CN111800301A - Network security evaluation method and system in machine type communication - Google Patents
Network security evaluation method and system in machine type communication Download PDFInfo
- Publication number
- CN111800301A CN111800301A CN202010842550.3A CN202010842550A CN111800301A CN 111800301 A CN111800301 A CN 111800301A CN 202010842550 A CN202010842550 A CN 202010842550A CN 111800301 A CN111800301 A CN 111800301A
- Authority
- CN
- China
- Prior art keywords
- machine type
- type communication
- deep learning
- learning network
- network model
- 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
- 238000004891 communication Methods 0.000 title claims abstract description 93
- 238000011156 evaluation Methods 0.000 title claims abstract description 55
- 238000013135 deep learning Methods 0.000 claims abstract description 69
- 230000036541 health Effects 0.000 claims abstract description 59
- 238000004364 calculation method Methods 0.000 claims abstract description 15
- 238000012549 training Methods 0.000 claims abstract description 7
- 238000000034 method Methods 0.000 claims description 31
- 239000011159 matrix material Substances 0.000 claims description 21
- 238000009826 distribution Methods 0.000 claims description 8
- 238000004587 chromatography analysis Methods 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 4
- 238000009825 accumulation Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 3
- 230000005284 excitation Effects 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000013210 evaluation model Methods 0.000 description 4
- 238000012854 evaluation process Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000003862 health status Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- Computational Mathematics (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Analysis (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention relates to a network security evaluation method and a system in machine type communication, which comprises the steps of constructing a deep learning network model based on predefined network security key characteristic quantity in the machine type communication; the network safety and health state in machine type communication is comprehensively evaluated by combining a deep learning network model and an expert discussion system; and updating the deep learning network model on line according to the evaluation result. The online training and updating of the multilayer extreme learning machine are realized through the feedback iteration of the expert discussion system and the deep learning network, so that the input results of the two are finally consistent, and the calculation result of the network safety and health index is more real and credible.
Description
Technical Field
The invention relates to the technical field of monitoring, in particular to a network security evaluation method and system in machine type communication.
Background
Machine type communication is an important communication facility in modern cities, and the network safety and the quality of users can be directly influenced by the good or bad communication operation state.
In the past, evaluation on machine type communication mainly focuses on indexes such as reliability, economy, safety and quality of machine type communication, and the health state of machine type communication cannot be comprehensively grasped, so that a network safety and health index concept in machine type communication needs to be introduced. The traditional network security evaluation method adopts a calculation formula proposed by the United kingdom EA company, but the method only considers the influence of aging on equipment, cannot comprehensively consider various factors and cannot be expanded to a machine type communication network. In recent years, machine type communication health evaluation methods based on an analytic hierarchy process, a delphire method, an optimization principle, gray correlation analysis, and the like have been proposed. However, some of the methods are only suitable for single equipment, some parameter selections are too subjective, the inheritance and the multiplexing of expert experiences cannot be realized, and the problem of how to carry out network security health index calculation for a large-scale communication network still cannot be solved.
Currently, although the conventional evaluation method can realize the evaluation of the network security health state in the machine type communication, the evaluation error is caused by the lack of instant feedback in the evaluation process, and the consequent negative influence and the severity of economic loss can not be evaluated.
Disclosure of Invention
In order to solve the above problems, the present invention provides a method and a system for evaluating network security in machine type communication, which evaluate a network security health index from a new perspective. The deep learning principle is combined with an expert discussion system, so that the online training and updating of the evaluation model are realized, and the output result is more reasonable; therefore, the problem of safety evaluation of the network safety and health index aiming at large-scale communication equipment and networks is solved, and the inheritance and the reuse of expert experience are facilitated.
The purpose of the invention is realized by adopting the following technical scheme:
a method for network security evaluation in machine type communication, the method comprising:
constructing a deep learning network model based on network security key characteristic quantity in predefined machine type communication;
the network safety and health state in machine type communication is comprehensively evaluated by combining a deep learning network model and an expert discussion system;
and updating the deep learning network model on line according to the evaluation result.
Preferably, the network security critical feature quantities in the predefined machine type communication include: taking machine type communication as an evaluation object, and dividing the machine type communication into power distribution equipment and a machine type communication network according to a self-defined machine type communication classification rule; and acquiring the classified characteristic quantities of all parts, selecting key characteristic quantities for evaluating the network security and health index from the characteristic quantities, and generating a characteristic space.
Further, the selecting key characteristic quantities for evaluating the network security health index comprises: and obtaining key characteristic quantity through oil chromatographic analysis according to the dynamics of a network topological structure and member relation, the unreliability of a wireless channel, the electric quantity, the storage space, the calculation and the communication capacity of the terminal node and the routing node.
Preferably, the deep learning network model is a deep learning network formed based on a plurality of layers of extreme learning machines, and the construction method includes: and mapping the key characteristic quantity as an input sample into a new characteristic space to form a training sample set X ═ Xi,ti},i=1,...,n;
Wherein x isiWhich represents the input samples of the sample to be tested,tirepresenting the network security health index corresponding to the input sample, wherein n is the number of the samples;
randomly generating connection weights for an input layer to a first hidden layerAnd an output matrix H of the first hidden layer1(ii) a Calculating beta by least square method1The expression is as follows:
will be (beta)1)TReplacing the connection weight β of the input layer to the first hidden layer1Randomly generating the connection weight beta of the first hidden layer to the second hidden layer2And an output matrix H of the second hidden layer2;
Obtaining the output weight beta by the following formula calculation by adopting a least square method3:
In the formula, ajAnd bjAnd respectively representing an input weight value and a hidden layer threshold value which are randomly set and are associated with the jth hidden node, wherein z is the number of the hidden nodes, H is a generalized Jacobian matrix, and T is the total quantity of the network security health index corresponding to the sample.
Preferably, the comprehensive evaluation of the network security and health state in the machine type communication by combining the deep learning network model and the expert discussion system comprises; the newly generated sample x to be testednewRespectively inputting the expert discussion system and the deep learning network model, comparing the obtained output results, and judging whether the deep learning network model is consistent with the network security health index output by the expert discussion system; if the two models are consistent, the deep learning network model is good; if not, judging whether to execute the online updating of the deep learning network model according to the difference value; wherein,
the expert discussion system is used for online scoring of the health state of the machine type communication according to expert experience, relevant reference documents or experimental reports so as to achieve the acquisition of the safety and health index of the machine type communication network.
Preferably, the online updating of the deep learning network model according to the evaluation result includes: if the difference value of the output results of the expert discussion system and the deep learning network model is larger than a preset threshold value, the network safety and health index output by the expert discussion system is used as a mark { x) of the current sample to be testednew,tnew};
Will { xnew,tnewAs a new sample subset X to be testednewWhen the number accumulation of the samples to be tested exceeds a user-defined threshold value, the deep learning network model is updated on line through the following formula:
mixing X with XnewInputting the updated deep learning network and respectively outputting the optimal matrixThe expression is as follows:
will be provided withSubstituted for beta3Completing the on-line updating of the deep learning network;
in the formula, I is an identity matrix, P is any one infinite differentiable excitation function, respectively inputting the connection weight of the input layer to the first hidden layer, the connection weight of the first hidden layer to the second hidden layer and the output weight in the updated deep learning network model;and outputting the matrix for the updated first hidden layer.
A network security evaluation system in machine type communication, comprising:
the building module is used for building a deep learning network model based on the network security key characteristic quantity in the predefined machine type communication;
the evaluation module is used for comprehensively evaluating the network security and health state in the machine type communication by combining a deep learning network model and an expert discussion system;
and the updating module is used for updating the deep learning network model on line according to the evaluation result.
Preferably, the building block comprises:
the device comprises a determining unit, a judging unit and a judging unit, wherein the determining unit is used for taking the machine type communication as an evaluation object and dividing the machine type communication into power distribution equipment and a machine type communication network according to a self-defined machine type communication classification rule;
and the acquisition unit is used for acquiring the classified characteristic quantities of all the parts, selecting key characteristic quantities for evaluating the network security health index from the characteristic quantities and generating a characteristic space.
Further, the selecting unit includes: and the acquisition subunit is used for acquiring the key characteristic quantity through oil chromatographic analysis according to the dynamics of a network topology structure and member relationship, the unreliability of a wireless channel, the electric quantity, the storage space, the calculation and the communication capacity of the terminal node and the routing node.
Compared with the prior art, the invention has the following beneficial effects:
the network security evaluation method and system in machine type communication provided by the invention embody the combination of human intelligence and artificial intelligence, realize the inheritance and reuse of expert experience and knowledge, adopt a deep learning network, and solve the problem of accurately evaluating the health states of machine type communication equipment and a communication network when human resources are insufficient.
In the scheme of the invention, the evaluation object is selected firstly, and then the key characteristic quantity and the corresponding data information are selected according to the actual situation, so that the evaluation has timeliness. Through the extraction of the key characteristic quantity, the number of input quantities in the evaluation model can be reduced, and meanwhile, the redundant condition of various characteristic quantities to state evaluation is reduced, and the method is important for establishing the evaluation model.
By constructing the evaluation model, the evaluation of the health state of the evaluation object by using the existing evaluation algorithm can be realized. In addition, an expert comprehensive study is constructed, so that the expert can evaluate the health state of the evaluation object on line. The two scores are comprehensively evaluated, and a deep learning method is used in the evaluation process, so that the evaluation is more accurate, the evaluation error caused by the error of one party is avoided, and the threat to the safe operation of the machine type communication network is formed.
Comprehensive evaluation is the core of the method, and has a crucial role in evaluating accuracy. The comprehensive evaluation is to train the deep learning model according to the historical evaluation process to obtain a comparison model, then to input the evaluation score into the model, to compare the evaluation results, through evaluation inconsistency feedback, the model evaluation and the comprehensive study can continue to be carried out, convergence towards consistency is carried out, and finally both parties converge near the real health status value. The comprehensive evaluation enables the method to evaluate the health state of each node of the machine type communication rapidly, comprehensively, reliably and efficiently.
Drawings
FIG. 1 is a flow chart of a method for evaluating network security in machine type communication according to the present invention;
FIG. 2 is a flowchart of a method for comprehensive evaluation of network security and health in machine type communication according to the present invention;
FIG. 3 is a deep learning network model topological graph formed based on a multi-layer extreme learning machine provided by the invention.
Detailed Description
The technical solution in the embodiment of the present invention is described below with reference to the accompanying drawings.
A method for evaluating network security in machine type communication as shown in fig. 1 includes the following steps:
s1, constructing a deep learning network model based on the network security key characteristic quantity in the predefined machine type communication;
s2, combining the deep learning network model and the expert discussion system, carrying out comprehensive evaluation on the network security and health state in the machine type communication;
and S3, updating the deep learning network model on line according to the evaluation result.
1) The predefined network security critical feature quantities in machine type communication include: taking machine type communication as an evaluation object, and dividing the machine type communication into power distribution equipment and a machine type communication network according to a self-defined machine type communication classification rule; and acquiring the classified characteristic quantities of all parts, selecting key characteristic quantities for evaluating the network security and health index from the characteristic quantities, and generating a characteristic space.
The method for evaluating the network security health index comprises the following steps: and obtaining key characteristic quantity through oil chromatographic analysis according to the dynamics of a network topological structure and member relation, the unreliability of a wireless channel, the electric quantity, the storage space, the calculation and the communication capacity of the terminal node and the routing node.
2) Constructing a deep learning network model; the deep learning network model is a deep learning network formed based on a plurality of layers of extreme learning machines, and is shown in FIG. 3. The key characteristic quantities of the power distribution equipment and the network are mapped to the characteristic space of the hidden layer from the original space, a plurality of hidden nodes and activation functions are arranged between each layer, the health state of the current equipment or the machine type communication network can be identified according to the input key characteristic quantities, and the condition of the power distribution equipment and the condition of the network can be matched; and finally outputting the machine type communication network safety and health index.
The construction method comprises the following steps: and mapping the key characteristic quantity as an input sample into a new characteristic space to form a training sample set X ═ Xi,t i1, ·, n; wherein x isiRepresenting an input sample, tiRepresenting the network security health index corresponding to the input sample, wherein n is the number of the samples;
randomly generating connection weights for an input layer to a first hidden layerAnd an output matrix H of the first hidden layer1(ii) a Calculating beta by least square method1The expression is as follows:
will be (beta)1)TReplacing the connection weight β of the input layer to the first hidden layer1Randomly generating the connection weight beta of the first hidden layer to the second hidden layer2And an output matrix H of the second hidden layer2;
Obtaining the output weight beta by the following formula calculation by adopting a least square method3:
In the formula, ajAnd bjAnd respectively representing an input weight value and a hidden layer threshold value which are randomly set and are associated with the jth hidden node, wherein z is the number of the hidden nodes, H is a generalized Jacobian matrix, and T is the total quantity of the network security health index corresponding to the sample.
The specific calculation principle for evaluating the health state index of machine type communication is as follows: the worse the health status, the higher the weight occupied by the part, and the more harmful the machine type communication, the higher the weight of the part. The calculation process mainly comprises the steps of firstly calculating a weight coefficient matrix, then multiplying the weight coefficient matrix with each health state index matrix to obtain a unified index value serving as the whole health state index of the machine type communication, and objectively reflecting the health state of the current machine type communication through the index to realize the monitoring of the network safety health state in the machine type communication.
3) The network safety and health state in machine type communication is comprehensively evaluated by combining a deep learning network model and an expert discussion system;
the expert discussion system is used for acquiring expert knowledge and experience, and regarding the network security health index output by the expert discussion system as an accurate value matched with the actual situation for marking a training sample, wherein the sample mark can be obtained from other data (such as reference documents, experimental reports and the like) outside the system; the online training and updating of the multilayer extreme learning machine are realized through the feedback iteration of the expert discussion system and the deep learning network, so that the input results of the two are finally consistent, and the calculation result of the network safety and health index is more real and credible.
The comprehensive evaluation of the network safety and health state in the machine type communication is carried out by combining a deep learning network model and an expert discussion system; the newly generated sample x to be testednewRespectively inputting the expert discussion system and the deep learning network model, comparing the obtained output results, and judging whether the deep learning network model is consistent with the network security health index output by the expert discussion system; if the two models are consistent, the deep learning network model is good; and if the difference values are not consistent, judging whether to execute online updating of the deep learning network model according to the difference values.
4) And updating the deep learning network model on line according to the evaluation result. The evaluation process of the machine type communication network safety and health index is a feedback adjustment process, a multi-layer extreme learning machine network is established by utilizing the principle of deep learning, and the deep learning network is trained according to historical evaluation data; and marking the newly input samples through an expert discussion system, and realizing the rolling update of the multilayer extreme learning machine model. The specific process is as follows:
if the difference value of the output results of the expert discussion system and the deep learning network model is larger than a preset threshold value, the network safety and health index output by the expert discussion system is used as a mark { x) of the current sample to be testednew,tnew};
Will { xnew,tnewAs a new sample subset X to be testednewWhen the number accumulation of the samples to be tested exceeds a user-defined threshold value, the deep learning network model is updated on line through the following formula:
mixing X with XnewInputting the updated deep learning network and respectively outputting the optimal matrixThe expression is as follows:
will be provided withSubstituted for beta3Completing the on-line updating of the deep learning network;
wherein I is an identity matrix, P is any one infinitely differentiable excitation function, P1=(H1)TH1,Respectively inputting the connection weight of the input layer to the first hidden layer, the connection weight of the first hidden layer to the second hidden layer and the output weight in the updated deep learning network model;and outputting the matrix for the updated first hidden layer.
Based on the same technical concept, the invention also provides a network security evaluation system in machine type communication, which comprises:
the building module is used for building a deep learning network model based on the network security key characteristic quantity in the predefined machine type communication;
the evaluation module is used for comprehensively evaluating the network security and health state in the machine type communication by combining a deep learning network model and an expert discussion system;
and the updating module is used for updating the deep learning network model on line according to the evaluation result.
Preferably, the building block comprises:
the device comprises a determining unit, a judging unit and a judging unit, wherein the determining unit is used for taking the machine type communication as an evaluation object and dividing the machine type communication into power distribution equipment and a machine type communication network according to a self-defined machine type communication classification rule;
and the acquisition unit is used for acquiring the classified characteristic quantities of all the parts, selecting key characteristic quantities for evaluating the network security health index from the characteristic quantities and generating a characteristic space.
Further, the selecting unit includes: and the acquisition subunit is used for acquiring the key characteristic quantity through oil chromatographic analysis according to the dynamics of a network topology structure and member relationship, the unreliability of a wireless channel, the electric quantity, the storage space, the calculation and the communication capacity of the terminal node and the routing node.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the present invention, and they should be construed as being included in the following claims and description.
Claims (9)
1. A method for evaluating network security in machine type communication, the method comprising:
constructing a deep learning network model based on network security key characteristic quantity in predefined machine type communication;
the network safety and health state in machine type communication is comprehensively evaluated by combining a deep learning network model and an expert discussion system;
and updating the deep learning network model on line according to the evaluation result.
2. The method of claim 1, wherein the predefined network security critical feature quantities in machine type communication comprise: taking machine type communication as an evaluation object, and dividing the machine type communication into power distribution equipment and a machine type communication network according to a self-defined machine type communication classification rule; and acquiring the classified characteristic quantities of all parts, selecting key characteristic quantities for evaluating the network security and health index from the characteristic quantities, and generating a characteristic space.
3. The method of claim 2, wherein selecting key feature quantities for evaluating network security health indices comprises: and obtaining key characteristic quantity through oil chromatographic analysis according to the dynamics of a network topological structure and member relation, the unreliability of a wireless channel, the electric quantity, the storage space, the calculation and the communication capacity of the terminal node and the routing node.
4. The method of claim 1, wherein the deep learning network model is a deep learning network constructed based on a plurality of layers of extreme learning machines, and the construction method comprises the following steps: and mapping the key characteristic quantity as an input sample into a new characteristic space to form a training sample set X ═ Xi,ti},i=1,...,n;
Wherein x isiWhich represents the input samples of the sample to be tested,tirepresenting the network security health index corresponding to the input sample, wherein n is the number of the samples;
randomly generating connection weights for an input layer to a first hidden layerAnd an output matrix H of the first hidden layer1;
Calculating beta by least square method1The expression is as follows:
will be (beta)1)TReplacing the connection weight β of the input layer to the first hidden layer1Randomly generating the connection weight beta of the first hidden layer to the second hidden layer2And an output matrix H of the second hidden layer2;
Obtaining the output weight beta by the following formula calculation by adopting a least square method3:
In the formula, ajAnd bjAnd respectively representing an input weight value and a hidden layer threshold value which are randomly set and are associated with the jth hidden node, wherein z is the number of the hidden nodes, H is a generalized Jacobian matrix, and T is the total quantity of the network security health index corresponding to the sample.
5. The method of claim 1, wherein the comprehensive assessment of network security health in machine type communication in conjunction with a deep learning network model and an expert seminar system comprises; the newly generated sample x to be testednewRespectively inputting the expert discussion system and the deep learning network model, comparing the obtained output results, and judging whether the deep learning network model is consistent with the network security health index output by the expert discussion system; if the two models are consistent, the deep learning network model is good; if not, judging whether to execute the online updating of the deep learning network model according to the difference value; wherein,
the expert discussion system is used for online scoring of the health state of the machine type communication according to expert experience, relevant reference documents or experimental reports so as to achieve the acquisition of the safety and health index of the machine type communication network.
6. The method of claim 1 or 4, wherein the online updating of the deep learning network model according to the evaluation result comprises: if the difference value of the output results of the expert discussion system and the deep learning network model is larger than a preset threshold value, the network safety and health index output by the expert discussion system is used as a mark { x) of the current sample to be testednew,tnew};
Will { xnew,tnewAs a new sample subset X to be testednewWhen the number accumulation of the samples to be tested exceeds a user-defined threshold value, the deep learning network model is updated on line through the following formula:
mixing X with XnewInputting the updated deep learning network and respectively outputting the optimal matrixThe expression is as follows:
wherein I is an identity matrix, P is any one infinitely differentiable excitation function, P1=(H1)TH1, Respectively inputting the connection weight of the input layer to the first hidden layer, the connection weight of the first hidden layer to the second hidden layer and the output weight in the updated deep learning network model;and outputting the matrix for the updated first hidden layer.
7. A system for evaluating network security in machine type communication, comprising:
the building module is used for building a deep learning network model based on the network security key characteristic quantity in the predefined machine type communication;
the evaluation module is used for comprehensively evaluating the network security and health state in the machine type communication by combining a deep learning network model and an expert discussion system;
and the updating module is used for updating the deep learning network model on line according to the evaluation result.
8. The system of claim 7, wherein the build module comprises:
the device comprises a determining unit, a judging unit and a judging unit, wherein the determining unit is used for taking the machine type communication as an evaluation object and dividing the machine type communication into power distribution equipment and a machine type communication network according to a self-defined machine type communication classification rule;
and the acquisition unit is used for acquiring the classified characteristic quantities of all the parts, selecting key characteristic quantities for evaluating the network security health index from the characteristic quantities and generating a characteristic space.
9. The system of claim 8, wherein the selecting unit comprises: and the acquisition subunit is used for acquiring the key characteristic quantity through oil chromatographic analysis according to the dynamics of a network topology structure and member relationship, the unreliability of a wireless channel, the electric quantity, the storage space, the calculation and the communication capacity of the terminal node and the routing node.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010842550.3A CN111800301A (en) | 2020-08-20 | 2020-08-20 | Network security evaluation method and system in machine type communication |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010842550.3A CN111800301A (en) | 2020-08-20 | 2020-08-20 | Network security evaluation method and system in machine type communication |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111800301A true CN111800301A (en) | 2020-10-20 |
Family
ID=72834612
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010842550.3A Pending CN111800301A (en) | 2020-08-20 | 2020-08-20 | Network security evaluation method and system in machine type communication |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111800301A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113017585A (en) * | 2021-03-18 | 2021-06-25 | 深圳市雅士长华智能科技有限公司 | Health management system based on intelligent analysis |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160353226A1 (en) * | 2015-06-01 | 2016-12-01 | Huawei Technologies Co., Ltd. | Method and System for MTC Event Management |
CN106899428A (en) * | 2016-09-27 | 2017-06-27 | 兰州交通大学 | A kind of machine type communication traffic forecast category of model method under Railway Environment |
CN109543818A (en) * | 2018-10-19 | 2019-03-29 | 中国科学院计算技术研究所 | A kind of link evaluation method and system based on deep learning model |
CN110379523A (en) * | 2019-07-19 | 2019-10-25 | 厦门医管家医疗科技有限公司 | Infrared remote based on cloud platform sees a doctor method and system |
CN110647900A (en) * | 2019-04-12 | 2020-01-03 | 中国人民解放军战略支援部队信息工程大学 | Intelligent safety situation prediction method, device and system based on deep neural network |
US10574512B1 (en) * | 2018-09-04 | 2020-02-25 | Cisco Technology, Inc. | Deep learning architecture for collaborative anomaly detection and explanation |
CN110927535A (en) * | 2019-11-12 | 2020-03-27 | 国网天津市电力公司电力科学研究院 | Power equipment partial discharge severity evaluation method based on extreme learning machine |
-
2020
- 2020-08-20 CN CN202010842550.3A patent/CN111800301A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160353226A1 (en) * | 2015-06-01 | 2016-12-01 | Huawei Technologies Co., Ltd. | Method and System for MTC Event Management |
CN106899428A (en) * | 2016-09-27 | 2017-06-27 | 兰州交通大学 | A kind of machine type communication traffic forecast category of model method under Railway Environment |
US10574512B1 (en) * | 2018-09-04 | 2020-02-25 | Cisco Technology, Inc. | Deep learning architecture for collaborative anomaly detection and explanation |
CN109543818A (en) * | 2018-10-19 | 2019-03-29 | 中国科学院计算技术研究所 | A kind of link evaluation method and system based on deep learning model |
CN110647900A (en) * | 2019-04-12 | 2020-01-03 | 中国人民解放军战略支援部队信息工程大学 | Intelligent safety situation prediction method, device and system based on deep neural network |
CN110379523A (en) * | 2019-07-19 | 2019-10-25 | 厦门医管家医疗科技有限公司 | Infrared remote based on cloud platform sees a doctor method and system |
CN110927535A (en) * | 2019-11-12 | 2020-03-27 | 国网天津市电力公司电力科学研究院 | Power equipment partial discharge severity evaluation method based on extreme learning machine |
Non-Patent Citations (9)
Title |
---|
JIANWEI ZHAO , ZHIHUIWANG, DONGSUNPARK, 《NEUROCOMPUTING》;ONLINE SEQUENTIAL EXTREME LEARNING MACHINE WITH FORGETTING MECHANISM * |
SAMAD ALI;HOSSEIN ASGHARIMOGHADDAM;NANDANA RAJATHEVA等: "Contextual Bandit Learning for Machine Type Communications in the Null Space of Multi-Antenna Systems", 《IEEE TRANSACTIONS ON COMMUNICATIONS 》 * |
叶亮等: "一种基于深度学习的网络安全态势评估方法", 《智能计算机与应用》 * |
周珑; 郭威; 王建永;等: "基于神经网络算法的网络安全评价模型", 《沈阳工业大学学报》 * |
李鹏,梁康有: "机器类通信终端蜂窝网接入拥塞控制", 《重庆科技学院学报(自然科学版) 》 * |
罗堡文: "基于深度学习的网络安全态势评估研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
邹航菲,罗婷婷, 《现代电子技术》;极限学习机算法的网络安全评价研究 * |
邹航菲等: "极限学习机算法的网络安全评价研究", 《现代电子技术》 * |
郎波霏, 《中国优秀硕士学位论文全文数据库信息科技辑》;新型双隐层极限学习机及其应用 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113017585A (en) * | 2021-03-18 | 2021-06-25 | 深圳市雅士长华智能科技有限公司 | Health management system based on intelligent analysis |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109086913B (en) | Power system transient stability assessment method and system based on deep learning | |
CN112054943B (en) | Traffic prediction method for mobile network base station | |
CN105976257A (en) | Power grid vulnerability evaluation method based on membership function fuzzy comprehensive evaluation method | |
CN107734512A (en) | A kind of network selecting method based on the analysis of gray scale relevance presenting levelses | |
CN112859822A (en) | Equipment health analysis and fault diagnosis method and system based on artificial intelligence | |
CN107038532A (en) | Distribution network load turning solution evaluation method based on optimum combination weight | |
CN105976020B (en) | A kind of network flow prediction method considering small echo cross-layer relevance | |
CN113705085B (en) | Intelligent power grid multi-level structure modeling and risk assessment method | |
CN110417011A (en) | A kind of online dynamic secure estimation method based on mutual information Yu iteration random forest | |
CN109246495A (en) | A kind of optical network service method for evaluating quality of oriented multilayer, multi objective | |
CN114006370B (en) | Power system transient stability analysis and evaluation method and system | |
CN110083951A (en) | A kind of solid insulation life-span prediction method based on transformer correlation operation data | |
CN105930924B (en) | Power distribution network situation perception method based on complex event processing technology and decision tree | |
CN112183999A (en) | Power distribution main equipment sensor reliability evaluation index feature extraction method | |
CN107294775A (en) | Communication optimization method based on analytic hierarchy process (AHP) and genetic algorithm | |
CN104077493A (en) | Method for constructing state evaluation index system of electric relaying protection system | |
CN110910026A (en) | Intelligent management and decision-making method and system for route loss of trans-provincial power transmission line | |
CN105954650A (en) | Power distribution network fault locating method and system | |
CN106228459A (en) | Equivalent reliability estimation method based on Monte Carlo | |
CN112966381A (en) | Power transformer comprehensive state evaluation method based on evidence cloud matter element model | |
CN115587685A (en) | Tough power distribution network evaluation system containing high-permeability distributed power supply | |
CN111800301A (en) | Network security evaluation method and system in machine type communication | |
CN117421918A (en) | Transformer state prediction model construction method and system for digital twin platform | |
CN112348401A (en) | Operation and maintenance management method for distribution network automation equipment | |
CN115860526A (en) | Comprehensive performance evaluation method of communication network based on comprehensive fuzzy evaluation |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201020 |