CN107919983B - Space-based information network efficiency evaluation system and method based on data mining - Google Patents
Space-based information network efficiency evaluation system and method based on data mining Download PDFInfo
- Publication number
- CN107919983B CN107919983B CN201711054574.7A CN201711054574A CN107919983B CN 107919983 B CN107919983 B CN 107919983B CN 201711054574 A CN201711054574 A CN 201711054574A CN 107919983 B CN107919983 B CN 107919983B
- Authority
- CN
- China
- Prior art keywords
- mining
- layer
- efficiency
- evaluation
- space
- 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.)
- Active
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
-
- 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
- H04L41/142—Network analysis or design using statistical or mathematical methods
Abstract
The invention relates to a space-based information network efficiency evaluation system and method based on data mining, which comprises an analysis data generation module, a mining method processing module and a model evaluation application module, wherein the analysis data generation module firstly establishes an efficiency evaluation index system, calculates the system performance of corresponding system parameters by using a simulation tool according to the index system, then carries out corresponding conversion by a fuzzy analytic hierarchy process to obtain the comprehensive efficiency of the system, carries out multiple groups of calculation, stores multiple groups of data into an analysis database, and regenerates a corresponding analysis data file; the mining method processing module selects a proper mining algorithm according to the characteristics of the evaluation system, and simultaneously, operates and creates a corresponding mining evaluation model based on the analysis data file; the model evaluation application module displays the mining knowledge to users in modes of analyzing reports, displaying charts and the like, and evaluates, monitors and maintains the model continuously during application, and correspondingly perfects and corrects opinions and feeds back the opinions to all processes of data mining.
Description
Technical Field
The invention belongs to the field of efficiency evaluation, and particularly relates to a space-based information network efficiency evaluation system and method based on data mining.
Background
The comprehensive efficiency evaluation of the combat system is always concerned by military parties of various countries, and as early as the early sixties of the last century, countries in the United states, Su and the like successively establish special research institutions for the analysis and evaluation of the combat efficiency. The battle effectiveness analysis and evaluation in China is later than systematic, and the research method is generally the research result of foreign countries with digestion and absorption and is further perfected and developed. After decades of research and exploration, the currently popular performance evaluation methods mainly include:
computational Methods for Experiments are a method for complex system studies. The calculation experiment method takes the simulation result as a substitute version of reality or a possible reality; meanwhile, the actual system is also used as one of the possible reality and is equivalent to the simulation result, and the idea transformation from calculation simulation to calculation experiment is realized. In the calculation experiment method, the traditional calculation simulation becomes a test process in a calculation laboratory, and becomes a means for growing and cultivating various complex systems, and the actual system is only one possible result of the calculation experiment. For complex system evaluation, computational experimentation is considered a very vital approach, at least a useful endeavor.
The exploratory method is one of the hot methods for the complex system research of wars at home and abroad, is an analysis method based on the integrity and uncertainty of the system, aims to understand the influence of uncertain elements on the researched problems, and simultaneously explores various abilities and strategies of the system capable of completing corresponding task requirements, thereby comprehensively grasping various key elements, obtaining a flexible and efficient problem solution with strong adaptability, and achieving the purposes of planning the abilities and optimizing the scheme. The biggest difficulty in realizing the exploratory method is the contradiction between large calculation scale and limited calculation capacity, and how to improve the calculation efficiency is the research focus of exploratory analysis.
The data mining technology is a mass data processing method which is mature in theory and application and popular at present. The invention mainly carries out efficiency evaluation on the space-based information network based on the data mining technology. At present, in the prior art, specific system performance indexes are mostly obtained through simulation, and then the comprehensive efficiency of the system is gradually calculated, so that the efficiency is low.
In the domestic and foreign patents, some simulation architectures for researching space-based network performance evaluation and some construction methods for researching performance evaluation systems do not have patents similar to the invention aiming at the space-based information network performance evaluation method.
Disclosure of Invention
The invention solves the problems: the system and the method for evaluating the efficiency of the space-based information network based on data mining are provided, the efficiency of evaluating the efficiency of the space-based network is improved, and the influence of system parameters on the comprehensive efficiency of the system is visually shown.
The technical scheme adopted by the invention is as follows: a data mining-based space-based information network performance evaluation system comprises: the system comprises an analysis data generation module, a mining method processing module and a model evaluation application module; wherein:
the analysis data generation module is used for establishing a space-based information network efficiency evaluation index system according to space-based information network efficiency evaluation requirements, taking a group of system parameters under the space-based information network efficiency evaluation index system, calculating the system performance corresponding to the group of system parameters by using a simulation tool, then converting the system performance by a fuzzy analytic hierarchy process to obtain the space-based information network system comprehensive efficiency corresponding to the group of system parameters, taking a plurality of groups of system parameters to calculate the space-based information network system comprehensive efficiency corresponding to the system parameters according to the process to obtain a plurality of groups of system parameters-corresponding comprehensive efficiency data, storing the plurality of groups of data into an analysis database, and generating corresponding analysis data files by the database; the space-based information network efficiency evaluation index system is divided into four parts, namely a system parameter layer, a system performance layer, a system capacity layer and a system comprehensive efficiency layer, wherein the system parameter layer and the system performance layer determine the relationship between the space-based information network system parameters and performance indexes;
the mining method processing module is used for determining the type of a mining algorithm adopted by the space-based information network system for analysis, then adopting the mining algorithm, calculating and creating a corresponding mining evaluation model for data mining based on the analysis data file; the mining evaluation model adopts a BP neural network model, takes system parameters as an input layer of the neural network, takes system comprehensive efficiency as an output layer of the neural network, takes a plurality of groups of input and output data obtained in the analysis data generation module as training data of the neural network, and can directly research the relationship between the system parameters and the system comprehensive efficiency;
the model evaluation application module takes the system parameters as the input of the mining model, the output is the comprehensive efficiency of the system, any system parameter at the input end is adjusted, the corresponding change of the comprehensive efficiency of the system is analyzed, how the change of the system parameter influences the comprehensive efficiency of the system is known, the mining knowledge is displayed to a user in the modes of analyzing a report and displaying a diagram, meanwhile, the model is continuously evaluated, monitored and maintained during application, and corresponding perfection and correction opinions are fed back to each process of data mining.
The invention relates to a space-based information network efficiency evaluation method based on data mining, which comprises the following implementation steps:
(1) establishing an efficiency evaluation index system according to the efficiency evaluation requirement, wherein the efficiency evaluation index system is divided into four parts, namely a system parameter layer, a system performance layer, a system capacity layer and a system comprehensive efficiency layer, and the relation between the space-based information network system parameters and performance indexes is determined;
(2) referring to the system parameter layer and the system performance layer of the index system, taking a group of system parameters, and calculating the system performance corresponding to the group of system parameters by using a simulation tool;
(3) referring to the system performance layer, the system performance layer and the system comprehensive efficiency layer of the index system, converting the system performance into the system capacity by a fuzzy analytic hierarchy process, and converting the system capacity into the system comprehensive efficiency to obtain the system comprehensive efficiency corresponding to the set of system parameters;
(4) repeating the steps (2) and (3) to perform multiple groups of calculation, storing multiple groups of data into an analysis database, and generating corresponding analysis data files;
(5) determining the type of the mining algorithm adopted by analysis, and mining the analysis data file in the step (4) by adopting a BP neural network model;
(6) adopting a mining algorithm, taking system parameters as an input layer of the neural network, taking system comprehensive efficiency as an output layer of the neural network, taking a plurality of groups of input and output data obtained in the analysis data generation module as training data of the neural network, and calculating and creating a corresponding mining evaluation model based on an analysis data file;
(7) and the mining knowledge is displayed to the user in a mode of analyzing a report and displaying a chart, and meanwhile, the model is continuously evaluated, monitored and maintained during application, so that corresponding perfection and correction opinions are fed back to each process of data mining.
The invention has the beneficial effects that: the invention realizes the efficiency evaluation of the space-based information network, establishes a scientific space-based network efficiency evaluation index system, provides an efficiency evaluation method based on data mining, and can well reflect the relationship between the system parameters of the space-based information network and the comprehensive efficiency of the system, namely how the change of the system parameters influences the comprehensive efficiency of the system. Compared with the method, the method has the advantages that the model for directly researching the relationship between the parameters and the efficiency is established through data mining, and the calculation efficiency is greatly improved.
Drawings
FIG. 1 is a block diagram of the system comprehensive performance evaluation system based on data mining according to the present invention;
FIG. 2 is a flow chart of an embodiment of an analysis data generation module according to the present invention;
FIG. 3 is a flowchart of a specific implementation of a processing module of the mining method of the present invention;
FIG. 4 is a flow chart of a specific implementation of the model evaluation application module of the present invention;
FIG. 5 is a graph of system parameters versus performance indicators;
FIG. 6 is a diagram of membership functions for indices;
FIG. 7 is a three-layer BP network learning process;
FIG. 8 is a graph of the effect of bandwidth on overall performance satisfaction of the system;
FIG. 9 is a graph of the effect of capacity on the overall performance of the system;
FIG. 10 is a graph illustrating the effect of interference rejection on overall system performance.
Detailed Description
The present invention provides a system and a method for evaluating performance of a space-based information network based on data mining, which are described below with reference to the accompanying drawings and embodiments.
As shown in fig. 1, a data mining-based space-based information network performance evaluation system according to the present invention includes three modules: the system comprises an analysis data generation module, a mining method processing module and a model evaluation application module. The analysis data generation module firstly establishes an efficiency evaluation index system according to the efficiency evaluation requirement, calculates the system performance of corresponding system parameters by using a simulation tool according to the index system, then carries out corresponding conversion by a fuzzy analytic hierarchy process to obtain the comprehensive efficiency of the system, carries out multi-group calculation, stores multi-group data into an analysis database and generates corresponding analysis data files; the mining method comprises the steps that a mining method processing module firstly determines the type of a mining algorithm adopted by system analysis, then the mining algorithm is adopted, and a corresponding mining evaluation model is calculated and created on the basis of an analysis data file; the model evaluation application module displays the mining knowledge to a user in a mode of analyzing a report and displaying a chart, and meanwhile, the model is continuously evaluated, monitored and maintained during application, and correspondingly perfects and corrects the suggestion and feeds back the suggestion to each process of data mining.
As shown in fig. 2, the analysis data generation module gives details of:
(1) establishing space-based information network efficiency evaluation index system
When data mining analysis data is generated through the analysis data interface module, a space-based information transmission network index needs to be established at first. The invention mainly aims at the space-based information transmission network to establish an index system, and the index system is divided into four parts, namely a system parameter layer, a system performance layer, a system capacity layer and a system comprehensive efficiency layer, as shown in table 1, wherein the first class is service capacity, which is the embodiment of the system on user support capacity, and the corresponding system comprehensive efficiency mainly comprises three second classes, namely service area, service capacity, service quality and the like, and the second class corresponds to the system capacity, which means that the system supports the user capacity in a certain specific aspect. The third level index, as in table 1, can be considered a performance index. The "beam width", "sensor bandwidth", "sensor capacity", "terminal transmission rate", "user transmission rate" in the last column are the underlying system parameters relevant to the third level of index calculation. The efficiency evaluation method in this report is to explore how system parameters affect the comprehensive efficiency of the system based on data mining.
TABLE 1
On the basis of the space-based information transmission network index system, the comprehensive efficiency of the system is calculated by utilizing three levels of indexes, and the calculation flow of the comprehensive efficiency of the system is shown as a figure 2.
(2) Determining each index weight by analytic hierarchy process
The present invention uses an Analytic Hierarchy Process (AHP) to determine the weight of each index relative to a particular task. Each evaluation index occupies certain importance in scheme evaluation, and the importance degree of each evaluation index is represented by index weight, which is related to the guiding idea of the scheme making by a decision maker. For example, when the satellite mission planning performance is evaluated, the task completion rate or the observation quality of the constellation system is emphasized, if the former is emphasized, the number of completed tasks is considered, and the index weight is relatively large. The specific size of the index weight needs to be determined by consulting decision mechanisms and users and then calculating by a certain weight calculation method. Table 2 shows a service capability judgment matrix, table 3 shows a service area judgment matrix, table 4 shows a service capacity judgment matrix, and table 5 shows a service quality judgment matrix.
TABLE 2
| Service area | Service capacity | Quality of |
| 1 | 3 | 2 |
| 0.333 | 1 | 0.333 |
| 0.5 | 3 | 1 |
TABLE 3
| Ground service area | Satisfaction of |
| 1 | 2 |
| 0.5 | 1 |
TABLE 4
TABLE 5
The service capability subordinate index weights obtained by the hierarchical analysis and calculation are shown in table 6.
TABLE 6
The weight a is (0.38,0.22,0.40), a1 is (0.5 ), a2 is (0.26,0.22,0.17,0.14,0.11,0.10), A3 is (0.33, 0.67).
(3) Establishing fuzzy vector of each index through fuzzy mathematical function
The invention utilizes a fuzzy algorithm to normalize all indexes. Because performance indexes have different values and properties in the comprehensive efficiency evaluation of the satellite system, quantitative indexes and qualitative indexes exist. In quantitative indexes, the dimension and the functional relationship of the quantitative indexes are different, the types of the quantitative indexes are inconsistent, the larger the requirement of some indexes is, the better the requirement of some indexes is, the smaller the requirement of some indexes is, the better the requirement of some indexes is, and the requirement of some indexes is moderate, so that the performance indexes cannot be compared when being integrated. Therefore, a uniform measurement method for the evaluation index is required. However, since the battlefield environment in which the satellite system performs missions is extremely complex, different performance impacts may occur for different tasks even if the same performance index is within the same range of values. Thus, it is impractical to perform accurate measurements when processing values of quantitative indicators. The Zadeh professor in the united states of fuzzy mathematics initiatives states that it would be meaningless to pursue numerical accuracy of the system when it is in a complex environment. In this case, the knowledge of the domain expert is utilized to contribute to the unified measurement of the evaluation index. The index systems in the invention are all quantitative indexes, and the specific method for obtaining the fuzzy satisfaction degree is as follows.
Let the number of fuzzy satisfaction levels be N, X1,X2,...,XNRespectively representing a high to low level of satisfaction, i.e. X1Indicates the highest degree of satisfaction, XNIndicating the lowest degree of satisfaction. From the fieldAnd giving out fuzzy set membership functions corresponding to each satisfaction degree level according to the data change range of the single index. For example, the smaller the number is, the better the type attribute index is, the satisfaction level is set to be five, and in practical application, the more widely used fuzzy numbers are the triangular fuzzy number and the trapezoidal fuzzy number, and the trapezoidal fuzzy number is adopted for convenience of calculation. Fig. 6 shows a graph of membership functions of the better-type index as smaller, which is shown in the following formula.
Similarly, for the larger the better the type, the moderate index gives the satisfaction degree grade and the membership function thereof by the same method. Obtaining an evaluation matrix R according to the method1,R2,R3. Table 7 shows a satisfaction parameter list, where the attribute is 1, the smaller the type is, and the attribute is 2, the larger the type is.
TABLE 7
(4) Comprehensive efficiency of multi-stage comprehensive evaluation computing system
Considering the previous weight vector, the first-order blur transformation is found using the following formula:
Bi＝Ai·Ri(i＝1，2，3)
let C be the satisfaction degree membership vector of the comprehensive efficiency of the satellite systemWith B1，B2，B3And constructing a single-factor evaluation matrix R, and taking weight factors into consideration to calculate the comprehensive efficiency of the secondary fuzzy system.
C＝A·R
Table 8 shows the system parameters and corresponding results for calculating the overall performance of the system according to the above method.
TABLE 8
| Serial number | Bandwidth (MHz) | Capacity (Mbps) | Antijamming capability (dB) |
| 1 | 500 | 2000 | 45 |
| 2 | 600 | 2000 | 45 |
| 3 | 700 | 2000 | 45 |
| 4 | 800 | 2000 | 45 |
| 5 | 500 | 3000 | 45 |
| 6 | 500 | 4000 | 45 |
| 7 | 500 | 5000 | 45 |
| 8 | 500 | 2000 | 50 |
| 9 | 500 | 2000 | 55 |
| 10 | 500 | 2000 | 60 |
And calculating to obtain the comprehensive efficiency of the system:
(0.380264，0.000000，0.000000，0.353602，0.266134)
(0.380264，0.024087，0.093195，0.359338，0.143117)
(0.413797,0.047559,0.036189,0.359338,0.143117)
(0.437270,0.024087,0.036189,0.359338,0.143117)
(0.380264,0.024087,0.072741,0.372659,0.150250)
(0.380264,0.024087,0.138194,0.307206,0.150250)
(0.380264,0.126092,0.036189,0.307206,0.150250)
(0.380264,0.024087,0.224614,0.211152,0.159883)
(0.380264,0.071180,0.256062,0.132611,0.159883)
(0.380264,0.291053,0.036189,0.132611,0.159883)
as shown in FIG. 3, the mining method processing module gives a detailed description
(1) Determining a mining algorithm
The BP neural network model topological structure comprises an input layer (input), a hidden layer (hide layer) and an output layer (output layer). Here the model for performance evaluation is trained using a three-layer BP network as shown in fig. 5.
(2) Unambiguous input-output parameters
In order to study the relationship between the system parameters and the system comprehensive efficiency, the input layer is set as the system parameters, and the output layer is set as the system comprehensive efficiency. There are generally 3 empirical formulas for determining the number of hidden layer nodes:
m＝log2n
wherein m is the number of hidden layer nodes to be set, n is the number of input layer nodes, l is the number of output layer nodes, and α is a constant between 1 and 10.
(3) Training assessment model
The training results thus obtained are as follows:
outputting a layer weight:
0.185165,-0.568423,-0.568423,-0.568423,-0.568423,-0.568423,-1.290139,-1.656380,-1.656380,-1.656380,-1.656380,-1.656380,-1.934754,-0.549250,-0.549250,-0.549250,-0.549250,-0.549250,-3.015884,2.168453,2.168453,2.168453,2.168453,2.168453,-1.678893,0.014873,0.014873,0.014873,0.014873,0.014873
hidden layer weight:
1.950282,-0.007581,-0.251218,-4.482175,1.950282,-0.007581,-0.251218,-4.482175,1.950282,-0.007581,-0.251218,-4.482175,1.950282,-0.007581,-0.251218,-4.482175,1.950282,-0.007581,-0.251218,-4.482175
and obtaining the influence of the bandwidth on the comprehensive efficiency satisfaction degree of the system, as shown in fig. 8, the satisfaction degree is gradually increased along with the increase of the bandwidth, and the change trend of the satisfaction degree is stable after the bandwidth is more than 800; the influence of the capacity on the comprehensive performance of the system is shown in fig. 9, the system capacity has a strong influence on the satisfaction degree after being greater than 5000, and the satisfaction degree increases with the increase of the capacity; as shown in fig. 10, when the anti-interference capability is greater than 60, the influence on the satisfaction degree is obvious, and the satisfaction degree increases with the increase of the anti-interference capability.
As shown in FIG. 4, the model evaluation application module details the narrative
(1) Test excavation model
According to the trained implicit and output layer weights, 3 sets of data are taken as test data, and system parameters are shown in table 9. And calculating the corresponding system comprehensive efficiency through a neural network model.
TABLE 9
| Serial number | Bandwidth (MHz) | Capacity (Mbps) | Antijamming capability (dB) |
| 1 | 900 | 2000 | 45 |
| 2 | 500 | 6000 | 45 |
| 3 | 500 | 2000 | 65 |
And calculating by using a traditional simulation method to obtain the comprehensive efficiency of the system:
(0.437270，0.024087，0.036189，0.359338，0.143117)
(0.453368，0.052988，0.036189，0.307206，0.150250)
(0.647230，0.024087，0.036189，0.132611.0.159883)
the comprehensive efficiency of the system is obtained by utilizing the weight values of the hidden layer and the output layer of the neural network model:
(0.389197，0.041367，0.072483，0.356592，0.159459)
(0.407728，0.051286，0.077669，0.292108，0.159188)
(0.498066，0.135609，0.107058，0.092793，0.157912)
(2) error analysis
And comparing the comprehensive efficiency of the system obtained through the neural network model with the comprehensive efficiency of the system obtained through simulation calculation, wherein the satisfaction is highest, and the conclusion is consistent.
(3) Perfecting and improving excavation models
The number of nodes, the number of training data sets and the like of the mining model can be adjusted according to the result error of the efficiency value calculated by the traditional method and the method disclosed by the invention, so that the mining model is perfected and improved.
The invention has not been described in detail and is part of the common general knowledge of a person skilled in the art.
The above examples are provided only for the purpose of describing the present invention, and are not intended to limit the scope of the present invention. The scope of the invention is defined by the appended claims. Various equivalent substitutions and modifications can be made without departing from the spirit and principles of the invention, and are intended to be within the scope of the invention.
Claims (2)
1. A data mining-based space-based information network efficiency evaluation system is characterized in that: the mining method comprises an analysis data generation module, a mining method processing module and a model evaluation application module; wherein:
the analysis data generation module is used for establishing a space-based information network efficiency evaluation index system according to space-based information network efficiency evaluation requirements, taking a group of system parameters under the space-based information network efficiency evaluation index system, calculating the system performance corresponding to the group of system parameters by using a simulation tool, converting the system performance into system capacity by using a fuzzy analytic hierarchy process, converting the system capacity into system comprehensive efficiency to obtain the space-based information network system comprehensive efficiency corresponding to the group of system parameters, taking a plurality of groups of system parameters, calculating the space-based information network system comprehensive efficiency corresponding to the system parameters according to the process to obtain a plurality of groups of system parameters-corresponding comprehensive efficiency data, storing the plurality of groups of data into an analysis database, and generating corresponding analysis data files by the database; the space-based information network efficiency evaluation index system is divided into four parts, namely a system parameter layer, a system performance layer, a system capacity layer and a system comprehensive efficiency layer, wherein the system parameter layer and the system performance layer determine the relationship between the space-based information network system parameters and performance indexes;
the mining method processing module is used for determining the type of a mining algorithm adopted by the space-based information network system for analysis, then adopting the mining algorithm, calculating and creating a corresponding mining evaluation model for data mining based on the analysis data file; the mining evaluation model adopts a BP neural network model, takes system parameters as an input layer of the neural network, takes system comprehensive efficiency as an output layer of the neural network, takes a plurality of groups of input and output data obtained in the analysis data generation module as training data of the neural network, and can directly research the relationship between the system parameters and the system comprehensive efficiency;
the model evaluation application module takes the system parameters as the input of the mining model, the output is the comprehensive efficiency of the system, any system parameter at the input end is adjusted, the corresponding change of the comprehensive efficiency of the system is analyzed, the mining knowledge is displayed to a user in the modes of analyzing reports and displaying charts, and the model is evaluated, monitored and maintained.
2. A space-based information network efficiency evaluation method based on data mining is characterized in that: the method comprises the following implementation steps:
(1) establishing an efficiency evaluation index system according to the efficiency evaluation requirement, wherein the efficiency evaluation index system is divided into four parts, namely a system parameter layer, a system performance layer, a system capacity layer and a system comprehensive efficiency layer, and the relation between the space-based information network system parameters and performance indexes is determined;
(2) referring to the system parameter layer and the system performance layer of the index system, taking a group of system parameters, and calculating the system performance corresponding to the group of system parameters by using a simulation tool;
(3) referring to the system performance layer, the system performance layer and the system comprehensive efficiency layer of the index system, converting the system performance into the system capacity by a fuzzy analytic hierarchy process, and converting the system capacity into the system comprehensive efficiency to obtain the system comprehensive efficiency corresponding to the set of system parameters;
(4) repeating the steps (2) and (3) to perform multiple groups of calculation, storing multiple groups of data into an analysis database, and generating corresponding analysis data files;
(5) determining the type of the mining algorithm adopted by analysis, and mining the analysis data file in the step (4) by adopting a BP neural network model;
(6) adopting a mining algorithm, taking system parameters as an input layer of the neural network, taking system comprehensive efficiency as an output layer of the neural network, taking a plurality of groups of input and output data obtained in the analysis data generation module as training data of the neural network, and calculating and creating a corresponding mining evaluation model based on an analysis data file;
(7) and displaying the mining knowledge to a user in a mode of analyzing a report and displaying a chart, and evaluating, monitoring and maintaining the model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711054574.7A CN107919983B (en) | 2017-11-01 | 2017-11-01 | Space-based information network efficiency evaluation system and method based on data mining |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711054574.7A CN107919983B (en) | 2017-11-01 | 2017-11-01 | Space-based information network efficiency evaluation system and method based on data mining |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107919983A CN107919983A (en) | 2018-04-17 |
| CN107919983B true CN107919983B (en) | 2020-07-10 |
Family
ID=61895912
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711054574.7A Active CN107919983B (en) | 2017-11-01 | 2017-11-01 | Space-based information network efficiency evaluation system and method based on data mining |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107919983B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109033497B (en) * | 2018-06-04 | 2022-08-26 | 南瑞集团有限公司 | High-concurrency-oriented multi-stage data mining algorithm intelligent selection method |
| CN112214524A (en) * | 2020-08-27 | 2021-01-12 | 优学汇信息科技(广东)有限公司 | Data evaluation system and evaluation method based on deep data mining |
| CN112926739B (en) * | 2021-03-11 | 2024-03-19 | 北京计算机技术及应用研究所 | Network countermeasure effectiveness evaluation method based on neural network model |
| CN113139759A (en) * | 2021-05-19 | 2021-07-20 | 杭州市电力设计院有限公司余杭分公司 | Power grid data asset management method and system |
| CN116501779A (en) * | 2023-06-26 | 2023-07-28 | 图林科技(深圳)有限公司 | Big data mining analysis system for real-time feedback |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102663232A (en) * | 2012-03-13 | 2012-09-12 | 江苏润和软件股份有限公司 | Multi-dimensional simulation analysis system and method thereof for user energy efficiency evaluation |
| CN106023561A (en) * | 2016-07-13 | 2016-10-12 | 袁留路 | 'Four-meter-in-one' energy management integrated service system |
| CN106411587A (en) * | 2016-09-26 | 2017-02-15 | 中国空间技术研究院 | Simulation architecture suitable for performance evaluation of satellite communications network |
| CN107038167A (en) * | 2016-02-03 | 2017-08-11 | 普华诚信信息技术有限公司 | Big data excavating analysis system and its analysis method based on model evaluation |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8095498B2 (en) * | 2008-12-17 | 2012-01-10 | International Business Machines Corporation | Data mining model interpretation, optimization, and customization using statistical techniques |
| US20170083823A1 (en) * | 2015-09-22 | 2017-03-23 | San Diego State University Research Foundation | Spectral Optimal Gridding: An Improved Multivariate Regression Analyses and Sampling Error Estimation |
-
2017
- 2017-11-01 CN CN201711054574.7A patent/CN107919983B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102663232A (en) * | 2012-03-13 | 2012-09-12 | 江苏润和软件股份有限公司 | Multi-dimensional simulation analysis system and method thereof for user energy efficiency evaluation |
| CN107038167A (en) * | 2016-02-03 | 2017-08-11 | 普华诚信信息技术有限公司 | Big data excavating analysis system and its analysis method based on model evaluation |
| CN106023561A (en) * | 2016-07-13 | 2016-10-12 | 袁留路 | 'Four-meter-in-one' energy management integrated service system |
| CN106411587A (en) * | 2016-09-26 | 2017-02-15 | 中国空间技术研究院 | Simulation architecture suitable for performance evaluation of satellite communications network |
Non-Patent Citations (1)
| Title |
|---|
| 基于数据挖掘的装备效能验证与评估方法;汪洲，胡会东;《第18届中国系统仿真技术及其应用学术年会》;20170811;第18卷;第333-336页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107919983A (en) | 2018-04-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107919983B (en) | Space-based information network efficiency evaluation system and method based on data mining | |
| Zhang et al. | Sound quality prediction of vehicle interior noise and mathematical modeling using a back propagation neural network (BPNN) based on particle swarm optimization (PSO) | |
| CN107886161A (en) | A kind of global sensitivity analysis method for improving Complex Information System efficiency | |
| CN110196814B (en) | Software quality evaluation method | |
| CN111860982A (en) | Wind power plant short-term wind power prediction method based on VMD-FCM-GRU | |
| CN103514259B (en) | Abnormal data detection and modification method based on numerical value relevance model | |
| Niu et al. | Uncertainty modeling for chaotic time series based on optimal multi-input multi-output architecture: Application to offshore wind speed | |
| CN106446444B (en) | Soil moisture space predicting method based on Bayes's maximum entropy and priori knowledge | |
| CN103514457B (en) | The multi-target improvement differential evolution model of Land use structure type when Ecology Restriction | |
| CN101802728A (en) | Gaseous emission is carried out system and method based on the virtual sensing of experience set | |
| CN101710304A (en) | Method for evaluating implementation quality of software process | |
| Xie | Explanations about grey information and framework of grey system modeling | |
| CN108647807B (en) | River flow prediction method | |
| CN108805268A (en) | Deeply learning strategy network training method based on evolution algorithm | |
| CN116150897A (en) | Machine tool spindle performance evaluation method and system based on digital twin | |
| CN107860889A (en) | The Forecasting Methodology and equipment of the soil organism | |
| CN109858180B (en) | Regional crop water consumption space pattern optimization design method | |
| CN105893669A (en) | Global simulation performance predication method based on data digging | |
| Tian et al. | Variable frequency wind speed trend prediction system based on combined neural network and improved multi-objective optimization algorithm | |
| CN103577676A (en) | Grey weighting method for sewage treatment process comprehensive evaluation | |
| CN104050547A (en) | Non-linear optimization decision-making method of planning schemes for oilfield development | |
| Boumaiza et al. | Modeling multi-criteria decision analysis in residential PV adoption | |
| CN201716727U (en) | Geographical simulation system based on remote sensing and GIS | |
| CN104484554B (en) | A kind of method and system for obtaining the course degree of association | |
| CN105117559A (en) | Firearm design scheme evaluation method based on fuzzy decision diagram and gray correlation 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |