Base station position optimization method and device of unmanned aerial vehicle base station networking communication system

Abstract

The invention provides a base station position optimization method and device for an unmanned aerial vehicle base station networking communication system, and belongs to the technical field of communication, and the method comprises the steps: initializing the particle position and the particle speed of each particle in a particle cluster; calculating the fitness of each particle in the particle cluster according to the particle position of each particle in the particle cluster to obtain a fitness set; taking each particle in the particle cluster as a current particle to execute an updating step to obtain an updated fitness set; after the updating step is executed circularly for preset times, a target fitness set is obtained; and adjusting the position of the unmanned aerial vehicle base station cluster based on the global particle optimal position. According to the base station position optimization method for the unmanned aerial vehicle base station networking communication system provided by the invention, the technical problem that the communication effect is affected due to the fact that the optimal position of the unmanned aerial vehicle base station cannot be reasonably deployed in the base station position optimization method for the unmanned aerial vehicle base station networking communication system in the related technology is solved.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to a method and device for optimizing the base station position of an unmanned aerial vehicle base station networking communication system. Background Art

[0002] Unmanned Aerial Vehicle Base Station (UAV-BS) networking service is a new type of wireless communication network architecture that uses drones as mobile communication base stations to provide flexible, fast and efficient wireless coverage.

[0003] In the related technologies, the research on optimizing the location of UAV base stations to improve the performance of communication systems mainly focuses on the scenarios of static user locations. These studies usually assume that the user's position in space remains unchanged and are suitable for communication needs in static environments. However, the actual scenarios are more complex, and the research on static user locations is difficult to fully meet the dynamically changing communication needs in urban scenarios in the real world. In actual applications, users are usually in a complex three-dimensional space environment, and their position changes involve movement in three-dimensional space. If the location of the UAV base station is optimized by only considering the user's planar position, it cannot meet the communication needs in such dynamic scenarios and affect the communication effect.

[0004] It can be seen from this that the base station location optimization method of the drone base station networking communication system in the related technology has the technical problem of being unable to reasonably deploy the optimal location of the drone base station, which affects the communication effect. Summary of the invention

[0005] The present invention provides a base station location optimization method and device for a drone base station networking communication system, which are used to solve the technical problem that the base station location optimization method for a drone base station networking communication system in the related art cannot reasonably deploy the optimal location of the drone base station, resulting in an impact on the communication effect.

[0006] The present invention provides a base station position optimization method for a drone base station networking communication system, comprising the following steps: initializing the particle position and particle speed of each particle in a particle cluster, wherein the particle position of each particle in the particle cluster is a feasible solution for the three-dimensional spatial position adjustment amount of the drone base station cluster, and the particle speed is used to represent the change speed of the particle position; calculating the fitness of each particle in the particle cluster according to the particle position of each particle in the particle cluster to obtain a fitness set; taking each particle in the particle cluster as a current particle and performing the following updating steps to obtain an updated fitness set: selecting the particle position corresponding to the largest fitness in the fitness set as an initial global particle optimal position; determining a current inertia weight based on the particle position of the current particle and the initial global particle optimal position; updating the current particle based on the current inertia weight. The particle speed of the particle is updated to obtain an updated particle speed; the particle position of the current particle is updated based on the updated particle speed to obtain an updated particle position; the current fitness is determined based on the updated particle position; the larger value of the fitness of the current particle before updating and the current fitness is added to the updated fitness set; after looping the updating step for a preset number of times, a target fitness set is obtained, wherein the target fitness set is the individual particle maximum fitness of each particle in the particle cluster, and the individual particle maximum fitness is the maximum value of the fitness obtained by each particle in the process of looping the updating step for a preset number of times; the position of the UAV base station cluster is adjusted based on the global particle optimal position, wherein the global particle optimal position is the particle position corresponding to the maximum fitness in the target fitness set.

[0007] The present invention also provides a base station position optimization device for a drone base station networking communication system, comprising the following modules: an initialization module, used to initialize the particle position and particle speed of each particle in a particle cluster, wherein the particle position of each particle in the particle cluster is a feasible solution for the three-dimensional spatial position adjustment amount of the drone base station cluster, and the particle speed is used to represent the changing speed of the particle position; a calculation module, used to calculate the fitness of each particle in the particle cluster according to the particle position of each particle in the particle cluster to obtain a fitness set; a first execution module, used to perform the following updating steps on each particle in the particle cluster as a current particle to obtain an updated fitness set: select the particle position corresponding to the largest fitness in the fitness set as the initial global particle optimal position; determine the current inertia weight based on the particle position of the current particle and the initial global particle optimal position; and The particle speed of the current particle is updated to obtain an updated particle speed; the particle position of the current particle is updated based on the updated particle speed to obtain an updated particle position; the current fitness is determined based on the updated particle position; the larger value of the fitness of the current particle before updating and the current fitness is added to the updated fitness set; a second execution module is used to obtain a target fitness set after looping the updating step for a preset number of times, wherein the target fitness set is the individual particle maximum fitness of each particle in the particle cluster, and the individual particle maximum fitness is the maximum value of the fitness obtained by each particle in the process of looping the updating step for a preset number of times; an adjustment module is used to adjust the position of the drone base station cluster based on the global particle optimal position, wherein the global particle optimal position is the particle position corresponding to the maximum fitness in the target fitness set.

[0008] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a base station location optimization method for a drone base station networking communication system as described above is implemented.

[0009] 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, a base station location optimization method for a drone base station networking communication system as described in any of the above-mentioned methods is implemented.

[0010] The present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements a base station location optimization method for a drone base station networking communication system as described in any one of the above-mentioned methods.

[0011] The base station position optimization method and device of the drone base station networking communication system provided by the present invention initialize the particle position and particle speed of each particle in the particle cluster, wherein the particle position of each particle in the particle cluster is a feasible solution of the three-dimensional spatial position adjustment amount of the drone base station cluster, and the particle speed is used to represent the changing speed of the particle position; the fitness of each particle in the particle cluster is calculated according to the particle position of each particle in the particle cluster to obtain a fitness set; each particle in the particle cluster is used as the current particle to perform the following updating steps to obtain an updated fitness set: select the particle position corresponding to the largest fitness in the fitness set as the initial global particle optimal position; determine the current inertia weight based on the particle position of the current particle and the initial global particle optimal position; update the particle speed of the current particle based on the current inertia weight to obtain an updated particle speed; update the particle position of the current particle based on the updated particle speed to obtain an updated particle position; determine the current fitness based on the updated particle position; and add the fitness of the current particle before the update and The larger value in the current fitness is added to the updated fitness set; after the update step is executed cyclically for a preset number of times, a target fitness set is obtained, wherein the target fitness set is the individual particle maximum fitness of each particle in the particle cluster, and the individual particle maximum fitness is the maximum value of the fitness obtained by each particle in the process of cyclically executing the update step for a preset number of times; the position of the drone base station cluster is adjusted based on the global particle optimal position, wherein the global particle optimal position is the particle position corresponding to the largest fitness in the target fitness set; the three-dimensional spatial adjustment amount of the drone base station cluster is used as the position of the particle, and the position change is controlled by continuously iteratively adjusting the speed of the particle to optimize the three-dimensional spatial adjustment amount of the drone base station cluster. In each iteration, the position, speed and fitness of the particle are updated. After the iteration is completed, the position of the drone base station cluster is adjusted according to the global particle optimal position, thereby solving the technical problem that the base station position optimization method of the drone base station networking communication system in the related technology cannot reasonably deploy the optimal position of the drone base station, resulting in an impact on the communication effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced one by one below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0013] Figure 1 It is one of the flow charts of the base station location optimization method of the UAV base station networking communication system provided by the present invention.

[0014] Figure 2It is a schematic diagram of the application environment of the base station location optimization method of the UAV base station networking communication system provided by the present invention.

[0015] Figure 3 This is the second flow chart of the base station location optimization method of the UAV base station networking communication system provided by the present invention.

[0016] Figure 4 This is the third flow chart of the base station location optimization method of the UAV base station networking communication system provided by the present invention.

[0017] Figure 5 It is a training schematic diagram of the base station location optimization method of the UAV base station networking communication system provided by the present invention.

[0018] Figure 6 It is a structural schematic diagram of a base station location optimization device of a UAV base station networking communication system provided by the present invention.

[0019] Figure 7 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] It should be noted that in the description of the present invention, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "include one..." do not exclude the existence of other identical elements in the process, method, article or device including the elements. The orientation or position relationship indicated by the terms "upper", "lower" and the like is based on the orientation or position relationship shown in the drawings, which is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present invention. Unless otherwise clearly specified and limited, the terms "installed", "connected" and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be a connection between the two elements. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0022] The terms "first", "second", etc. in the present invention are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present invention can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally of the same type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" means at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0023] In recent years, with the continuous changes in the global environment and the frequent occurrence of natural disasters, people's demand for emergency communications and communication networks with wider coverage has become particularly urgent. Although traditional ground base stations can provide stable communication services in normal times, they are often damaged or even paralyzed by natural disasters such as earthquakes, storms, and floods when disasters occur, resulting in communication interruption or obstruction. In this case, people urgently need a more reliable and flexible communication solution to ensure information transmission and rescue operations in emergency situations.

[0024] Compared with ground base stations, drones as aerial base stations have the characteristics of strong mobility, rapid deployment and strong channel robustness. These characteristics enable drones to be quickly deployed to target areas at relatively low costs under special environments, provide all-round communication coverage and reliable connections, and establish real-time communications. In particular, the development of the fifth-generation mobile communication technology has provided large bandwidth, low latency and high-density connections for drone base station communications. Drone base stations have become one of the feasible solutions for emergency communications in emergency situations.

[0025] Currently, drones have been widely used as aerial base stations to assist communications. They are used in various scenarios, such as providing temporary communication coverage for emergency response, enhancing communication capabilities in remote areas, and supporting large public events where ground infrastructure may be insufficient. The use of drones as aerial base stations not only expands the coverage of communication networks, but also can be quickly deployed and relocated according to dynamic communication needs. This innovative approach is of great significance in responding to the ever-changing needs of modern communication systems.

[0026] When using drone base stations to build wireless networks, an important issue that needs to be faced is the optimization of drone deployment locations, that is, how to optimize the three-dimensional spatial location of drones to serve user communications and meet optimization goals such as maximizing coverage, energy saving and sustainability. From the current research on drone base station deployment, the existing application scenarios are mainly divided into two categories: one is to use the ground communication network, and drones carry communication equipment as aerial users to perform specific tasks; the other is that drones act as aerial base stations or relays to provide services for ground communication equipment. At present, the relevant research on drones in the second type of application scenarios is mainly aimed at energy consumption, latency, user service quality, etc., and has broad development prospects.

[0027] In current research, common drone deployment schemes include clustering algorithms and heuristic algorithms. The core idea of ​​these schemes is to divide user devices or areas into different clusters or clusters, and regard the center of each cluster as the horizontal position of the drone. Subsequently, the vertical deployment of the drone is determined by a height formula or an iterative search method to complete the three-dimensional spatial deployment of the drone base station. Usually, these algorithms can obtain local optimal solutions, but there is still a large optimization space, so further research and optimization are still needed.

[0028] In the emergency rescue scenario of urban blocks, the research on the dynamic deployment of three-dimensional positions of drone base stations is of great significance, and is expected to fill the gaps in existing research and solve the challenges faced by current technologies. First, current research mainly focuses on the scenario of static user positions, and is committed to optimizing the positions of drone base stations to improve the performance of communication systems to ensure the communication needs of users in the coverage area. These studies usually assume that the user's position in space remains unchanged and are suitable for communication needs in static environments. However, the actual scenarios are much more complicated, and the research on static user positions is difficult to fully meet the dynamically changing communication needs in real-world urban scenarios.

[0029] Secondly, in the research under dynamic scenarios, it is usually assumed that the drone and the user move in one direction within a specific area or that the user moves only on the horizontal plane. Most existing studies focus on optimizing the location of the drone base station to improve the performance of the communication system, usually only considering the signal attenuation in free space, and not fully considering the potential impact of other environmental factors. However, at disaster sites or temporary events, people are usually in a complex three-dimensional space environment, and their position changes involve movement in three-dimensional space. It is obviously not enough to only consider the user's planar position, and it is impossible to meet the communication needs in such dynamic scenarios and achieve good communication effects.

[0030] Finally, in practical applications, tall buildings in urban environments are not just static physical obstacles, they also have a profound impact on the communication performance of drone base stations. Tall buildings may cause complex reflections and multipath effects of signals, which in turn cause signal attenuation and multipath interference. These phenomena not only reduce the coverage of the signal, but may also cause signal instability and fluctuations in communication quality. If only free space loss is considered, it will greatly affect the communication service of the drone base station to users, thereby affecting the overall communication effect.

[0031] In order to at least solve some of the above problems, the following Figure 1-Figure 7 The present invention describes a method and device for optimizing the base station location of a UAV base station networking communication system.

[0032] The base station location optimization method of the drone base station networking communication system provided in this embodiment can be applied to the scenario where the location of the human-machine base station cluster is optimized to improve the communication effect. The base station location optimization method of the drone base station networking communication system in this embodiment can be executed by a server, and the server is connected to the drone base station cluster in communication.

[0033] Figure 1 FIG. 1 is one of the flow charts of the base station location optimization method of the UAV base station networking communication system provided by the present invention, such as Figure 1 As shown, including but not limited to the following steps: Step 101, initialize the particle position and particle velocity of each particle in the particle cluster, wherein the particle position of each particle in the particle cluster is a feasible solution for the three-dimensional spatial position adjustment amount of the drone base station cluster, and the particle velocity is used to represent the changing speed of the particle position.

[0034] Figure 2 This is a schematic diagram of the application environment of the base station location optimization method of the drone base station networking communication system provided by the present invention, see Figure 2 The base station location optimization method of the drone base station networking communication system in this embodiment can be applied to the scenario where multiple drone base stations (UAV-BS) are networked to serve users in a mixed indoor and outdoor environment. The scene area is a rectangular space area, and its size is recorded as There is a multi-story building in the scene, and its length and width are recorded as , the number of layers is recorded as The number of users in the scenario is recorded as , the user set is , the number of UAV-BS is recorded as , the UAV-BS set is Users and UAV-BS can move freely in the scene. Users and UAV-BS are distributed in various floors of buildings and in streets and open spaces outside buildings.

[0035] This application is The scene is observed and adjusted at time step intervals. time step, the coordinates of the user and UAV-BS positions are marked as and ,in , , representing users and UAV-BS The three-dimensional spatial position of .

[0036] It should be noted that the number of sub-bands available in the scene is , the bandwidth of each sub-band is , each UAV-BS uses a certain number of sub-bands; time steps, user Access UAV-BS The signal to interference plus noise ratio (SINR) is recorded as .

[0037] In this embodiment, define The position of the particle For the optimization variable (position adjustment of all UAV-BS) A feasible solution is to use UAV-BS Position adjustment Expand with horizontal distance adjustment, horizontal angle adjustment, and height adjustment, that is At this time, The particle position of the particle ( The feasible solution of the optimization variables corresponding to the particles is , as shown in formula (1).

[0038] (1)

[0039] It should be noted that the particle cluster in this embodiment includes Particles.

[0040] Definition The particle position of a particle during the algorithm search process is , which reflects the speed of algorithm search, It is composed of the changing speed of the particle position in each dimension, as shown in formula (2).

[0041] (2)

[0042] Preferably, before executing step 101, the process also includes initializing relevant parameters; defining the number of particles , the maximum number of algorithm iterations is , set the initial temperature , cooling coefficient . Maximum distance for UAV-BS horizontal position adjustment , maximum angle of horizontal adjustment , the maximum value of UAV-BS altitude adjustment , the minimum distance for UAV-BS horizontal position adjustment , minimum angle of horizontal adjustment , the minimum value of UAV-BS altitude adjustment , the above variables correspond to the variation range of the corresponding elements in the particle position matrix. Limit the range of particle movement speed in each dimension, that is, , , In addition, the maximum value of the inertia weight is defined , the minimum value of the inertia weight .

[0043] Optionally, initialize the particle position and particle velocity of each particle in the particle cluster, including: The particle position and particle velocity of each particle in the particle cluster are initialized by chaotic mapping, wherein the three-dimensional spatial position adjustment of the drone base station cluster includes the horizontal distance adjustment, horizontal angle adjustment and height adjustment of each drone base station.

[0044] Specifically, the chaotic map is used to initialize the particle position and particle velocity. The particle population position , and the particle speed .

[0045] Since the selection of the initial position of the particles will also affect the final result to a certain extent, the traditional random distribution may lead to uneven distribution of particles. Therefore, this design uses the chaotic mapping method to initialize the particle population and speed, making the distribution of particles more uniform and easier to search for the global optimal adjustment position of UAV-BS. Location and speed Initialize the chaos map to and No. Taking the column as an example, the specific initialization method is shown in formula (3).

[0046] (3)

[0047] in , A random number between 0 and 1.

[0048] Step 102 , calculating the fitness of each particle in the particle cluster according to the particle position of each particle in the particle cluster to obtain a fitness set.

[0049] In this embodiment, the optimization goal of the optimization problem can be adjusted according to the UAV-BS position, and the first The fitness function of a particle is specifically shown in formula (4).

[0050] (4)

[0051] in, For On the basis of The position of the particle Adjusted all UAV-BS positions After that, according to the user Access UAV-BS SINR Users estimated by Shannon's formula In the The transmission rate under feasible solutions. The fitness vector of the entire particle swarm is .

[0052] Optionally, the fitness of each particle in the particle cluster is calculated according to the particle position of each particle in the particle cluster to obtain a fitness set, including: Each particle in the particle cluster is used as a target particle to perform the following steps to obtain the target fitness: calculate the temporary position of the drone base station cluster in the three-dimensional space according to the particle position of the target particle; obtain the current user position set, wherein the current user position set is a set of current positions of multiple users; determine the current average transmission rate according to the temporary position and the current user position set, wherein the current average transmission rate is the average value of the transmission rates between multiple users and the drone base station cluster; determine the current average transmission rate as the target fitness.

[0053] Specifically, particles (target particle) as an example, at position Under this condition, the temporary positions of all UAV-BS in three-dimensional space are simulated and calculated. , calculated as . In getting After that, the SINR is estimated based on the indoor and outdoor mixed channel model in combination with the current user location, and then the user access switching is performed according to the load balancing method. The transmission rate of each user is estimated based on the new access relationship and the frequency band resources of each UAV-BS, which is used as the particle Fitness , that is, get the target fitness; traverse After the particles, the fitness of all particles is obtained .

[0054] Optional, according to Initialize the individual particle maximum fitness vector of all particles and the optimal position of individual particles , further initialize the global particle maximum fitness And its corresponding global optimal particle position .

[0055] It should be noted that the maximum fitness of an individual particle is the maximum fitness of all fitnesses obtained by the individual particle during the update process, and the optimal position of an individual particle is the particle position of the particle corresponding to the maximum fitness of the individual particle; the maximum fitness of a global particle is the maximum fitness of all fitnesses obtained by all particles in a particle cluster during the update process, and the optimal position of a global particle is the particle position of the particle corresponding to the maximum fitness of the global particle.

[0056] Here, the Improved Particle Swarm Optimization (IPSO) algorithm in this embodiment is explained. This application assumes that at the time step When solving optimization problems, the most In the iteration, At the iteration, The fitness of a particle is , records the number of iterations from the initial to the current one The maximum fitness of an individual particle is Then the individual particle maximum fitness vector of all particles is expressed as The optimal position of the individual particle corresponding to the maximum fitness of the above individual particle is recorded as On this basis, Represents the global maximum particle fitness up to the current iteration, that is, , and its corresponding global optimal particle position is recorded as , as shown in formula (4).

[0057] (5)

[0058] In each iteration, each particle will Update and adjust according to the current particle Location Simulate and calculate the temporary positions of all UAV-BS On this basis, the particle size of the current iteration is calculated The average transmission rate of all users corresponding to the particle scalar in the current iteration Fitness .go through After all particles are processed in iterations, the time step The global optimal particle position Determine and use to actually update the position of the UAV-BS .

[0059] Step 103, taking each particle in the particle cluster as the current particle and executing the following update steps to obtain an updated fitness set: selecting the particle position corresponding to the largest fitness in the fitness set as the initial global particle optimal position; determining the current inertia weight based on the particle position of the current particle and the initial global particle optimal position; updating the particle velocity of the current particle based on the current inertia weight to obtain an updated particle velocity; updating the particle position of the current particle based on the updated particle velocity to obtain an updated particle position; determining the current fitness based on the updated particle position; adding the larger value of the fitness before the current particle is updated and the current fitness to the updated fitness set.

[0060] Optionally, at the beginning of the overall iteration process of the UAV position adjustment algorithm, the individual learning factors of the UAV-BS position adjustment algorithm need to be And the global learning factor Perform nonlinear adjustment, as shown in formula (5).

[0061] (5)

[0062] The adjustment enables the algorithm to have stronger local search capabilities in the early stage of the search and stronger global search capabilities in the later stage of the search when searching the three-dimensional space near the UAV-BS.

[0063] Optionally, the current inertia weight is determined based on the particle position of the current particle and the initial global particle optimal position, including: Calculate the current distance vector between the particle position of the current particle and the initial global particle optimal position, wherein the current distance vector includes the distance between the current particle and the initial global particle optimal position in the horizontal adjustment distance dimension, the distance between the current particle and the initial global particle optimal position in the horizontal adjustment angle dimension, and the distance between the current particle and the initial global particle optimal position in the height adjustment dimension; determine the current inertia weight according to the current distance vector.

[0064] Specifically, we start to update the iteration and update the speed of each particle one by one. Here, we use an adaptive adjustment method to adjust the inertia weight to control the update speed of the particle position and thus control the speed of the drone's search for a new position near the current position. Before calculating the inertia weight, we first calculate the particle The distance between the current particle and the optimal position of the global particle in three dimensions , the specific calculation method is shown in formula (6).

[0065] (6)

[0066] In the formula For particles Adjust the distance dimension to the global particle optimal position at the UAV-BS level, For particles The distance from the global particle optimal position in the UAV-BS horizontal adjustment angle dimension, For particles The distance from the global particle optimal position in the UAV-BS height adjustment dimension.

[0067] Afterwards through Calculated particles The inertia weight , the mathematical expression is shown in formula (7).

[0068] (7)

[0069] in For particles Inertia weight in each dimension.

[0070] After completing the above calculations, the current particle Particle speed in each dimension To update, Taking the nth column of as an example, the specific calculation method is shown in formula (8).

[0071] (8)

[0072] in, , A random number between 0 and 1.

[0073] Finally, the particles The out-of-bounds elements in the velocity are processed as particles Taking the nth column of speed as an example, the specific formula is as shown in formula (9).

[0074] (9)

[0075] Optionally, the particle position of the current particle is updated based on the updated particle velocity to obtain an updated particle position, including: Add the updated particle velocity to the current particle's particle position to obtain the updated particle position.

[0076] Specifically, for the current particle Location The particle position threshold is updated in a similar way as in formula (9), and the particle Fitness .

[0077] Step 104, after looping the update step for a preset number of times, a target fitness set is obtained, wherein the target fitness set is the individual particle maximum fitness of each particle in the particle cluster, and the individual particle maximum fitness is the maximum value of the fitness obtained by each particle in the process of looping the update step for a preset number of times.

[0078] In this embodiment, each update step is executed in a loop, and is updated based on the fitness set after the most recent update. Each updated fitness set includes the individual particle maximum fitness of all particles iterated so far, and the number of fitness in each updated fitness set is the same as the number of particles in the particle cluster.

[0079] Step 105, adjusting the position of the drone base station cluster based on the global particle optimal position, wherein the global particle optimal position is the particle position corresponding to the maximum fitness in the target fitness set.

[0080] Optionally, after determining the current fitness based on the updated particle position, further comprising: The current optimal position probability is determined according to the current temperature, the current fitness and the maximum fitness of the individual particle, wherein the current optimal position probability is used to indicate the probability that the particle position of the current particle is the optimal position of the individual particle; the individual particle optimal position and the individual particle maximum fitness are updated according to the current optimal position probability.

[0081] In this embodiment, in order to jump out of the local optimal solution as much as possible, the present invention is combined with the simulated annealing algorithm, and the current temperature is adjusted according to the Metropolis criterion. , Current Particle Fitness And the maximum fitness of the individual particles that have not been updated Calculate the probability of updating the current particle's position to the optimal position of the individual particle , as shown in formula (10).

[0082] (10)

[0083] Further, according to The optimal position of individual particles and the maximum fitness of individual particles are updated. The specific updating method is shown in formula (11).

[0084] (11)

[0085] in, It is a random number between 0 and 1, which determines whether to update the optimal position of the current individual particle.

[0086] Furthermore, the global particle maximum fitness is updated by the individual particle maximum fitness of all particles. The update method is: , and the global particle optimal position Update the particle position corresponding to the maximum fitness among the individual maximum fitness of all particles.

[0087] Further, determine whether all particles have been traversed. If not, execute And return the step of calculating the inertia weight, and execute the subsequent steps if the traversal is completed.

[0088] Furthermore, after completing the traversal of all particles, the temperature is updated and cooled down. , then update the number of iterations And determine whether the maximum number of iterations has been reached (preset number of times), if the maximum number of iterations is not reached Returns the individual learning factor for the UAV-BS position adjustment algorithm And the global learning factor Perform the nonlinear adjustment step, otherwise perform the subsequent steps.

[0089] Furthermore, according to the global optimal particle position Simulate the three-dimensional spatial position of the UAV-BS in the scene, calculate the average transmission rate under the simulated position of the UAV-BS and compare it with the average transmission rate under the current UAV-BS position distribution to determine The corresponding updated UAV-BS 3D spatial position communication performance Is it higher than the communication performance under the current UAV-BS position distribution? , if higher than, then according to The UAV-BS is dynamically adjusted, otherwise no position adjustment is performed.

[0090] It can be understood that in this embodiment, in view of the characteristics of the indoor and outdoor mixed environment, a method of modeling the position optimization problem of UAV-BS at a certain time step as a particle swarm optimization problem is proposed. Specifically: at each time step, the three-dimensional spatial adjustment amount of each UAV-BS is used as the position of the particle, and the average transmission rate of the users in the scene is used as the optimization target; the position change is controlled by continuously iteratively adjusting the speed of the particle to optimize the three-dimensional spatial adjustment amount of the UAV-BS; in each iteration, the position, speed and fitness of the particle are updated, and the global particle optimal position and the individual particle optimal position are updated in real time; finally, after the iteration is completed, the three-dimensional spatial position of the UAV-BS is adjusted according to the position of the global optimal particle.

[0091] It should be noted that, based on the modeling of the above problem, a particle position optimization method combined with a simulated annealing strategy is proposed to address the large solution space of a large number of UAV-BS three-dimensional position optimization problems and the problem that the search process is prone to fall into the local optimum. Specifically: first, the position and velocity of the particles are initialized through chaotic mapping, and the fitness of each particle is calculated; the global particle optimal position and the individual particle optimal position are initialized; in the iterative process, the learning factor of the algorithm is nonlinearly adjusted, and the inertia weight of the particles is adaptively adjusted; the particle velocity and position are updated, and the velocity and position thresholds are processed at the same time, the temporary position of the UAV-BS is simulated according to the particle position, and the fitness of the current particle is calculated; the individual particle optimal position is updated using the simulated annealing algorithm, and the global particle optimal position is adjusted; after the iteration is completed, the three-dimensional spatial adjustment amount of the UAV-BS is determined according to the global particle optimal position.

[0092] Through the embodiments provided by the present application, the particle position and particle velocity of each particle in the particle cluster are initialized, wherein the particle position of each particle in the particle cluster is a feasible solution for the three-dimensional spatial position adjustment amount of the drone base station cluster, and the particle velocity is used to represent the changing speed of the particle position; the fitness of each particle in the particle cluster is calculated according to the particle position of each particle in the particle cluster to obtain a fitness set; each particle in the particle cluster is used as the current particle to perform the following update steps to obtain an updated fitness set: the particle position corresponding to the largest fitness in the fitness set is selected as the initial global particle optimal position; the current inertia weight is determined based on the particle position of the current particle and the initial global particle optimal position; the particle velocity of the current particle is updated based on the current inertia weight to obtain an updated particle velocity; the particle position of the current particle is updated based on the updated particle velocity to obtain an updated particle Position; determine the current fitness based on the updated particle position; select the larger value of the fitness of the current particle before updating and the current fitness to form the updated fitness set; after looping the update step for a preset number of times, obtain the target fitness set, wherein the target fitness set is the individual particle maximum fitness of each particle in the particle cluster, and the individual particle maximum fitness is the maximum value of the fitness obtained by each particle in the process of looping the update step for a preset number of times; adjust the position of the UAV base station cluster based on the global particle optimal position, wherein the global particle optimal position is the particle position corresponding to the maximum fitness in the target fitness set; solve the base station position optimization method of the UAV base station networking communication system in the related technology, there is a technical problem that the optimal position of the UAV base station cannot be reasonably deployed, resulting in affecting the communication effect, and improves the rationality of the position layout of the UAV base station cluster.

[0093] In order to verify the performance of the method proposed in this application, a relevant simulation environment was built to realize the simulation of UAV-BS movement and user movement, and to perform simulated calculation of wireless channel quality and simulated operation of system service process.

[0094] The base station location optimization method of the drone base station networking communication system of the embodiment of the present application is described below in conjunction with optional examples.

[0095] (1) Overall simulation process

[0096] In order to verify the performance of the method proposed in this application, a relevant simulation environment was built to realize the simulation of UAV-BS movement and user movement, and to perform simulated calculation of wireless channel quality and simulated operation of system service process.

[0097] Figure 3 This is the second flow diagram of the base station location optimization method of the UAV base station networking communication system provided by the present invention. The overall simulation process of the UAV-BS dynamic location deployment of the present application is as follows: Figure 3 As shown. At the beginning of the simulation, the scene parameters (simulation parameters, channel model) are initialized and users are randomly scattered in the scene (user position initialization). The horizontal position deployment of UAV-BS is initialized by K-means algorithm (K-Means algorithm). Then, intuitive particle swarm modeling is used, and each particle position corresponds to the height of all UAV-BS in the scene. The traditional particle swarm optimization (PSO) algorithm is used to perform initial height deployment of UAV-BS, and finally the initial position deployment of all UAV-BS is completed (drone position initialization). Then, the channel quality (user access) between users and UAV-BS is simulated and calculated based on the indoor and outdoor mixed channel model, and users are associated with UAV-BS according to the load balancing access criteria. Figure 3 The t in represents the time step. In each subsequent time step, the user moves randomly in the simulation scene according to the mobile model. After the user moves, the UAV-BS position is updated (drone position adjustment) using the method proposed in this application. Then, the channel gain between the user and the UAV-BS is simulated and calculated based on the indoor and outdoor mixed channel model. The user performs the association switching (user switching) with the UAV-BS according to the access criteria of the balanced load, and the communication performance indicators are counted, and the statistical results are stored. Then enter the next time step until the simulation ends (traversing T time steps).

[0098] (2) UAV-BS initial position planning

[0099] The horizontal initial position of UAV-BS is deployed through the K-Means algorithm, and then the PSO algorithm is used to iteratively search and update the particles with the average transmission rate of the user as the fitness, and the height of all UAV-BS is deployed, and finally the initial position deployment of UAV-BS is realized, so that the initial deployment position of UAV-BS can achieve the purpose of maximizing the average transmission rate of the user and obtain better communication quality.

[0100] (3) User mobility model

[0101] At each time step, the user will move at a speed not exceeding the maximum Speed Move in a random direction. After a period of time, the user's moving direction will change. If the user is on the street or in an open space outside the building, if it is detected that the user is about to leave the scene area or enter the building, the user will change his or her moving direction to ensure that the user is always in the scene area. If the user is in a building, when the user moves to the edge of the building, it will change its moving direction with probability. , , The probability of choosing the three strategies of changing direction and moving horizontally, going upstairs, and going downstairs is 0.0, but if the selected behavior will cause the user to leave the building area, then the user will choose the strategy of horizontal movement to complete the user's three-dimensional space movement.

[0102] (4) Indoor and outdoor mixed channel model

[0103] The following is a hybrid channel model of the test environment for testing the algorithm constructed in this application, and is introduced in detail: The present invention refers to the 3GPP protocol to establish a hybrid channel model in the emergency rescue scenario of urban blocks, and performs specific calculations on the channel gain between the UAV-BS and the user according to the different positional relationships between the user and the UAV-BS. Specifically, it can be divided into the following situations: 1) The user is inside the building and the UAV-BS is above the building

[0104] The transmission between UAV-BS and users is non-line-of-sight at high altitude. Considering the basic path loss, indoor loss, penetration loss and shadow fading, the transmission is carried out at the time step. ,user and UAV-BS The channel gain is expressed as ;in, is the time step user and UAV-BS The path loss between ; ; ; ; ; In the above calculation formula, is the time step Users at high altitude and UAV-BS The basic loss of the outdoor path between is the three-dimensional space distance between the user and UAV-BS, Indicates the carrier frequency of UAV-BS, in units of , Represents UAV-BS Height, Representative User Height, represents the speed of light, The penetration loss caused by the signal passing through the wall, is the number of floors passed through, is the internal loss of the signal entering the building, is the standard deviation of the penetration loss, For users at high altitude With UAV-BS Shadow fading under outdoor non-line-of-sight transmission, .

[0105] Consider that the carrier frequency of UAV-BS is less than The specific parameter values ​​are shown in Table 1: Table 1 Building penetration loss model

[0106] Table 1 is The minimum value between two independently generated uniformly distributed variables.

[0107] 2) The user is inside a building, and the UAV-BS is higher than the building and not above it

[0108] The transmission between UAV-BS and users is considered as non-line-of-sight transmission at high altitude, taking into account path loss, indoor loss, penetration loss and shadow fading. ,user and UAV-BS The channel gain is expressed as: ;in, For users at high altitude With UAV-BS Shadow fading under non-line-of-sight transmission outdoors, and .

[0109] 3) The user and UAV-BS are located on the same floor of the building

[0110] The transmission between UAV-BS and the user is considered as line-of-sight transmission, considering the path loss and shadow fading. ,user and UAV-BS The channel gain is expressed as: ; ; ; ; For users With UAV-BS Shadow fading under line-of-sight transmission indoors, and .

[0111] 4) The user and UAV-BS are located on different floors of the building

[0112] The transmission between UAV-BS and the user is considered as non-line-of-sight, and path loss and shadow fading are considered. ,user and UAV-BS The channel gain is expressed as: ; ; ; ; ; For users With UAV-BS Shadow fading under indoor non-line-of-sight transmission, .

[0113] 5) The user is inside the building, and the UAV-BS is outside the building but at a height lower than the building height

[0114] The transmission between UAV-BS and the user is considered as non-line-of-sight transmission at low altitude, taking into account path loss, penetration loss, internal loss and shadow fading. ,user and UAV-BS The channel gain is expressed as: ; ; ; ; ; ; ; ; ; For users in low altitude situations With UAV-BS Shadow fading in outdoor non-line-of-sight transmission, .

[0115] 6) The user and UAV-BS are outside the building, and the height of UAV-BS is higher than the building

[0116] The transmission between UAV-BS and the user is considered as line-of-sight transmission, considering the path loss and shadow fading. ,user and UAV-BS The channel gain is expressed as: ; ; ; ; ; For users at high altitude With UAV-BS Shadow fading under outdoor line-of-sight transmission, .

[0117] 7) The user and UAV-BS are located outside the building, and the height of UAV-BS is lower than the building height

[0118] The transmission between UAV-BS and the user is considered as non-line-of-sight, and path loss and shadow fading are considered. ,user and UAV-BS The channel gain is expressed as: ; ; For low altitude users With UAV-BS Shadow fading in non-line-of-sight transmission outdoors, and .

[0119] 8) The user is outside the building and the UAV-BS is inside the building

[0120] The transmission between UAV-BS and the user is considered as non-line-of-sight transmission, and path loss, penetration loss and shadow fading are considered. ,user and UAV-BS The channel gain is expressed as: ; ; For low altitude use With UAV-BS Shadow fading in outdoor non-line-of-sight transmission, .

[0121] (5) User access switching criteria

[0122] The flow chart of load balancing is as follows Figure 4 As shown, when the UAV-BS is initially deployed and dynamically adjusted, it is necessary to switch the user access, which is explained as follows: The expected number of service users of each UAV-BS is defined as ; For each user , it is necessary to calculate the channel gain between it and each UAV-BS, and calculate the SINR based on the channel gain and the connection relationship between the user and the UAV-BS. First, the user is connected to the UAV-BS with the largest SINR. After the access is completed, the number of users currently connected to each UAV-BS is counted. For UAV-BSs whose access number exceeds the expected number of service users, the users are arranged from large to small according to their SINR. Considering the access user limit, only users with larger SINRs for the expected number of service users are retained, and the remaining users are disconnected. After the disconnection, the users choose to access the UAV-BS with the largest SINR according to the SINR between them and the UAV-BSs that have not reached the expected number of services. The above process is repeated until all users are connected to a UAV-BS in the scene and all users are connected to drones, completing the overall access switching of users.

[0123] (6) Communication performance calculation

[0124] After calculating the channel gain between the UAV-BS and the user, it is necessary to calculate the signal-to-interference-plus-noise ratio (SINR) between the user and the UAV-BS in order to estimate the fitness during the algorithm iteration process. When calculating, it is necessary to consider factors such as the interference of the same-frequency UAV-BS and user noise. To calculate SINR, is the transmission power of UAV-BS, is the ambient noise power.

[0125] After the user access is switched based on the calculated SINR, the Shannon channel capacity is used to estimate the user Access UAV-BS The transfer rate that can be obtained by To calculate, Currently connected to UAV-BS Number of users, The frequency band resources allocated to UAV-BS are in Hz. The average transmission rate of the current simulation time step is then calculated as .

[0126] (7) Simulation parameters and results

[0127] Table 2 Scenario simulation parameters

[0128] Figure 5 1 is a training schematic diagram of a base station location optimization method for a UAV base station networking communication system provided by the present invention, Figure 5 The communication performance results of the three algorithms, namely K-Means, fixed drone position (Static) and IPSO, in the current test scenario are statistically shown. It can be seen that when good communication quality is obtained in the initial deployment, the design scheme of the present invention can maintain the current communication quality and provide good communication services.

[0129] It can be understood that the present invention proposes a method for dynamic deployment of unmanned aerial vehicles in the emergency communication scenario of urban blocks, which can realize the tracking communication of unmanned aerial vehicles to users in continuous time, realize the dynamic adjustment of the position of UAV-BS, and improve the communication quality; when the K-Means algorithm and the PSO algorithm are used to initially deploy UAV-BS, the present invention obtains good initial communication performance and provides communication services for users. As time goes by, the three-dimensional spatial position of the user changes, and at the same time, the channel gain between the user and the UAV-BS will also change accordingly. Compared with the UAV-BS dynamic adjustment method used in this article, other methods cannot well cope with the impact caused by the change of the current environment. The adjustment of UAV-BS has not achieved a significant improvement in communication performance, and the user's communication service has not been significantly improved. Even when the position is not adjusted, the user's communication service quality has declined to a certain extent. Compared with other methods, the method used in the present invention can obtain relatively good communication performance in a changing environment, improve the user's communication quality, meet the user's normal communication service for a long time, overcome the interference problem caused by environmental changes to a certain extent, and improve the overall communication performance.

[0130] Figure 6 : is a structural schematic diagram of a base station location optimization device of a UAV base station networking communication system provided by the present invention, such as Figure 6 As shown, including but not limited to the following modules: Initialization module 601 is used to initialize the particle position and particle velocity of each particle in the particle cluster, wherein the particle position of each particle in the particle cluster is a feasible solution of the three-dimensional spatial position adjustment amount of the drone base station cluster, and the particle velocity is used to represent the change speed of the particle position; A calculation module 602 is used to calculate the fitness of each particle in the particle cluster according to the particle position of each particle in the particle cluster to obtain a fitness set; The first execution module 603 is used to perform the following update steps on each particle in the particle cluster as the current particle to obtain an updated fitness set: select the particle position corresponding to the largest fitness in the fitness set as the initial global particle optimal position; determine the current inertia weight based on the particle position of the current particle and the initial global particle optimal position; update the particle speed of the current particle based on the current inertia weight to obtain an updated particle speed; update the particle position of the current particle based on the updated particle speed to obtain an updated particle position; determine the current fitness based on the updated particle position; add the larger value of the fitness before the current particle is updated and the current fitness to the updated fitness set; The second execution module 604 is used to obtain a target fitness set after cyclically executing the update step for a preset number of times, wherein the target fitness set is the individual particle maximum fitness of each particle in the particle cluster, and the individual particle maximum fitness is the maximum value of the fitness obtained by each particle in the process of cyclically executing the update step for a preset number of times; The adjustment module 605 is used to adjust the position of the drone base station cluster based on the global particle optimal position, wherein the global particle optimal position is the particle position corresponding to the maximum fitness in the target fitness set.

[0131] Through the embodiments of the present application, the particle position and particle velocity of each particle in the particle cluster are initialized, wherein the particle position of each particle in the particle cluster is a feasible solution to the three-dimensional spatial position adjustment amount of the drone base station cluster, and the particle velocity is used to represent the changing speed of the particle position; the fitness of each particle in the particle cluster is calculated according to the particle position of each particle in the particle cluster to obtain a fitness set; each particle in the particle cluster is used as the current particle to perform the following update steps to obtain an updated fitness set: the particle position corresponding to the largest fitness in the fitness set is selected as the initial global particle optimal position; the current inertia weight is determined based on the particle position of the current particle and the initial global particle optimal position; the particle velocity of the current particle is updated based on the current inertia weight to obtain an updated particle velocity; the particle position of the current particle is updated based on the updated particle velocity to obtain an updated The invention discloses a method for optimizing the base station position of a UAV base station in the present invention, which is a method for optimizing the base station position of a UAV base station network communication system. The method comprises the following steps: a. determining the position of a particle after updating; b. determining the current fitness based on the updated particle position; c. selecting the larger value of the fitness before the current particle is updated and the current fitness to form an updated fitness set; d. obtaining a target fitness set after cyclically executing the update step for a preset number of times, wherein the target fitness set is the individual particle maximum fitness of each particle in the particle cluster, and the individual particle maximum fitness is the maximum value of the fitness obtained by each particle in the process of cyclically executing the update step for a preset number of times; c. adjusting the position of the UAV base station cluster based on the global optimal position of the particle, wherein the global optimal position of the particle is the particle position corresponding to the maximum fitness in the target fitness set; the method solves the technical problem that the optimal position of the UAV base station cannot be reasonably deployed in the related art, which affects the communication effect, and improves the rationality of the position layout of the UAV base station cluster.

[0132] It should be noted that the base station location optimization device of the drone base station networking communication system provided by the present invention can execute the base station location optimization method of the drone base station networking communication system of any of the above-mentioned embodiments during specific operation, which will not be elaborated in this embodiment.

[0133] Figure 7 is a schematic diagram of the structure of the electronic device provided by the present invention, such as Figure 7As shown, the electronic device may include: a processor 710, a communication interface 720, a memory 730 and a communication bus 740, wherein the processor 710, the communication interface 720 and the memory 730 communicate with each other through the communication bus 740. The processor 710 may call the logic instructions in the memory 730 to execute the base station position optimization method of the drone base station networking communication system, the method comprising: initializing the particle position and particle velocity of each particle in the particle cluster, wherein the particle position of each particle in the particle cluster is a feasible solution of the three-dimensional spatial position adjustment amount of the drone base station cluster, and the particle velocity is used to represent the change speed of the particle position; calculating the fitness of each particle in the particle cluster according to the particle position of each particle in the particle cluster to obtain a fitness set; taking each particle in the particle cluster as the current particle to perform the following update steps to obtain an updated fitness set: selecting the particle position corresponding to the largest fitness in the fitness set as the initial global particle optimal position; determining the current inertia weight based on the particle position of the current particle and the initial global particle optimal position; Based on the current inertia weight, the particle velocity of the current particle is updated to obtain the updated particle velocity; based on the updated particle velocity, the particle position of the current particle is updated to obtain the updated particle position; based on the updated particle position, the current fitness is determined; the larger value of the fitness of the current particle before the update and the current fitness is added to the updated fitness set; after looping the update step for a preset number of times, a target fitness set is obtained, wherein the target fitness set is the individual particle maximum fitness of each particle in the particle cluster, and the individual particle maximum fitness is the maximum value of the fitness obtained by each particle in the process of looping the update step for a preset number of times; based on the global particle optimal position, the position of the UAV base station cluster is adjusted, wherein the global particle optimal position is the particle position corresponding to the maximum fitness in the target fitness set.

[0134] In addition, the logic instructions in the above-mentioned memory 730 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0135] On the other hand, the present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by the computer, the computer can execute the base station position optimization method of the drone base station networking communication system provided by the above-mentioned embodiments, and the method includes: initializing the particle position and particle velocity of each particle in the particle cluster, wherein the particle position of each particle in the particle cluster is a feasible solution to the three-dimensional spatial position adjustment amount of the drone base station cluster, and the particle velocity is used to represent the changing speed of the particle position; calculating the fitness of each particle in the particle cluster according to the particle position of each particle in the particle cluster to obtain a fitness set; taking each particle in the particle cluster as the current particle to perform the following update steps to obtain an updated fitness set: selecting the particle position corresponding to the largest fitness in the fitness set as the initial global particle maximum fitness optimal position; determine the current inertia weight based on the particle position of the current particle and the initial global particle optimal position; update the particle speed of the current particle based on the current inertia weight to obtain an updated particle speed; update the particle position of the current particle based on the updated particle speed to obtain an updated particle position; determine the current fitness based on the updated particle position; add the larger value of the fitness of the current particle before updating and the current fitness to the updated fitness set; after looping the update step for a preset number of times, obtain the target fitness set, wherein the target fitness set is the individual particle maximum fitness of each particle in the particle cluster, and the individual particle maximum fitness is the maximum value of the fitness obtained by each particle in the process of looping the update step for a preset number of times; adjust the position of the drone base station cluster based on the global particle optimal position, wherein the global particle optimal position is the particle position corresponding to the maximum fitness in the target fitness set.

[0136] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the base station position optimization method of the drone base station networking communication system provided in the above-mentioned embodiments, the method comprising: initializing the particle position and particle velocity of each particle in a particle cluster, wherein the particle position of each particle in the particle cluster is a feasible solution for the three-dimensional spatial position adjustment amount of the drone base station cluster, and the particle velocity is used to represent the changing speed of the particle position; calculating the fitness of each particle in the particle cluster according to the particle position of each particle in the particle cluster to obtain a fitness set; taking each particle in the particle cluster as the current particle and performing the following updating steps to obtain an updated fitness set: selecting the particle position corresponding to the largest fitness in the fitness set as the initial global particle optimal position; based on the particle position of the current particle and The initial global particle optimal position determines the current inertia weight; based on the current inertia weight, the particle speed of the current particle is updated to obtain an updated particle speed; based on the updated particle speed, the particle position of the current particle is updated to obtain an updated particle position; based on the updated particle position, the current fitness is determined; the larger value of the fitness of the current particle before the update and the current fitness is added to the updated fitness set; after looping the update step for a preset number of times, a target fitness set is obtained, wherein the target fitness set is the individual particle maximum fitness of each particle in the particle cluster, and the individual particle maximum fitness is the maximum value of the fitness obtained by each particle in the process of looping the update step for a preset number of times; based on the global particle optimal position, the position of the drone base station cluster is adjusted, wherein the global particle optimal position is the particle position corresponding to the maximum fitness in the target fitness set.

[0137] The device embodiments described above are merely illustrative, wherein 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, i.e., they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative effort.

[0138] Through the description of the above implementation modes, those skilled in the art can clearly understand that each implementation mode can be implemented by means of software plus a necessary general hardware platform, or of course by hardware. Based on such an understanding, the above technical solution can essentially or in other words be embodied in the form of a software product that contributes to the prior art. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or some parts of the embodiment.

[0139] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for optimizing the base station location of a drone base station networking communication system, characterized in that: include: Initialize the particle position and particle velocity of each particle in the particle cluster, wherein the particle position of each particle in the particle cluster is a feasible solution of the three-dimensional spatial position adjustment amount of the drone base station cluster, and the particle velocity is used to represent the changing speed of the particle position; Calculating the fitness of each particle in the particle cluster according to the particle position of each particle in the particle cluster to obtain a fitness set; Each particle in the particle cluster is used as the current particle to perform the following update steps to obtain an updated fitness set: the particle position corresponding to the largest fitness in the fitness set is selected as the initial global particle optimal position; the current inertia weight is determined based on the particle position of the current particle and the initial global particle optimal position; the particle speed of the current particle is updated based on the current inertia weight to obtain an updated particle speed; the particle position of the current particle is updated based on the updated particle speed to obtain an updated particle position; the current fitness is determined based on the updated particle position; the larger value of the fitness of the current particle before the update and the current fitness is added to the updated fitness set; After the updating step is executed cyclically for a preset number of times, a target fitness set is obtained, wherein the target fitness set is the individual particle maximum fitness of each particle in the particle cluster, and the individual particle maximum fitness is the maximum value of the fitness obtained by each particle in the process of cyclically executing the updating step for a preset number of times; The position of the drone base station cluster is adjusted based on the global particle optimal position, wherein the global particle optimal position is the particle position corresponding to the maximum fitness in the target fitness set.

2. The base station location optimization method of the drone base station networking communication system according to claim 1 is characterized in that: After determining the current fitness based on the updated particle position, the method further includes: Determine a current optimal position probability according to the current temperature, the current fitness and the maximum fitness of the individual particle, wherein the current optimal position probability is used to indicate the probability that the particle position of the current particle is the optimal position of the individual particle; The individual particle optimal position and the individual particle maximum fitness are updated according to the current optimal position probability.

3. The base station location optimization method of the drone base station networking communication system according to claim 1 is characterized in that: The initializing the particle position and particle velocity of each particle in the particle cluster includes: The particle position and particle velocity of each particle in the particle cluster are initialized by chaotic mapping, wherein the three-dimensional spatial position adjustment of the drone base station cluster includes the horizontal distance adjustment, horizontal angle adjustment and height adjustment of each drone base station.

4. The base station location optimization method of the drone base station networking communication system according to claim 1, characterized in that: The step of calculating the fitness of each particle in the particle cluster according to the particle position of each particle in the particle cluster to obtain a fitness set includes: Take each particle in the particle cluster as the target particle and perform the following steps to obtain the target fitness: Calculating the temporary position of the drone base station cluster in three-dimensional space according to the particle position of the target particle; Obtaining a current user location set, wherein the current user location set is a set of current locations of multiple users; Determine a current average transmission rate according to the temporary position and the current user position set, wherein the current average transmission rate is an average value of transmission rates between the multiple users and the drone base station cluster; The current average transmission rate is determined as the target fitness.

5. The base station location optimization method of the drone base station networking communication system according to claim 1, characterized in that: The determining the current inertia weight based on the particle position of the current particle and the initial global particle optimal position includes: Calculating a current distance vector between the particle position of the current particle and the initial global particle optimal position, wherein the current distance vector includes the distance between the current particle and the initial global particle optimal position in a horizontal adjustment distance dimension, the distance between the current particle and the initial global particle optimal position in a horizontal adjustment angle dimension, and the distance between the current particle and the initial global particle optimal position in a height adjustment dimension; The current inertia weight is determined according to the current distance vector.

6. The base station location optimization method of the drone base station networking communication system according to claim 1, characterized in that: The updating of the particle position of the current particle based on the updated particle velocity to obtain the updated particle position includes: The updated particle position is obtained by adding the updated particle velocity to the particle position of the current particle.

7. A base station location optimization device for a drone base station networking communication system, characterized in that: include: An initialization module, used to initialize the particle position and particle velocity of each particle in the particle cluster, wherein the particle position of each particle in the particle cluster is a feasible solution of the three-dimensional spatial position adjustment amount of the drone base station cluster, and the particle velocity is used to represent the changing speed of the particle position; A calculation module, used for calculating the fitness of each particle in the particle cluster according to the particle position of each particle in the particle cluster to obtain a fitness set; The first execution module is used to perform the following update steps on each particle in the particle cluster as the current particle to obtain an updated fitness set: select the particle position corresponding to the largest fitness in the fitness set as the initial global particle optimal position; determine the current inertia weight based on the particle position of the current particle and the initial global particle optimal position; update the particle speed of the current particle based on the current inertia weight to obtain an updated particle speed; update the particle position of the current particle based on the updated particle speed to obtain an updated particle position; determine the current fitness based on the updated particle position; add the larger value of the fitness of the current particle before the update and the current fitness to the updated fitness set; A second execution module is used to obtain a target fitness set after cyclically executing the updating step for a preset number of times, wherein the target fitness set is the individual particle maximum fitness of each particle in the particle cluster, and the individual particle maximum fitness is the maximum value of the fitness obtained by each particle in the process of cyclically executing the updating step for a preset number of times; An adjustment module is used to adjust the position of the drone base station cluster based on the global particle optimal position, wherein the global particle optimal position is the particle position corresponding to the maximum fitness in the target fitness set.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the base station location optimization method of the drone base station networking communication system is implemented as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the base station location optimization method of the drone base station networking communication system as described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by the processor, the base station location optimization method of the drone base station networking communication system as described in any one of claims 1 to 6 is implemented.

Images