阅读说明：本技术 空中基站部署方法、装置、电子装置和存储介质 (Aerial base station deployment method, aerial base station deployment device, electronic device and storage medium ) 是由 吴端坡 严军荣 于 2021-07-29 设计创作，主要内容包括：本申请涉及一种空中基站部署方法、装置、电子装置和存储介质,其中,该方法包括：获取多个待部署区域所对应的初始部署信息,其中,初始部署信息包括每个待部署区域内分布的终端用户所对应的用户信息、以及基于用户信息确定的空中基站信息；在用户信息中写入与终端用户对应的用户移动模型,生成动态部署信息；利用预设优化算法对动态部署信息所对应的空中基站信息进行处理,得到多个空中基站所对应的服务位置,在位于服务位置处的空中基站与每个待部署区域内的终端用户的传输距离小于预设阈值的情况下,确定服务位置为空中基站所对应的部署位置。通过本申请,解决了对空中基站的部署未考虑终端用户的移动性,造成的通信网络性能差的问题。(The application relates to an aerial base station deployment method, an aerial base station deployment device, an electronic device and a storage medium, wherein the method comprises the following steps: acquiring initial deployment information corresponding to a plurality of areas to be deployed, wherein the initial deployment information comprises user information corresponding to terminal users distributed in each area to be deployed and aerial base station information determined based on the user information; writing a user movement model corresponding to the terminal user in the user information to generate dynamic deployment information; and processing the air base station information corresponding to the dynamic deployment information by using a preset optimization algorithm to obtain service positions corresponding to a plurality of air base stations, and determining the service positions as the deployment positions corresponding to the air base stations under the condition that the transmission distance between the air base station positioned at the service positions and the terminal user in each to-be-deployed area is smaller than a preset threshold value. By the method and the device, the problem of poor communication network performance caused by the fact that mobility of the terminal user is not considered in deployment of the air base station is solved.)

1. An over-the-air base station deployment method, comprising:

acquiring initial deployment information corresponding to a plurality of areas to be deployed, wherein the initial deployment information comprises user information corresponding to terminal users distributed in each area to be deployed and aerial base station information determined based on the user information;

writing a user movement model corresponding to the terminal user in the user information to generate dynamic deployment information, wherein the user movement model is generated based on a recurrent neural network and movement track information corresponding to the terminal user and is used for generating movement prediction information corresponding to the terminal user;

and processing the air base station information corresponding to the dynamic deployment information by using a preset optimization algorithm to obtain service positions corresponding to a plurality of air base stations, and determining the service positions as the deployment positions corresponding to the air base stations under the condition that the transmission distance between the air base station positioned at the service positions and the terminal user in each to-be-deployed area is smaller than a preset threshold value.

2. The over-the-air base station deployment method of claim 1, wherein after obtaining initial deployment information corresponding to a plurality of areas to be deployed, the method further comprises:

detecting movement characteristic information corresponding to the terminal user in the movement track information;

determining first movement rule information corresponding to the terminal user according to the movement characteristic information, wherein the first movement rule information is used for representing a transition rule of the terminal user;

and fusing the user information corresponding to the terminal user and the first movement rule information to generate movement prediction information, and fitting the movement prediction information to generate a user movement model corresponding to the terminal user.

3. The over-the-air base station deployment method of claim 2, wherein detecting the movement characteristic information corresponding to the terminal user in the movement trajectory information comprises:

extracting first moving track information from the moving track information, wherein the first moving track information comprises track data corresponding to a plurality of current terminal users;

detecting moving track sequence information corresponding to a plurality of current terminal users in the first moving track information, and taking the moving track sequence information as the moving characteristic information, wherein the moving track sequence information is used for representing the moving sequence of the current terminal users, and the track moving complexity corresponding to the moving track sequence information is greater than a preset threshold.

4. The over-the-air base station deployment method of claim 3, wherein determining the first mobility rule information corresponding to the end user according to the mobility feature information comprises:

detecting the moving track sequence information in the moving characteristic information;

and determining the movement sequence of the terminal user according to the movement track sequence information, wherein the first movement rule information comprises the movement sequence.

5. The over-the-air base station deployment method of claim 3, wherein detecting the movement characteristic information corresponding to the terminal user in the movement trajectory information comprises: extracting second movement track information from the movement track information, and detecting a plurality of candidate track characteristics in the second movement track information, wherein the second movement track information comprises track data corresponding to a plurality of historical terminal users;

obtaining a plurality of candidate track features corresponding to the first moving track information, and determining feature similarity of the candidate track features and the candidate track features;

and generating similarity information corresponding to the first movement track information and the second movement track information according to the feature similarity, wherein the movement feature information comprises the similarity information.

6. The over-the-air base station deployment method of claim 5, wherein determining the first mobility rule information corresponding to the end user according to the mobility feature information comprises:

determining the candidate track characteristics corresponding to each candidate track characteristic according to the similarity information;

capturing a first dependency relationship between the track data of the historical terminal user corresponding to each candidate track feature and the second movement track information, wherein the first dependency relationship is used for representing the change rule of the track data of the historical terminal user;

and taking the first dependency relationship as dependency relationship information in a moving track of the current terminal user corresponding to the candidate track feature, wherein the first moving rule information comprises the dependency relationship information.

7. The aerial base station deployment method of claim 1, wherein processing the aerial base station information corresponding to the dynamic deployment information by using a preset optimization algorithm comprises: and optimizing the air base station information corresponding to the dynamic deployment information by utilizing a gray wolf optimization algorithm.

8. The method of claim 1, wherein after determining that the service location is a deployment location corresponding to an airborne base station, the method further comprises:

acquiring an estimated load value corresponding to each aerial base station, and allocating candidate aerial base stations to the terminal user according to the estimated load value and a preset data transmission rate;

detecting a first load value of the candidate aerial base station in the current state, and judging whether a difference value between the first load value and a second load value of the candidate aerial base station in the previous state is smaller than a preset threshold value;

and under the condition that the difference value is smaller than a preset threshold value, determining the candidate aerial base station as a target aerial base station corresponding to the terminal user.

9. An airborne base station deployment apparatus, comprising:

an obtaining module, configured to obtain initial deployment information corresponding to multiple to-be-deployed areas, where the initial deployment information includes user information corresponding to terminal users distributed in each to-be-deployed area and air base station information determined based on the user information;

a generating module, configured to write a user movement model corresponding to the end user in the user information, and generate dynamic deployment information, where the user movement model is generated based on a recurrent neural network and movement trajectory information corresponding to the end user, and is used to generate movement prediction information corresponding to the end user;

and the processing module is used for processing the air base station information corresponding to the dynamic deployment information by using a preset optimization algorithm to obtain service positions corresponding to a plurality of air base stations, and determining the service positions as the deployment positions corresponding to the air base stations under the condition that the transmission distance between the air base station positioned at the service positions and the terminal user in each to-be-deployed area is smaller than a preset threshold value.

10. An electronic apparatus comprising a memory and a processor, wherein the memory has stored therein a computer program, and the processor is arranged to execute the computer program to perform the over the air base station deployment method of any of claims 1 to 8.

11. A computer readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, performs the steps of the method for over the air base station deployment of any of claims 1 to 8.

Technical Field

The present application relates to the field of wireless communications, and in particular, to an over-the-air base station deployment method, apparatus, electronic apparatus, and storage medium.

Background

In recent years, as the unmanned aerial vehicle is miniaturized, low in cost, high in mobility, easy to deploy, stop immediately after use and excellent in line-of-sight link, a Base Station function is added on the unmanned aerial vehicle, so that the unmanned aerial vehicle becomes a movable Base Station (DBS) in the air, and the unmanned aerial vehicle has great significance for improving the performance of a communication network.

Aerial location planning of aerial base stations is central to the deployment of aerial base stations. A good position planning scheme can improve the service quality of users, reduce the interference among aerial base stations, simultaneously can remove redundant base stations in the deployed base stations, reduce the operation cost and reduce the energy consumption, and the change of the position of the aerial base stations is large due to the high mobility and flexibility of the aerial base stations.

In the air base station deployment in the related art, a certain index in the optimized communication process is mainly used as a core, for example: the minimum base station deployment number, the maximum throughput and the influence of the horizontal position and the flight height of the aerial base station on the optimization target are only considered; meanwhile, in the air base station deployment process of the related technology, the model is not set without the influence of the change of the number of the service people caused by the mobility of the reference terminal user on the air base station service, so that the performance of a communication network is poor and the interference among the air base stations is large.

For the problems of poor communication network performance and large interference among aerial base stations caused by the fact that the mobility of terminal users is not considered in the deployment of the aerial base stations in the related technology, no effective solution is provided at present.

Disclosure of Invention

The embodiment provides an air base station deployment method, an air base station deployment device, an air base station deployment system, an electronic device and a storage medium, so as to solve the problems that the air base station deployment in the related art does not consider the mobility of a terminal user, so that the performance of a communication network is poor and the interference among air base stations is large.

In a first aspect, in this embodiment, a method for deploying an over-the-air base station is provided, including: acquiring initial deployment information corresponding to a plurality of areas to be deployed, wherein the initial deployment information comprises user information corresponding to terminal users distributed in each area to be deployed and aerial base station information determined based on the user information; writing a user movement model corresponding to the terminal user in the user information to generate dynamic deployment information, wherein the user movement model is generated based on a recurrent neural network and movement track information corresponding to the terminal user and is used for generating movement prediction information corresponding to the terminal user; and processing the air base station information corresponding to the dynamic deployment information by using a preset optimization algorithm to obtain service positions corresponding to a plurality of air base stations, and determining the service positions as the deployment positions corresponding to the air base stations under the condition that the transmission distance between the air base station positioned at the service positions and the terminal user in each to-be-deployed area is smaller than a preset threshold value.

In some embodiments, after obtaining initial deployment information corresponding to a plurality of areas to be deployed, the method further includes: detecting movement characteristic information corresponding to the terminal user in the movement track information; determining first movement rule information corresponding to the terminal user according to the movement characteristic information, wherein the first movement rule information is used for representing a transition rule of the terminal user; and fusing the user information corresponding to the terminal user and the first movement rule information to generate movement prediction information, and fitting the movement prediction information to generate a user movement model corresponding to the terminal user.

In some embodiments, detecting, in the movement trace information, movement feature information corresponding to the end user includes: extracting first moving track information from the moving track information, wherein the first moving track information comprises track data corresponding to a plurality of current terminal users; detecting moving track sequence information corresponding to a plurality of current terminal users in the first moving track information, and taking the moving track sequence information as the moving characteristic information, wherein the moving track sequence information is used for representing the moving sequence of the current terminal users, and the track moving complexity corresponding to the moving track sequence information is greater than a preset threshold.

In some embodiments, determining, according to the movement characteristic information, first movement rule information corresponding to the end user includes: detecting the moving track sequence information in the moving characteristic information; and determining the movement sequence of the terminal user according to the movement track sequence information, wherein the first movement rule information comprises the movement sequence.

In some embodiments, detecting, in the movement trace information, movement feature information corresponding to the end user includes: extracting second movement track information from the movement track information, and detecting a plurality of candidate track characteristics in the second movement track information, wherein the second movement track information comprises track data corresponding to a plurality of historical terminal users; obtaining a plurality of candidate track features corresponding to the first moving track information, and determining feature similarity of the candidate track features and the candidate track features; and generating similarity information corresponding to the first movement track information and the second movement track information according to the feature similarity, wherein the movement feature information comprises the similarity information.

In some embodiments, determining, according to the movement characteristic information, first movement rule information corresponding to the end user includes: determining the candidate track characteristics corresponding to each candidate track characteristic according to the similarity information; capturing a first dependency relationship between the track data of the historical terminal user corresponding to each candidate track feature and the second movement track information, wherein the first dependency relationship is used for representing the change rule of the track data of the historical terminal user; and taking the first dependency relationship as dependency relationship information in a moving track of the current terminal user corresponding to the candidate track feature, wherein the first moving rule information comprises the dependency relationship information.

In some embodiments, the processing, by using a preset optimization algorithm, the air base station information corresponding to the dynamic deployment information includes: and optimizing the air base station information corresponding to the dynamic deployment information by utilizing a gray wolf optimization algorithm.

In some embodiments, after determining that the service location is a deployment location corresponding to an over-the-air base station, the method further includes: acquiring an estimated load value corresponding to each aerial base station, and allocating candidate aerial base stations to the terminal user according to the estimated load value and a preset data transmission rate; detecting a first load value of the candidate aerial base station in the current state, and judging whether a difference value between the first load value and a second load value of the candidate aerial base station in the previous state is smaller than a preset threshold value; and under the condition that the difference value is smaller than a preset threshold value, determining the candidate aerial base station as a target aerial base station corresponding to the terminal user.

In a second aspect, in this embodiment, an over-the-air base station deployment apparatus is provided, including: an obtaining module, configured to obtain initial deployment information corresponding to multiple to-be-deployed areas, where the initial deployment information includes user information corresponding to terminal users distributed in each to-be-deployed area and air base station information determined based on the user information; a generating module, configured to write a user movement model corresponding to the end user in the user information, and generate dynamic deployment information, where the user movement model is generated based on a recurrent neural network and movement trajectory information corresponding to the end user, and is used to generate movement prediction information corresponding to the end user; and the processing module is used for processing the air base station information corresponding to the dynamic deployment information by using a preset optimization algorithm to obtain service positions corresponding to a plurality of air base stations, and determining the service positions as the deployment positions corresponding to the air base stations under the condition that the transmission distance between the air base station positioned at the service positions and the terminal user in each to-be-deployed area is smaller than a preset threshold value.

In a third aspect, in this embodiment, an electronic apparatus is provided, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the computer program, the processor implements the over-the-air base station deployment method according to the first aspect.

In a fourth aspect, in the present embodiment, there is provided a storage medium having stored thereon a computer program which, when executed by a processor, implements the over-the-air base station deployment method of the first aspect.

Compared with the related art, the aerial base station deployment method, the aerial base station deployment device, the electronic device and the storage medium provided in the embodiment acquire initial deployment information corresponding to a plurality of to-be-deployed areas, wherein the initial deployment information includes user information corresponding to terminal users distributed in each to-be-deployed area and aerial base station information determined based on the user information; writing a user movement model corresponding to the terminal user in the user information to generate dynamic deployment information, wherein the user movement model is generated based on the recurrent neural network and the movement track information corresponding to the terminal user and is used for generating movement prediction information corresponding to the terminal user; the method comprises the steps of processing air base station information corresponding to dynamic deployment information by using a preset optimization algorithm to obtain service positions corresponding to a plurality of air base stations, and determining the service positions as the deployment positions corresponding to the air base stations under the condition that the transmission distance between the air base station at the service position and a terminal user in each to-be-deployed area is smaller than a preset threshold value.

The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below to provide a more thorough understanding of the application.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:

fig. 1 is a block diagram of a hardware structure of a terminal of an over-the-air base station deployment method according to an embodiment of the present application.

Fig. 2 is a flow chart of an over-the-air base station deployment method according to an embodiment of the application.

Fig. 3 is a flow chart of an over the air base station deployment method according to a preferred embodiment of the present application.

Fig. 4 is a schematic deployment diagram corresponding to the initial deployment information of the aerial base station according to the preferred embodiment of the present application.

Fig. 5 is a flowchart of a user movement model obtained based on a recurrent neural network according to a preferred embodiment of the present application.

Fig. 6 is a schematic structural diagram of a recurrent neural network according to an embodiment of the present application.

Fig. 7 is a flowchart of optimizing air base station information corresponding to dynamic deployment information by using a grey wolf optimization algorithm according to an embodiment of the present application.

Fig. 8 is a flow chart of an over the air base station deployment method according to a preferred embodiment of the present application.

Fig. 9 is a block diagram of an aerial base station deployment apparatus according to an embodiment of the present application.

Detailed Description

For a clearer understanding of the objects, aspects and advantages of the present application, reference is made to the following description and accompanying drawings.

Unless defined otherwise, technical or scientific terms used herein shall have the same general meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The use of the terms "a" and "an" and "the" and similar referents in the context of this application do not denote a limitation of quantity, either in the singular or the plural. The terms "comprises," "comprising," "has," "having," and any variations thereof, as referred to in this application, are intended to cover non-exclusive inclusions; for example, a process, method, and system, article, or apparatus that comprises a list of steps or modules (elements) is not limited to the listed steps or modules, but may include other steps or modules (elements) not listed or inherent to such process, method, article, or apparatus. Reference throughout this application to "connected," "coupled," and the like is not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. Reference to "a plurality" in this application means two or more. "and/or" describes an association relationship of associated objects, meaning that three relationships may exist, for example, "A and/or B" may mean: a exists alone, A and B exist simultaneously, and B exists alone. In general, the character "/" indicates a relationship in which the objects associated before and after are an "or". The terms "first," "second," "third," and the like in this application are used for distinguishing between similar items and not necessarily for describing a particular sequential or chronological order.

The method embodiments provided in the present embodiment may be executed in a terminal, a computer, or a similar computing device. For example, the terminal is operated, and fig. 1 is a block diagram of a hardware structure of the terminal according to the air base station deployment method of the embodiment of the present application. As shown in fig. 1, the terminal may include one or more processors 102 (only one shown in fig. 1) and a memory 104 for storing data, wherein the processor 102 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA. The terminal may also include a transmission device 106 for communication functions and an input-output device 108. It will be understood by those of ordinary skill in the art that the structure shown in fig. 1 is merely an illustration and is not intended to limit the structure of the terminal described above. For example, the terminal may also include more or fewer components than shown in FIG. 1, or have a different configuration than shown in FIG. 1.

The memory 104 may be used for storing computer programs, for example, software programs and modules of application software, such as a computer program corresponding to the air base station deployment method in the present embodiment, and the processor 102 executes various functional applications and data processing by running the computer programs stored in the memory 104, so as to implement the above-mentioned method. The memory 104 may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory located remotely from the processor 102, which may be connected to the terminal over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The transmission device 106 is used to receive or transmit data via a network. The network described above includes a wireless network provided by a communication provider of the terminal. In one example, the transmission device 106 includes a Network adapter (NIC) that can be connected to other Network devices through a base station to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module, which is used to communicate with the internet in a wireless manner.

In this embodiment, an air base station deployment method is provided, and fig. 2 is a flowchart of the air base station deployment method according to the embodiment of the present application, and as shown in fig. 2, the flowchart includes the following steps:

step S201, acquiring initial deployment information corresponding to a plurality of areas to be deployed, where the initial deployment information includes user information corresponding to terminal users distributed in each area to be deployed and air base station information determined based on the user information.

In this embodiment, before deployment of an air base station, a corresponding deployment area range is given, and then the deployment area range is given, the given deployment area is divided into a plurality of sub-areas, that is, a plurality of areas to be deployed, and a corresponding terminal user distribution rule in each area to be deployed is obtained, so as to create initial deployment information, where the initial deployment information corresponds to one area-user model; specifically, in a region-user model, at least one air base station and a plurality of terminal users are included, and the air base station and the plurality of terminal users form a communication system with a minimum unit; in this embodiment, the corresponding deployment area range and the plurality of sub-areas are given as limited areas, and the distribution of the end users is random.

In this embodiment, due to the mobility of the air base station and the end user, the deployment of the air base station belongs to a dynamic deployment process, that is, as the end user moves, the position and the number of the end user associated with the air base station change, so that the air base station changes dynamically, and thus when the air base station performs data transmission, a Line of Sight (LOS) transmission channel, a Non-Line of Sight (NLOS) transmission channel, and a path LOSs all meet design requirements, thereby meeting requirements for improving communication service quality.

In this embodiment, the initial deployment information only considers deployment information generated according to the distribution density of the terminal users in the corresponding to-be-deployed area and the transmission channel distance between each terminal user and the air base station at the initial time of deployment of the air base station.

Step S202, writing a user movement model corresponding to the terminal user in the user information, and generating dynamic deployment information, wherein the user movement model is generated based on the recurrent neural network and the movement track information corresponding to the terminal user, and is used for generating movement prediction information corresponding to the terminal user.

In this embodiment, after the initial deployment information is acquired, dynamic deployment adjustment is started, that is, adjustment to the air base station is determined according to the information of the position movement of each end user, that is, the movement trajectory and the user movement model.

In this embodiment, the user movement model is used to represent the predicted movement track information corresponding to each end user in the next state, that is, in the next state, to which position the end user will move, so as to obtain a position change variable (for example, a position change rule) corresponding to the end user in advance, thereby obtaining an advance change amount, and determining the position to which the end user will change according to the advance change amount, thereby setting the preset advance change amount for the air base station, and adjusting the distance between the air base station and the end user in the whole network according to the estimated movement position corresponding to the end user, so as to make the distance between the end user and the air base station corresponding to the air base station shortest, thereby ensuring the transmission quality.

In this embodiment, the user movement model is used to characterize the expectation of relevant information that the end user is expected to move in the future, such as: in the next state, the future location of the corresponding end user.

In this embodiment, the user movement model is written into the user information in the initial deployment information, so that the information indicating the position in the user information corresponding to the end user includes the initial position information and the predicted future position, and the deployment of the air base station is performed in consideration of the influence of the movement of the end user, thereby ensuring that the distance between the deployed air base station and the transmission channel of the end user satisfies the limited requirement.

In this embodiment, the user movement model is obtained by training through a recurrent neural network, specifically, a neural network prediction model is generated by using a collected preset movement trajectory of an end user or a movement trajectory of a historical end user as training data, and then a current trajectory of a current end user is used as an input to obtain a predicted future position of the end user; in this embodiment, the prediction interval for the prediction of the current end user future location is set to 30 minutes.

Step S203, processing the air base station information corresponding to the dynamic deployment information by using a preset optimization algorithm to obtain service positions corresponding to a plurality of air base stations, and determining the service positions as the deployment positions corresponding to the air base stations under the condition that the transmission distance between the air base station at the service position and the terminal user in each to-be-deployed area is smaller than a preset threshold value.

In this embodiment, through a corresponding optimization algorithm, the air base station information corresponding to the dynamic deployment information is processed based on the user information of the corresponding end user in the dynamic deployment information, that is, the air base station information in the initial deployment information is optimized based on the user information (including the initial location information and the future location information) in the dynamic deployment information, where the optimization is performed with the following objectives: the distance between a terminal user in the whole communication network and the corresponding air base station is enabled to be the closest; the optimized variables are: the position coordinates and the connection relation of the air base stations, wherein the connection relation comprises the number and the distribution density of connected terminal users; the optimized limiting conditions are as follows: the coordinates of the service position corresponding to each air base station can not exceed the range of the given corresponding deployment area, and each terminal user can only be connected with one air base station and is necessary to be connected with one air base station.

Through the steps S201 to S203, acquiring initial deployment information corresponding to a plurality of areas to be deployed, where the initial deployment information includes user information corresponding to terminal users distributed in each area to be deployed and air base station information determined based on the user information; writing a user movement model corresponding to the terminal user in the user information to generate dynamic deployment information; the method comprises the steps of processing air base station information corresponding to dynamic deployment information by using a preset optimization algorithm to obtain service positions corresponding to a plurality of air base stations, and determining the service positions as the deployment positions corresponding to the air base stations under the condition that the transmission distance between the air base station at the service position and a terminal user in each to-be-deployed area is smaller than a preset threshold value.

Fig. 3 is a flowchart of an over-the-air base station deployment method according to a preferred embodiment of the present application, and as shown in fig. 3, the flowchart includes the following steps:

step S301: and giving a deployment area range, obtaining a distribution rule of terminal users, and establishing initial deployment information.

Step S302: and adding a user movement model for the terminal user in the established initial deployment information to generate dynamic deployment information, wherein the user movement model of each terminal user is obtained through a recurrent neural network.

Step S303: and obtaining the service position of the aerial base station by taking the minimized distance between the aerial base station and the user as a target through a wolf optimization algorithm.

In this embodiment, the air base station corresponding to the established initial deployment information follows the following communication model, fig. 4 is a deployment schematic diagram corresponding to the initial deployment information of the air base station according to the preferred embodiment of the present application, referring to fig. 4, when the air base station performs data transmission, the air base station is influenced by two transmission channels, namely Line of Sight (LOS) and Non-Line of Sight (NLOS), and the influence probabilities thereof are respectively calculated according to the following formulas:

p^nlos＝1-p^los

wherein p is^los、p^nlosRespectively representing the sight distance influence probability and the non-sight distance influence probability, a and b are environment variable influence factors which are constants, theta_ijIs the elevation angle, theta_ij＝arctan(h_d/δ_ij)，h_dIs the jth airborne base station DBS_jVertical distance to user i, δ_ijIs the horizontal distance.

The line-of-sight and non-line-of-sight path loss suffered by the air base station in the data transmission process is calculated by the following formula:

wherein the content of the first and second substances,respectively representing the path loss xi and xi of the visual distance and non-visual distance suffered by the air base station in the data transmission process^losAnd xi^nlosRepresenting path loss at reference distances, τ, for line-of-sight and non-line-of-sight, respectively^losAnd τ^nlosWhich represent path loss indices for line of sight and non-line of sight, respectively.

Therefore, the jth air base station DBS_jAverage way to end user iThe radial loss is:

end user i DBS from j air base stations_jObtained transmission rate r_ijComprises the following steps:

wherein, W_jIs DBS_jBandwidth of σ²Is noise.

In some embodiments, after obtaining initial deployment information corresponding to a plurality of areas to be deployed, the following steps are further implemented:

step 1, detecting movement characteristic information corresponding to a terminal user in the movement track information.

In this embodiment, a movement rule corresponding to the terminal user is detected in the movement track information, so as to obtain a corresponding movement characteristic, where the movement track information includes a movement track corresponding to the historical terminal user and a movement track corresponding to the current terminal user, the movement track includes position information corresponding to the movement track, a timestamp, and corresponding terminal user identification information, and the terminal user identification information is used to identify the terminal user corresponding to the corresponding movement track.

In this embodiment, the movement characteristic information includes sequence information corresponding to the movement trajectory, that is, a sequence of the movement trajectory, where the sequence information represents a complex sequence transition rule of multi-level periodicity, time dependency, and high order in the movement process of the terminal user; the corresponding rule is determined through the sequence information, and the rule can be sensed to predict the future position of the movement of the corresponding terminal user.

And 2, determining first movement rule information corresponding to the terminal user according to the movement characteristic information, wherein the first movement rule information is used for representing the transition rule of the terminal user.

In this embodiment, a movement rule of the end user in a movement trajectory generated in the past is obtained or summarized based on the movement feature information, and then, the movement of the end user in the next state, that is, the future position is predicted based on the movement rule.

And 3, fusing the user information corresponding to the terminal user and the first movement rule information to generate movement prediction information, and fitting the movement prediction information to generate a user movement model corresponding to the terminal user.

In this embodiment, the user information and the first movement rule information are fused to generate movement prediction information corresponding to the corresponding end user, after the movement prediction information is generated, the movement prediction information is converted into a corresponding user movement model through information fitting, and based on the user movement model, the future position corresponding to the corresponding end user is obtained through rapid prediction.

Detecting the movement characteristic information corresponding to the terminal user in the movement track information in the step; determining first movement rule information corresponding to the terminal user according to the movement characteristic information; the user information corresponding to the terminal user and the first movement rule information are fused to generate movement prediction information, the movement prediction information is fitted to generate a user movement model corresponding to the terminal user, and the user movement model is obtained based on the recurrent neural network.

In some embodiments, detecting the movement characteristic information corresponding to the end user in the movement track information is implemented by:

step 1, extracting first moving track information from the moving track information, wherein the first moving track information comprises track data corresponding to a plurality of current terminal users.

And 2, detecting moving track sequence information corresponding to a plurality of current terminal users in the first moving track information, and taking the moving track sequence information as moving characteristic information, wherein the moving track sequence information is used for representing the moving sequence of the current terminal users, and the track moving complexity corresponding to the moving track sequence information is greater than a preset threshold.

Extracting first movement track information from the movement track information in the step; the moving track sequence information corresponding to a plurality of current terminal users is detected in the first moving track information, the moving track sequence information is used as moving characteristic information, and the moving track sequence information in the moving track corresponding to the current terminal users is obtained, so that the moving characteristic information detection of the moving track corresponding to the current terminal users is realized.

In some embodiments, determining the first movement rule information corresponding to the end user according to the movement characteristic information is implemented by:

step 1, detecting moving track sequence information in the moving characteristic information.

And 2, determining the moving sequence of the terminal user according to the moving track sequence information, wherein the first moving rule information comprises the moving sequence.

In this embodiment, after the movement characteristic information of the movement track corresponding to the current terminal user is detected by obtaining the movement track sequence information in the movement track corresponding to the current terminal user, the detected movement track sequence information is extracted, and then the movement sequence rule of the corresponding terminal user is determined according to the movement track sequence information, so as to determine the corresponding first movement rule information.

Detecting moving track sequence information in the moving characteristic information in the step; and determining the movement sequence of the terminal user according to the movement track sequence information, wherein the first movement rule information comprises the movement sequence, so that the examination of determining the corresponding movement rule information according to the movement track sequence information in the movement track of the current terminal user is realized, and the prediction of the future position of the terminal user according to the first movement rule information is realized.

In some embodiments, detecting the movement characteristic information corresponding to the end user in the movement track information is implemented by:

step 1, respectively extracting first moving track information and second moving track information from the moving track information, and detecting a plurality of candidate track characteristics from the second moving track information, wherein the first moving track information comprises track data corresponding to a plurality of current terminal users, and the second moving track information comprises track data corresponding to a plurality of historical terminal users.

In this embodiment, feature extraction is performed on the first movement track information and the second movement track information respectively through a feature extraction layer corresponding to the recurrent neural network, where the candidate track feature extracted from the second movement track is an extracted motion rule of the corresponding end user, and based on the motion rule, a possible motion or movement direction, position, and time of the corresponding end user in the next state can be obtained.

And step 2, obtaining a plurality of candidate track features corresponding to the first moving track information, and determining feature similarity of the plurality of candidate track features and the plurality of candidate track features.

In this embodiment, the feature extraction layer extracts the first movement trajectory information to obtain a plurality of corresponding candidate movement features, performs feature similarity matching between the obtained plurality of corresponding candidate movement features and candidate trajectory features extracted from the second movement trajectory, when it is detected that the candidate movement features and the candidate movement features are similar movement features, may use a movement law corresponding to the candidate movement features as a movement law of the end user corresponding to the candidate movement features, and correspondingly predicts the future position of the end user based on the movement law.

And 3, generating similarity information corresponding to the first movement track information and the second movement track information according to the feature similarity, wherein the movement feature information comprises the similarity information.

In this embodiment, the similarity information corresponding to the first movement track information and the second movement track information is used as the movement feature information, so that the movement rule corresponding to the first movement track information is determined according to the movement rule corresponding to the second movement track information, and the future position of the current terminal user can be predicted according to the movement rule.

Respectively extracting first movement track information and second movement track information from the movement track information in the step, and detecting a plurality of candidate track characteristics in the second movement track information; obtaining a plurality of candidate track features corresponding to the first moving track information, and determining feature similarity of the plurality of candidate track features and the plurality of candidate track features; and generating similarity information corresponding to the first movement track information and the second movement track information according to the feature similarity, wherein the movement feature information comprises the similarity information, so that the movement rule corresponding to the current terminal user is determined according to the similar movement features of the historical terminal user and the current terminal user, and the detection of the movement feature information for generating the first movement rule information is realized.

In some embodiments, determining the first movement rule information corresponding to the end user according to the movement characteristic information is implemented by:

step 1, determining candidate track characteristics corresponding to each candidate track characteristic according to the similarity information.

And 2, capturing a first dependency relationship between the track data of the historical terminal user corresponding to each candidate track feature and the second movement track information, wherein the first dependency relationship is used for representing the change rule of the track data of the historical terminal user.

In this embodiment, a motion law corresponding to the trajectory data of the historical end user, that is, a change law of the trajectory data is captured, and the change law can predict the direction, time, and the like of the future trajectory.

And 3, taking the first dependency relationship as the dependency relationship information in the moving track of the current terminal user corresponding to the candidate track feature, wherein the first moving rule information comprises the dependency relationship information.

Determining candidate track characteristics corresponding to each candidate track characteristic according to the similarity information in the steps; capturing a first dependency relationship between the track data of the historical terminal user corresponding to each candidate track feature and the second movement track information; and taking the first dependency relationship as the dependency relationship information in the moving track of the current terminal user corresponding to the candidate track feature, wherein the first moving rule information comprises the dependency relationship information, so that the capturing of the dependency relationship information in the moving track corresponding to the current terminal user is realized, and the determination of the first moving rule information is realized.

Fig. 5 is a flowchart of a user movement model obtained based on a recurrent neural network according to a preferred embodiment of the present application, and referring to fig. 5, the flowchart includes the following steps:

step S501, the current movement track and the historical movement track of the terminal user are jointly input into a feature extraction layer, and the movement feature information of the terminal user is extracted, wherein the current movement track and the historical movement track comprise information such as time, place, terminal user identification and the like.

Step S502, inputting the extracted movement characteristic information into a preset recursion and history characteristic processing layer to obtain the sequence information of the movement track corresponding to the terminal user or the dependency relationship information in the movement track corresponding to the terminal user.

Step S503, inputting the user information of the terminal user and the information dependency relationship information into a preset prediction module for feature fusion, and obtaining the movement prediction information corresponding to the user information.

And step S504, fitting the movement prediction information to finally obtain a user movement model corresponding to the corresponding terminal user.

Fig. 6 is a schematic structural diagram of a recurrent neural network according to an embodiment of the present application, and referring to fig. 6, the recurrent neural network includes: the functions of each module are described as follows:

in the present embodiment, the input trajectory data includes: current end user trajectory data and historical end user trajectory data.

The characteristic extraction layer carries out modeling processing on complex moving track sequence information in the track data of the current terminal user, and the characteristic extraction layer also carries out processing on the track data of the historical terminal user and extracts a corresponding motion rule.

Before the input trajectory data enters the history attention module of the recursion and history feature processing layer, the trajectory data needs to be embedded by the multi-mode embedding module of the feature extraction layer, and the corresponding spatio-temporal features and personal features including location, time and user identification in the trajectory data are vectorized and numbered, so that the trajectory data is converted into a vector in a preset vector format, for example: one-hot vector.

The recursion and history feature processing layer comprises a history attention module and a recursion layer, wherein the history attention module is used for finding out the track similar features of the track data corresponding to the history end user and the track data corresponding to the current end user, the history attention module comprises a candidate vector generator and a history information selector, the candidate vector generator is used for extracting the data corresponding to the history end user in the track data input by the multi-mode embedding module and used as an independent candidate vector, and the history information selector is used for inquiring the track data corresponding to the history end user in the track data of the current end user and generating the similarity information of the two data to be output as a vector.

In the recurrent neural network, complex moving track sequence information in track data input by the multi-mode embedding module and corresponding dependency relationship information in the track data of the current terminal user are captured through a recurrent layer.

The prediction output layer, which is the last component to combine data transmitted from different modules to accomplish the prediction task, consists of a connection layer, several fully connected layers, and an output layer, wherein,

and the connection layer combines all the characteristics in the history attention module, the recursion layer module and the multi-mode embedding module into a new vector.

A fully connected layer for processing the feature vectors into smaller, more expressive vectors.

And an output layer for outputting the motion prediction information, wherein the output layer is composed of soft-max with negative samples, the negative samples can approximately maximize the logarithmic probability of the soft-max, and can be converged quickly, and the examples of the negative samples are generated by following a uniform distribution.

In some embodiments, processing the air base station information corresponding to the dynamic deployment information by using a preset optimization algorithm is implemented by the following steps: and optimizing the air base station information corresponding to the dynamic deployment information by using a wolf optimization algorithm.

Fig. 7 is a flowchart of optimizing processing for air base station information corresponding to dynamic deployment information by using a grey wolf optimization algorithm according to an embodiment of the present application, and referring to fig. 7, the flowchart includes the following steps:

step S701, initializing a position variable of a wolf group in a preset wolf optimization algorithm, and modeling the position coordinate of the aerial base station into an element of the wolf group.

Step S702, updating the position of the wolf group.

Step S703, calculating a fitness function according to the optimization target, and updating the local optimal solution and the global optimal solution, where the optimization target is: the distance between a terminal user in the whole communication network and the corresponding air base station is enabled to be the closest; the optimized variables are: the position coordinates and the connection relation of the air base stations, wherein the connection relation comprises the number and the distribution density of connected terminal users; the optimized limiting conditions are as follows: the coordinates of the service position corresponding to each air base station can not exceed the range of the given corresponding deployment area, and each terminal user can only be connected with one air base station and is necessary to be connected with one air base station.

Step S704, determining whether the optimal solution satisfies the constraint condition, and if not, executing step S702.

Fig. 8 is a flowchart of an aerial base station deployment method according to a preferred embodiment of the present application, and referring to fig. 8, after determining that the service location is a deployment location corresponding to an aerial base station, the following steps are further implemented:

step S801, obtaining an estimated load value corresponding to each aerial base station, and allocating candidate aerial base stations to the terminal user according to the estimated load value and a preset data transmission rate.

Step S802, detecting a first load value of the candidate aerial base station in the current state, and judging whether a difference value between the first load value and a second load value of the candidate aerial base station in the previous state is smaller than a preset threshold value.

Step S803, determining the candidate air base station as the target air base station corresponding to the terminal user when it is determined that the difference is smaller than the preset threshold.

Acquiring an estimated load value corresponding to each aerial base station in the steps, and allocating candidate aerial base stations to the terminal user according to the estimated load value and a preset data transmission rate; detecting a first load value of the candidate aerial base station in the current state, and judging whether a difference value between the first load value and a second load value of the candidate aerial base station in the previous state is smaller than a preset threshold value; and under the condition that the difference value is smaller than the preset threshold value, determining the candidate aerial base station as a target aerial base station corresponding to the terminal user, realizing the determination of the service position of the aerial base station, selecting the optimal aerial base station for each terminal user by adopting a preset re-association algorithm, and realizing the minimum optimization of the communication delay ratio.

It should be noted that, in this embodiment, the goal of optimizing by using the re-association algorithm is to minimize the total delay ratio of the entire network, and the optimization is performed according to the following formula:

wherein eta is_ijIndicating end user i and jth air base station DBS_jIf connected, η_ijIs 1, otherwise, η_ijIs 0, ρ_jRepresenting an airborne base station DBS_jThe load is calculated by referring to the following formula:

λ_iindicating the arrival rate of end user i packets, l_iIndicating the average size of the data packets, I indicates the air base station DBS_jA set of medium end users.

From the above calculation formula, it can be seen that by making ρ_jAt a minimum, minimizing the overall latency ratio of the overall network may be achieved.

In this embodiment, an air base station deployment apparatus is further provided, and the apparatus is used to implement the foregoing embodiments and preferred embodiments, and the description of the apparatus is omitted for brevity. The terms "module," "unit," "subunit," and the like as used below may implement a combination of software and/or hardware for a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.

Fig. 9 is a block diagram of an aerial base station deployment apparatus according to an embodiment of the present application, and as shown in fig. 9, the apparatus includes:

an obtaining module 91, configured to obtain initial deployment information corresponding to multiple to-be-deployed areas, where the initial deployment information includes user information corresponding to terminal users distributed in each to-be-deployed area and air base station information determined based on the user information;

a generating module 92, coupled to the obtaining module 91, configured to write a user movement model corresponding to the end user in the user information, and generate dynamic deployment information, where the user movement model is generated based on the recurrent neural network and the movement trajectory information corresponding to the end user, and is used to generate movement prediction information corresponding to the end user;

and the processing module 93 is coupled to the generating module 92, and configured to process the air base station information corresponding to the dynamic deployment information by using a preset optimization algorithm to obtain service positions corresponding to the plurality of air base stations, and determine that the service position is the deployment position corresponding to the air base station when a transmission distance between the air base station located at the service position and the terminal user in each to-be-deployed area is smaller than a preset threshold.

In some embodiments, after acquiring initial deployment information corresponding to a plurality of areas to be deployed, the apparatus is further configured to detect movement characteristic information corresponding to an end user in the movement trajectory information; determining first movement rule information corresponding to the terminal user according to the movement characteristic information, wherein the first movement rule information is used for representing a transition rule of the terminal user; and fusing the user information corresponding to the terminal user and the first movement rule information to generate movement prediction information, and fitting the movement prediction information to generate a user movement model corresponding to the terminal user.

In some embodiments, the apparatus is further configured to extract first movement trace information from the movement trace information, where the first movement trace information includes trace data corresponding to a plurality of current end users; detecting moving track sequence information corresponding to a plurality of current terminal users in the first moving track information, and taking the moving track sequence information as moving characteristic information, wherein the moving track sequence information is used for representing the moving sequence of the current terminal users, and the track moving complexity corresponding to the moving track sequence information is greater than a preset threshold value.

In some embodiments, the apparatus is further configured to detect movement trajectory sequence information in the movement feature information; and determining the moving sequence of the terminal user according to the moving track sequence information, wherein the first moving rule information comprises the moving sequence.

In some embodiments, the apparatus is further configured to extract second movement track information from the movement track information, and detect a plurality of candidate track features in the second movement track information, where the second movement track information includes track data corresponding to a plurality of historical end users; obtaining a plurality of candidate track features corresponding to the first moving track information, and determining feature similarity of the plurality of candidate track features and the plurality of candidate track features; and generating similarity information corresponding to the first movement track information and the second movement track information according to the feature similarity, wherein the movement feature information comprises the similarity information.

In some embodiments, the apparatus is further configured to determine, according to the similarity information, a candidate trajectory feature corresponding to each candidate trajectory feature; capturing a first dependency relationship between the track data of the historical terminal user and the second movement track information corresponding to each candidate track feature, wherein the first dependency relationship is used for representing the change rule of the track data of the historical terminal user; and taking the first dependency relationship as the dependency relationship information in the moving track of the current terminal user corresponding to the candidate track feature, wherein the first moving rule information comprises the dependency relationship information.

In some embodiments, the apparatus is further configured to perform optimization processing on the air base station information corresponding to the dynamic deployment information by using a grey wolf optimization algorithm.

In some embodiments, the apparatus is further configured to obtain an estimated load value corresponding to each air base station, and allocate a candidate air base station to the terminal user according to the estimated load value and a preset data transmission rate; detecting a first load value of the candidate aerial base station in the current state, and judging whether a difference value between the first load value and a second load value of the candidate aerial base station in the previous state is smaller than a preset threshold value; and under the condition that the difference value is smaller than the preset threshold value, determining the candidate air base station as a target air base station corresponding to the terminal user.

The above modules may be functional modules or program modules, and may be implemented by software or hardware. For a module implemented by hardware, the modules may be located in the same processor; or the modules can be respectively positioned in different processors in any combination.

There is also provided in this embodiment an electronic device comprising a memory having a computer program stored therein and a processor arranged to run the computer program to perform the steps of any of the above method embodiments.

Optionally, the electronic apparatus may further include a transmission device and an input/output device, wherein the transmission device is connected to the processor, and the input/output device is connected to the processor.

Optionally, in this embodiment, the processor may be configured to execute the following steps by a computer program:

and S1, acquiring initial deployment information corresponding to a plurality of areas to be deployed, wherein the initial deployment information includes user information corresponding to terminal users distributed in each area to be deployed and aerial base station information determined based on the user information.

And S2, writing a user movement model corresponding to the terminal user in the user information to generate dynamic deployment information, wherein the user movement model is generated based on the recurrent neural network and the movement track information corresponding to the terminal user and is used for generating movement prediction information corresponding to the terminal user.

And S3, processing the air base station information corresponding to the dynamic deployment information by using a preset optimization algorithm to obtain service positions corresponding to a plurality of air base stations, and determining the service positions as the deployment positions corresponding to the air base stations under the condition that the transmission distance between the air base station at the service position and the terminal user in each to-be-deployed area is smaller than a preset threshold value.

It should be noted that, for specific examples in this embodiment, reference may be made to the examples described in the foregoing embodiments and optional implementations, and details are not described again in this embodiment.

In addition, in combination with the method for deploying an over-the-air base station provided in the foregoing embodiment, a storage medium may also be provided to implement the method in this embodiment. The storage medium having stored thereon a computer program; the computer program, when executed by a processor, implements any of the above-described embodiments of an airborne base station deployment method.

It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to be limiting. All other embodiments, which can be derived by a person skilled in the art from the examples provided herein without any inventive step, shall fall within the scope of protection of the present application.

It is obvious that the drawings are only examples or embodiments of the present application, and it is obvious to those skilled in the art that the present application can be applied to other similar cases according to the drawings without creative efforts. Moreover, it should be appreciated that in the development of any such actual implementation, as in any engineering or design project, numerous implementation-specific decisions must be made to achieve the developers' specific goals, such as compliance with system-related and business-related constraints, which may vary from one implementation to another.

The term "embodiment" is used herein to mean that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is to be expressly or implicitly understood by one of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.

The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the patent protection. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.