CN114760210A - Ship communication protocol simulation result quantitative evaluation method - Google Patents
Ship communication protocol simulation result quantitative evaluation method Download PDFInfo
- Publication number
- CN114760210A CN114760210A CN202210337528.2A CN202210337528A CN114760210A CN 114760210 A CN114760210 A CN 114760210A CN 202210337528 A CN202210337528 A CN 202210337528A CN 114760210 A CN114760210 A CN 114760210A
- Authority
- CN
- China
- Prior art keywords
- matrix
- principal component
- simulation
- communication protocol
- principal components
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Maintenance And Management Of Digital Transmission (AREA)
Abstract
The invention discloses a ship communication protocol simulation result quantitative evaluation method, which comprises the following steps: step 1, establishing a ship protocol simulation test scheme sample library based on an orthogonal design test design principle; step 2, collecting original data of protocol communication simulation tests by taking a plurality of protocols as simulation cases; step 3, carrying out normalization processing and principal component analysis on the data, establishing a characteristic matrix for the principal components, calculating the contribution rate and the accumulated contribution rate of the principal components, and selecting the principal components; and 4, training an SMO model by taking the characteristic value of the characteristic matrix as an input value, and establishing a quantitative relation between the characteristic value and the transmission parameter. The invention establishes standard parameters of an evaluation simulation test to make up for the deficiency of evaluation criteria; and establishing a quantitative relation between the test effect and each parameter, and training SMO simulation to achieve a quantitative evaluation target.
Description
Technical Field
The invention relates to the technical field of communication protocol simulation, in particular to a quantitative evaluation method for a ship communication protocol simulation result.
Background
With the increase of informatization integration level of a certain system, the composition scale, complexity and internal communication protocol types of the system are increased, the scale and complexity of the corresponding simulation system are also increased continuously, a large number of simulation tests are required, and the simulation data are evaluated. The evaluation process comprises multiple links of collecting test data, determining an evaluation object, establishing an evaluation criterion, executing the evaluation process, outputting an evaluation result and the like, and an evaluation index system and evaluation algorithm parameters are key links. Therefore, a quantification means is needed to promote the evaluation of the ship communication protocol simulation test result and support the evaluation and analysis of the joint debugging test result of a certain system.
Disclosure of Invention
The invention aims to solve the technical problem of providing a ship communication protocol simulation result quantitative evaluation method aiming at the defects in the prior art.
The technical scheme adopted by the invention for solving the technical problem is as follows:
the invention provides a ship communication protocol simulation result quantitative evaluation method, which comprises the following steps:
and 4, training an SMO model by taking the characteristic value of the characteristic matrix as an input value, and establishing a quantitative relation between the characteristic value and the transmission parameter.
Further, the protocol used as the simulation case in step 2 of the present invention includes: OPC _ DA, OPC _ UA, TCP, UDP, MQTT, MODBUS TCP, CoAP, HTTP.
Further, the method in step 3 of the present invention comprises:
constructing a matrix through the data samples obtained by testing, and arranging the matrix according to rows:
X=[X1,X2,…Xi…,Xn]
wherein:
Xi=[X1i,X2i,…Xii…,Xmi]T
where n represents the number of data samples and m represents the number of principal components.
Further, the method in step 3 of the present invention comprises:
carrying out normalization processing on the matrix:
averaging for each dimension:
subtracting the average value from each column of X to obtain a new matrix Y, and solving a covariance matrix through the following formula:
Further, the method in step 3 of the present invention comprises:
calculating the eigenvalue and eigenvector of the covariance matrix:
the eigenvalues of the covariance matrix cov are found and arranged in descending order, i.e., λ1>λ2>…>λn(ii) a At the same time, the eigenvector corresponding to the eigenvalue is obtained, and the characteristic matrix S ═ S is formed1,S2,…,Sn]。
Further, the method in step 3 of the present invention comprises:
calculating the principal component contribution rate and the accumulated contribution rate:
the contribution ratio is used for quantifying the proportion of the information amount contained in the principal component to the total information amount, and the calculation formula of the contribution ratio of each principal component is as follows:
the larger the contribution rate is, the more information contained in the principal component is shown, and a few principal components containing main information are screened out from all the principal components by adopting an accumulated contribution rate method; defining the cumulative contribution rate of the first m principal components as
Further, the method in step 3 of the present invention comprises:
the principal component linear transformation is represented as follows:
wherein F ═ F1,F2,…,Fm]TAll information of the observed quantity is contained in the set of each principal component; wherein a isijAs corresponding elements of the coefficient matrix, F1、F2、…、FmThe data are respectively a 1 st principal component, a 2 nd principal component, … th principal component and an m th principal component, and are arranged from big to small according to characteristic values, and information contained in each principal component is sequentially decreased; in order to extract all principal components as far as possible, the first m principal components with the accumulated contribution rate of more than 95% are selected, and a feature matrix is established.
Further, the method in step 4 of the present invention comprises:
selecting the eigenvalue of the selected eigen matrix as an input value, and taking the corresponding transmission parameter: and training an SMO model by taking the protocol type, the transmission speed and the data type as output values, so that the data of the characteristic vector can be separated in a high-order space, and establishing a mapping relation model between the characteristic vector and the transmission parameter, wherein the characteristic vector is a corresponding evaluation index, and the mapping model is an evaluation model.
The invention has the following beneficial effects: the quantitative evaluation method for the ship communication protocol simulation result comprises the steps of solving a covariance matrix of the matrix, further solving a contribution rate, obtaining main factors influencing a ship communication protocol simulation test, establishing standard parameters of the evaluation simulation test, and making up for the defects of the evaluation standard; secondly, establishing a quantitative relation between the test effect and each parameter, and simulating by training SMO until the quantitative relation is stable to reach a quantitative evaluation target; and thirdly, corresponding software is developed, and a protocol simulation test is carried out.
Drawings
The invention will be further described with reference to the accompanying drawings and examples, in which:
FIG. 1 is a business process flow diagram of an embodiment of the invention;
FIG. 2 is a diagram of a design protocol for an example of the present invention;
FIG. 3 is a graph of the results of the data normalization process according to the embodiment of the present invention;
fig. 4 is a diagram of the results of training the SMO model according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention.
The invention mainly solves two technical problems of quantitative evaluation of test results in a simulation test of a communication protocol of a system joint debugging ship:
one is an evaluation index, namely, the evaluation of test parameters can select main components which influence the test effect.
And the other is an evaluation model, namely modeling the evaluation index, and obtaining a convergence model based on the evaluation index through model training.
The invention provides a quantitative evaluation method for ship communication protocol simulation results, which is based on the problem of insufficient autonomous evaluation capability of ship communication protocol simulation test results in a certain system joint debugging test. Based on the orthogonal design test design principle, a ship protocol simulation test scheme sample library is established, OPC _ DA, OPC _ UA, TCP, UDP, MQTT, MODBUS TCP, CoAP and HTTP are used as simulation cases, original data of a protocol communication simulation test are collected, normalization processing and principal component analysis are carried out on the data, a feature matrix is established on the principal component, the feature value of the feature matrix is used as an input value, an SMO model is trained, the quantitative relation between the feature value and a transmission parameter is established, and evaluation of the ship communication protocol simulation test is realized.
The ship communication protocol simulation result quantitative evaluation method provided by the embodiment of the invention comprises the following steps:
1) constructing a simulation test sample library based on an orthogonal test design principle;
2) acquiring original data of a simulation test through ship communication protocol simulation;
3) carrying out normalization processing and principal component analysis on the data;
4) and carrying out quantitative evaluation on the simulation result data by adopting a two-classification support vector machine algorithm.
The algorithm flow in the step 3) is as follows:
a. constructing a matrix through the data samples obtained by testing, and arranging the matrix according to rows:
X=[X1,X2,…Xi…,Xn]
wherein:
Xi=[X1i,X2i,…Xii…,Xmi]T
b. carrying out normalization processing on the matrix:
averaging for each dimension:
subtracting the average value from each column of X to obtain a new matrix Y, and solving a covariance matrix through the following formula:
c. calculating eigenvalues and eigenvectors of the covariance matrix:
the eigenvalues of the covariance matrix cov are found and arranged in descending order, i.e., λ1>λ2>…>λn(ii) a At the same time, the eigenvector corresponding to the eigenvalue is obtained, and the characteristic matrix S ═ S is formed1,S2,…,Sn];
d. Calculating the principal component contribution rate and the accumulated contribution rate:
the contribution ratio is used for quantifying the proportion of the information amount contained in the principal component to the total information amount, and the calculation formula of the contribution ratio of each principal component is as follows:
the larger the contribution rate is, the more information contained in the principal component is shown, and a few principal components containing main information are screened out from all the principal components by adopting an accumulated contribution rate method; defining the cumulative contribution rate of the first m principal components as
e. Selecting principal components
The principal components are linearly transformed as follows:
F=[F1,F2,…,Fm]Tall information of the observed quantity is contained in the set of each principal component; wherein a isijAs corresponding elements of the coefficient matrix, F1、F2、…、FmRespectively are the 1 st principal component, the 2 nd principal component, … and the m th principal component, and are arranged according to the characteristic values from large to smallThe included information is decreased in sequence; in order to extract all principal components as far as possible, selecting the first m principal components with the accumulated contribution rate of more than 95 percent, and establishing a feature matrix;
in step 4), the eigenvalue of the selected eigen matrix is taken as an input value, and the corresponding transmission parameters are: and taking the protocol type, the transmission speed and the data type as output values, training the SMO model to enable the data of the feature vector to be separable in a high-order space, and establishing a mapping relation model between the feature vector and the transmission parameter. The feature vector is a corresponding evaluation index, and the mapping model is an evaluation model.
In another embodiment of the invention: the ship communication protocol simulation result quantitative evaluation method is used for ship communication protocol simulation test result evaluation.
In the ship communication protocol simulation test, the whole service process comprises the following steps: designing a test scheme, acquiring test data, carrying out data normalization processing, analyzing data principal components, establishing a feature matrix, training an SMO model by taking the value of the feature matrix as an input value until the error is close to 0, and showing a business flow chart in figure 1.
Firstly, designing a test scheme (figure 2) based on an orthogonal test design theory;
further selecting a certain scheme, developing a simulation test, and collecting test data;
further normalizing the collected data (fig. 3);
further performing principal component analysis and establishing a feature matrix;
further, the value of the feature matrix is used as an input value, the SMO model is trained until the error rate approaches zero, which indicates that the obtained feature matrix is stable and is a quantitative relation between the evaluation effect and the influence parameter (fig. 4).
It will be understood that modifications and variations can be made by persons skilled in the art in light of the above teachings and all such modifications and variations are intended to be included within the scope of the invention as defined in the appended claims.
Claims (8)
1. A ship communication protocol simulation result quantitative evaluation method is characterized by comprising the following steps:
step 1, establishing a ship protocol simulation test scheme sample library based on an orthogonal design test design principle;
step 2, collecting original data of a protocol communication simulation test by taking a plurality of protocols as simulation cases;
step 3, carrying out normalization processing and principal component analysis on the data, establishing a characteristic matrix for the principal components, calculating the contribution rate and the accumulated contribution rate of the principal components, and selecting the principal components;
And 4, training an SMO model by taking the characteristic value of the characteristic matrix as an input value, and establishing a quantitative relation between the characteristic value and the transmission parameter.
2. The method for quantitatively evaluating the simulation result of the ship communication protocol according to claim 1, wherein the protocol used as the simulation case in the step 2 comprises: OPC _ DA, OPC _ UA, TCP, UDP, MQTT, MODBUS TCP, CoAP, HTTP.
3. The method for quantitatively evaluating the simulation result of the ship communication protocol according to claim 1, wherein the method in the step 3 comprises:
constructing a matrix through the data samples obtained by testing, and arranging the matrix according to rows:
X=[X1,X2,…Xi…,Xn]
wherein:
Xi=[X1i,X2i,…Xii…,Xmi]T
where n represents the number of data samples and m represents the number of principal components.
4. The method for quantitatively evaluating the simulation result of the ship communication protocol according to claim 3, wherein the method in the step 3 comprises:
carrying out normalization processing on the matrix:
averaging for each dimension:
subtracting the average value from each column of X to obtain a new matrix Y, and solving a covariance matrix through the following formula:
5. the method for quantitatively evaluating the simulation result of the ship communication protocol according to claim 4, wherein the method in the step 3 comprises:
Calculating eigenvalues and eigenvectors of the covariance matrix:
the eigenvalues of the covariance matrix cov are found and arranged in descending order, i.e., λ1>λ2>…>λn(ii) a At the same time, the eigenvector corresponding to the eigenvalue is obtained, and the characteristic matrix S ═ S is formed1,S2,…,Sn]。
6. The method for quantitatively evaluating the simulation result of the ship communication protocol according to claim 5, wherein the method in the step 3 comprises:
calculating the principal component contribution rate and the accumulated contribution rate:
the contribution ratio is used for quantifying the proportion of the information amount contained in the principal component to the total information amount, and the calculation formula of the contribution ratio of each principal component is as follows:
the larger the contribution rate is, the more information contained in the principal component is shown, and a few principal components containing main information are screened out from all the principal components by adopting an accumulated contribution rate method; defining the cumulative contribution rate of the first m principal components as
7. The method for quantitatively evaluating the simulation result of the ship communication protocol according to claim 6, wherein the method in the step 3 comprises:
the principal component linear transformation is represented as follows:
wherein F ═ F1,F2,…,Fm]TAll information of the observed quantity is contained in the set of each principal component; wherein a isijAs corresponding elements of the coefficient matrix, F1、F2、…、FmThe data are respectively a 1 st principal component, a 2 nd principal component, … th principal component and an m th principal component, and are arranged from big to small according to characteristic values, and information contained in each principal component is sequentially decreased; in order to extract all principal components as far as possible, the first m principal components with the accumulated contribution rate of more than 95% are selected, and a feature matrix is established.
8. The method for quantitatively evaluating the simulation result of the marine communication protocol according to claim 1, wherein the method in the step 4 comprises:
selecting the eigenvalue of the selected eigen matrix as an input value, and taking the corresponding transmission parameter: and training an SMO model by taking the protocol type, the transmission speed and the data type as output values, so that the data of the characteristic vector can be separated in a high-order space, and establishing a mapping relation model between the characteristic vector and the transmission parameter, wherein the characteristic vector is a corresponding evaluation index, and the mapping model is an evaluation model.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210337528.2A CN114760210A (en) | 2022-03-31 | 2022-03-31 | Ship communication protocol simulation result quantitative evaluation method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210337528.2A CN114760210A (en) | 2022-03-31 | 2022-03-31 | Ship communication protocol simulation result quantitative evaluation method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114760210A true CN114760210A (en) | 2022-07-15 |
Family
ID=82329198
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210337528.2A Pending CN114760210A (en) | 2022-03-31 | 2022-03-31 | Ship communication protocol simulation result quantitative evaluation method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114760210A (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109831705A (en) * | 2019-02-22 | 2019-05-31 | 西安交通大学 | A kind of subjective QoE appraisal procedure for HTTP video stream traffic |
CN111046341A (en) * | 2019-12-12 | 2020-04-21 | 重庆地质矿产研究院 | Unconventional natural gas fracturing effect evaluation and capacity prediction method based on principal component analysis |
CN111163487A (en) * | 2019-12-31 | 2020-05-15 | 上海微波技术研究所(中国电子科技集团公司第五十研究所) | Method and system for evaluating comprehensive transmission performance of communication waveform |
CN111948279A (en) * | 2020-07-27 | 2020-11-17 | 南昌航空大学 | Quantitative evaluation method for weak magnetic detection of paramagnetic metal material crack defects |
-
2022
- 2022-03-31 CN CN202210337528.2A patent/CN114760210A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109831705A (en) * | 2019-02-22 | 2019-05-31 | 西安交通大学 | A kind of subjective QoE appraisal procedure for HTTP video stream traffic |
CN111046341A (en) * | 2019-12-12 | 2020-04-21 | 重庆地质矿产研究院 | Unconventional natural gas fracturing effect evaluation and capacity prediction method based on principal component analysis |
CN111163487A (en) * | 2019-12-31 | 2020-05-15 | 上海微波技术研究所(中国电子科技集团公司第五十研究所) | Method and system for evaluating comprehensive transmission performance of communication waveform |
CN111948279A (en) * | 2020-07-27 | 2020-11-17 | 南昌航空大学 | Quantitative evaluation method for weak magnetic detection of paramagnetic metal material crack defects |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Sun et al. | A new two-stage evolutionary algorithm for many-objective optimization | |
McGarigal et al. | Multivariate statistics for wildlife and ecology research | |
Carrascal et al. | Partial least squares regression as an alternative to current regression methods used in ecology | |
CN108520357B (en) | Method and device for judging line loss abnormality reason and server | |
Mitchell et al. | Bayesian model selection with BAMM: effects of the model prior on the inferred number of diversification shifts | |
US11283991B2 (en) | Method and system for tuning a camera image signal processor for computer vision tasks | |
Yucel et al. | Impact of non-normal random effects on inference by multiple imputation: A simulation assessment | |
CN111290967A (en) | Software defect prediction method, device, equipment and storage medium | |
CN115184193B (en) | Automatic testing method, device, equipment and storage medium for cable | |
Trutschel et al. | Experiment design beyond gut feeling: statistical tests and power to detect differential metabolites in mass spectrometry data | |
CN113065702A (en) | Landslide displacement multi-linear prediction method based on ST-SEEP segmentation method and space-time ARMA model | |
CN115423594A (en) | Enterprise financial risk assessment method, device, equipment and storage medium | |
Isik et al. | Multi environmental trials | |
CN113642209B (en) | Structure implantation fault response data acquisition and evaluation method based on digital twinning | |
Wesolowski et al. | The SAGE Encyclopedia of Educational Research, Measurement, and Evaluation | |
Todorov | Robust selection of variables in linear discriminant analysis | |
CN113722098A (en) | Server capacity prediction method, device, equipment and medium based on artificial intelligence | |
CN114760210A (en) | Ship communication protocol simulation result quantitative evaluation method | |
Kleinke et al. | countimp 1.0–A multiple imputation package for incomplete count data | |
CN116975567A (en) | Method, system, equipment and storage medium for testing radiation interference resistance of server | |
CN114487976B (en) | Method and system for evaluating traceability uncertainty of MCM electronic transformer calibrator | |
CN112860531B (en) | Block chain wide consensus performance evaluation method based on deep heterogeneous graph neural network | |
CN111220565B (en) | CPLS-based infrared spectrum measuring instrument calibration migration method | |
Bourdache et al. | Active preference elicitation by bayesian updating on optimality polyhedra | |
Shabestari et al. | Model based QFD method with the integrated sensitivity analysis |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |