CN107959675A - The exception flow of network detection method and device of power distribution network wireless communication access - Google Patents

The exception flow of network detection method and device of power distribution network wireless communication access Download PDF

Info

Publication number
CN107959675A
CN107959675A CN201711196282.7A CN201711196282A CN107959675A CN 107959675 A CN107959675 A CN 107959675A CN 201711196282 A CN201711196282 A CN 201711196282A CN 107959675 A CN107959675 A CN 107959675A
Authority
CN
China
Prior art keywords
network
flow
data
exception
wireless communication
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
Application number
CN201711196282.7A
Other languages
Chinese (zh)
Inventor
郭志民
吴春明
周伯阳
周海峰
肖荣华
牛霜霞
莫坚松
刘文军
吕卓
张伟
陈岑
张之刚
张红义
马彩霞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang University ZJU
State Grid Corp of China SGCC
Electric Power Research Institute of State Grid Henan Electric Power Co Ltd
Original Assignee
Zhejiang University ZJU
State Grid Corp of China SGCC
Electric Power Research Institute of State Grid Henan Electric Power Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Zhejiang University ZJU, State Grid Corp of China SGCC, Electric Power Research Institute of State Grid Henan Electric Power Co Ltd filed Critical Zhejiang University ZJU
Priority to CN201711196282.7A priority Critical patent/CN107959675A/en
Publication of CN107959675A publication Critical patent/CN107959675A/en
Pending legal-status Critical Current

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L63/00—Network architectures or network communication protocols for network security
    • H04L63/14—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic
    • H04L63/1408—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic by monitoring network traffic
    • H04L63/1425—Traffic logging, e.g. anomaly detection
    • 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
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L63/00—Network architectures or network communication protocols for network security
    • H04L63/14—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic
    • H04L63/1408—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic by monitoring network traffic
    • H04L63/1416—Event detection, e.g. attack signature detection
    • 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
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
    • H04W12/08—Access security

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Security & Cryptography (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Computing Systems (AREA)
  • Computer Hardware Design (AREA)
  • General Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Physics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Algebra (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

The invention discloses the exception flow of network detection method and device of a kind of access of power distribution network wireless communication.Wherein method includes：Obtain the network flow data of power distribution network wireless communication access；Network flow data is detected using the adaptive neural network fuzzy system model pre-established, exports testing result；Determine whether network flow data exception occurs according to detection structure.The present invention can dynamically filter out the abnormal flow feature set for meeting feature by higher-dimension low-rank abnormal traffic detection model ANFIS models, accurately detect abnormal flow in electric power wireless network, and classify to it, improve abnormal traffic detection rate, rate of false alarm is reduced, which, which puts, can be used for improving electric power wireless communication access procedure security protection ability.

Description

The exception flow of network detection method and device of power distribution network wireless communication access
Technical field
The present invention relates to Distribution Network Communication technical field, in particular to a kind of net of power distribution network wireless communication access Network anomalous traffic detection method and device.
Background technology
For abnormal flow monitoring method in electric power wireless communication, usually it is difficult to determine there are parameter base line, very flexible, Rate of false alarm it is high the defects of, such as, using BP neural network model algorithm carry out exception flow of network detection when, be easily trapped into office Portion's minimum value, and the problems such as convergence rate is low, and then the problem of cause accuracy rate higher than relatively low and rate of false alarm.
The content of the invention
It is a primary object of the present invention to provide a kind of exception flow of network detection method of power distribution network wireless communication access And device, to solve, the exception flow of network Detection accuracy of power distribution network wireless communication in the prior art is low, rate of false alarm is high asks Topic.
To achieve these goals, according to an aspect of the invention, there is provided what a kind of power distribution network wireless communication accessed Exception flow of network detection method.The method according to the invention includes：Obtain the network traffics number of power distribution network wireless communication access According to；The network flow data is detected using the adaptive neural network fuzzy system model pre-established, output detection knot Fruit；Determine whether the network flow data exception occurs according to the detection structure.
Alternatively, before the network flow data of power distribution network wireless communication access is obtained, further include：Establish described adaptive Answer neuro fuzzy systems model.
Alternatively, establishing the adaptive neural network fuzzy system model includes：Gather exception flow of network data；Using subtracting Method clustering algorithm carries out Non-Linear Programming to the exception flow of network data, and training is optimized to data using initial model Obtain the adaptive neural network fuzzy system model.
Alternatively, collection exception flow of network data include：The Network Abnormal of default quantity is randomly selected from database Data on flows sample, using a portion as training sample, another part is as test sample；According to the Network Abnormal of extraction The stream feature of data, is normalized the Network Abnormal data of the extraction.
Alternatively, the exception flow of network data include at least one of：AlphaAnomaly abnormal flows, DDos Abnormal flow, PortScan abnormal flows, NetworkScan abnormal flows, Worms abnormal flows and FlashCrowd are abnormal Flow.
Alternatively, it is normalized by the following formula：
Wherein, x ' is the data after normalized, and numerical value is between 0~1；It is the number average value for flowing characteristic,S is that the characteristic standard of sample is poor,N is exception flow of network data sample Quantity, xiRepresent i-th exception flow of network data sample.
Alternatively, the adaptive neural network fuzzy system model selects the membership function of trigonometric function.
The another aspect of the embodiment of the present invention, additionally provides a kind of exception flow of network inspection of power distribution network wireless communication access Device is surveyed, including：Acquisition module, for obtaining the network flow data of power distribution network wireless communication access；Detection module, for profit The network flow data is detected with the adaptive neural network fuzzy system model pre-established, exports testing result；Really Cover half block, for determining whether the network flow data exception occurs according to the detection structure.
Alternatively, further include：Establish module, for obtain power distribution network wireless communication access network flow data it Before, establish the adaptive neural network fuzzy system model.
Alternatively, the module of establishing includes：Collecting unit, for gathering exception flow of network data；Training unit, is used In carrying out Non-Linear Programming to the exception flow of network data using subtraction clustering algorithm, data are carried out using initial model Optimization training obtains the adaptive neural network fuzzy system model.
The exception stream for meeting feature can be dynamically filtered out by higher-dimension low-rank abnormal traffic detection model-ANFIS models Measure feature collection, accurately detects abnormal flow in electric power wireless network, and classifies to it, improves abnormal traffic detection Rate, reduces rate of false alarm, which, which puts, can be used for improving electric power wireless communication access procedure security protection ability.
Brief description of the drawings
The attached drawing for forming the part of the application is used for providing a further understanding of the present invention, schematic reality of the invention Apply example and its explanation is used to explain the present invention, do not form inappropriate limitation of the present invention.In the accompanying drawings：
Fig. 1 is the flow of the exception flow of network detection method of power distribution network wireless communication access according to embodiments of the present invention Figure；
Fig. 2 is the training error curve map of ANFIS models；
Fig. 3 is the training error curve map of BP neural network model；
Fig. 4 is the structure chart of ANFIS models according to embodiments of the present invention；
Fig. 5 is ANFIS model training Error Graphs according to embodiments of the present invention；
Fig. 6 is the test result schematic diagram of ANFIS models according to embodiments of the present invention；
Fig. 7 is the test result schematic diagram of BP neural network model according to embodiments of the present invention；
Fig. 8 is the signal of the exception flow of network detection device of power distribution network wireless communication access according to embodiments of the present invention Figure.
Embodiment
It should be noted that in the case where there is no conflict, the feature in embodiment and embodiment in the application can phase Mutually combination.Below with reference to the accompanying drawings and the present invention will be described in detail in conjunction with the embodiments.
In order to make those skilled in the art more fully understand the present invention program, below in conjunction with the embodiment of the present invention Attached drawing, is clearly and completely described the technical solution in the embodiment of the present invention, it is clear that described embodiment is only The embodiment of a part of the invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill people Member's all other embodiments obtained without making creative work, should all belong to the model that the present invention protects Enclose.
It should be noted that term " first " in description and claims of this specification and above-mentioned attached drawing, " Two " etc. be for distinguishing similar object, without for describing specific order or precedence.It should be appreciated that so use Data can exchange in the appropriate case, so as to the embodiment of the present invention described herein.In addition, term " comprising " and " tool Have " and their any deformation, it is intended that cover it is non-exclusive include, for example, containing series of steps or unit Process, method, system, product or equipment are not necessarily limited to those steps clearly listed or unit, but may include without clear It is listing to Chu or for the intrinsic other steps of these processes, method, product or equipment or unit.
Fig. 1 is the flow of the exception flow of network detection method of power distribution network wireless communication access according to embodiments of the present invention Figure.As shown in Figure 1, that the method comprising the steps of is as follows：
Step S101, obtains the network flow data of power distribution network wireless communication access.The network flow data is to be detected Network flow data.Network flow data bag can be captured online using network interface mirror-image fashion.
Step S102, is detected network flow data using the adaptive neural network fuzzy system model pre-established, Export testing result.
Need first to establish detection model system, i.e. adaptive neural network fuzzy system before exception of network traffic detection is carried out (Adaptive Network-based Fuzzy Inference System, referred to as ANFIS) model.Specifically, obtaining Before the network flow data of power distribution network wireless communication access, further include：Establish adaptive neural network fuzzy system model.Utilize this The ANFIS models of foundation come detect power distribution network wireless communication access network traffics.
Step S103, determines whether network flow data exception occurs according to detection structure.
The exception stream for meeting feature can be dynamically filtered out by higher-dimension low-rank abnormal traffic detection model-ANFIS models Measure feature collection, accurately detects abnormal flow in electric power wireless network, and classifies to it, improves abnormal traffic detection Rate, reduces rate of false alarm, which, which puts, can be used for improving electric power wireless communication access procedure security protection ability.
Specifically, establishing adaptive neural network fuzzy system model includes：Gather exception flow of network data；Gathered using subtraction Class algorithm to exception flow of network data carry out Non-Linear Programming, using initial model to data optimize training obtain it is adaptive Answer neuro fuzzy systems model.
Specifically, the data of collection can include：The exception flow of network number of default quantity is randomly selected from database According to sample, using a portion as training sample, another part is as test sample；According to the Network Abnormal data of extraction Feature is flowed, the Network Abnormal data of extraction are normalized.
Exception flow of network data include at least one of：AlphaAnomaly abnormal flows, DDos abnormal flows, PortScan abnormal flows, NetworkScan abnormal flows, Worms abnormal flows and FlashCrowd abnormal flows.Can be with Used from MySQL database comprising above-mentioned left and right abnormal flow data, gather 200 sample datas altogether, wherein, 100 works For training sample, in addition 100 are used as test sample.
Further, it is normalized by the following formula：
Wherein, x ' is the data after normalized, and numerical value is between 0~1；It is the number average value for flowing characteristic,S is that the characteristic standard of sample is poor,N is exception flow of network data sample Quantity, xi represent i-th exception flow of network data sample.
After data have been gathered, subtraction clustering algorithm can be used to carry out the stream characteristic sample after normalized Non-Linear Programming, using the Sugeno types structure of generation as initial configuration, to final detection model (after training ANFIS models) parameters use hybrid learning algorithm and momentum technique successive optimization.The ANFIS moulds established Type selects the membership function of trigonometric function type, a of ANFIS models, b, and c parameter learning rates are preferably set to 0.01, in error It is limited to 10-3.The training error curve example of ANFIS models is as shown in Figure 2.
In order to contrast the advantage of the ANFIS models of the present invention, contrast experiment is carried out using BP neural network.BP neural network The input layer unit number of model is set as 6 according to stream characteristic, and output layer unit is several to be set as according to exception flow of network species 6, rule of thumb formula is set as 11 to hidden layer unit number.The training error curve of BP neural network model is as shown in Figure 3.
ANFIS models can be seen that than training time that BP neural network algorithm uses by contrast model training error It is shorter.Using momentum technique correction model parameter, enable a system to cross the local minimum of error surface.
In the embodiment of the present invention, ANFIS models include 1 input layer and output layer, 2 rules layers, structure such as Fig. 4 institutes Show.In first network layer, input variable is blurred, the output of each node is：
In formula：x1, x2It is the node of input；It is the node of output.
In second network layer, input variable is multiplied, each node output valve represents that rule intensity is：
In the 3rd network layer, the intensity of normalized rule is：
In the 4th network layer, each model rule output value is calculated：
In the 5th network layer, the output valve of calculate node：
Total output of ANFIS algorithms has given premise, consequent parameter to obtain：
The ANFIS model algorithms of the embodiment of the present invention carry out correction model parameter using momentum technique, enable a system to Cross the local minimum of error surface.The concrete form of momentum technique is：
ci(n+1)=ci(n)+Δci(n)
σi(n+1)=σi(n)+Δσi(n)
Wherein：λ is factor of momentum, can take 0.95 or so；N is iterative steps；β (n) is the learning rate of the n-th step computing.
The ANFIS model training Error Graphs of the embodiment of the present invention are as shown in Figure 5.
In order to judge the performance for each exception flow of network detection model established herein, using accuracy rate and rate of false alarm into Row evaluation.
The ANFIS models proposed using the embodiment of the present invention and the exception flow of network for establishing BP neural network algorithm are examined Survey the test result difference of model as shown in Figure 6 and Figure 7.The implication that wherein longitudinal and transverse axial coordinate represents is as shown in table 1.Use this The ANFIS models that inventive embodiments propose and the exception flow of network detection model established using BP neural network algorithm, to surveying The accuracy rate and rate of false alarm contrast that examination data are detected are as shown in table 2.
Table 1：
Table 2：
The embodiment of the present invention additionally provides a kind of exception flow of network detection device of power distribution network wireless communication access, the party Method can be used for performing the above-mentioned detection method of the embodiment of the present invention, as shown in figure 8, the device includes：Acquisition module 801, detection Module 802 and determining module 803.
Acquisition module 801 is used for the network flow data for obtaining the access of power distribution network wireless communication.The network flow data is Network flow data to be detected.Network flow data bag can be captured online using network interface mirror-image fashion.
Detection module 802 is used for using the adaptive neural network fuzzy system model pre-established to the network flow data It is detected, exports testing result.Need first to establish detection model system before exception of network traffic detection is carried out, i.e., it is adaptive Answer neuro fuzzy systems (Adaptive Network-based Fuzzy Inference System, referred to as ANFIS) mould Type.Specifically, which further includes：Module is established, for establishing adaptive neural network fuzzy system model.Utilize the foundation ANFIS models come detect power distribution network wireless communication access network traffics.
Determining module 803 is used to determine whether the network flow data exception occurs according to the detection structure.
The exception stream for meeting feature can be dynamically filtered out by higher-dimension low-rank abnormal traffic detection model-ANFIS models Measure feature collection, accurately detects abnormal flow in electric power wireless network, and classifies to it, improves abnormal traffic detection Rate, reduces rate of false alarm, which, which puts, can be used for improving electric power wireless communication access procedure security protection ability.
Specifically, establishing module includes：Collecting unit, for gathering exception flow of network data；Training unit, for making Non-Linear Programming is carried out to the exception flow of network data with subtraction clustering algorithm, data are optimized using initial model Training obtains the adaptive neural network fuzzy system model.
Specifically, collecting unit is specifically used for the exception flow of network data sample that default quantity is randomly selected from database This, using a portion as training sample, another part is as test sample；It is special according to the stream of the Network Abnormal data of extraction Sign, is normalized the Network Abnormal data of the extraction.
Exception flow of network data include at least one of：AlphaAnomaly abnormal flows, DDos abnormal flows, PortScan abnormal flows, NetworkScan abnormal flows, Worms abnormal flows and FlashCrowd abnormal flows.Can be with Used from MySQL database comprising above-mentioned left and right abnormal flow data, gather 200 sample datas altogether, wherein, 100 works For training sample, in addition 100 are used as test sample.
Further, it is normalized by the following formula：
Wherein, x ' is the data after normalized, and numerical value is between 0~1；It is the number average value for flowing characteristic,S is that the characteristic standard of sample is poor,N is exception flow of network data sample Quantity, xiRepresent i-th exception flow of network data sample.
After data have been gathered, subtraction clustering algorithm can be used to carry out the stream characteristic sample after normalized Non-Linear Programming, using the Sugeno types structure of generation as initial configuration, to final detection model (after training ANFIS models) parameters use hybrid learning algorithm and momentum technique successive optimization.The ANFIS moulds established Type selects the membership function of trigonometric function type, a of ANFIS models, b, and c parameter learning rates are preferably set to 0.01, in error It is limited to 10-3.The training error curve example of ANFIS models is as shown in Figure 2.
It should be noted that for foregoing each method embodiment, in order to be briefly described, therefore it is all expressed as a series of Combination of actions, but those skilled in the art should know, the present invention and from the limitation of described sequence of movement because According to the present invention, some steps can use other orders or be carried out at the same time.Secondly, those skilled in the art should also know Know, embodiment described in this description belongs to preferred embodiment, and involved action and module are not necessarily of the invention It is necessary.
In the above-described embodiments, the description to each embodiment all emphasizes particularly on different fields, and does not have the portion being described in detail in some embodiment Point, it may refer to the associated description of other embodiment.
In several embodiments provided herein, it should be understood that disclosed device, can be by another way Realize.For example, device embodiment described above is only schematical, such as the division of the unit, it is only one kind Division of logic function, can there is an other dividing mode when actually realizing, such as multiple units or component can combine or can To be integrated into another system, or some features can be ignored, or not perform.Another, shown or discussed is mutual Coupling, direct-coupling or communication connection can be by some interfaces, the INDIRECT COUPLING or communication connection of device or unit, Can be electrical or other forms.
The unit illustrated as separating component may or may not be physically separate, be shown as unit The component shown may or may not be physical location, you can with positioned at a place, or can also be distributed to multiple In network unit.Some or all of unit therein can be selected to realize the mesh of this embodiment scheme according to the actual needs 's.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, can also That unit is individually physically present, can also two or more units integrate in a unit.Above-mentioned integrated list Member can both be realized in the form of hardware, can also be realized in the form of SFU software functional unit.
If the integrated unit is realized in the form of SFU software functional unit and is used as independent production marketing or use When, it can be stored in a computer read/write memory medium.Based on such understanding, technical scheme is substantially The part to contribute in other words to the prior art or all or part of the technical solution can be in the form of software products Embody, which is stored in a storage medium, including some instructions are used so that a computer Equipment (can be personal computer, mobile terminal, server or network equipment etc.) performs side described in each embodiment of the present invention The all or part of step of method.And foregoing storage medium includes：USB flash disk, read-only storage (ROM, Read-Only Memory), Random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disc or CD etc. are various to be stored The medium of program code.
The foregoing is only a preferred embodiment of the present invention, is not intended to limit the invention, for the skill of this area For art personnel, the invention may be variously modified and varied.Within the spirit and principles of the invention, that is made any repaiies Change, equivalent substitution, improvement etc., should all be included in the protection scope of the present invention.

Claims (10)

  1. A kind of 1. exception flow of network detection method of power distribution network wireless communication access, it is characterised in that including：
    Obtain the network flow data of power distribution network wireless communication access；
    The network flow data is detected using the adaptive neural network fuzzy system model pre-established, output detection knot Fruit；
    Determine whether the network flow data exception occurs according to the detection structure.
  2. 2. exception flow of network detection method according to claim 1, it is characterised in that obtaining power distribution network wireless communication Before the network flow data of access, further include：
    Establish the adaptive neural network fuzzy system model.
  3. 3. exception flow of network detection method according to claim 2, it is characterised in that establish the adaptive neural network mould Paste system model includes：
    Gather exception flow of network data；
    Using subtraction clustering algorithm to the exception flow of network data carry out Non-Linear Programming, using initial model to data into Row optimization training obtains the adaptive neural network fuzzy system model.
  4. 4. exception flow of network detection method according to claim 3, it is characterised in that collection exception flow of network data Including：
    The exception flow of network data sample of default quantity is randomly selected from database, using a portion as training sample This, another part is as test sample；
    According to the stream feature of the Network Abnormal data of extraction, the Network Abnormal data of the extraction are normalized.
  5. 5. exception flow of network detection method according to claim 3, it is characterised in that the exception flow of network data Including at least one of：AlphaAnomaly abnormal flows, DDos abnormal flows, PortScan abnormal flows, NetworkScan abnormal flows, Worms abnormal flows and FlashCrowd abnormal flows.
  6. 6. exception flow of network detection method according to claim 4, it is characterised in that normalizing is carried out by the following formula Change is handled：
    <mrow> <msubsup> <mi>x</mi> <mi>i</mi> <mo>&amp;prime;</mo> </msubsup> <mo>=</mo> <mfrac> <mrow> <msub> <mi>x</mi> <mi>i</mi> </msub> <mo>-</mo> <mover> <mi>x</mi> <mo>&amp;OverBar;</mo> </mover> </mrow> <mi>S</mi> </mfrac> <mo>,</mo> <mi>i</mi> <mo>=</mo> <mn>1</mn> <mo>,</mo> <mn>2</mn> <mo>,</mo> <mo>...</mo> <mo>,</mo> <mi>n</mi> </mrow>
    Wherein, x ' is the data after normalized, and numerical value is between 0~1；It is the number average value for flowing characteristic,S is that the characteristic standard of sample is poor,N is exception flow of network data sample Quantity, xiRepresent i-th exception flow of network data sample.
  7. 7. according to the exception flow of network detection method described in optional one of claim 1-6, it is characterised in that described adaptive The membership function of neuro fuzzy systems model selection trigonometric function.
  8. A kind of 8. exception flow of network detection device of power distribution network wireless communication access, it is characterised in that including：
    Acquisition module, for obtaining the network flow data of power distribution network wireless communication access；
    Detection module, for being examined using the adaptive neural network fuzzy system model pre-established to the network flow data Survey, export testing result；
    Determining module, for determining whether the network flow data exception occurs according to the detection structure.
  9. 9. exception flow of network detection device according to claim 8, it is characterised in that further include：
    Module is established, for before the network flow data of power distribution network wireless communication access is obtained, establishing the adaptive god Through fuzzy system model.
  10. 10. exception flow of network detection method according to claim 9, it is characterised in that the module of establishing includes：
    Collecting unit, for gathering exception flow of network data；
    Training unit, for carrying out Non-Linear Programming to the exception flow of network data using subtraction clustering algorithm, using first Beginning model optimizes data training and obtains the adaptive neural network fuzzy system model.
CN201711196282.7A 2017-11-25 2017-11-25 The exception flow of network detection method and device of power distribution network wireless communication access Pending CN107959675A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201711196282.7A CN107959675A (en) 2017-11-25 2017-11-25 The exception flow of network detection method and device of power distribution network wireless communication access

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711196282.7A CN107959675A (en) 2017-11-25 2017-11-25 The exception flow of network detection method and device of power distribution network wireless communication access

Publications (1)

Publication Number Publication Date
CN107959675A true CN107959675A (en) 2018-04-24

Family

ID=61961799

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711196282.7A Pending CN107959675A (en) 2017-11-25 2017-11-25 The exception flow of network detection method and device of power distribution network wireless communication access

Country Status (1)

Country Link
CN (1) CN107959675A (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109445417A (en) * 2018-11-13 2019-03-08 浙江大学 A kind of industrial control system data exception detection method based on normalized
CN109450934A (en) * 2018-12-18 2019-03-08 国家电网有限公司 Terminal accesses data exception detection method and system
CN111698209A (en) * 2020-05-08 2020-09-22 国网安徽省电力有限公司亳州供电公司 Network abnormal flow detection method and device
CN112953933A (en) * 2021-02-09 2021-06-11 恒安嘉新（北京）科技股份公司 Abnormal attack behavior detection method, device, equipment and storage medium
WO2021114231A1 (en) * 2019-12-11 2021-06-17 中国科学院深圳先进技术研究院 Training method and detection method for network traffic anomaly detection model
CN113347184A (en) * 2021-06-01 2021-09-03 国家计算机网络与信息安全管理中心 Method, device, equipment and medium for testing network flow security detection engine

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109445417A (en) * 2018-11-13 2019-03-08 浙江大学 A kind of industrial control system data exception detection method based on normalized
CN109450934A (en) * 2018-12-18 2019-03-08 国家电网有限公司 Terminal accesses data exception detection method and system
WO2021114231A1 (en) * 2019-12-11 2021-06-17 中国科学院深圳先进技术研究院 Training method and detection method for network traffic anomaly detection model
CN111698209A (en) * 2020-05-08 2020-09-22 国网安徽省电力有限公司亳州供电公司 Network abnormal flow detection method and device
CN112953933A (en) * 2021-02-09 2021-06-11 恒安嘉新（北京）科技股份公司 Abnormal attack behavior detection method, device, equipment and storage medium
CN112953933B (en) * 2021-02-09 2023-02-17 恒安嘉新（北京）科技股份公司 Abnormal attack behavior detection method, device, equipment and storage medium
CN113347184A (en) * 2021-06-01 2021-09-03 国家计算机网络与信息安全管理中心 Method, device, equipment and medium for testing network flow security detection engine

Similar Documents

Publication Publication Date Title
CN107959675A (en) The exception flow of network detection method and device of power distribution network wireless communication access
CN108228706A (en) For identifying the method and apparatus of abnormal transaction corporations
CN110309840A (en) Risk trade recognition methods, device, server and storage medium
CN105005711B (en) Obtain the method and device of statistical line losses
CN106982359A (en) A kind of binocular video monitoring method, system and computer-readable recording medium
CN103514566A (en) Risk control system and method
CN107767055A (en) A kind of mass-rent result assemblage method and device based on collusion detection
CN109818798A (en) A kind of wireless sensor network intruding detection system and method merging KPCA and ELM
CN104092601B (en) The recognition methods of social networks account and device
CN104660464B (en) A kind of network anomaly detection method based on non-extension entropy
CN107797931A (en) A kind of method for evaluating software quality and system based on second evaluation
CN109325232A (en) A kind of user behavior exception analysis method, system and storage medium based on LDA
CN107274042A (en) A kind of business participates in the Risk Identification Method and device of object
CN104113452B (en) Network quality Forecasting Methodology and device
CN106645934A (en) Power utilization behavior electricity theft prevention diagnosis method and device based on dynamic grid outliers
CN107369043A (en) A kind of used car price evaluation optimized algorithm based on BP neural network
CN106569030A (en) Alarm threshold optimizing method and device in electric energy metering abnormity diagnosis
CN115222303B (en) Industry risk data analysis method and system based on big data and storage medium
CN108833139A (en) A kind of OSSEC alert data polymerization divided based on category attribute
CN112529685A (en) Loan user credit rating method and system based on BAS-FNN
CN114580829A (en) Power utilization safety sensing method, equipment and medium based on random forest algorithm
CN106529953A (en) Method and device for carrying out risk identification on business attributes
CN116094837A (en) Network terminal application acquisition analysis method, system and medium based on network big data
CN103942604A (en) Prediction method and system based on forest discrimination model
CN117156442A (en) Cloud data security protection method and system based on 5G network

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: 20180424