CN107919983A - A kind of space information network Effectiveness Evaluation System and method based on data mining - Google Patents
A kind of space information network Effectiveness Evaluation System and method based on data mining Download PDFInfo
- Publication number
- CN107919983A CN107919983A CN201711054574.7A CN201711054574A CN107919983A CN 107919983 A CN107919983 A CN 107919983A CN 201711054574 A CN201711054574 A CN 201711054574A CN 107919983 A CN107919983 A CN 107919983A
- Authority
- CN
- China
- Prior art keywords
- effectiveness
- systematic parameter
- layer
- space information
- data
- 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.)
- Granted
Links
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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Signal Processing (AREA)
- General Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Pure & Applied Mathematics (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Probability & Statistics with Applications (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Optimization (AREA)
- Software Systems (AREA)
- Mathematical Analysis (AREA)
- Algebra (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention relates to a kind of space information network Effectiveness Evaluation System and method based on data mining, include analysis data generation module, method for digging processing module and model evaluation application module, analyze data generation module and establish effectiveness evaluation index system first, with reference to index system, the system performance of corresponding system parameter is calculated using emulation tool, then changed accordingly by Fuzzy AHP, obtain system comprehensive effectiveness, carry out multigroup calculating, multi-group data is stored into analytical database, regenerates corresponding analysis data file；Method for digging processing module selects suitable mining algorithm according to the characteristics of assessment system, while based on analysis data file computing and creates corresponding excavation assessment models；Extracting Knowledge is presented to user by model evaluation application module in a manner of analysis report, display chart etc., and constantly model is assessed, monitored and is safeguarded in application, corresponding to improve and correct each process of the suggestion feedback to data mining.
Description
Technical field
The invention belongs to measures of effectiveness field, and in particular to a kind of space information network measures of effectiveness based on data mining
System and method.
Background technology
Combat system measures of effectiveness is always by the concern of the military of various countries, early in the initial stage sixties in last century, the U.S. and Russia etc.
Country has just set up special operational Effectiveness Analysis and evaluation studies mechanism in succession.China systematically carries out operational Effectiveness Analysis
Then will a little later with assessing, the method for research is usually to digest and assimilate the achievement in research of foreign country, and further improves and develop.System
Efficiency estimation method of uniting passes through the research and discovery of decades, and efficiency estimation method popular at present mainly has：
Experiment with computing method (Computational Methods for Experiments) is a kind of for complicated system
The method of system research.Experiment with computing method as a real alternate version, or a kind of is likely to occur " emulation " result
Reality；Real system is also served as at the same time one kind in the reality that is likely to occur, same to simulation result " equivalence ", realizes and imitate from calculating
The true thought transformation for moving towards experiment with computing.In experiment with computing method, it is inner that traditional calculating simulation becomes " computing laboratory "
" experiment " process, become the means of " growth cultivate " all kinds of complication systems, and real system is this " experiment with computing "
A kind of possible outcome.For complicated system evaluation, experiment with computing method is considered as to have very much a kind of method of vitality, extremely
It is a kind of good try less.
Heuristic approaches, are one of hotspot approach of domestic and international war complex system research, it is to be based on systematic entirety
With a kind of probabilistic analysis method, the targets of heuristic approaches is to understand uncertain key element for the shadow that is studied a question
Ring, while explore the various abilities of system and strategy that can complete corresponding task demand, so as to comprehensively hold various be critical to
Element, obtains the problem of flexible and efficient and adaptable solution, achievees the purpose that the planning of carry out ability and scheme optimizing.Realize
The maximum difficult point of heuristic approaches is exactly contradiction of the calculation scale greatly between finite computational abilities, how to improve computational efficiency
It is exactly the research emphasis of exploratory analysis.
Data mining technology is a kind of theoretical and application all comparative maturities, while is also currently a popular mass data processing
Method.Measures of effectiveness is carried out to space information network present invention is primarily based on data mining technology.Current existing technology is most
It is that specific system performance index is obtained by emulation, then step by step calculation goes out system comprehensive effectiveness, it is less efficient.
In domestic and international patent, the simulation framework of some research astro network measures of effectiveness, some research measures of effectiveness systems
Construction method, not for space information network efficiency estimation method and the similar patent of the present invention.
The content of the invention
The technology of the present invention solves the problems, such as：Overcome the deficiencies of the prior art and provide a kind of space-based information based on data mining
Network efficiency assessment system and method, improve the efficiency of astro network measures of effectiveness, intuitively display systems parameter is comprehensive to system
Close the influence that efficiency produces.
The present invention adopts the technical scheme that：A kind of space information network Effectiveness Evaluation System based on data mining, bag
Include：Analyze data generation module, method for digging processing module and model evaluation application module；Wherein：
Data generation module is analyzed, according to space information network measures of effectiveness demand, space information network efficiency is established and comments
Assessment system, under the space information network effectiveness evaluation index system, takes one group of systematic parameter, utilizes emulation tool meter
The corresponding system performance of this group of systematic parameter is calculated, then system performance is changed by Fuzzy AHP, is obtained
The corresponding space information network system comprehensive effectiveness of this group of systematic parameter, takes multigroup systematic parameter to carry out system ginseng by the above process
The corresponding space information network system comprehensive effectiveness of number calculates, and obtains multigroup systematic parameter-corresponding comprehensive effectiveness data, will be more
Group data storage generates corresponding analysis data file to analytical database, database；The space information network measures of effectiveness
Index system is divided into systematic parameter layer, wherein systemic four part of ergosphere, system capability layer and comprehensive effectiveness layer, systematic parameter layer
The relation of space information network systematic parameter and performance indicator is determined with systemic ergosphere；
Method for digging processing module, determines mining algorithm type used by space information network network analysis, then adopts
With mining algorithm, based on analysis data file, computing and create corresponding excavation assessment models progress data mining；The excavation
Assessment models use BP neural network model, using systematic parameter as the input layer of neutral net, using system comprehensive effectiveness as
The output layer of neutral net, the training using the multigroup inputoutput data obtained in analysis data generation module as neutral net
Data, obtained mining model can directly study the relation between systematic parameter and system effectiveness；
Model evaluation application module, using systematic parameter as the input of mining model, output is system effectiveness, and adjustment is defeated
Enter the arbitrary system parameter at end, the respective change of analysis system efficiency, the change for knowing systematic parameter is how to influence system effect
Can, Extracting Knowledge is presented to user, while constantly model is commented in application with analysis report, display graph mode
Estimate, monitor with safeguarding, it is corresponding to improve and correct each process of the suggestion feedback to data mining.
Space information network efficiency estimation method of the invention based on data mining, realizes that step is as follows：
(1) effectiveness evaluation index system is established according to measures of effectiveness demand, is divided into systematic parameter layer, systemic ergosphere, is
Four part of system capability layer and comprehensive effectiveness layer, specifies the relation of space information network systematic parameter and performance indicator；
(2) the systematic parameter layer with reference to These parameters system and systemic ergosphere, take one group of systematic parameter, using emulating work
Tool calculates the corresponding system performance of this group of systematic parameter；
(3) with reference to systemic ergosphere, system capability layer and the comprehensive effectiveness layer of These parameters system, fuzzy hierarchy point is passed through
System performance is converted to system capability by analysis method, then system capability is converted to system comprehensive effectiveness, obtains above-mentioned this system system
The corresponding system comprehensive effectiveness of parameter；
(4) (2), the multigroup calculating of (3) progress are repeated, multi-group data is stored into analytical database, regenerates corresponding point
Analyse data file；
(5) the mining algorithm type that analysis uses is determined, using BP neural network model to the analysis data file in (4)
Carry out data mining；
(6) mining algorithm is used, using systematic parameter as the input layer of neutral net, nerve is used as using system comprehensive effectiveness
The output layer of network, the training number using the multigroup inputoutput data obtained in analysis data generation module as neutral net
According to based on analysis data file, computing simultaneously creates corresponding excavation assessment models；
(7) Extracting Knowledge is presented to by user with analysis report, display graph mode, while in application constantly to model
Assessed, monitored and safeguarded, it is corresponding to improve and correct each process of the suggestion feedback to data mining.
The beneficial effects of the invention are as follows：The present invention realizes the measures of effectiveness to space information network, establishes science
Astro network effectiveness evaluation index system, there is provided a kind of efficiency estimation method based on data mining, can be good at reflecting
Relation between the systematic parameter and system effectiveness of space information network, the i.e. change of systematic parameter are how to influence system effectiveness
, the prior art can only be finally obtained corresponding by systematic parameter computing system performance indicator, further computing system ability
System effectiveness, step complicated and time consumption.In contrast, the present invention establishes directly research parameter by data mining and efficiency is closed
The model of system, greatly improved computational efficiency.
Brief description of the drawings
Fig. 1 is the Effectiveness Evaluation block diagram of system of the invention based on data mining；
Fig. 2 implements flow chart for present invention analysis data generation module；
The method for digging processing module that Fig. 3 is the present invention implements flow chart；
The model evaluation application module that Fig. 4 is the present invention implements flow chart；
Fig. 5 is systematic parameter and performance indicator graph of a relation；
Fig. 6 is index membership function schematic diagram；
Fig. 7 is three layers of BP network learning procedures；
Fig. 8 is influence of the bandwidth to system effectiveness satisfaction；
Fig. 9 is influence of the capacity to system effectiveness；
Figure 10 is influence of the antijamming capability to system effectiveness.
Embodiment
With reference to the accompanying drawings and examples to a kind of space information network efficiency based on data mining provided by the invention
Assessment system and method are introduced.
As shown in Figure 1, a kind of space information network Effectiveness Evaluation System based on data mining of the present invention, includes three
Module：Analyze data generation module, method for digging processing module and model evaluation application module.Wherein analyze data generation mould
Block establishes effectiveness evaluation index system according to measures of effectiveness demand first, and with reference to the index system, phase is calculated using emulation tool
The system performance of systematic parameter is answered, is then changed accordingly by Fuzzy AHP, obtains system comprehensive effectiveness, into
The multigroup calculating of row, is stored into analytical database by multi-group data, regenerates corresponding analysis data file；Method for digging handles mould
Block determines the mining algorithm type that network analysis uses first, and then using mining algorithm, based on analysis data file, computing is simultaneously
Create corresponding excavation assessment models；Model evaluation application module is showed Extracting Knowledge with analysis report, display graph mode
To user, while constantly model is assessed, monitored and is safeguarded in application, it is corresponding to improve and correct suggestion feedback to number
According to each process of excavation.
As shown in Fig. 2, narration is shown in detail in analysis data generation module：
(1) space information network effectiveness evaluation index system is established
When generating data mining analysis data by analyzing data interface module, it is necessary first to establish space-based information transmission network
Index.Present invention is generally directed to the foundation that space-based information transmission network carries out index system, systematic parameter layer, systematicness are classified as
Four part of ergosphere, system capability layer and comprehensive effectiveness layer, as shown in table 1, wherein first order classification is service ability, is system pair
The embodiment of User support ability, correspondence system comprehensive effectiveness index, mainly including coverage, service capacity, service quality etc.
Three two level classifications, two class rank correspondence system abilities.Third level index such as table 1, can be considered as performance indicator.Last row
In " beam angle ", " sensor bandwidth ", " capacity sensor ", " terminal transmission rate ", " user's transmission rate " be and
Three-level index calculates relevant first floor system parameter.Efficiency estimation method in this report is exactly to be visited on the basis of data mining
Study carefully how systematic parameter influences system comprehensive effectiveness index.
Table 1
On the basis of space-based information transmission network index system, the comprehensive effectiveness of three-level indication computing system, system are utilized
The calculation process of comprehensive effectiveness is as shown in Figure 2.
(2) analytic hierarchy process (AHP) establishes each index weights
The present invention determines weight of each index relative to particular task with analytic hierarchy process (AHP) (AHP).Each evaluation index exists
Certain importance is all occupied in scheme evaluation, its significance level is embodied by index weights, this works out a scheme with policymaker
Guiding theory it is related.For example during the assessment of satellite task planning performance, lay particular emphasis on task completion rate or the sight of constellation systems
Mass metering, if laying particular emphasis on the former, emphasis considers the quantity that task is completed, and index weights also compare larger.Index weights have
Body size is needed by seeking advice from policy-making body and user, is then calculated and determined by certain weighing computation method.Table 2
Represent service ability judgment matrix, table 3 represents coverage judgment matrix, and table 4 represents service capacity judgment matrix, and table 5 represents
Service quality judgment matrix.
Table 2
| Coverage | Service capacity | Service quality |
| 1 | 3 | 2 |
| 0.333 | 1 | 0.333 |
| 0.5 | 3 | 1 |
Table 3
| Ground service area area | Ground service area satisfaction |
| 1 | 2 |
| 0.5 | 1 |
Table 4
| Average frequency bandwidth | Average system capacity | Average transmission rate | Support average user number | Business support type | Terminal supports type |
| 1 | 2 | 2 | 3 | 2 | 3 |
| 0.5 | 1 | 3 | 2 | 3 | 3 |
| 0.5 | 0.333 | 1 | 3 | 2 | 2 |
| 0.333 | 0.5 | 0.333 | 1 | 3 | 2 |
| 0.5 | 0.333 | 0.5 | 0.333 | 1 | 2 |
| 0.333 | 0.333 | 0.5 | 0.5 | 0.5 | 1 |
Table 5
| Average communication time delay | Average antijamming capability |
| 1 | 0.5 |
| 2 | 1 |
It is as shown in table 6 that service ability subordinate's index weights are calculated using step analysis.
Table 6
Weight A=(0.38,0.22,0.40), A1=(0.5,0.5), A2=(0.26,0.22,0.17,0.14,0.11,
0.10), A3=(0.33,0.67).
(3) each index Fuzzy vector is established by fuzzy mathematics function
The present invention utilizes fuzzy algorithmic approach, and indices are normalized.Since performance indicator takes in Effectiveness Evaluation for Satellite Systems
It is different to be worth property, there is quantitative target also difinite quality index.In quantitative target, not only their dimension, functional relation are different, and
And their type is also inconsistent, some index requests are the bigger the better, some require the smaller the better, some require moderate, cause
It can not be contrasted when carrying out performance index comprehensive.Therefore, it is necessary to use unified metric form to evaluation index.But due to
The battlefield surroundings that satellite system completes mission are extremely complex, therefore to different task, even if same performance index is in identical number
In the range of value, can also produce different efficiency influences.In this way, when handling the value of quantitative target, carrying out accurate measurement is
It is unpractical.Professor Zadeh in the fuzzy mathematics founder U.S. points out, " when system is under complex environment, pursues system number
It is accurate in value, will be skimble-skamble ".In this case, the knowledge of domain expert is utilized, it will help evaluation index
Unified metric.Index system in the present invention is all quantitative target, and the specific method for obtaining its fuzzy satisfactory degree is as follows.
If fuzzy satisfactory degree number of levels is N, X is used1,X2,...,XNThe rank of degree of being satisfied with from high to low, i.e. X respectively1
Degree of being satisfied with highest, XNDegree of being satisfied with is minimum.Data variation scope by domain expert according to single index, provide with respectively
The corresponding fuzzy set membership function of satisfaction rank.Such as the smaller the better type ATTRIBUTE INDEX, if satisfaction rank has five, respectively
For highest, and it is higher, it is medium, it is relatively low, minimum in practical applications, it is Triangular Fuzzy Number and ladder with extensive fuzzy number must be compared
Shape fuzzy number, for convenience of calculation, using Trapezoid Fuzzy Number.Shown in Fig. 6 is the figure of the membership function of the smaller the better type index
Shape, its membership function are shown as the following formula.
Similarly, then are provided by satisfaction grade and its is subordinate to using identical method for the type of being the bigger the better, medium polarity
Function.Evaluations matrix R is obtained according to the above method1,R2,R3.Table 7 is satisfaction parameter list, and attribute 1, is the smaller the better
Type, attribute 2, then be the type of being the bigger the better.
Table 7
(4) Multi-level comprehensive evaluation computing system comprehensive effectiveness
Consider weight vectors above, level-one blurring mapping is obtained with following equation：
Bi=Ai·Ri(i=1,2,3)
If C is the satisfaction Membership Vestor of satellite system efficiency, B is used1, B2, B3Single factor evaluation matrix R is constructed, considers power
Weight factor, carries out two level fuzzy system efficiency and calculates.
C=AR
Table 8 is the systematic parameter and accordingly result according to above method computing system efficiency.
Table 8
| Sequence 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 |
By calculating, system effectiveness is obtained：
(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 figure 3, narration is shown in detail in method for digging processing module
(1) mining algorithm is determined
BP neural network model topology structure includes input layer (input), hidden layer (hide layer) and output layer
(output layer).The model of measures of effectiveness is trained here with three layers of BP networks as shown in Figure 5.
(2) clear and definite input/output argument
In order to study the relation between systematic parameter and efficiency index, if input layer is systematic parameter, output layer is system
Efficiency index.Determine that node in hidden layer generally there are 3 empirical equations：
M=log2n
Wherein, m is the node in hidden layer to be set, and n is input layer number, and l is output layer number of nodes, and α is 1 to 10
Between constant.In the present invention, m takes 5.
(3) Training valuation model
Thus it is as follows to obtain training result：
Output layer weights：
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 weights：
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 influence of the bandwidth to system effectiveness satisfaction is obtained, as shown in figure 8, with the increase of bandwidth, satisfaction is progressively
Increase, after band is wider than 800, the variation tendency of satisfaction is steady；Influence of the capacity to system effectiveness, as shown in figure 9, system is held
Amount is stronger to satisfaction after more than 5000, as capacity increases, satisfaction increase；Antijamming capability is to system effectiveness
Influence, as shown in Figure 10, after antijamming capability is more than 60, to the obvious effect of satisfaction, with the increase of antijamming capability,
Satisfaction increases therewith.
As shown in figure 4, narration is shown in detail in model evaluation application module
(1) mining model is tested
According to the implicit and output layer weight trained, 3 groups of data are taken as test data, systematic parameter as shown in table 9.
By neural network model, corresponding system effectiveness is calculated.
Table 9
| Sequence number | Bandwidth (MHz) | Capacity (Mbps) | Antijamming capability (dB) |
| 1 | 900 | 2000 | 45 |
| 2 | 500 | 6000 | 45 |
| 3 | 500 | 2000 | 65 |
Calculated by traditional simulation method, obtain system effectiveness：
(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)
System effectiveness is obtained using the hidden layer of neural network model, output layer weights：
(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
The system effectiveness and the system effectiveness of simulation calculation obtained by neural network model is contrasted, and is all satisfaction
Highest, conclusion are consistent.
(3) mining model is improved
The efficiency value resultant error that can be calculated according to conventional method and the method for the present invention, adjusts the node of mining model
Number, training data group number etc., to improve mining model.
Non-elaborated part of the present invention belongs to the known technology of those skilled in the art.
Above example is provided just for the sake of the description purpose of the present invention, and is not intended to limit the scope of the present invention.This
The scope of invention is defined by the following claims.The various equivalent substitutions that do not depart from spirit and principles of the present invention and make and repair
Change, should all cover within the scope of the present invention.
Claims (2)
- A kind of 1. space information network Effectiveness Evaluation System based on data mining, it is characterised in that：Including analysis data generation Module, method for digging processing module and model evaluation application module；Wherein：Data generation module is analyzed, according to space information network measures of effectiveness demand, space information network measures of effectiveness is established and refers to Mark system, under the space information network effectiveness evaluation index system, takes one group of systematic parameter, this is calculated using emulation tool The corresponding system performance of one group of systematic parameter, then changes system performance by Fuzzy AHP, obtains this group The corresponding space information network system comprehensive effectiveness of systematic parameter, takes multigroup systematic parameter to carry out systematic parameter pair by the above process The space information network system comprehensive effectiveness answered calculates, and multigroup systematic parameter-corresponding comprehensive effectiveness data is obtained, by multigroup number According to analytical database is stored into, database generates corresponding analysis data file；The space information network effectiveness evaluation index System is divided into systematic parameter layer, systemic four part of ergosphere, system capability layer and comprehensive effectiveness layer, wherein systematic parameter layer and is System performance layer determines the relation of space information network systematic parameter and performance indicator；Method for digging processing module, determines mining algorithm type used by space information network network analysis, then using digging Algorithm is dug, based on data file is analyzed, computing and establishment excavate assessment models and carry out data mining accordingly；It is described to excavate assessment Model uses BP neural network model, and using systematic parameter as the input layer of neutral net, nerve is used as using system comprehensive effectiveness The output layer of network, the training number using the multigroup inputoutput data obtained in analysis data generation module as neutral net According to obtained mining model can directly study the relation between systematic parameter and system effectiveness；Model evaluation application module, using systematic parameter as the input of mining model, output is system effectiveness, adjusts input terminal Arbitrary system parameter, the respective change of analysis system efficiency, the change for knowing systematic parameter is how to influence system effectiveness, Extracting Knowledge is presented to user, while constantly model is assessed in application, is supervised with analysis report, display graph mode Survey and maintenance, it is corresponding to improve and correct each process of the suggestion feedback to data mining.
- A kind of 2. space information network efficiency estimation method based on data mining, it is characterised in that：Realize that step is as follows：(1) effectiveness evaluation index system is established according to measures of effectiveness demand, is divided into systematic parameter layer, systemic ergosphere, system energy Four part of power layer and comprehensive effectiveness layer, specifies the relation of space information network systematic parameter and performance indicator；(2) the systematic parameter layer with reference to These parameters system and systemic ergosphere, take one group of systematic parameter, utilize emulation tool meter Calculate the corresponding system performance of this group of systematic parameter；(3) with reference to systemic ergosphere, system capability layer and the comprehensive effectiveness layer of These parameters system, Fuzzy AHP is passed through System performance is converted into system capability, then system capability is converted into system comprehensive effectiveness, obtains above-mentioned this group of systematic parameter Corresponding system comprehensive effectiveness；(4) (2), the multigroup calculating of (3) progress are repeated, multi-group data is stored into analytical database, regenerates corresponding analysis number According to file；(5) determine the mining algorithm type that analysis uses, the analysis data file in (4) is carried out using BP neural network model Data mining；(6) mining algorithm is used, using systematic parameter as the input layer of neutral net, neutral net is used as using system comprehensive effectiveness Output layer, obtained multigroup inputoutput data will be analyzed in data generation module as the training data of neutral net, base In analysis data file, computing simultaneously creates corresponding excavation assessment models；(7) Extracting Knowledge is presented to user, while constantly model is carried out in application with analysis report, display graph mode Assessment, monitor and safeguard, corresponding to improve and correct each process of the suggestion feedback to data mining.
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 true CN107919983A (en) | 2018-04-17 |
| CN107919983B 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) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109033497A (en) * | 2018-06-04 | 2018-12-18 | 南瑞集团有限公司 | A kind of multistage data mining algorithm intelligent selecting method towards high concurrent |
| 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 |
| CN112926739A (en) * | 2021-03-11 | 2021-06-08 | 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 (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100153332A1 (en) * | 2008-12-17 | 2010-06-17 | Rollins John B | Data mining model interpretation, optimization, and customization using statistical techniques |
| 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 |
| 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 |
| 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 |
-
2017
- 2017-11-01 CN CN201711054574.7A patent/CN107919983B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100153332A1 (en) * | 2008-12-17 | 2010-06-17 | Rollins John B | Data mining model interpretation, optimization, and customization using statistical techniques |
| 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 |
| 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 |
| 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 |
|---|
| 汪洲，胡会东: "基于数据挖掘的装备效能验证与评估方法", 《第18届中国***仿真技术及其应用学术年会》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109033497A (en) * | 2018-06-04 | 2018-12-18 | 南瑞集团有限公司 | A kind of multistage data mining algorithm intelligent selecting method towards high concurrent |
| 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 |
| CN112926739A (en) * | 2021-03-11 | 2021-06-08 | 北京计算机技术及应用研究所 | Network countermeasure effectiveness evaluation method based on neural network model |
| 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 |
| CN113139759B (en) * | 2021-05-19 | 2024-06-04 | 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107919983B (en) | 2020-07-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107919983A (en) | A kind of space information network Effectiveness Evaluation System and method based on data mining | |
| Liu et al. | A future land use simulation model (FLUS) for simulating multiple land use scenarios by coupling human and natural effects | |
| Liu et al. | Boosting slime mould algorithm for parameter identification of photovoltaic models | |
| Reddy et al. | Multi‐objective particle swarm optimization for generating optimal trade‐offs in reservoir operation | |
| CN110887790B (en) | Urban lake eutrophication simulation method and system based on FVCOM and remote sensing inversion | |
| GB2547816B (en) | Actually-measured marine environment data assimilation method based on sequence recursive filtering three-dimensional variation | |
| Niu et al. | Uncertainty modeling for chaotic time series based on optimal multi-input multi-output architecture: Application to offshore wind speed | |
| CN105260786B (en) | A kind of simulation credibility of electric propulsion system assessment models comprehensive optimization method | |
| Gómez et al. | Optimal placement and sizing from standpoint of the investor of Photovoltaics Grid-Connected Systems using Binary Particle Swarm Optimization | |
| Jiang et al. | Automatic calibration a hydrological model using a master–slave swarms shuffling evolution algorithm based on self-adaptive particle swarm optimization | |
| CN107860889A (en) | The Forecasting Methodology and equipment of the soil organism | |
| Tian et al. | Variable frequency wind speed trend prediction system based on combined neural network and improved multi-objective optimization algorithm | |
| Zou et al. | Wind turbine power curve modeling using an asymmetric error characteristic-based loss function and a hybrid intelligent optimizer | |
| CN105222787A (en) | Based on the location fingerprint base construction method of matrix fill-in | |
| Rashid et al. | Optimization of hydropower and related benefits through Cascade Reservoirs for sustainable economic growth | |
| CN105701568A (en) | Heuristic power distribution network state estimation measurement position rapid optimization method | |
| CN109931903A (en) | A kind of cylindricity assessment method based on improvement whale optimization algorithm | |
| CN108235347A (en) | A kind of wireless sensor network consumption control method | |
| Huang et al. | A data-driven method for hybrid data assimilation with multilayer perceptron | |
| Sedki et al. | Swarm intelligence for groundwater management optimization | |
| Wang et al. | Spatial heterogeneity automatic detection and estimation | |
| CN104657442A (en) | Multi-target community discovering method based on local searching | |
| Cao et al. | A grey wolf optimizer–cellular automata integrated model for urban growth simulation and optimization | |
| Liu et al. | Cost and capacity optimization of regional wind-hydrogen integrated energy system | |
| CN116029618B (en) | Dynamic safety partition assessment method and system for power system |
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 |