Deployment method, device and electronic equipment for air expansion base station

Abstract

The present invention provides a method, device and electronic device for deploying an aerial capacity expansion base station, the method comprising: determining the location information of each user terminal in the area to be deployed; inputting the location information of each user terminal into a hot spot area determination model to obtain at least one hot spot area location output by the hot spot area determination model; and deploying at least one aerial capacity expansion base station at the center of each hot spot area location. The method for deploying an aerial capacity expansion base station of the present invention can obtain the hot spot area location where user terminals are concentrated by analyzing the location information of user terminals in the area to be covered, and deploy the aerial capacity expansion base station according to the obtained hot spot area location, so as to expand communication coverage for the hot spot area, increase network capacity, and improve the stability of network performance.

Description

Technical Field

[0001] The present invention relates to the field of communication technologies, and in particular, to a method, apparatus, and electronic device for deploying an air-expanded base station. Background Art

[0002] Emergency communication refers to the communication means and methods that comprehensively utilize various communication resources to ensure rescue, emergency assistance, and necessary communication when natural or man-made sudden emergencies occur, including when the communication demand surges during important holidays. With the development of mobile communication devices and the complex changes in emergencies, the information and instructions transmitted in 5G and 6G networks are no longer limited to voice services, but also need to provide stable, secure, and instant video transmission services.

[0003] With the emergence of a new generation of unmanned aerial vehicles (UAVs), UAVs are equipped with more advanced avionics equipment, guidance, and autopilot systems. There are more and more uses for UAVs, such as establishing a dynamic and scalable communication network for disaster relief. Currently, related research on air base stations has received extensive attention. Compared with high-altitude platforms (HAPs), low-altitude platforms (LAPs) are easier to deploy and are consistent with the application concept of cellular networks.

[0004] Under the severe impact of natural disasters or special events, ground communication infrastructure may be severely damaged. After deploying an air base station, communication coverage of the covered area can be achieved. However, in some areas, users are prone to gather, the regional traffic volume surges, and network resources are limited. How to deploy an expanded base station on a low-altitude platform to enhance network capacity is an urgent problem to be solved. Summary of the Invention

[0005] The present invention provides a method, apparatus, and electronic device for deploying an air-expanded base station to solve the defect in the prior art that hotspot area expansion is not achieved in emergency scenarios, and realizes...

[0006] The present invention provides a method, apparatus, and electronic device for deploying an air-expanded base station, including:

[0007] Determine the location information of each user terminal in the area to be deployed;

[0008] Input the location information of each user terminal into a hotspot area determination model to obtain at least one hotspot area location output by the hotspot area determination model; the hotspot area location is the location where the user terminals gather;

[0009] Deploy at least one air-expanded base station at the center of each hotspot area location.

[0010] According to a deployment method of an air-expanded base station provided by the present invention, the hotspot area determination model is established based on a mixture Gaussian model, and the hotspot area determination model is established in the following manner:

[0011] Based on the location information of each user terminal, initialize the parameters of the hotspot area determination model;

[0012] Based on the initialized parameters, use the maximum likelihood algorithm to iteratively process the hotspot area determination model until convergence;

[0013] Determine the final parameters of the hotspot area determination model with the converged parameters, and establish the hotspot area determination model.

[0014] According to a deployment method of an air-expanded base station provided by the present invention, the step of initializing the parameters of the hotspot area determination model based on the location information of each user terminal includes:

[0015] Based on the location information of each user terminal, globally search to determine each newly added mixture Gaussian component;

[0016] Determine the log-likelihood function of the mixture Gaussian model including each newly added mixture Gaussian component;

[0017] When the log-likelihood function value is the largest, based on the parameters of the newly added mixture Gaussian component corresponding to the mixture Gaussian model, determine the initialization parameters of the hotspot area determination model.

[0018] According to a deployment method of an air-expanded base station provided by the present invention, the step of using the maximum likelihood algorithm to iteratively process the hotspot area determination model until convergence based on the initialized parameters includes:

[0019] Based on the location information of each user terminal, determine the gradient of each user terminal;

[0020] Based on the gradient of each user terminal and the initialized parameters, determine the target probability that each user terminal belongs to each target Gaussian component;

[0021] Based on the target probability, use the maximum likelihood algorithm to determine the maximum a posteriori probability that each user terminal belongs to each target cluster until convergence during the iteration process, and obtain the converged parameters.

[0022] According to a deployment method of an air-expanded base station provided by the present invention, before determining the location information of each user terminal in the area to be deployed, the method includes:

[0023] Based on the first quantity and coverage area of the first aerial base stations, the deployment positions of the first aerial base stations in the area to be deployed are determined by maximizing the coverage of the area to be deployed with the first aerial base stations of the first quantity;

[0024] Based on the deployment positions and coverage ranges of the first aerial base stations, the second quantity and deployment positions of the second aerial base stations in the area to be deployed are determined, so that the first aerial base stations and the second aerial base stations provide full coverage for the area to be deployed;

[0025] Deploy the first aerial base stations based on the deployment positions of the first aerial base stations; deploy the second aerial base stations based on the deployment positions of the second aerial base stations;

[0026] Obtain the location information of the user terminals through the deployed first aerial base stations and second aerial base stations.

[0027] According to a deployment method of an aerial capacity expansion base station provided by the present invention, the aerial capacity expansion base station communicates with the user terminal through a millimeter wave band.

[0028] The present invention also provides a deployment device for an aerial capacity expansion base station, including:

[0029] A first processing module, configured to determine the location information of each user terminal in the area to be deployed;

[0030] A second processing module, configured to input the location information of each user terminal into a hot spot area determination model, and obtain at least one hot spot area location output by the hot spot area determination model; the hot spot area location is the location where the user terminals gather;

[0031] A third processing module, configured to deploy at least one aerial capacity expansion base station at the center of each hot spot area location.

[0032] 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, where when the processor executes the program, the deployment method of the aerial capacity expansion base station as described in any one of the above is implemented.

[0033] 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, the deployment method of the aerial capacity expansion base station as described in any one of the above is implemented.

[0034] The present invention also provides a computer program product, including a computer program, and when the computer program is executed by a processor, the deployment method of the aerial capacity expansion base station as described in any one of the above is implemented.

[0035] The deployment method, device, and electronic device of the air-expanded base station provided by the present invention can analyze the location information of user terminals in the area to be covered, obtain the location of the hot spot area where user terminals gather, and deploy the air-expanded base station according to the obtained hot spot area location, so as to perform communication capacity expansion coverage for the hot spot area, increase the network capacity, and improve the stability of network performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] 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.

[0037] Figure 1 is a schematic flowchart of the deployment method of the air-expanded base station provided by the present invention;

[0038] Figure 2 is a schematic structural diagram of the deployment device of the air-expanded base station provided by the present invention;

[0039] Figure 3 is a schematic structural diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0040] 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 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 in the present invention belong to the scope of protection of the present invention.

[0041] The following combines Figures 1 - 3 to describe the deployment method, device, and electronic device of the air-expanded base station of the present invention.

[0042] The execution subject of the deployment method of the air-expanded base station in the embodiments of the present invention can be a control center. In some embodiments, it can also be a controller or a server, and the execution subject is not limited here. The following takes the control center as the execution subject to illustrate the deployment method of the air-expanded base station in the embodiments of the present invention.

[0043] It should be noted that the control center is used for the emergency deployment of the post-disaster communication system. The control center can receive the input of users and send relevant instructions to relevant facilities. Or, the control center can also automatically send relevant instructions to relevant devices according to the default policy.

[0044] Such asFigure 1 As shown in Figure 1 , the deployment method of the air-expanded base station according to the embodiment of the present invention mainly includes step 110, step 120, and step 130.

[0045] Step 110: Determine the location information of each user terminal in the area to be deployed.

[0046] It should be noted that the area to be deployed may be an area affected by a disaster, or the area to be deployed is an area that needs to restore emergency communication after a disaster.

[0047] In some embodiments, the area and shape of the area to be deployed can be obtained by surveying through satellites or drones first.

[0048] For example, a patrol drone can be used to scan the area to be deployed. The scanning method is that the drone continuously takes high-definition images of the disaster area along a fixed direction, speed, and altitude. In this case, there must be a certain overlapping area between every two taken photos to ensure that the images can be completely stitched together, and thus the complete and accurate range of the area to be deployed can be obtained.

[0049] It should be noted that the location information of the user terminal may include the positioning information of the user terminal.

[0050] A user terminal (User Terminal) can also be referred to as user equipment (User Equipment, UE), mobile station (Mobile Station, abbreviated as MS), mobile terminal (Mobile Terminal), access terminal, terminal device, user unit, user station, mobile station, mobile platform, remote station, remote terminal, mobile device, user terminal, wireless communication device, user agent, or user device, etc. This terminal can communicate with one or more core networks through a base station. The user terminal can be a cellular phone, cordless phone, Session Initiation Protocol (SIP) phone, Wireless Local Loop (WLL) station, Personal Digital Assistant (PDA), a handheld device with wireless communication function, a computer device or in-vehicle device, a wearable device, and a terminal device in the future 5G network, etc.

[0051] It should be noted that the location information of each user terminal in the area to be deployed can be determined according to the communication data between the user terminal and the existing communication facilities.

[0052] In some embodiments, the location information of the current user terminal can also be determined according to the historical location information of user terminals in the area to be deployed.

[0053] In some embodiments, the location information of the user terminals may also be determined according to the distribution of various facilities and personnel in the area to be deployed.

[0054] For example, according to the distribution of each facility in the area to be deployed and the number of personnel distributed in each facility, the distribution of user terminals in each area can be deduced, and then the location information of the user terminals can be obtained.

[0055] Of course, in some other embodiments, other methods may also be adopted to determine the location information of each user terminal in the area to be deployed, which is not limited herein.

[0056] Step 120: Input the location information of each user terminal into the hotspot area determination model to obtain at least one hotspot area location output by the hotspot area determination model.

[0057] It can be understood that due to planned activities or a sharp increase in regional business volume, the basic communication requirements of the target area can be met through existing communication technologies and communication devices. In the scenario of post-disaster communication, since there is a lack of solutions to the capacity enhancement problem after network aggregation, it is necessary to determine the hotspot area location at the location where user terminals gather. In the emergency scenario, while realizing aerial networking to meet the coverage requirements, the problem of a sharp increase in locally aggregated business volume can be solved.

[0058] It can be understood that the hotspot area location is the location where user terminals gather. The hotspot area model is used to determine the hotspot area where user terminals gather according to the location information of the user terminals, so as to facilitate the determination of the location for deploying aerial expansion base stations.

[0059] It should be noted that in outdoor areas such as crowded stations, squares, and stadiums, due to excessive population density, regional business volume hotspots caused by user aggregation will occur. These users aggregated in the hotspot area are called hotspot aggregated users. For a hotspot area, the closer to the center, the higher the degree of user aggregation.

[0060] In some embodiments, assuming that all users move in the horizontal space, from the perspective of probability statistics, the location distribution of hotspot aggregated users conforms to the law of large numbers and follows a two-dimensional Gaussian distribution. When there are multiple hotspots, the distribution of hotspot aggregated users follows a Gaussian Mixture Model (GMM). The GMM model is a linear combination of multiple Gaussian components, and each component follows a multi-dimensional Gaussian distribution. In the aggregation scenario of user terminals, the hotspot area location follows a two-dimensional Gaussian distribution, that is, the distribution of user terminals follows a two-dimensional Gaussian distribution.

[0061] Assume that the horizontal and vertical coordinates of each user location are independent of each other and both follow a Gaussian distribution with a certain covariance. Let \(X\) represent the set of user terminals, and \(x\) represent one of the user terminals. \(K\) is the number of Gaussian components, that is, the number of hotspot areas. \(\omega\) k is the weight coefficient of the \(k\)-th Gaussian component, and the mean \(\mu\) k represents the central position of the \(k\)-th hotspot identified, and \(\sum\) k then reflects the degree of user aggregation. Then the distribution of user terminals follows the GMM model, and the model expression is:

[0062]

[0063] It can be understood that the hotspot area determination model can be established based on the above Gaussian mixture model.

[0064] In some embodiments, the hotspot area determination model can be established in the following manner.

[0065] Based on the location information of each user terminal, the initialization parameters of the hotspot area determination model can be determined.

[0066] It can be understood that the Greedy Expectation Maximization (GEM) algorithm is an improved way to obtain the initialization parameters of the EM algorithm and avoid falling into local optimal solutions. The GEM model starts with one Gaussian component and gradually increases the mixture components until the termination condition is met.

[0067] In this embodiment, based on the location information of each user terminal, Gaussian components in the GMM model can be assigned to each user terminal first. The GEM model determines each newly added mixture Gaussian component through global search and determines the log-likelihood function of the mixture Gaussian model including each newly added mixture Gaussian component.

[0068] During the iteration process, if a new component is found, it can be added to the GMM model with the \(k\) components that have been found. Through global search, the parameters of the newly added mixture Gaussian component can be determined.

[0069] In this case, the log-likelihood function of this GMM model is solved.

[0070] When the value of the log-likelihood function is the largest, based on the parameters of the newly added mixture Gaussian component corresponding to the mixture Gaussian model, the newly added Gaussian component that maximizes the maximum likelihood function value is determined, and the approximate value of the parameters of this newly added Gaussian component is determined as the initialization parameters of the hotspot area determination model.

[0071] In this embodiment, the initial parameters of the model can be optimized considering the distribution positions of each user terminal, thereby improving the accuracy of the GMM model in clustering.

[0072] After determining the initialization parameters of the GMM model, based on the initialization parameters, the maximum likelihood algorithm is used to iteratively process the hotspot area determination model until convergence.

[0073] Each iteration of the GMM model includes two main steps: the E-Step and the M-Step. The E-Step is used to solve the posterior probability that each user terminal belongs to the k-th cluster in the previous iteration step, and the M-Step is used to solve the maximum likelihood function value of the model parameters in the previous iteration step and use it as the model parameters for the current iteration step. Stop the iterative process after the iterative operation reaches the convergence condition; determine the cluster to which the user terminal belongs obtained by the last execution of the M-Step as the cluster corresponding to the final hotspot area position of the user terminal.

[0074] It can be understood that an error threshold can be set as the convergence condition. The E-Step and the M-Step can be looped until convergence, that is, the clustering error between the results of the (t + 1)-th time and the t-th time is less than the threshold error threshold.

[0075] To accelerate the convergence speed and avoid boundary classification errors, in the E-Step, gradient enhancement can be performed by weighting neighborhood information. The gradient reflects the direction in which the user terminal coordinates change fastest.

[0076] For the user terminals passing along the gradient direction, the possibility of belonging to the same Gaussian component is the lowest, and these user terminals are determined as divergent user terminals. For the user terminals passing along the direction orthogonal to the gradient, they are more likely to belong to the same Gaussian component as the central user, and these user terminals are determined as convergent users.

[0077] Assume that the gradient dG=(dx,dy) of the user terminal at the clustering center, then the equation of the gradient orthogonal line is dx(x - xi)+dy(y - yi)=0. The convergent users passing through the orthogonal line can be used to construct a neighborhood information function, and the neighborhood information function can be fused into the EM algorithm to solve GMM, and gradient distribution weight information represented by the neighborhood function is added to the posterior probability function.

[0078] In other words, based on the position information of each user terminal, the gradient of each user terminal can be determined, and based on the gradient and initialization parameters of each user terminal, the target probability that each user terminal belongs to each target Gaussian component can be determined.

[0079] The target probabilities of each user terminal belonging to each target Gaussian component reflect the gradient information between each user terminal and each target Gaussian component, and a neighborhood function is constructed based on this to solve the posterior probability. That is, based on the target probabilities, the maximum likelihood algorithm is used to determine the maximum posterior probability of each user terminal belonging to each target cluster during the iterative process until convergence, and the converged parameters are obtained.

[0080] In this embodiment, during the iterative process, considering the gradient law of the distribution of each user terminal to solve the model parameters can obtain more accurate model parameters, thereby better reflecting the aggregation situation of user terminals and improving the accuracy of the model output results.

[0081] After the iteration ends, the converged parameters are determined as the final parameters of the hot spot area determination model, and the hot spot area determination model is established.

[0082] On this basis, the location information of each user terminal is input into the hot spot area determination model, and at least one hot spot area location output by the hot spot area determination model is obtained.

[0083] Step 130, deploy at least one aerial expansion base station at the center of each hot spot area location.

[0084] After determining the deployment location of the aerial expansion base station, a drone can be used for deployment.

[0085] Drone types can be divided into rotorcraft, fixed-wing aircraft, and airships. The payload capacity of rotorcraft ranges from a few tens of grams to seven kilograms, and they cannot carry enough communication units. Moreover, their autonomous capabilities are relatively low, and they can only operate at low altitudes for a few minutes, so they are not suitable for the post-disaster network repair scenario.

[0086] Fixed-wing aircraft have sufficient payload capacity, allowing trajectory management and positioning. Compared with rotorcraft, they generally have stronger autonomy and can work for about an hour. They can be used to carry network modules, with a fast deployment speed and easy cost control.

[0087] Airships and balloons are classified as aerostatic platforms that float in the air using buoyancy. They are very flexible in terms of payload and autonomous capabilities and can fly and stay in the air at an altitude of 200 meters to 30 kilometers above the ground for a long time.

[0088] Therefore, considering the specific situations of different communication facilities, the location of the large aerial base station basically does not change, so an airship can be used to deploy the first aerial base station. Considering the changes in hot spot locations and the flexibility of RF unit deployment, a fixed-wing aircraft can be used as a carrier to deploy the aerial expansion base station and RF remote units.

[0089] In this embodiment, by selecting a suitable vehicle for different types of network devices to deploy the network devices, the normal deployment of the network devices can be ensured, and thus the communication requirements of the target area can be met.

[0090] According to the deployment method of the aerial capacity expansion base station provided by the embodiments of the present invention, by analyzing the location information of user terminals in the area to be covered, the location of the hot spot area where user terminals gather can be obtained, and the aerial capacity expansion base station is deployed according to the obtained hot spot area location, so that communication capacity expansion coverage can be performed for the hot spot area, the network capacity is increased, and the stability of network performance is improved.

[0091] In some embodiments, the aerial capacity expansion base station communicates with user terminals through millimeter wave bands.

[0092] In other words, the aerial capacity expansion base station is a millimeter wave base station. In this case, the millimeter wave base station can provide sufficient bandwidth, low latency, and high-capacity communication support.

[0093] Millimeter waves have the advantage of large bandwidth, and bandwidth is the most important resource in communication. To achieve a higher download rate, the simplest way is to widen the bandwidth. Millimeter waves have a large bandwidth in the range from 24 GHz to 100 GHz, which is 25 times more than the bandwidth used by 3G / 4G, and can easily achieve an increase in rate.

[0094] Millimeter waves have the advantage of low latency. Millimeter wave technology supports reducing the duration of sub-frames, can transmit information in a very short time, and can quickly feedback whether the information is received or not, which can reduce communication latency.

[0095] Millimeter waves also have the advantage of high capacity. If there are hundreds of people in a square, or thousands or even tens of thousands of people in a stadium, and a large number of users download data simultaneously, the requirements for the bandwidth and download rate of wireless communication are different from those when only a single user downloads. Millimeter waves can well meet the wireless communication needs of a large number of users and provide a larger capacity.

[0096] In this case, the millimeter wave base station can provide a faster and more stable network service for hot spot locations, and thus can better meet the communication capacity expansion requirements of hot spot areas in emergency scenarios.

[0097] In some embodiments, before determining the location information of each user terminal in the area to be deployed, the deployment method of the aerial capacity expansion base station according to the embodiments of the present invention further includes: based on the first quantity and coverage area of the first aerial base stations, covering and maximizing the filling of the area to be deployed by the first quantity of first aerial base stations, and determining the deployment locations of each first aerial base station in the area to be deployed.

[0098] The first aerial base station is a public mobile communication base station for emergency use, which can be an Aerial Base Station (AeBS) in this embodiment. The first aerial base station is a radio transceiver that transmits and receives information between a mobile communication switching center and a terminal in a certain radio coverage area. The baseband part and the radio frequency part of the first aerial base station can be separated. Among them, the baseband part can be called a baseband processing unit, and the radio frequency part can be called a radio remote unit. The baseband processing unit and the radio remote unit can be connected by wired optical fiber or wireless means.

[0099] It can be understood that the first quantity of the first aerial base stations deployed can be determined first, and then the coverage area of each first aerial base station can be determined. The first aerial base stations with the first quantity are used to maximize the coverage of the area to be deployed, and then the deployment positions of the first aerial base stations in the area to be deployed can be determined.

[0100] On this basis, based on the deployment positions and coverage ranges of the first aerial base stations, the un-covered edge positions and gap positions in the area to be deployed can be determined. Then, the second quantity and deployment positions of the second aerial base stations in the area to be deployed can be determined so that the first aerial base stations and the second aerial base stations can achieve full coverage of the area to be deployed. That is, the second aerial base stations completely cover the un-covered edge positions and gap positions, thereby determining the deployment positions of the first aerial base stations and the second aerial base stations.

[0101] It can be understood that the second aerial base station in this embodiment can be an Aerial Remote Radio Head (AeRRH), and the AeRRH is used to achieve communication coverage of the edge positions and gap positions.

[0102] When multiple second aerial base stations are set, under certain conditions, the user terminal can also perform cell switching between multiple second aerial base stations.

[0103] In this embodiment, the second aerial base station is communicatively connected to the first aerial base station, and the first aerial base station and the second aerial base station are used to achieve full-domain communication coverage in the area to be deployed.

[0104] The baseband processing unit of the first aerial base station can support multiple radio remote units. In this embodiment, the baseband signal is transmitted between the second aerial base station and the baseband processing unit. The baseband processing unit can send the baseband signal to the second aerial base station. The second aerial base station can convert the baseband signal into a radio frequency signal and transmit it through the antenna. The second aerial base station can also receive the radio frequency signal through the antenna, convert the received radio frequency signal into a baseband signal and send the baseband signal to the baseband processing unit.

[0105] On this basis, deploy the first aerial base stations based on the deployment positions of the first aerial base stations, and deploy the second aerial base stations based on the deployment positions of the second aerial base stations.

[0106] In some embodiments, the first aerial base stations are deployed with airships as carriers, and the second aerial base stations are deployed with fixed-wing aircraft as carriers.

[0107] After the deployment is completed, communicate between each deployed first aerial base station and each second aerial base station and the user terminals, and determine the location information of the user terminals according to the communication data, thereby achieving the acquisition of the location information of the user terminals.

[0108] Next, the deployment device of the aerial capacity expansion base station provided by the present invention will be described. The deployment device of the aerial capacity expansion base station described below can be correspondingly referred to the deployment method of the aerial capacity expansion base station described above.

[0109] Refer to Figure 2 , the deployment device of the aerial capacity expansion base station according to the embodiment of the present invention includes a first processing module 210, a second processing module 220, and a third processing module 230.

[0110] The first processing module 210 is used to determine the location information of each user terminal in the area to be deployed;

[0111] The second processing module 220 is used to input the location information of each user terminal into the hot spot area determination model, and obtain at least one hot spot area location output by the hot spot area determination model; the hot spot area location is the location where user terminals gather;

[0112] The third processing module 230 is used to deploy at least one aerial capacity expansion base station at the center of each hot spot area location.

[0113] According to the deployment device of the aerial capacity expansion base station provided by the embodiment of the present invention, by analyzing the location information of the user terminals in the area to be covered, the hot spot area locations where the user terminals gather can be obtained, and the aerial capacity expansion base stations are deployed according to the obtained hot spot area locations, so as to be able to perform communication capacity expansion coverage for the hot spot areas, increase the network capacity, and improve the stability of the network performance.

[0114] In some embodiments, the hot spot area determination model is established based on the mixture Gaussian model, and the second processing module 220 is further used to determine the initialization parameters of the hot spot area determination model based on the location information of each user terminal; based on the initialization parameters, use the maximum likelihood algorithm to perform iterative processing on the hot spot area determination model until convergence; determine the converged parameters as the final parameters of the hot spot area determination model, and establish the hot spot area determination model.

[0115] In some embodiments, the second processing module 220 is further configured to determine each newly added Gaussian mixture component through global search based on the location information of each user terminal; determine the log-likelihood function of the Gaussian mixture model including each newly added Gaussian mixture component; and in the case where the log-likelihood function value is the largest, determine the initialization parameters of the hot spot area determination model based on the parameters of the newly added Gaussian mixture components corresponding to the Gaussian mixture model.

[0116] In some embodiments, the second processing module 220 is further configured to determine the gradient of each user terminal based on the location information of each user terminal; determine the target probability that each user terminal belongs to each target Gaussian component based on the gradient of each user terminal and the initialization parameters; and determine the maximum a posteriori probability that each user terminal belongs to each target cluster during the iterative process until convergence by using the maximum likelihood algorithm based on the target probability, so as to obtain the converged parameters.

[0117] In some embodiments, the deployment device of the air-expanded base station according to the embodiment of the present invention further includes a fourth processing module, and the fourth processing module is configured to perform a coverage maximization filling on the area to be deployed by the first air base stations with the first number based on the first number and the coverage area of the first air base stations, and determine the deployment positions of the first air base stations in the area to be deployed; determine the second number and the deployment positions of the second air base stations in the area to be deployed based on the deployment positions and the coverage ranges of the first air base stations, so that the first air base stations and the second air base stations perform full coverage on the area to be deployed; deploy the first air base stations based on the deployment positions of the first air base stations; deploy the second air base stations based on the deployment positions of the second air base stations; and obtain the location information of the user terminals through the deployed first air base stations and second air base stations.

[0118] In some embodiments, the air-expanded base station communicates with the user terminal through the millimeter wave band.

[0119] Figure 3 An example of a schematic physical structure diagram of an electronic device is shown as Figure 3 As shown, the electronic device may include: a processor 310, a communications interface 320, a memory 330, and a communication bus 340. Among them, the processor 310, the communications interface 320, and the memory 330 complete mutual communication through the communication bus 340. The processor 310 may call the logical instructions in the memory 330 to execute the deployment method of the air-expanded base station, and the method includes: determining the location information of each user terminal in the area to be deployed; inputting the location information of each user terminal into the hot spot area determination model to obtain at least one hot spot area location output by the hot spot area determination model; the hot spot area location is the location where the user terminals gather; and deploying at least one air-expanded base station at the center of each hot spot area location.

[0120] In addition, when the logical instructions in the above-mentioned memory 330 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an 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 can 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. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.

[0121] On the other hand, the present invention also provides a computer program product. The computer program product 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 deployment method of the air-expanded base station provided by the above-mentioned various methods. The method includes: determining the location information of each user terminal in the area to be deployed; inputting the location information of each user terminal into a hot spot area determination model to obtain at least one hot spot area location output by the hot spot area determination model; the hot spot area location is the location where user terminals gather; deploying at least one air-expanded base station at the center of each hot spot area location.

[0122] On 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 deployment method of the air-expanded base station provided by the above-mentioned various methods. The method includes: determining the location information of each user terminal in the area to be deployed; inputting the location information of each user terminal into a hot spot area determination model to obtain at least one hot spot area location output by the hot spot area determination model; the hot spot area location is the location where user terminals gather; deploying at least one air-expanded base station at the center of each hot spot area location.

[0123] 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 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. A person of ordinary skill in the art can understand and implement it without creative labor.

[0124] 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 essence of the above technical solution, 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 to enable 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.

[0125] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended 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 for 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 method for deploying an air capacity expansion base station, characterized in that: include: Determine the location information of each user terminal in the area to be deployed; Inputting the location information of each user terminal into a hotspot area determination model to obtain at least one hotspot area location output by the hotspot area determination model; the hotspot area location is a location where the user terminals gather; Deploy at least one aerial expansion base station at the center of each hotspot location; The hotspot area determination model is established based on a mixed Gaussian model, and the hotspot area determination model is established in the following manner: Determining initialization parameters of the hotspot area determination model based on the location information of each user terminal; Based on the initialization parameters, the hotspot area determination model is iteratively processed using a maximum likelihood algorithm until convergence; Determine the converged parameters as the final parameters of the hotspot area determination model, and establish the hotspot area determination model; The determining, based on the location information of each user terminal, initialization parameters of the hotspot area determination model includes: Based on the location information of each user terminal, each newly added mixed Gaussian component is determined through global search; Determining a log-likelihood function of a Gaussian mixture model including each newly added Gaussian mixture component; When the log-likelihood function value is maximum, the initialization parameters of the hot spot area determination model are determined based on the parameters of the newly added mixed Gaussian components corresponding to the mixed Gaussian model.

2. The method for deploying an air expansion base station according to claim 1, characterized in that: The iterative processing of the hotspot area determination model using a maximum likelihood algorithm based on the initialization parameters until convergence includes: Determining a gradient for each user terminal based on location information of each user terminal; Determining a target probability that each user terminal belongs to each target Gaussian component based on the gradient of each user terminal and the initialization parameter; Based on the target probability, a maximum likelihood algorithm is used to determine the maximum a posteriori probability that each user terminal belongs to each target cluster during the iteration process until convergence, and a converged parameter is obtained.

3. The method for deploying an air expansion base station according to claim 1, characterized in that: Before determining the location information of each user terminal in the area to be deployed, the method includes: Based on the first number and coverage area of ​​the first aerial base stations, the to-be-deployed area is filled with coverage by the first number of the first aerial base stations to maximize coverage, and a deployment position of each first aerial base station in the to-be-deployed area is determined; Based on the deployment positions and coverage ranges of the first aerial base stations, determining a second number and deployment positions of the second aerial base stations in the area to be deployed, so that the first aerial base stations and the second aerial base stations fully cover the area to be deployed; Deploy the first aerial base stations based on the deployment positions of the first aerial base stations; deploy the second aerial base stations based on the deployment positions of the second aerial base stations; The location information of the user terminal is obtained through each deployed first aerial base station and each second aerial base station.

4. The method for deploying an air capacity expansion base station according to claim 1, characterized in that: The air capacity expansion base station communicates with the user terminal via a millimeter wave band.

5. A deployment device for an aerial expansion base station, characterized in that: include: A first processing module, used to determine the location information of each user terminal in the area to be deployed; A second processing module is used to input the location information of each user terminal into a hotspot area determination model to obtain at least one hotspot area location output by the hotspot area determination model; the hotspot area location is the location where the user terminals gather; the hotspot area determination model is established based on a mixed Gaussian model; The third processing module is used to deploy at least one air capacity expansion base station at the center of each hot spot area; The second processing module is further used to determine the initialization parameters of the hotspot area determination model based on the location information of each user terminal; based on the initialization parameters, use the maximum likelihood algorithm to iteratively process the hotspot area determination model until convergence; determine the converged parameters as the final parameters of the hotspot area determination model, and establish the hotspot area determination model; The second processing module is also used to determine each newly added mixed Gaussian component through global search based on the location information of each user terminal; determine the log-likelihood function of the mixed Gaussian model including each newly added mixed Gaussian component; and when the log-likelihood function value is maximum, determine the initialization parameters of the hot spot area determination model based on the parameters of the newly added mixed Gaussian components corresponding to the mixed Gaussian model.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method for deploying the air capacity expansion base station as described in any one of claims 1 to 4 is implemented.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for deploying an air capacity expansion base station as claimed in any one of claims 1 to 4 is implemented.

8. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for deploying an air capacity expansion base station as claimed in any one of claims 1 to 4 is implemented.

Images