Time delay estimation model optimization method and system based on kernel density, medium and equipment

Abstract

The invention discloses a time delay estimation model optimization method and system based on kernel density, a medium and equipment, and the method comprises the steps: obtaining time delay related data of a power distribution network communication network, and the time delay related data comprises the number of access subjects of the power distribution network communication network, the kernel density function bandwidth and a time delay measurement value; constructing a time delay estimation model of the power distribution network communication network by adopting a non-parametric kernel density estimation method according to the time delay related data; and optimizing the fixed bandwidth of the time delay estimation model by adopting a Gaussian kernel function and a geometric distance to obtain a time delay estimation optimization model. Under the condition of multivariate main body access, the adaptive nonparametric kernel density estimation method is utilized to adjust the time delay estimation model, the probability density function is estimated according to the characteristics of the data, different characteristics in the data are conveniently captured, and the obtained time delay estimation model of the communication network of the power distribution network is high in data processing precision and high in reliability. The method has good engineering application value.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution network, and in particular to a kernel density-based time delay estimation model optimization method, system, medium and equipment. Background Art

[0002] The dispatching and protection of power systems rely on accurate communication networks. Delays affect the sending and response of commands, which is crucial for the stability and efficiency of distributed energy and smart grids. As the construction of new power systems gradually advances, new elements such as distributed power sources, controllable loads, microgrids, virtual power plants, and charging and swapping infrastructure are connected on a large scale. The number of distribution network business terminals has increased significantly, and the data transmission and processing pressure of the distribution network communication network has also increased, and the requirements for distribution network delay estimation have also increased. Selecting a suitable delay estimation model for the distribution network communication network system can improve the stability and reliability of the signal during transmission and improve the communication quality. Accurate delay estimation helps to reduce resource waste and repeated transmission caused by delays during information transmission, and improve the overall efficiency of the distribution network communication system. By analyzing the changes in signal transmission delays, the fault location can be located faster and measures can be taken. In addition, accurate delay estimation can also better allocate system resources.

[0003] However, the existing methods for estimating the time delay of the communication network of the distribution network only consider the access of a few entities, which cannot meet the requirements of diverse distribution network scenarios, large data volumes, and rapid processing, and the data processing efficiency and response speed are insufficient. For example, in terms of processing and analyzing time delay data, traditional thinking usually uses parameter estimation as a common method. The parameter estimation method requires a priori assumptions about the distribution form of the sample data, and infers the parameter values ​​of the distribution based on the sample data, but it cannot process a large amount of data that does not conform to the assumed distribution form. The accuracy of data processing and analysis decreases with the increase in the amount of data, making it difficult for the model to adapt to the complex and heterogeneous data flow characteristics in the large-scale access scenario of multiple entities in the distribution network. Therefore, it is urgent to adjust the current delay estimation model to adapt to the new changes in the distribution network. Summary of the invention

[0004] The present invention provides a kernel density-based time delay estimation model optimization method, system, medium and device, which use an adaptive non-parametric kernel density estimation method to adjust the time delay estimation model, estimate the probability density function according to the characteristics of the data itself, and facilitate capturing different features in the data. The bandwidth of the kernel density function is automatically adjusted according to the sample. The obtained distribution network communication network delay estimation model has high data processing accuracy and good engineering application value.

[0005] In order to achieve the above object, an embodiment of the present invention provides a delay estimation model optimization method based on kernel density, including:

[0006] Acquire delay-related data of the distribution network communication network, wherein the delay-related data includes the number of access entities of the distribution network communication network, the kernel density function bandwidth and the delay measurement value;

[0007] Based on the delay-related data, a delay estimation model of the distribution network communication network is constructed using a non-parametric kernel density estimation method;

[0008] The fixed bandwidth of the delay estimation model is optimized by using a Gaussian kernel function and a geometric distance to obtain a delay estimation optimization model.

[0009] As an improvement of the above solution, the expression of the delay estimation model is:

[0010]

[0011] In the formula, is the estimated value of the kernel density f(x), x is the delay measurement value, n is the number of access entities, and x i is the delay measurement value of the ith access subject, h is the bandwidth of the kernel density function, and K(*) is the kernel function.

[0012] As an improvement of the above solution, the fixed bandwidth of the delay estimation model is optimized by using Gaussian kernel function and geometric distance to obtain a delay estimation optimization model, including:

[0013] Using a Gaussian kernel function to perform kernel density estimation to obtain a fixed bandwidth of the delay estimation model;

[0014] A geometric distance of the delay measurement value is obtained, and the fixed bandwidth is optimized using the geometric distance to obtain a delay estimation optimization model.

[0015] As an improvement of the above solution, after obtaining the delay estimation optimization model, the method further includes:

[0016] Solve the delay estimation optimization model to obtain the delay estimation value of the distribution network communication network.

[0017] As an improvement of the above solution, the expression of the delay estimation optimization model is:

[0018]

[0019] In the formula, is the estimated value of the kernel density f(x), x is the delay measurement value, n is the number of access entities, and x i is the delay measurement value of the ith access subject, H li is the bandwidth of the sample interval l of the delay measurement value of the i-th access subject, and K(*) is the kernel function.

[0020] As an improvement of the above solution, the expression of the fixed bandwidth is:

[0021]

[0022] In the formula, H m is the fixed bandwidth, n is the number of access entities, is the standard deviation of the delay measurement value.

[0023] As an improvement of the above solution, the expression of the delay measurement value is:

[0024]

[0025] In the formula, x i is the delay measurement value of the ith access subject, T 1i is the signal sending time, T 2i is the time when the signal returns to the sending end, T P is the delay value from the receiving end receiving the signal to the sending of the return signal, is a fixed constant, and n is the number of access entities.

[0026] As an improvement of the above solution, the expression of the geometric distance is:

[0027]

[0028] Where, d Si (H m ) is the geometric distance of the delay measurement value of the i-th access subject, H m is the fixed bandwidth, is the kernel density f(x i ), x i is the delay measurement value of the i-th access subject.

[0029] In order to achieve the above object, an embodiment of the present invention provides a kernel density-based delay estimation model optimization system, including:

[0030] A delay data acquisition module, used to acquire delay-related data of the distribution network communication network, wherein the delay-related data includes the number of access entities of the distribution network communication network, the kernel density function bandwidth and the delay measurement value;

[0031] A delay model building module, used to build a delay estimation model of the distribution network communication network according to the delay-related data by using a non-parametric kernel density estimation method;

[0032] The delay model optimization module is used to optimize the fixed bandwidth of the delay estimation model by using a Gaussian kernel function and a geometric distance to obtain a delay estimation optimization model.

[0033] As an improvement of the above solution, the delay model optimization module is used to:

[0034] Using a Gaussian kernel function to perform kernel density estimation to obtain a fixed bandwidth of the delay estimation model;

[0035] A geometric distance of the delay measurement value is obtained, and the fixed bandwidth is optimized using the geometric distance to obtain a delay estimation optimization model.

[0036] In order to achieve the above-mentioned purpose, an embodiment of the present invention further provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the above-mentioned kernel density-based delay estimation model optimization method.

[0037] In order to achieve the above-mentioned objectives, an embodiment of the present invention provides a kernel density-based delay estimation model optimization device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, the above-mentioned kernel density-based delay estimation model optimization method is implemented.

[0038] Compared with the prior art, the embodiment of the present invention discloses a method, system, medium and device for optimizing a delay estimation model based on kernel density, which obtains delay-related data of a distribution network communication network, wherein the delay-related data includes the number of access subjects of the distribution network communication network, the bandwidth of the kernel density function and the delay measurement value; according to the delay-related data, a non-parametric kernel density estimation method is used to construct a delay estimation model of the distribution network communication network; and a Gaussian kernel function and geometric distance are used to optimize the fixed bandwidth of the delay estimation model to obtain a delay estimation optimization model. In the case of multi-subject access, the delay estimation model can be adjusted using an adaptive non-parametric kernel density estimation method, which does not need to rely on the prior distribution assumption of the data, but estimates the probability density function based on the characteristics of the data itself, so as to capture different features in the data. At the same time, the delay estimation model can also automatically adjust the bandwidth of the kernel density function according to the sample, and the obtained distribution network communication network delay estimation model has high data processing accuracy and good engineering application value. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a flowchart of a delay estimation model optimization method based on kernel density provided by an embodiment of the present invention;

[0040] Figure 2 It is a structural schematic diagram of a kernel density-based delay estimation model optimization system provided by an embodiment of the present invention;

[0041] Figure 3 It is a structural schematic diagram of a kernel density-based delay estimation model optimization device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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.

[0043] It should be noted that the terms "comprises" and "specifically" and any variations of the present invention are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products or apparatuses.

[0044] Embodiment 1

[0045] See also Figure 1 , Figure 1 1 is a flow chart of a method for optimizing a delay estimation model based on kernel density provided by an embodiment of the present invention. The method for optimizing a delay estimation model based on kernel density includes:

[0046] S1, obtaining delay-related data of the distribution network communication network, wherein the delay-related data includes the number of access entities of the distribution network communication network, the kernel density function bandwidth and the delay measurement value;

[0047] S2, constructing a delay estimation model of the distribution network communication network using a non-parametric kernel density estimation method based on the delay-related data;

[0048] S3, using Gaussian kernel function and geometric distance to optimize the fixed bandwidth of the delay estimation model to obtain a delay estimation optimization model.

[0049] Exemplarily, the kernel density-based delay estimation model optimization method described in the embodiment of the present invention takes into account the delay estimation in the case of multiple subject access, which is more in line with the actual situation of multiple devices connected at the same time and complex interactions in the new power system, making the delay estimation more comprehensive and accurate. The non-parametric kernel density estimation method is applied, which can capture different features in the data, so as to more flexibly process the data in the actual distribution network communication network. The adaptive kernel density function bandwidth is selected to improve the adaptability and flexibility of the delay estimation model.

[0050] Specifically, the expression of the delay estimation model is:

[0051]

[0052] In the formula, is the estimated value of the kernel density f(x), x is the delay measurement value, n is the number of access entities, and x i is the delay measurement value of the ith access subject, h is the bandwidth of the kernel density function, and K(*) is the kernel function.

[0053] Specifically, the step S3 includes:

[0054] S31, performing kernel density estimation using a Gaussian kernel function to obtain a fixed bandwidth of the delay estimation model;

[0055] S32, obtaining a geometric distance of the delay measurement value, and optimizing the fixed bandwidth by using the geometric distance to obtain a delay estimation optimization model.

[0056] For example, a Gaussian kernel function is used for kernel density estimation. When the average integrated mean square error takes the minimum value, the bandwidth H is obtained. m As a fixed optimal bandwidth, the expression of the fixed bandwidth is:

[0057]

[0058] In the formula, H m is the fixed bandwidth, n is the number of access entities, is the standard deviation of the delay measurement value.

[0059] By fixing the bandwidth H m The delay estimation model obtained has a low local fitting accuracy. Therefore, it is necessary to adjust the kernel function bandwidth of some intervals in a targeted manner. For example, let d Si (H m ) is the geometric distance of the delay measurement value of the i-th access subject, and the expression of the geometric distance is:

[0060]

[0061] In the formula, is the kernel density f(x i ), x i is the delay measurement value of the i-th access subject.

[0062] For any sample interval l∈[l 1 ,l 2 ](where l 2 > 1 And l 1 ,l 2 ∈[1,n]), if the following inequality is satisfied, then the sample interval is said to have a local adaptability problem.

[0063]

[0064] Where, d Sl (H m ) is the geometric distance within the sample interval l of any delay measurement value; is the average geometric distance of the entire sample space; λ is the adjustment coefficient. The smaller λ is, the stricter the screening is and the more intervals need to be adjusted. This can improve the modeling accuracy but greatly increase the complexity of model solution. The larger λ is, the lower the complexity of solution is, but the model accuracy will also decrease. The specific value can be determined according to the actual test situation.

[0065] The average geometric distance The mathematical expression of is:

[0066]

[0067] For the interval with local adaptability problems, the fixed bandwidth is optimized, and the expression of the optimized fixed bandwidth is:

[0068]

[0069] In the formula, H l is the bandwidth of the sample interval l; n l is the number of samples in the sample interval l; d S (H m ) mid is the median of the geometric distance within the sample interval l; δ is the kernel function threshold.

[0070] It is worth mentioning that kernel density estimation (KDE) is a non-parametric method used to estimate the probability density function of data. KDE is based on the kernel function, with a certain bandwidth parameter, and estimates the probability density of data points by weighted averaging the kernel function near each data point, that is, inferring the population based on a limited data sample. For each data point, a kernel density function is constructed using a kernel function (such as a Gaussian kernel function) with the point as the center. By calculating the kernel density function value of each data point and weighted averaging them, the overall probability density function estimate is obtained.

[0071] Furthermore, after obtaining the delay estimation optimization model, the method further includes:

[0072] Solve the delay estimation optimization model to obtain the delay estimation value of the distribution network communication network.

[0073] Specifically, the expression of the delay estimation optimization model is:

[0074]

[0075] In the formula, is the estimated value of the kernel density f(x), x is the delay measurement value, n is the number of access entities, and x i is the delay measurement value of the ith access subject, H li is the bandwidth of the sample interval l of the delay measurement value of the i-th access subject, and K(*) is the kernel function.

[0076] Specifically, the expression of the fixed bandwidth is:

[0077]

[0078] In the formula, H m is the fixed bandwidth, n is the number of access entities, is the standard deviation of the delay measurement value.

[0079] Specifically, the expression of the delay measurement value is:

[0080]

[0081] In the formula, x i is the delay measurement value of the ith access subject, T 1i is the signal sending time, T 2i is the time when the signal returns to the sending end, T P is the delay value from the receiving end receiving the signal to the sending of the return signal, is a fixed constant, and n is the number of access entities.

[0082] Specifically, the expression of the geometric distance is:

[0083]

[0084] Where, d Si (H m ) is the geometric distance of the delay measurement value of the i-th access subject, H m is the fixed bandwidth, is the kernel density f(x i ), x i is the delay measurement value of the i-th access subject.

[0085] The embodiment of the present invention discloses a method for optimizing a delay estimation model based on kernel density, which obtains delay-related data of a distribution network communication network, wherein the delay-related data includes the number of access subjects of the distribution network communication network, the bandwidth of the kernel density function, and the delay measurement value; based on the delay-related data, a non-parametric kernel density estimation method is used to construct a delay estimation model of the distribution network communication network; and a Gaussian kernel function and geometric distance are used to optimize the fixed bandwidth of the delay estimation model to obtain a delay estimation optimization model. In the case of multi-subject access, the delay estimation model can be adjusted using an adaptive non-parametric kernel density estimation method, without relying on the prior distribution assumption of the data, but estimating the probability density function based on the characteristics of the data itself, so as to capture different features in the data. At the same time, the delay estimation model can also automatically adjust the bandwidth of the kernel density function based on the sample, and the obtained distribution network communication network delay estimation model has high data processing accuracy and good engineering application value.

[0086] Embodiment 2

[0087] See also Figure 2 , Figure 2 1 is a schematic diagram of a structure of a kernel density-based delay estimation model optimization system 10 provided in an embodiment of the present invention. The kernel density-based delay estimation model optimization system 10 includes:

[0088] The delay data acquisition module 11 is used to acquire the delay-related data of the distribution network communication network, wherein the delay-related data includes the number of access entities of the distribution network communication network, the kernel density function bandwidth and the delay measurement value;

[0089] A delay model building module 12 is used to build a delay estimation model of the distribution network communication network according to the delay related data by using a non-parametric kernel density estimation method;

[0090] The delay model optimization module 13 is used to optimize the fixed bandwidth of the delay estimation model by using a Gaussian kernel function and a geometric distance to obtain a delay estimation optimization model.

[0091] Specifically, the delay model optimization module 13 is used to:

[0092] Using a Gaussian kernel function to perform kernel density estimation to obtain a fixed bandwidth of the delay estimation model;

[0093] A geometric distance of the delay measurement value is obtained, and the fixed bandwidth is optimized using the geometric distance to obtain a delay estimation optimization model.

[0094] Furthermore, the kernel density-based delay estimation model optimization system 10 further includes:

[0095] The delay model solving module is used to solve the delay estimation optimization model to obtain the delay estimation value of the distribution network communication network.

[0096] A kernel density-based delay estimation model optimization system 10 provided in an embodiment of the present invention can implement all the processes of the kernel density-based delay estimation model optimization method of the above-mentioned embodiment. The functions of each module in the system and the technical effects achieved are respectively the same as the functions and technical effects achieved by the kernel density-based delay estimation model optimization method of the above-mentioned embodiment, and will not be repeated here.

[0097] An embodiment of the present invention also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the kernel density-based delay estimation model optimization method as described in the above embodiment.

[0098] See also Figure 3 , Figure 3 It is a structural diagram of a delay estimation model optimization device 20 based on kernel density provided in an embodiment of the present invention. The delay estimation model optimization device 20 based on kernel density of this embodiment includes: a processor 21, a memory 22, and a computer program stored in the memory 22 and executable on the processor 21. When the processor 21 executes the computer program, the steps in the above-mentioned delay estimation model optimization method embodiment based on kernel density are implemented. Alternatively, when the processor 21 executes the computer program, the functions of each module in the above-mentioned delay estimation model optimization system embodiment based on kernel density are implemented.

[0099] Exemplarily, the computer program may be divided into one or more modules, which are stored in the memory 22 and executed by the processor 21 to complete the present invention. The one or more modules may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program in the kernel density-based delay estimation model optimization device 20.

[0100] The kernel density-based delay estimation model optimization device 20 may be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The kernel density-based delay estimation model optimization device 20 may include, but is not limited to, a processor 21 and a memory 22. Those skilled in the art may understand that the schematic diagram is merely an example of the kernel density-based delay estimation model optimization device 20 and does not constitute a limitation on the kernel density-based delay estimation model optimization device 20. It may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, the kernel density-based delay estimation model optimization device 20 may also include input and output devices, network access devices, buses, etc.

[0101] The processor 21 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor 21 is the control center of the kernel density-based delay estimation model optimization device 20, and uses various interfaces and lines to connect various parts of the entire kernel density-based delay estimation model optimization device 20.

[0102] The memory 22 can be used to store the computer program and / or module. The processor 21 implements various functions of the kernel density-based delay estimation model optimization device 20 by running or executing the computer program and / or module stored in the memory 22 and calling the data stored in the memory 22. The memory 22 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.). In addition, the memory 22 can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0103] Wherein, if the module integrated in the kernel density-based delay estimation model optimization device 20 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor 21. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practices in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practices, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0104] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, 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. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0105] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A kernel density-based delay estimation model optimization method, characterized in that: include: Acquire delay-related data of the distribution network communication network, wherein the delay-related data includes the number of access entities of the distribution network communication network, the kernel density function bandwidth and the delay measurement value; Based on the delay-related data, a delay estimation model of the distribution network communication network is constructed using a non-parametric kernel density estimation method; The fixed bandwidth of the delay estimation model is optimized by using a Gaussian kernel function and a geometric distance to obtain a delay estimation optimization model.

2. The method for optimizing a delay estimation model based on kernel density according to claim 1, wherein: The expression of the delay estimation model is: In the formula, is the estimated value of the kernel density f(x), x is the delay measurement value, n is the number of access entities, and x i is the delay measurement value of the ith access subject, h is the bandwidth of the kernel density function, and K(*) is the kernel function.

3. The method for optimizing a delay estimation model based on kernel density according to claim 1, wherein: The method of optimizing the fixed bandwidth of the delay estimation model by using the Gaussian kernel function and the geometric distance to obtain the delay estimation optimization model includes: Using a Gaussian kernel function to perform kernel density estimation to obtain a fixed bandwidth of the delay estimation model; A geometric distance of the delay measurement value is obtained, and the fixed bandwidth is optimized using the geometric distance to obtain a delay estimation optimization model.

4. The method for optimizing a delay estimation model based on kernel density according to claim 1, wherein: After obtaining the delay estimation optimization model, the method further includes: Solve the delay estimation optimization model to obtain the delay estimation value of the distribution network communication network.

5. The method for optimizing a delay estimation model based on kernel density according to claim 1, wherein: The expression of the delay estimation optimization model is: In the formula, is the estimated value of the kernel density f(x), x is the delay measurement value, n is the number of access entities, and x i is the delay measurement value of the ith access subject, H li is the bandwidth of the sample interval l of the delay measurement value of the i-th access subject, and K(*) is the kernel function.

6. The kernel density-based delay estimation model optimization method according to claim 3, characterized in that: The expression of the fixed bandwidth is: In the formula, H m is the fixed bandwidth, n is the number of access entities, is the standard deviation of the delay measurement value.

7. The method for optimizing a delay estimation model based on kernel density according to claim 1, wherein: The expression of the delay measurement value is: In the formula, x i is the delay measurement value of the ith access subject, T 1i is the signal sending time, T 2i is the time when the signal returns to the sending end, T P is the delay value from the receiving end receiving the signal to the sending of the return signal, is a fixed constant, and n is the number of access entities.

8. The method for optimizing a delay estimation model based on kernel density according to claim 3, characterized in that: The expression of the geometric distance is: Where, d Si (H m ) is the geometric distance of the delay measurement value of the i-th access subject, H m is the fixed bandwidth, is the kernel density f(x i ), x i is the delay measurement value of the i-th access subject.

9. A kernel density-based delay estimation model optimization system, characterized in that: include: A delay data acquisition module, used to acquire delay-related data of the distribution network communication network, wherein the delay-related data includes the number of access entities of the distribution network communication network, the kernel density function bandwidth and the delay measurement value; A delay model building module, used to build a delay estimation model of the distribution network communication network according to the delay-related data by using a non-parametric kernel density estimation method; The delay model optimization module is used to optimize the fixed bandwidth of the delay estimation model by using a Gaussian kernel function and a geometric distance to obtain a delay estimation optimization model.

10. The kernel density-based delay estimation model optimization system according to claim 9, characterized in that: The delay model optimization module is used to: Using a Gaussian kernel function to perform kernel density estimation to obtain a fixed bandwidth of the delay estimation model; A geometric distance of the delay measurement value is obtained, and the fixed bandwidth is optimized using the geometric distance to obtain a delay estimation optimization model.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the kernel density-based delay estimation model optimization method according to any one of claims 1 to 8.

12. A kernel density-based delay estimation model optimization device, characterized in that: It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the kernel density-based delay estimation model optimization method as described in any one of claims 1 to 8.

Images