Electromagnetic environment reconstruction method and device based on electromagnetic characteristic parameter calibration

Abstract

The invention provides an electromagnetic environment reconstruction method and device based on electromagnetic characteristic parameter calibration, and is applied to the technical field of wireless communication, and the method comprises the steps: obtaining an initial electromagnetic characteristic parameter in a pre-constructed communication scene; performing first calibration processing on the initial electromagnetic characteristic parameter based on a logistic chaos algorithm to obtain a reference electromagnetic characteristic parameter; performing second calibration processing on the reference electromagnetic characteristic parameter based on a simulated annealing algorithm to obtain a target electromagnetic characteristic parameter; and obtaining corresponding electromagnetic field data based on the target electromagnetic characteristic parameters, the scatterer position information and the emission signal intensity, and constructing an electromagnetic environment according to the electromagnetic field data. According to the method, the rapid detection advantage of the logistic chaos algorithm in the initial stage and the refinement advantage of the simulated annealing algorithm are combined, the balance of the speed and the precision is realized, the globally optimal solution can be rapidly converged, and the problem that electromagnetic characteristic parameters cannot be efficiently and accurately calibrated at present is solved.

Description

Technical Field

[0001] The present application relates to the field of wireless communication technology, and in particular to a method and device for reconstructing an electromagnetic environment based on electromagnetic characteristic parameter calibration. Background Art

[0002] With the rapid development of wireless communication technology, especially in the critical period of moving from the fifth generation (5G) mobile communication system to the sixth generation (6G) mobile communication system, the requirements for the accuracy and reliability of the electromagnetic environment are becoming more and more stringent. Electromagnetic environment reconstruction refers to the process of reproducing the electromagnetic environment in a certain actual area by using certain methods. In military communications, radar detection and other scenarios, electromagnetic environment reconstruction can be used to simulate the electromagnetic environment in the enemy area to test the performance and adaptability of our electronic equipment. In complex communication environments, multipath propagation occurs frequently. Traditional electromagnetic environment reconstruction methods are unable to cope with these complex situations, and their accuracy is difficult to meet the needs of modern communication systems. Ray tracing (RT) is a simulation technology based on geometric optics and electromagnetic theory. It stands out with its unique advantages and provides an accurate method for electromagnetic environment reconstruction. It can simulate the propagation path of wireless signals in complex three-dimensional space in detail, including direct, reflected, refraction and other paths, thereby providing a more accurate description of the electromagnetic environment than traditional statistical models. However, despite the significant advantages of RT in accuracy, it still faces many challenges in practical applications. The calibration of electromagnetic (EM) parameters is a key step in RT, which directly affects the accuracy of electromagnetic environment reconstruction.

[0003] However, the EM parameters of different materials vary significantly with frequency and are difficult to measure accurately in actual environments, which increases the complexity of EM parameter calibration. In addition, the large amount of calculations in RT places high demands on computing resources. For example, the existing EM parameter calibration method in RT includes the simulated annealing (SA) algorithm, which is a general probabilistic algorithm used to approximate the global optimal solution of a given function in a large search space. However, the existing scheme needs to start from the initial solution and gradually search around, and cannot quickly traverse every sub-interval of the value space, resulting in high computational complexity and long time consumption. And it is easy to fall into the local optimal solution. Therefore, in order to meet the high precision and high efficiency requirements of 6G and future communication systems for channel models, there is an urgent need for a new electromagnetic environment reconstruction method that can efficiently and accurately calibrate EM parameters. Summary of the invention

[0004] The technical purpose to be achieved by the embodiments of the present application is to provide an electromagnetic environment reconstruction method and device based on electromagnetic characteristic parameter calibration, so as to solve the current problem that electromagnetic characteristic parameters cannot be calibrated efficiently and accurately.

[0005] In order to solve the above technical problems, the embodiment of the present application provides an electromagnetic environment reconstruction method based on electromagnetic characteristic parameter calibration, including:

[0006] Obtaining initial electromagnetic characteristic parameters in a pre-built communication scenario;

[0007] Performing a first calibration process on the initial electromagnetic characteristic parameters based on a logistic chaos (LC) algorithm to obtain reference electromagnetic characteristic parameters after the first calibration process;

[0008] A second calibration process is performed on the reference electromagnetic characteristic parameters based on a simulated annealing algorithm to obtain target electromagnetic characteristic parameters after the second calibration process.

[0009] Corresponding electromagnetic field data are obtained based on the target electromagnetic characteristic parameters, scatterer position information and signal strength emitted by the base station, and an electromagnetic environment is constructed according to the electromagnetic field data.

[0010] Specifically, in the method described above, the first calibration process is performed on the initial electromagnetic characteristic parameters based on the logistic chaos algorithm to obtain the reference electromagnetic characteristic parameters after the first calibration process, including:

[0011] Linearly mapping the initial electromagnetic characteristic parameters to an interval of a logistic mapping;

[0012] Based on the recursive formula of the logistic mapping, performing a first preset number of first iterations, and obtaining first electromagnetic characteristic parameters corresponding to each of the first iterations;

[0013] Acquire a first loss function corresponding to each of the first iterations according to the first electromagnetic characteristic parameter;

[0014] The first electromagnetic characteristic parameter corresponding to the minimum value in the first loss function is determined as the reference electromagnetic characteristic parameter.

[0015] Specifically, in the method described above, the second calibration process is performed on the reference electromagnetic characteristic parameters based on the simulated annealing algorithm to obtain the target electromagnetic characteristic parameters after the second calibration process, including:

[0016] Setting the reference electromagnetic characteristic parameter to the initial value of the solution in the simulated annealing algorithm, the iteration threshold to the second preset number, the loss function threshold to the first threshold, and the control parameter to be related to the initial electromagnetic characteristic parameter;

[0017] Perform a second iteration to generate a second solution based on the initial value and a uniformly distributed first random variable, or generate a second solution based on the first solution in the previous second iteration and a uniformly distributed first random variable, wherein the first random variable is related to the accuracy of the target electromagnetic characteristic parameter;

[0018] Determine, according to the Metropolis criterion and the control parameter, the second solution or the first solution in the previous second iteration as the first solution in the current second iteration;

[0019] If the loss function corresponding to the first solution in the current second iteration is less than the first threshold, or the number of iterations reaches the second preset number, the first solution is determined to be the target electromagnetic characteristic parameter.

[0020] Further, in the method as described above, determining, according to the Metropolis criterion and the control parameter, the second solution or the first solution in the previous second iteration as the first solution in the current second iteration includes:

[0021] Obtain a second loss function corresponding to the first solution in the second iteration and a third loss function corresponding to the second solution;

[0022] Obtaining a loss function difference of the third loss function minus the second loss function;

[0023] If the loss function difference is less than zero, determining that the second solution is the first solution in the current second iteration;

[0024] If the loss function difference is greater than or equal to zero, determining a reference probability according to the loss function difference and the control parameter, and generating a second random variable with uniform distribution;

[0025] If the second random variable is less than the reference probability, the second solution is determined to be the first solution in the current second iteration; otherwise, the first solution in the previous second iteration is determined to be the first solution in the current second iteration.

[0026] Preferably, in the above method, the step of obtaining the loss function corresponding to the target iteration includes:

[0027] According to the electromagnetic characteristic parameters corresponding to the target iteration, obtaining simulated path loss data and real path loss data corresponding to each user terminal in the communication scenario, wherein the simulated path loss data is determined based on ray tracing simulation, and the real path loss data is determined based on impulse response;

[0028] Acquire a path loss error corresponding to each of the user terminals in the target iteration according to the simulated path loss data and the real path loss data;

[0029] Determine a distance weight corresponding to each of the user terminals according to a terminal position and a base station (BS) position in the communication scenario;

[0030] Based on the distance weight and the path loss error corresponding to each user terminal (User Equipment, UE), the loss function corresponding to the target iteration is calculated, wherein the loss function is a weighted sum of the path loss errors in the target iteration.

[0031] Specifically, in the method as described above, determining the distance weight corresponding to each of the user terminals according to the terminal position and the base station position in the communication scenario includes:

[0032] Determining a distance parameter between each of the user terminals and the base station according to the terminal position and the base station position;

[0033] Performing equal distance division according to the distance parameter to obtain a plurality of distance ranges, wherein the number of the distance ranges is related to the total number of the user terminals;

[0034] The distance weight corresponding to each user terminal is determined according to the total number of the user terminals, the number of the distance ranges, and the number of the user terminals within the distance range where each user terminal is located.

[0035] Another embodiment of the present application further provides a control device for electromagnetic environment reconstruction based on electromagnetic characteristic parameter calibration, comprising:

[0036] A parameter acquisition module, used to acquire initial electromagnetic characteristic parameters in a pre-built communication scenario;

[0037] A first calibration processing module, used for performing a first calibration process on the initial electromagnetic characteristic parameters based on a logistic chaos algorithm to obtain reference electromagnetic characteristic parameters after the first calibration process;

[0038] A second calibration processing module, used for performing a second calibration processing on the reference electromagnetic characteristic parameters based on a simulated annealing algorithm to obtain target electromagnetic characteristic parameters after the second calibration processing;

[0039] The electromagnetic environment construction module is used to obtain corresponding electromagnetic field data based on the target electromagnetic characteristic parameters, scatterer location information and signal strength transmitted by the base station, and to construct an electromagnetic environment according to the electromagnetic field data.

[0040] Another embodiment of the present application also provides an electronic device, including a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the electromagnetic environment reconstruction method based on electromagnetic characteristic parameter calibration as described above.

[0041] Another embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the electromagnetic environment reconstruction method based on electromagnetic characteristic parameter calibration as described above are implemented.

[0042] Another embodiment of the present application further provides a computer program product, including computer instructions, which, when executed by a processor, implement the steps of the electromagnetic environment reconstruction method based on electromagnetic characteristic parameter calibration as described above.

[0043] Compared with the prior art, the electromagnetic environment reconstruction method and device based on electromagnetic characteristic parameter calibration provided in the embodiment of the present application have at least the following beneficial effects:

[0044] This application uses the logistic chaos algorithm to perform the first calibration process, and uses the rapid detection capability of the logistic chaos algorithm in the initial stage to efficiently traverse and roughly adjust the parameter space to accelerate the convergence efficiency. Then, the simulated annealing algorithm is used to perform the second calibration process to refine the solution obtained above, avoid local optimality, and ensure the accuracy and optimal adjustment of the parameters. Combining the advantages of the logistic chaos algorithm and the simulated annealing algorithm, a balance between speed and accuracy is achieved, and it can quickly converge to the global optimal solution, solving the current problem of being unable to efficiently and accurately calibrate the electromagnetic characteristic parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is one of the flow charts of the electromagnetic environment reconstruction method based on electromagnetic characteristic parameter calibration;

[0046] Figure 2 The second flowchart of the electromagnetic environment reconstruction method based on electromagnetic characteristic parameter calibration;

[0047] Figure 3 The third flowchart of the electromagnetic environment reconstruction method based on electromagnetic characteristic parameter calibration;

[0048] Figure 4 The fourth flowchart of the electromagnetic environment reconstruction method based on electromagnetic characteristic parameter calibration;

[0049] Figure 5 The fifth flowchart of the electromagnetic environment reconstruction method based on electromagnetic characteristic parameter calibration;

[0050] Figure 6 The sixth flowchart of the electromagnetic environment reconstruction method based on electromagnetic characteristic parameter calibration;

[0051] Figure 7 One of the structural schematic diagrams of the control device for electromagnetic environment reconstruction based on electromagnetic characteristic parameter calibration;

[0052] Figure 8 The second structural schematic diagram of the control device for electromagnetic environment reconstruction based on electromagnetic characteristic parameter calibration;

[0053] Fig. 9 The third structural schematic diagram of the control device for electromagnetic environment reconstruction based on electromagnetic characteristic parameter calibration;

[0054] Fig.10 The fourth structural schematic diagram of the control device for electromagnetic environment reconstruction based on electromagnetic characteristic parameter calibration;

[0055] Fig.11 The fifth structural schematic diagram of the control device for electromagnetic environment reconstruction based on electromagnetic characteristic parameter calibration;

[0056] Fig.12 The sixth structural schematic diagram of the control device for reconstructing the electromagnetic environment based on the calibration of electromagnetic characteristic parameters. DETAILED DESCRIPTION

[0057] In order to make the technical problems, technical solutions and advantages to be solved by the application clearer, the following will be described in detail in conjunction with the accompanying drawings and specific embodiments. In the following description, specific details such as specific configurations and components are provided only to help fully understand the embodiments of the application. Therefore, it should be clear to those skilled in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the application. In addition, for clarity and brevity, the description of known functions and structures has been omitted.

[0058] It should be understood that the references to "one embodiment" or "an embodiment" throughout the specification mean that the specific features, structures, or characteristics associated with the embodiment are included in at least one embodiment of the present application. Therefore, the references to "in one embodiment" or "in an embodiment" appearing throughout the specification do not necessarily refer to the same embodiment. In addition, these specific features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0059] In the various embodiments of the present application, it should be understood that the size of the serial numbers of the following processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0060] It should be understood that the term "and / or" in this article is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0061] In the embodiments provided in the present application, it should be understood that "B corresponding to A" means that B is associated with A, and B can be determined according to A. However, it should also be understood that determining B according to A does not mean determining B only according to A, and B can also be determined according to A and / or other information.

[0062] See also Figure 1 An embodiment of the present application provides an electromagnetic environment reconstruction method based on electromagnetic characteristic parameter calibration, comprising:

[0063] Step S101, obtaining initial electromagnetic characteristic parameters in a pre-built communication scenario;

[0064] Step S102, performing a first calibration process on the initial electromagnetic characteristic parameters based on a logistic chaos algorithm to obtain reference electromagnetic characteristic parameters after the first calibration process;

[0065] Step S103, performing a second calibration process on the reference electromagnetic characteristic parameters based on a simulated annealing algorithm to obtain target electromagnetic characteristic parameters after the second calibration process.

[0066] Step S104, obtaining corresponding electromagnetic field data based on the target electromagnetic characteristic parameters, the scatterer position information and the signal strength transmitted by the base station, and constructing an electromagnetic environment according to the electromagnetic field data.

[0067] In this embodiment, when reconstructing the electromagnetic environment, the initial electromagnetic characteristic parameters in the pre-constructed communication scene are first obtained, where the pre-constructed communication scene is a three-dimensional scene, in which the specific locations of the user terminal and the base station are clearly defined, and communication system related parameters such as the center frequency, bandwidth, and waveform of the signal are set. At the same time, propagation conditions in the simulation such as the maximum number of reflections, the minimum received power, and the scattering model are also configured. The initial electromagnetic characteristic parameters can be recorded as ε initial , which can be obtained from [ε min ,ε max ], where ε min and ε max They are the minimum and maximum values ​​of electromagnetic characteristic parameters related to the communication scenario. Scatterers include, for example, buildings, trees, vehicles, etc. Electromagnetic characteristic parameters include relative permittivity, conductivity, magnetic permeability, loss tangent, etc. Electromagnetic field data include electric field strength, magnetic field strength, etc.

[0068] After obtaining the initial electromagnetic characteristic parameters, the first calibration process (initial calibration) is first performed through the logistic chaos algorithm. The rapid detection capability of the logistic chaos algorithm in the initial stage is used to efficiently traverse and roughly adjust the parameter space to accelerate the convergence efficiency. Then, the second calibration process (further calibration) is performed through the simulated annealing algorithm to refine the above solution, avoid local optimality, and ensure accurate and optimal adjustment of the parameters.

[0069] In summary, this application achieves a balance between speed and accuracy by combining the advantages of the logistic chaos algorithm and the simulated annealing algorithm, and can quickly converge to the global optimal solution, solving the current problem of being unable to efficiently and accurately calibrate electromagnetic characteristic parameters.

[0070] See also Figure 2 Specifically, in the method described above, the step S102, i.e., performing a first calibration process on the initial electromagnetic characteristic parameters based on the logistic chaos algorithm to obtain reference electromagnetic characteristic parameters after the first calibration process, includes:

[0071] Step S201, linearly mapping the initial electromagnetic characteristic parameters to an interval of a logistic mapping;

[0072] Step S202, performing a first preset number of first iterations based on a recursive formula of the logistic mapping, and obtaining first electromagnetic characteristic parameters corresponding to each of the first iterations;

[0073] Step S203, obtaining a first loss function corresponding to each of the first iterations according to the first electromagnetic characteristic parameters;

[0074] Step S204: determine the first electromagnetic characteristic parameter corresponding to the minimum value in the first loss function as the reference electromagnetic characteristic parameter.

[0075] In this embodiment, since the interval range of the logistic mapping is [0,1], and the range of the initial electromagnetic characteristic parameters is [ε min ,ε max ], in order to facilitate the execution of the logistic chaos algorithm, the initial electromagnetic characteristic parameters are linearly mapped to the interval of the logistic mapping through the first preset algorithm, wherein the first preset algorithm can be expressed as:

[0076]

[0077] Among them, x i is the logistic mapping value corresponding to the electromagnetic characteristic parameter in the i-th iteration; ε i is the electromagnetic characteristic parameter corresponding to the i-th iteration.

[0078] Then, based on the recursive formula of the logistic mapping, a first preset number of first iterations are performed, and the first electromagnetic characteristic parameters corresponding to each first iteration are obtained, wherein the recursive formula can be expressed as: i+1 =4x i (1-x i ), where x i+1 is the logistic mapping value corresponding to the electromagnetic characteristic parameter in the i+1th iteration; the first preset number is preferably an integer greater than or equal to 10. After 10 algorithm iterations, the sample space is basically traversed once, and setting the first preset number to an integer greater than or equal to 10 is conducive to ensuring the search range and avoiding omissions.

[0079] Furthermore, the first loss function corresponding to each first iteration in the communication scenario can be obtained based on the first electromagnetic characteristic parameters corresponding to each first iteration; and the first electromagnetic characteristic parameters corresponding to the minimum value in the first loss function are determined as reference electromagnetic characteristic parameters, so that they can be output to the simulated annealing algorithm for the next step of calculation.

[0080] See also Figure 3 Specifically, in the method described above, the step S103, i.e., performing a second calibration process on the reference electromagnetic characteristic parameters based on the simulated annealing algorithm to obtain the target electromagnetic characteristic parameters after the second calibration process, includes:

[0081] Step S301, setting the reference electromagnetic characteristic parameter to the initial value of the solution in the simulated annealing algorithm, the iteration threshold to the second preset number, the loss function threshold to the first threshold, and the control parameter to be related to the initial electromagnetic characteristic parameter; wherein the control parameter can be expressed as T = |ε i -ε initial |.

[0082] Step S302, performing a second iteration, generating a second solution based on the initial value and the uniformly distributed first random variable, or generating a second solution based on the first solution in the previous second iteration and the uniformly distributed first random variable, wherein the first random variable is related to the accuracy of the target electromagnetic characteristic parameter, for example, the first random variable belongs to [-ε rand ,ε rand ], where ε rand The value is positive and is determined by the accuracy required for calibration. The higher the accuracy, the greater the rand The smaller the value of . By generating the second solution based on the first random variable, the accuracy of the final solution can be effectively guaranteed. In one embodiment, the second solution is the sum of the first solution and the first random variable.

[0083] Step S303, according to the Metropolis criterion and the control parameter, determine that the second solution or the first solution in the previous second iteration is the first solution in the current second iteration; in this step, the final value corresponding to the current iteration is determined by the Metropolis criterion, which is helpful to avoid falling into a local optimum.

[0084] Step S304: if the loss function corresponding to the first solution in the current second iteration is less than the first threshold, or the number of iterations reaches the second preset number, the first solution is determined to be the target electromagnetic characteristic parameters. In this step, if the loss function of the first solution currently obtained is less than the first threshold, it is determined that the algorithm has converged at this time, so the first solution is determined to be the required target electromagnetic characteristic parameters; if the number of iterations reaches the preset second preset number, it means that the iteration number requirement has been met, which is equivalent to considering that the algorithm has converged, so the first solution is determined to be the required target electromagnetic characteristic parameters.

[0085] It should also be noted that if the loss function corresponding to the first solution in the current second iteration is greater than or equal to the threshold, and the number of iterations has not reached the second preset number, it means that the current algorithm has not converged, so it is necessary to increase the number of iterations by one, and return to execute the step of generating a second solution based on the first solution in the previous second iteration and the uniformly distributed first random variable, and start the next iteration.

[0086] See also Figure 4 Further, for the convenience of understanding by those skilled in the art, the method described above is exemplified herein for step S303, i.e., the step of determining, according to the Metropolis criterion and the control parameter, the second solution or the first solution in the previous second iteration as the first solution in the current second iteration, which includes:

[0087] Step S401, obtaining a second loss function corresponding to the first solution in the previous second iteration and a third loss function corresponding to the second solution;

[0088] Step S402, obtaining a loss function difference of the third loss function minus the second loss function;

[0089] Step S403: if the loss function difference is less than zero, determining the second solution as the first solution in the current second iteration;

[0090] Step S404, if the loss function difference is greater than or equal to zero, determining a reference probability according to the loss function difference and the control parameter, and generating a second random variable with uniform distribution;

[0091] Step S405: if the second random variable is less than the reference probability, determine the second solution as the first solution in the current second iteration; otherwise, determine the first solution in the previous second iteration as the first solution in the current second iteration.

[0092] In this embodiment, when determining the first solution in the current second iteration according to the Metropolis criterion and the control parameter, first obtain the second loss function corresponding to the first solution in the previous second iteration and the third loss function corresponding to the second solution, and subtract the second loss function from the third loss function to obtain the loss function difference, which can be used to indicate whether the second solution generated by the current second iteration is better than the first solution in the previous second iteration. If the loss function difference is less than zero, it is determined that the second solution generated by the current second iteration is better than the first solution in the previous second iteration, so the second solution is determined to be the first solution in the current second iteration; otherwise, the second solution is probabilistically accepted as the first solution in the current second iteration. Specifically, it can be expressed as determining a reference probability based on the loss function difference and the control parameter, and generating a uniformly distributed second random variable, and then judging the reference probability and the second random variable. If the second random variable is less than the reference probability, the second solution is determined to be the first solution in the current second iteration, otherwise, the first solution in the previous second iteration is determined to be the first solution in the current second iteration.

[0093] When the loss function difference is greater than or equal to zero, the judgment based on the second random variable and the reference probability can be expressed as:

[0094]

[0095] Among them, rand(·) is the second random variable, is the reference probability, ΔC is the loss function difference, and T is the control parameter.

[0096] See also Figure 5 Preferably, in the method as described above, the step of obtaining the loss function corresponding to the target iteration includes:

[0097] Step S501, obtaining simulated path loss data and real path loss data corresponding to each user terminal in the communication scenario according to the electromagnetic characteristic parameters corresponding to the target iteration, wherein the simulated path loss data is determined based on ray tracing simulation, and the real path loss data is determined based on impulse response;

[0098] Step S502, obtaining a path loss error corresponding to each of the user terminals in the target iteration according to the simulated path loss data and the real path loss data;

[0099] Step S503, determining a distance weight corresponding to each of the user terminals according to the terminal position and the base station position in the communication scenario;

[0100] Step S504: Calculate the loss function corresponding to the target iteration based on the distance weight and the path loss error corresponding to each of the user terminals, wherein the loss function is a weighted sum of the path loss errors in the target iteration.

[0101] In this embodiment, the steps of obtaining the loss function involved in the above two algorithms are illustrated, wherein the iteration for obtaining the loss function is recorded as the target iteration, which is the first iteration in the logistic chaos algorithm or the previous second iteration in the simulated annealing algorithm (i.e., the iteration corresponding to the second loss function) or the current second iteration (i.e., the iteration corresponding to the third loss function).

[0102] In the communication scenario, RT simulation and impulse response are performed based on the electromagnetic characteristic parameters corresponding to the target iteration to obtain the simulated path loss data and the actual path loss data corresponding to each user terminal. After obtaining the simulated path loss data and the actual path loss data corresponding to each user terminal, the path loss error corresponding to each user terminal can be obtained by making a difference, and then the loss function can be determined according to the path loss difference.

[0103] Furthermore, since the traditional electromagnetic environment reconstruction method often evenly distributes distance weights to all user terminals when calculating the loss function, the distance distribution between user terminals is not considered. This method may introduce deviations when processing short-distance and long-distance measurement points, because the propagation characteristics of wireless signals often vary significantly at different distances. The traditional average distribution distance weight method cannot effectively handle this sparsity, resulting in a decrease in the prediction accuracy of the model at a specific distance segment. Therefore, in this embodiment, the distance weight corresponding to each user terminal is determined according to the terminal position and base station position in the communication scenario; and then the loss function corresponding to the target iteration is calculated according to the distance weight and path loss error corresponding to each user terminal. By introducing a weighted fitting method and considering the sparse distribution characteristics of the user terminal distance, the stability of the electromagnetic environment reconstruction at different propagation distances is enhanced, the speed of electromagnetic environment reconstruction is accelerated, the model deviation is reduced, and the electromagnetic environment reconstruction result is more reliable.

[0104] In one embodiment, the loss function is the weighted sum of the path loss errors in the target iteration, which can be expressed as: Where C is the loss function; ω n is the distance weight corresponding to the nth user terminal, and n∈[1,N b ],N b is the total number of user terminals; PLn is the path loss error corresponding to the nth user terminal.

[0105] It should be noted that the method for obtaining the simulated path loss data and the real path loss data in this embodiment can be implemented by conventional technical means in the prior art, so it will not be described in detail here.

[0106] See also Figure 6 Specifically, in the method described above, step S503, i.e., determining the distance weight corresponding to each user terminal according to the terminal position and the base station position in the communication scenario, includes:

[0107] Step S601, determining a distance parameter between each user terminal and a base station according to the terminal position and the base station position;

[0108] Step S602, performing equal distance division according to the distance parameter to obtain a plurality of distance ranges, wherein the number of the distance ranges is related to the total number of the user terminals;

[0109] Step S603: determining the distance weight corresponding to each user terminal according to the total number of the user terminals, the number of the distance ranges, and the number of the user terminals within the distance range where each user terminal is located.

[0110] In this embodiment, an example is given of how to determine the distance weight corresponding to each user terminal according to the terminal position and the base station position in the communication scenario, wherein first, the distance parameter between each user terminal and the base station is determined according to the terminal position and the base station position, and the distance parameter includes but is not limited to the distance and the value after a simple operation on the distance, wherein the value after a simple operation on the distance can be one of: logarithmic distance, distance square, etc. In this embodiment, logarithmic distance is preferably used, for example: log 10 (d), where d is the distance between the user terminal and the base station.

[0111] Then, equal distance division is performed according to the distance parameter to obtain a plurality of distance ranges, wherein the number of distance ranges is related to the total number of user terminals, for example, the number of distance ranges is approximately one quarter of the total number of user terminals;

[0112] Finally, according to the total number of user terminals, the number of distance ranges, and the number of user terminals within the distance range where each user terminal is located, the distance weight corresponding to each user terminal is determined, which can be specifically expressed as:

[0113]

[0114] Among them, N b is the total number of user terminals;

[0115] N is the number of distance ranges;

[0116] N s is the number of user terminals within the sth distance range, and s∈[1,N];

[0117] ω n is the distance weight corresponding to the nth user terminal, and n∈[1,N b ].

[0118] See also Figure 7 Another embodiment of the present application further provides a control device for electromagnetic environment reconstruction based on electromagnetic characteristic parameter calibration, comprising:

[0119] The parameter acquisition module 701 is used to acquire the initial electromagnetic characteristic parameters in the pre-built communication scenario;

[0120] A first calibration processing module 702 is used to perform a first calibration process on the initial electromagnetic characteristic parameters based on a logistic chaos algorithm to obtain reference electromagnetic characteristic parameters after the first calibration process;

[0121] The second calibration processing module 703 is used to perform a second calibration process on the reference electromagnetic characteristic parameters based on a simulated annealing algorithm to obtain target electromagnetic characteristic parameters after the second calibration process.

[0122] The electromagnetic environment construction module 704 is used to obtain corresponding electromagnetic field data based on the target electromagnetic characteristic parameters, scatterer location information and signal strength transmitted by the base station, and construct an electromagnetic environment according to the electromagnetic field data.

[0123] See also Figure 8 Specifically, in the control device as described above, the first calibration processing module 702 includes:

[0124] A mapping unit 801, used for linearly mapping the initial electromagnetic characteristic parameters to an interval of a logistic mapping;

[0125] A first iteration unit 802 is used to perform a first preset number of first iterations based on a recursive formula of a logistic mapping, and obtain first electromagnetic characteristic parameters corresponding to each of the first iterations;

[0126] A first loss function acquisition unit 803 is used to acquire a first loss function corresponding to each first iteration according to the first electromagnetic characteristic parameter;

[0127] The reference electromagnetic characteristic parameter determining unit 804 is used to determine the first electromagnetic characteristic parameter corresponding to the minimum value in the first loss function as the reference electromagnetic characteristic parameter.

[0128] See also Fig. 9 Specifically, in the control device as described above, the second calibration processing module 703 includes:

[0129] An iterative initialization unit 901 is used to set the reference electromagnetic characteristic parameter to the initial value of the solution in the simulated annealing algorithm, the loss function threshold to the first threshold, the iteration threshold to the second preset number, and the control parameter to be related to the initial electromagnetic characteristic parameter;

[0130] A second solution generating unit 902 is used to perform a second iteration, generate a second solution according to an initial value and a uniformly distributed first random variable, or generate a second solution according to a first solution in a previous second iteration and a uniformly distributed first random variable, wherein the first random variable is related to the accuracy of the electromagnetic characteristic parameter;

[0131] A first solution determining unit 903 is configured to determine, according to the Metropolis criterion and the control parameter, the second solution or the first solution in the previous second iteration as the first solution in the current second iteration;

[0132] The target electromagnetic characteristic parameter determination unit 904 is used to determine that the first solution is the target electromagnetic characteristic parameter if the loss function corresponding to the first solution in the current second iteration is less than the first threshold, or the number of iterations reaches the second preset number.

[0133] See also Fig.10 Further, in the control device as described above, the first solution determining unit 903 includes:

[0134] A second loss function acquisition unit 1001 is used to acquire a second loss function corresponding to the first solution in the previous second iteration and a third loss function corresponding to the second solution;

[0135] A loss function difference obtaining unit 1002 is used to obtain a loss function difference of the third loss function minus the second loss function;

[0136] A judging unit 1003, configured to determine that the second solution is the first solution in the current second iteration if the loss function difference is less than zero;

[0137] If the loss function difference is greater than or equal to zero, determining a reference probability according to the loss function difference and the control parameter, and generating a second random variable with uniform distribution;

[0138] If the second random variable is less than the reference probability, the second solution is determined to be the first solution in the current second iteration; otherwise, the first solution in the previous second iteration is determined to be the first solution in the current second iteration.

[0139] See also Fig.11 Preferably, the first loss function acquisition unit 803 and the second loss function acquisition unit 1002 in the control device as described above further include:

[0140] A path loss data acquisition unit 1101 is used to acquire simulated path loss data and real path loss data corresponding to each user terminal in the communication scenario according to the electromagnetic characteristic parameters corresponding to the target iteration, wherein the simulated path loss data is determined based on ray tracing simulation, and the real path loss data is determined based on impulse response;

[0141] A path loss error acquisition unit 1102 is configured to acquire a path loss error corresponding to each of the user terminals in the target iteration according to the simulated path loss data and the real path loss data;

[0142] The distance weight determining unit 1103 determines the distance weight corresponding to each of the user terminals according to the terminal position and the base station position in the communication scenario;

[0143] The loss function calculation unit 1104 calculates the loss function corresponding to the target iteration based on the distance weight and the path loss error corresponding to each of the user terminals, wherein the loss function is the weighted sum of the path loss errors in the target iteration.

[0144] See also Fig.12 Specifically, the distance weight determination unit 1103 in the control device as described above includes:

[0145] The distance parameter determining unit 1201 is used to determine the distance parameter between each user terminal and the base station according to the terminal position and the base station position;

[0146] A distance division unit 1202 is configured to perform equal distance division according to the distance parameter to obtain a plurality of distance ranges, wherein the number of the distance ranges is related to the total number of the user terminals;

[0147] The weight calculation unit 1203 is used to determine the distance weight corresponding to each user terminal according to the total number of the user terminals, the number of the distance ranges, and the number of the user terminals within the distance range where each user terminal is located.

[0148] The control device embodiment of the electromagnetic environment reconstruction based on electromagnetic characteristic parameter calibration of the present application is a device corresponding to the embodiment of the electromagnetic environment reconstruction method based on electromagnetic characteristic parameter calibration described above. All implementation means in the above method embodiment are applicable to the embodiment of the device and can achieve the same technical effect. The above control device provided in the embodiment of the present application can implement all the method steps implemented in the above method embodiment and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as those in the method embodiment will not be described in detail here.

[0149] Another embodiment of the present application further provides an electronic device, including a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the steps of the electromagnetic environment reconstruction method based on electromagnetic characteristic parameter calibration as described above are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0150] Another embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the electromagnetic environment reconstruction method based on electromagnetic characteristic parameter calibration as described above are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0151] Another embodiment of the present application also provides a computer program product, including computer instructions, which, when executed by a processor, implement the steps of the electromagnetic environment reconstruction method based on electromagnetic characteristic parameter calibration as described above, and can achieve the same technical effect. To avoid repetition, they are not repeated here.

[0152] In addition, the present application may repeat reference numerals and / or letters in different examples. This repetition is for the purpose of simplicity and clarity, and does not in itself indicate the relationship between the various embodiments and / or settings discussed.

[0153] It should also be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusions.

[0154] The above is a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles described in the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for reconstructing an electromagnetic environment based on electromagnetic characteristic parameter calibration, characterized in that: include: Obtaining initial electromagnetic characteristic parameters in a pre-built communication scenario; Performing a first calibration process on the initial electromagnetic characteristic parameters based on a logistic chaos algorithm to obtain reference electromagnetic characteristic parameters after the first calibration process; Performing a second calibration process on the reference electromagnetic characteristic parameters based on a simulated annealing algorithm to obtain target electromagnetic characteristic parameters after the second calibration process; Corresponding electromagnetic field data are obtained based on the target electromagnetic characteristic parameters, scatterer position information and signal strength emitted by the base station, and an electromagnetic environment is constructed according to the electromagnetic field data.

2. The method according to claim 1, characterized in that The first calibration process is performed on the initial electromagnetic characteristic parameters based on the logistic chaos algorithm to obtain reference electromagnetic characteristic parameters after the first calibration process, including: Linearly mapping the initial electromagnetic characteristic parameters to an interval of a logistic mapping; Based on the recursive formula of the logistic mapping, performing a first preset number of first iterations, and obtaining first electromagnetic characteristic parameters corresponding to each of the first iterations; Acquire a first loss function corresponding to each of the first iterations according to the first electromagnetic characteristic parameter; The first electromagnetic characteristic parameter corresponding to the minimum value in the first loss function is determined as the reference electromagnetic characteristic parameter.

3. The method according to claim 1, characterized in that The second calibration process is performed on the reference electromagnetic characteristic parameters based on the simulated annealing algorithm to obtain the target electromagnetic characteristic parameters after the second calibration process, including: Setting the reference electromagnetic characteristic parameter to the initial value of the solution in the simulated annealing algorithm, the iteration threshold to the second preset number, the loss function threshold to the first threshold, and the control parameter to be related to the initial electromagnetic characteristic parameter; Perform a second iteration to generate a second solution based on the initial value and a uniformly distributed first random variable, or generate a second solution based on the first solution in the previous second iteration and a uniformly distributed first random variable, wherein the first random variable is related to the accuracy of the target electromagnetic characteristic parameter; Determine, according to the Metropolis criterion and the control parameter, the second solution or the first solution in the previous second iteration as the first solution in the current second iteration; If the loss function corresponding to the first solution in the current second iteration is less than the first threshold, or the number of iterations reaches the second preset number, the first solution is determined to be the target electromagnetic characteristic parameter.

4. The method according to claim 3, characterized in that The determining, according to the Metropolis criterion and the control parameter, that the second solution or the first solution in the previous second iteration is the first solution in the current second iteration includes: Obtain a second loss function corresponding to the first solution in the second iteration and a third loss function corresponding to the second solution; Obtaining a loss function difference of the third loss function minus the second loss function; If the loss function difference is less than zero, determining that the second solution is the first solution in the current second iteration; If the loss function difference is greater than or equal to zero, determining a reference probability according to the loss function difference and the control parameter, and generating a second random variable with uniform distribution; If the second random variable is less than the reference probability, the second solution is determined to be the first solution in the current second iteration; otherwise, the first solution in the previous second iteration is determined to be the first solution in the current second iteration.

5. The method according to claim 2 or 4, characterized in that: The steps to obtain the loss function corresponding to the target iteration include: According to the electromagnetic characteristic parameters corresponding to the target iteration, the simulated path loss data and the real path loss data corresponding to each user terminal in the communication scenario are obtained, wherein the simulated path loss data is determined based on ray tracing simulation, and the real path loss data is determined based on impulse response; Acquire a path loss error corresponding to each of the user terminals in the target iteration according to the simulated path loss data and the real path loss data; Determining a distance weight corresponding to each of the user terminals according to a terminal position and a base station position in the communication scenario; Based on the distance weight and the path loss error corresponding to each of the user terminals, the loss function corresponding to the target iteration is calculated, wherein the loss function is a weighted sum of the path loss errors in the target iteration.

6. The method according to claim 5, characterized in that The determining, according to the terminal position and the base station position in the communication scenario, a distance weight corresponding to each of the user terminals includes: Determining a distance parameter between each of the user terminals and the base station according to the terminal position and the base station position; Performing equal distance division according to the distance parameter to obtain a plurality of distance ranges, wherein the number of the distance ranges is related to the total number of the user terminals; The distance weight corresponding to each user terminal is determined according to the total number of the user terminals, the number of the distance ranges, and the number of the user terminals within the distance range where each user terminal is located.

7. A control device for electromagnetic environment reconstruction based on electromagnetic characteristic parameter calibration, characterized in that: include: A parameter acquisition module, used to acquire initial electromagnetic characteristic parameters in a pre-built communication scenario; A first calibration processing module, used for performing a first calibration process on the initial electromagnetic characteristic parameters based on a logistic chaos algorithm to obtain reference electromagnetic characteristic parameters after the first calibration process; A second calibration processing module, used for performing a second calibration processing on the reference electromagnetic characteristic parameters based on a simulated annealing algorithm to obtain target electromagnetic characteristic parameters after the second calibration processing; The electromagnetic environment construction module is used to obtain corresponding electromagnetic field data based on the target electromagnetic characteristic parameters, scatterer location information and signal strength transmitted by the base station, and to construct an electromagnetic environment according to the electromagnetic field data.

8. An electronic device, characterized in that: The invention comprises a processor, a memory and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps of the electromagnetic environment reconstruction method based on electromagnetic characteristic parameter calibration as described in any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the electromagnetic environment reconstruction method based on electromagnetic characteristic parameter calibration as described in any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The method comprises computer instructions, which, when executed by a processor, implement the steps of the electromagnetic environment reconstruction method based on electromagnetic characteristic parameter calibration as described in any one of claims 1 to 6.

Images