station services and the location information of users in the target area at the target time.

[0034] Furthermore, the determination process of the transmission data volume calculation formula for drones is as follows: Considering the characteristics of the air - to - ground channel mainly being line - of - sight, the following path loss model is used: Among them, is the path loss (in dB) between the drone base station and the user , is the height of the drone base station (in meters), is the distance between the drone base station and the user (in meters), is the carrier frequency (in GHz), and the parameter .

[0035] The signal - to - noise ratio between the drone base station and the user is expressed as: Among them, is the noise power (in ), is the bandwidth (in ).

[0036] Based on Shannon's formula, the instantaneous transmission data volume of the drone base station, that is, the instantaneous capacity, is expressed as: Integrating the instantaneous transmission data volume over the service time of the drone gives the total transmission data volume of the drone over the service time.

[0037] It can be understood that the distance from the deployment position of the UAV base station to the user position is used in the above calculation process of the total transmission data volume. where the deployment position of the UAV base station is the parameter to be determined.

[0038] As mentioned above, when determining the deployment position of the UAV in the embodiments of the present invention, the mobility of users in the target area is considered. Specifically, due to the mobility of users, the user position information obtained when UAV A is dispatched is no longer applicable to UAV B. That is to say, the user position information used when determining the deployment position of UAV B cannot be used again for the user position information used when determining the deployment position of UAV A. In this regard, before dispatching UAV B, the embodiments of the present invention re-collect the user position information (that is, the user position information is collected at the target moment described in this article, and the target moment is a certain moment before the end of the previous UAV service). Based on the newly collected user position information, the deployment position of UAV B can be determined more accurately.

[0039] For the target moment in the above embodiments, in some embodiments of the present invention, a further determination method is given. Specifically, according to the dispatch time and service time of the previous UAV, the end time of the previous UAV service is determined; according to the deployment position fluctuation range, the flight time of the next UAV is determined; according to the end time of the previous UAV service and the flight time of the next UAV, the target moment is determined.

[0040] Starting from the dispatch moment of the UAV, the UAV needs to experience flight time, service time, and recovery time. The target moment in this embodiment is a certain moment before the UAV takes off. Taking UAV B as an example, before UAV B takes off, based on historical experience, we can preliminarily determine the deployment position of UAV B. Specifically, for example, according to historical experience, a change range of the UAV deployment position is determined, and the position farthest from the UAV take-off position in this change range is used as the empirical estimated position. Based on this empirical estimated position, the estimated flight time of UAV B is determined, and then the end time of UAV A's service is subtracted by the estimated flight time of UAV B, and the above target moment can be determined. Of course, some time can also be reserved to cope with some errors and emergencies. For example, after subtracting the estimated flight time of UAV B from the end time of UAV A's service, subtract another 2 minutes of reserved time.

[0041] In some embodiments of the present invention, the deployment position of the above UAV is determined by a deployment decision model based on reinforcement learning. The reward function of this deployment decision model is constructed based on the total transmission data volume during the UAV service time. Specifically, this reward function can be the total transmission data volume during the UAV service time.

[0042] Due to the mobility of the user, although the user location information collected at the target moment is relatively close to the user's location information when the UAV arrives at the deployment position, they are not the same after all. Therefore, in some embodiments of the present invention, to further improve the accuracy of the UAV deployment position, the above deployment decision-making model takes into account the change of the user location information. Specifically, the training method of the above deployment decision-making model is as follows: (1) Obtain the user historical location trajectory data within the target time period . Divide the virtual decision-making moment sequence within the target time period , corresponding to the user location information . Correspond a virtual service window to each moment, where is the theoretical service duration, is the theoretical flight duration, which can be set according to experience; (2) Construct the state space: The state space includes the user location information at the virtual decision-making moment and the virtual deployment location information of the previous UAV, expressed as ; (3) Construct the action space of the UAV: Five discrete motion options of the UAV; can be expressed as , where respectively represent moving forward a set distance, moving backward a set distance, moving right a set distance, moving left a set distance, and hovering based on the deployment position of the previous UAV. The current UAV action is randomly selected from the five action options, and based on and to obtain ; (4) Construct the reward function; The reward function is defined as the total transmission data volume of the UAV, and the total transmission data volume is the integral of the instantaneous capacity of the virtual service window, written as: where the instantaneous capacity is calculated by the Shannon formula based on the user historical location trajectory data and the current UAV virtual deployment location information ; (5) Based on the state space, the action space, and the reward function, use the algorithm of reinforcement learning based on value distribution to train the deployment decision-making model.

[0043] Specifically, first, based on the above-obtained user location information and state, reward, and action definitions, obtain multiple virtual decision-making experience tuples, in the form of , to form an experience replay pool.

[0044] Taking the QR-DQN algorithm as an example, the state is input into the model, and a description of the cumulative reward expectation distribution for each discrete action is output. For example, when the state is input, the part corresponding to the action in the output , where are the model parameters.

[0045] For each experience tuple, calculate the target value of the quantile value: where and are preset parameters, is the discount factor, is the number of quantile values, represents the part corresponding to the action and the quantile in the output after inputting the state into the model. Its meaning is the cumulative reward expectation of the model for taking the action under the state at the quantile . It should be noted that in this embodiment, different quantile values share the same target value calculation method.

[0046] For a single quantile , the quantile regression loss is defined as: where is the residual between the model prediction value and the target value, is the indicator function (taking 1 when the model prediction value is less than the target value, otherwise taking 0).

[0047] The final optimization target loss is the weighted regression loss of all quantiles: By minimizing as the target to optimize the model parameters , that is, the training process.

[0048] When using the trained model for online inference, after defining the state, action, and reward in the same way as in training, select the optimal action that maximizes the cumulative reward expectation under the state , which is expressed as: It should be noted that in this embodiment, the reward function is defined as the total amount of transmitted data during the UAV service time, that is, the cumulative integral during the service time , during training, it refers to the integral of the instantaneous capacity within the virtual service window, that is: Among them, the user location information is used in the calculation of the instantaneous capacity, and the user location information here comes from the user historical location trajectory data in this embodiment. In addition, the input data of the decision model during training includes the user location information at the virtual decision moment and the deployment location information of the previous drone.

[0049] In some embodiments of the present invention, for the first dispatched drone, the method for determining its deployment location is as follows: Collect the location information of users in the current target area. Based on the location information of the users, with the goal that the distances between the drone and each user do not differ by more than a set threshold, determine the deployment location of the first drone.

[0050] In some embodiments of the present invention, after determining the deployment location of the drone, the dispatch time of the drone can be determined, specifically as follows: Obtain the deployment location of the next drone; determine the flight time of the next drone according to the deployment location; determine the dispatch time of the next drone according to the dispatch time of the previous drone, the service time of the previous drone, and the flight time of the next drone.

[0051] Taking the dispatch time of drone B as an example, after determining the deployment location of drone B, the flight time of drone B can be determined. According to the dispatch time and service time of drone A, the service end time of drone A can be determined. Drone B only needs to fly to the deployment location before the service of drone A ends. Based on this, the dispatch time of drone B can be calculated.

[0052] For the flight time, it can be specifically determined according to the following method.

[0053] The relationship between the propulsion power and flight speed of a rotor drone is: Among them, is the power consumption of the blade section during hovering, is the power consumption of the rotor induced flow during hovering, is the tip speed of the rotor blade, is the average rotor induced speed during hovering, is the fuselage drag ratio, is the rotor solidity, is the air density, is the rotor disk area. To save energy, the drone uses the maximum range speed from the drone station to the service area , which can be solved by the following equation: Denote the deployment location of the drone as , and denote the starting position of the drone as , and the flight time Then there is: In some embodiments of the present invention, determining the service time of the drone includes: Determine the service time of the drone according to the battery energy, flight energy consumption, basic energy consumption of the drone, and the service energy consumption per unit time of the drone; the basic energy consumption is the energy consumption other than flight energy consumption and service energy consumption, such as the energy consumption of sensors.

[0054] Determine the energy consumption model of the drone base station.

[0055] Divide the total energy consumption of the drone base station into three parts: basic energy consumption, flight energy consumption, and service energy consumption: Among them, the basic energy consumption is the energy consumption continuously generated during the service process and flight process of the drone base station, such as the energy consumption of the on-board camera of the drone; the flight energy consumption is the energy consumption generated during the flight process, mainly the propulsion energy consumption; the service energy consumption is the energy consumption generated during hovering and service, including the energy consumption of hovering and service.

[0056] Substitute the above relational formula into , and obtain the suspension power when the drone base station hovers as .

[0057] The energy consumption model of the drone base station is as follows: Among them, the first term represents the basic energy consumption, and respectively represent the basic power during flight and service, such as the energy consumption required by some sensors, and respectively represent the flight time and service time of the drone; the second term is the energy consumption of propulsion during the flight process, represents the propulsion power. The third term represents the energy consumption during the service process, and the suspension energy consumption is represented by , and the energy consumption brought by the service requirements of all associated users is represented by .

[0058] Based on the above derivation, substitution, and arrangement, the calculation formula for the upper limit of the theoretical service time can be obtained: Among them, Indicates the battery energy of the drone, Indicates The sum of And Indicates The sum of And

[0059] It should be noted that Is the service energy consumption of the user at the corresponding time based on historical data statistics i Of

[0060] In some embodiments of the present invention, if the demand area cannot be covered by only one drone base station, then the demand area needs to be divided so that each sub-area obtained after division can be covered by only one drone base station. Specifically, users in the demand area can be clustered based on location information. At the same time, with the condition that each cluster can be covered by only one drone base station as a constraint, users in the demand area are classified, and the area where each class of users is located is the divided sub-area, that is, the target area described in the embodiments of the present invention.

[0061] It should be noted that the coverage described in the embodiments of the present invention means that the signal strength from the drone base station to the user i Or from the user i To the drone base station is not lower than a preset value, that is, this user i Can be covered by the drone base station.

[0062] Next, the airborne base station dynamic deployment device provided by the present invention based on continuous service will be described. The airborne base station dynamic deployment device described below can be mutually referred to corresponding to the airborne base station dynamic deployment method described above.

[0063] As Figure 2 Shown, the airborne base station dynamic deployment device based on continuous service includes: Dispatch strategy determination module 201, configured to determine the dispatch time, service time, and deployment location of the drones in the drone group; each drone in the drone group is used to rotate to provide airborne base station services to the target area to ensure the continuity of the base station services.

[0064] Dispatch strategy sending module 202, configured to send the corresponding dispatch time, service time, and deployment location to the drones; the drones are configured to take off based on the dispatch time, hover based on the deployment location, and provide base station services in the air based on the service time.

[0065] For how each module in the above device specifically works, it can be mutually referred to the content of the embodiments of the airborne base station dynamic deployment method described above, and will not be elaborated here.

[0066] Figure 3 illustrates a schematic diagram of the physical structure of an electronic device, as Figure 3 shown, the electronic device may include: a processor 310, a communication interface 320, a memory 330, and a communication bus 340. Among them, the processor 310, the communication interface 320, and the memory 330 complete communication with each other through the communication bus 340. The processor 310 can call the logical instructions in the memory 330 to execute the method for dynamically deploying an air base based on continuous service. The method includes: determining the dispatch time, service time, and deployment location of the unmanned aerial vehicles (UAVs) in the UAV fleet; each UAV in the UAV fleet is used to rotate to provide air base services for the target area to ensure the continuity of the base services; sending the corresponding dispatch time, service time, and deployment location to the UAVs; the UAVs are configured to take off based on the dispatch time, hover based on the deployment location, and provide base services in the air based on the service time. As for more specific methods, reference may be made to the method for dynamically deploying an air base based on continuous service described above, which will not be elaborated here.

[0067] In addition, when the logical instructions in the above-mentioned memory 330 can be implemented in the form of software functional units and sold or used as an independent product, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. And the foregoing storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs and other various media that can store program codes.

[0068] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the method for dynamically deploying an aerial base station based on continuous service provided by each of the above methods. The method includes: determining the dispatch time, service time, and deployment location of the unmanned aerial vehicles (UAVs) in the UAV fleet; each UAV in the UAV fleet is used to rotate to provide aerial base station services to a target area to ensure the continuity of the base station services; sending the corresponding dispatch time, service time, and deployment location to the UAVs; the UAVs are configured to take off based on the dispatch time, hover based on the deployment location, and provide base station services in the air based on the service time. As for more specific methods, reference can be made to the method for dynamically deploying an aerial base station based on continuous service described above, which will not be elaborated here.

[0069] In yet another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it is implemented to execute the method for dynamically deploying an aerial base station based on continuous service provided by each of the above methods. The method includes: determining the dispatch time, service time, and deployment location of the UAVs in the UAV fleet; each UAV in the UAV fleet is used to rotate to provide aerial base station services to a target area to ensure the continuity of the base station services; sending the corresponding dispatch time, service time, and deployment location to the UAVs; the UAVs are configured to take off based on the dispatch time, hover based on the deployment location, and provide base station services in the air based on the service time. As for more specific methods, reference can be made to the method for dynamically deploying an aerial base station based on continuous service described above, which will not be elaborated here.

[0070] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0071] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solution, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0072] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A dynamic deployment method for an aerial base station based on consecutive services, characterized in that Including: Determine the dispatch time, service time, and deployment location of the unmanned aerial vehicles (UAVs) within the UAV group; each UAV within the UAV group is used to rotate to provide aerial base station services for the target area to ensure the continuity of the base station services in the target area; Send the corresponding dispatch time, service time, and deployment location to the UAV; the UAV is configured to take off based on the dispatch time, hover based on the deployment location, and provide base station services in the air based on the service time.

2. The method for dynamically deploying an air base station based on consecutive services according to claim 1, wherein Determine the deployment location of the UAV, including: Obtain the deployment location of the previous UAV; Collect the positions of the users in the target area at the target moment to obtain user position information; the target moment is a certain moment before the end of the service of the previous UAV; Based on the user position information and the deployment location of the previous UAV, with the goal of maximizing the transmission data volume of the next UAV, determine the deployment location of the next UAV; the previous UAV and the next UAV are two adjacent UAVs in time sequence, the previous UAV is the UAV to be replaced, and the next UAV is the UAV that replaces the previous UAV.

3. The method for dynamically deploying an air base station based on continuous service according to claim 2, wherein The method for determining the target moment includes: According to the dispatch time and service time of the previous UAV, determine the end time of the service of the previous UAV; Determine the flight time of the next UAV according to the deployment position fluctuation range; According to the end time of the service of the previous UAV and the flight time of the next UAV, determine the target moment.

4. The method for dynamically deploying an airborne base station based on continuous service according to claim 2, wherein Based on the user position information and the deployment location of the previous UAV, with the goal of maximizing the transmission data volume of the next UAV, determine the deployment location of the next UAV, including: Input the user position information and the deployment location of the previous UAV into the deployment decision model to obtain the deployment location of the next UAV; wherein, the deployment decision model is a reinforcement learning model, and the reward function of the reinforcement learning model is constructed based on the total transmission data volume during the UAV service time.

5. The method for dynamically deploying an air base station based on continuous service according to claim 4, wherein The training method of the deployment decision model includes: Obtain the historical position information of the users in the target area; Construct a reward function; the reward function is the total transmission data volume of the UAV during the service time, and the total transmission data volume is determined based on the historical position information; Construct the action space of the drone; the action space is represented as , where respectively represent moving forward a set distance based on the deployment position of the previous drone, moving backward a set distance, moving right a set distance, moving left a set distance, and hovering; Based on the deployment location of the previous UAV, the action space, the user historical position information, and the reward function, use the reinforcement learning algorithm based on value distribution to determine the deployment decision model.

6. The method for dynamically deploying an air base station based on continuous service according to claim 1, wherein Determine the deployment location of the UAV, further including: Collect the position information of the users in the target area; Based on the position information of the users, with the goal that the distances between the UAV and each user do not exceed a set threshold, determine the deployment location of the first UAV.

7. The method for dynamically deploying an aerial base station based on continuous service according to claim 1, wherein Determine the dispatch time of the UAV, including: Obtain the deployment location of the next UAV; Determine the flight time of the next UAV according to the deployment location; Determine the dispatch time of the next unmanned aerial vehicle (UAV) according to the dispatch time of the previous UAV, the service time of the previous UAV, and the flight time of the next UAV; the previous UAV and the next UAV are two adjacent UAVs in time sequence, the previous UAV is the UAV to be replaced, and the next UAV is the UAV to replace the previous UAV.

8. The method for dynamically deploying an air base station based on continuous service according to claim 1, wherein Determining the service time of the UAV includes: Determine the service time of the UAV according to the battery energy of the UAV, the flight energy consumption, the basic energy consumption, and the service energy consumption per unit time of the UAV.

9. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and running on the processor, characterized in that, When the processor executes the program, it implements the method for dynamic deployment of an air base based on consecutive services as described in any one of claims 1 to 8.

10. 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 method for dynamic deployment of an air base based on consecutive services as described in any one of claims 1 to 8.

Images