CN107404471A - One kind is based on ADMM algorithm network flow abnormal detecting methods - Google Patents
One kind is based on ADMM algorithm network flow abnormal detecting methods Download PDFInfo
- Publication number
- CN107404471A CN107404471A CN201710217331.4A CN201710217331A CN107404471A CN 107404471 A CN107404471 A CN 107404471A CN 201710217331 A CN201710217331 A CN 201710217331A CN 107404471 A CN107404471 A CN 107404471A
- Authority
- CN
- China
- Prior art keywords
- network
- data
- network flow
- detecting methods
- flow 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.)
- Pending
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
Landscapes
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Computer Hardware Design (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses one kind to be based on ADMM algorithm network flow abnormal detecting methods, and detection method comprises the following steps：S1, network flow data is read, network flow data is subjected to different time sections set division.ADMM algorithm network flow abnormal detecting methods should be based on, effectively and it can be quickly detected present in network abnormal, can possess certain antijamming capability simultaneously, strong robustness, pass through the continuous monitoring to network operation state, it was found that abnormal conditions that may be present in network, and alert notice network administrative staff are sent in time and are taken appropriate measures, to ensure the normal use of network, the present invention to having stronger detection power and higher accuracy rate extremely in network, there is higher operation efficiency, even if in the network traffics of exception and noise pollution, the present invention still has stronger robustness, required iterations reduces a lot compared to Speed gradient algorithm, and arithmetic speed has been lifted.
Description
Technical field
The present invention relates to network intrusions and exception of network traffic detection technique field, are specially that one kind is based on ADMM algorithm nets
Network Traffic anomaly detection method.
Background technology
Network traffics detection is always a hot issue of network technology research field, also in network management most
The part on basis, network traffics detect behavior for awareness network, improve network performance, and guarantee network security and have emphatically
The meaning wanted, the purpose is to by the continuous monitoring to network operation state, find abnormal conditions that may be present in network, and
Send alert notice network administrative staff in time to take appropriate measures, to ensure the normal use of network, principal component is divided at present
Analyse and network flow is widely used in based on acceleration near-end gradient method (such as document of Patent No. 201210560973.1)
In the analysis and detection of amount, but the method is there are still certain limitation, can not entirely accurate intuitively analyse whether to deposit
It is relatively low in network attack, Network anomaly detection poor-performing, robustness.
The content of the invention
(1) technical problem solved
In view of the shortcomings of the prior art, the invention provides one kind to be based on ADMM algorithm network flow abnormal detecting methods,
Solve the problems, such as that Network anomaly detection poor-performing and robustness are relatively low.
(2) technical scheme
To achieve the above object, the present invention provides following technical scheme：One kind is examined based on ADMM algorithms exception of network traffic
Survey method, detection method comprise the following steps：
S1, network flow data is read, network flow data is subjected to different time sections set division；
S2, the network flow data is pre-processed；
S3, network behavior characteristic value is extracted from the network flow data；
S4, data normalization processing is carried out to the network behavior characteristic value；
S5, by data normalization handle after network behavior characteristic value based on, to the network flow of different time sections set
Measure data and carry out unusual checking analysis.
Preferably, the network flow data pretreatment includes the cleaning of network flow data, turn of network flow data
Change the stipulations with network flow data.
Preferably, the network flow data is from interchanger, router, network test tool, network data acquisition
Instrument and disparate networks management software.
Preferably, the network flow data is data packet-related information, address relevant information, agreement relevant information, stream
Measure the one or more in relevant information, port flow relevant information.
Preferably, the method that the data normalization processing is standardized using Min-Max：Presetting MinA and MaxA is respectively
Attribute A minimum value and maximum, an A original value x is mapped in section [0,1] by Min-Max standardization
Value x ', its formula are：New data=(former data-minimum)/(maximum-minimum).
Preferably, in the S5, the network flow data after detection and analysis is categorized as low-rank matrix and sparse matrix, and
Low-rank matrix is normal discharge matrix, and sparse matrix is abnormal flow matrix.
Preferably, the cleaning of the network flow data includes the cleaning of wrong data, incomplete data and duplicate data etc.,
The conversion of the network flow data is to convert the data into the form for meeting data format requirement, main to include standardization, return
The operation such as receive, switch, rotate and project, the stipulations of the network flow data use Attributions selection method, in removal data set
Redundant attributes and uncorrelated attribute.
Preferably, in S5, abnormality detection is carried out to sparse matrix, when matrix all elements are zero, is then no different permanent current
Amount or network attack, when matrix all elements are not zero, then there may be abnormal flow or network attack.
(3) beneficial effect
The invention provides one kind to be based on ADMM algorithm network flow abnormal detecting methods, possesses following beneficial effect：
(1) ADMM algorithm network flow abnormal detecting methods, the actual need of the invention according to network flow management should be based on
Ask, the network traffics detection model based on alternating direction multiplier method of proposition, the network flow abnormal detecting method can advise greatly
It is more efficient and be quickly detected present in network abnormal in the environment of mould network traffics, while can possess certain
Antijamming capability, strong robustness.
(2) ADMM algorithm network flow abnormal detecting methods should be based on, and passed through the continuous monitoring to network operation state, hair
Abnormal conditions that may be present in existing network network, and send alert notice network administrative staff in time and take appropriate measures, to protect
Demonstrate,prove the normal use of network.
(3) ADMM algorithm network flow abnormal detecting methods should be based on, the present invention compares PCA, and the present invention is right
There is stronger detection power and higher accuracy rate extremely in network, compare and accelerate near-end gradient algorithm, the present invention has more
High operation efficiency, even if in the network traffics of exception and noise pollution, the present invention still has stronger robustness, the present invention
Network traffics matrix is decomposed using alternating direction multiplier method, required iterations is reduced very compared to Speed gradient algorithm
It is more, and arithmetic speed has been lifted.
Brief description of the drawings
Fig. 1 is inventive network abnormal flow data analysis schematic diagram；
Fig. 2 is the invention belongs to Sexual behavior mode method abstract analysis schematic diagram.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, rather than whole embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained every other under the premise of creative work is not made
Embodiment, belong to the scope of protection of the invention.
Fig. 1-2 is referred to, the present invention provides a kind of technical scheme：One kind is based on ADMM algorithm exception of network traffic detection side
Method, detection method comprise the following steps：
S1, network flow data is read, network flow data is subjected to different time sections set division；
S2, network flow data is pre-processed；
S3, network behavior characteristic value is extracted from network flow data；
S4, data normalization processing is carried out to network behavior characteristic value；
S5, by data normalization handle after network behavior characteristic value based on, to the network flow of different time sections set
Measure data and carry out unusual checking analysis.
Wherein, ADMM is alternating direction multiplier method, and ADMM is a kind of Computational frame of solving-optimizing problem, suitable for solving
Distributed convex optimization problem, the present invention are decomposed using alternating direction multiplier method to network traffics matrix, required iteration time
Number is reduced much compared to Speed gradient algorithm, and arithmetic speed has been lifted.
Data normalization is by data bi-directional scaling, is allowed to fall into a small specific section, due to credit index body
Each measure of criterions unit of system is different, is calculated in order to which index is participated in into evaluation, it is necessary to standardize to index
Processing, some numerical intervals is mapped to by functional transformation by its numerical value, the method standardized using Min-Max, can be to net
Network data on flows is standardized, and by data normalization handle after network behavior characteristic value based on, to it is different when
Between section set network flow data carry out unusual checking analysis.
Preferably, network flow data pretreatment include the cleaning of network flow data, the conversion of network flow data and
The stipulations of network flow data, wherein, the principle of data scrubbing is exactly to pass through the producing cause for analyzing " dirty data " and shape be present
Formula, go to clean " dirty data " using existing technological means and method, " dirty data " is converted into and meets the quality of data or application
Required standard data, so as to improve the quality of data of data set, the main network flow data cleared up and handled includes mistake
Data, incomplete data and duplicate data etc., the conversion of network flow data, which converts the data into, meets data format requirement
Form, it is main include standardization, conclude, switching, the operation such as rotation and projection, because the model utilizes mathematical method and matrix
Relevant nature, it is expressly noted that the nonumeric type data in network flow data need to be converted to numeric type data, to meet
Analyzing and processing demand afterwards, network flow data collection typically can all contain substantial amounts of attribute, and example is also very huge, such as
The data analysis that fruit carries out complexity on large-scale data then needs the long period so that this analysis efficiency step-down, not even
Feasible, the reduction that data regularization technology can obtain data set represents, the data set after stipulations is less than original on data dimension
Data set, but remain close to keep the integrality of former data, being excavated on the data set so after reduction will be more effective, and produce
Identical or almost identical analysis result, conventional method have Attributions selection method, it is possible to reduce redundant attributes in data set and
Uncorrelated attribute, it see in Fig. 2 and represent abstract Feature Selection Algorithm using false code.
Preferably, network flow data is from interchanger, router, network test tool, network data acquisition instrument
And disparate networks management software, network flow data can effectively be detected.
Preferably, network flow data is data packet-related information, address relevant information, agreement relevant information, flow phase
The one or more in information, port flow relevant information are closed, ensure that the variation of network flow data, Network anomaly detection
Accuracy is more preferable.
Preferably, the method that data normalization processing is standardized using Min-Max：Default MinA and MaxA is respectively attribute
A minimum value and maximum, an A original value x is mapped to the value x ' in section [0,1] by Min-Max standardization,
Its formula is：Data can be standardized by new data=(former data-minimum)/(maximum-minimum).
Preferably, in S5, the network flow data after detection and analysis is categorized as low-rank matrix and sparse matrix, and low-rank
Matrix is normal discharge matrix, and sparse matrix is abnormal flow matrix.
Preferably, the cleaning of network flow data includes the cleaning of wrong data, incomplete data and duplicate data etc., network
The conversion of data on flows is to convert the data into the form for meeting data format requirement, it is main include standardization, conclude, switching,
The operation such as rotation and projection, the stipulations of network flow data use Attributions selection method, redundant attributes in removal data set and not
Association attributes.
Preferably, in S5, abnormality detection is carried out to sparse matrix, when matrix all elements are zero, is then no different permanent current
Amount or network attack, when matrix all elements are not zero, then there may be abnormal flow or network attack.
In summary, ADMM algorithm network flow abnormal detecting methods should be based on, the present invention is according to network flow management
Actual demand, the network traffics detection model based on alternating direction multiplier method of proposition, the network flow abnormal detecting method can
It is more efficient and be quickly detected present in network abnormal in the environment of large-scale network traffic, while can possess
Certain antijamming capability, strong robustness, by the continuous monitoring to network operation state, find that may be present different in network
Reason condition, and send alert notice network administrative staff in time and take appropriate measures, to ensure the normal use of network, this hair
Bright to compare PCA, the present invention compares and added to having stronger detection power and higher accuracy rate in network extremely
Fast near-end gradient algorithm, the present invention have higher operation efficiency, even if in the network traffics of exception and noise pollution, this hair
Bright still to have stronger robustness, the present invention is decomposed using alternating direction multiplier method to network traffics matrix, and required changes
Generation number is reduced much compared to Speed gradient algorithm, and arithmetic speed has been lifted.
It should be noted that herein, such as first and second or the like relational terms are used merely to a reality
Body or operation make a distinction with another entity or operation, and not necessarily require or imply and deposited between these entities or operation
In any this actual relation or order.Moreover, term " comprising ", "comprising" or its any other variant are intended to
Nonexcludability includes, so that process, method, article or equipment including a series of elements not only will including those
Element, but also the other element including being not expressly set out, or it is this process, method, article or equipment also to include
Intrinsic key element.In the absence of more restrictions.By sentence " including one ... the key element limited, it is not excluded that
Other identical element in the process including the key element, method, article or equipment also be present ", the electricity occurred in this article
Device element electrically connects with the main controller and 220V civil powers in the external world, and main controller can be that computer etc. has played the routine of control
Know equipment.
Although an embodiment of the present invention has been shown and described, for the ordinary skill in the art, can be with
A variety of changes, modification can be carried out to these embodiments, replace without departing from the principles and spirit of the present invention by understanding
And modification, the scope of the present invention is defined by the appended.
Claims (8)
1. one kind is based on ADMM algorithm network flow abnormal detecting methods, it is characterised in that：Detection method comprises the following steps：
S1, network flow data is read, network flow data is subjected to different time sections set division；
S2, the network flow data is pre-processed；
S3, network behavior characteristic value is extracted from the network flow data；
S4, data normalization processing is carried out to the network behavior characteristic value；
S5, by data normalization handle after network behavior characteristic value based on, to the network traffics number of different time sections set
According to progress unusual checking analysis.
2. one kind according to claim 1 is based on ADMM algorithm network flow abnormal detecting methods, it is characterised in that：It is described
Network flow data pre-processes the rule for including the cleaning of network flow data, the conversion of network flow data and network flow data
About.
3. one kind according to claim 1 is based on ADMM algorithm network flow abnormal detecting methods, it is characterised in that：It is described
Network flow data derives from interchanger, router, network test tool, network data acquisition instrument and disparate networks management
Software.
4. one kind according to claim 1 is based on ADMM algorithm network flow abnormal detecting methods, it is characterised in that：It is described
Network flow data is data packet-related information, address relevant information, agreement relevant information, flow relevant information, port flow
One or more in relevant information.
5. one kind according to claim 1 is based on ADMM algorithm network flow abnormal detecting methods, it is characterised in that：It is described
The method that data normalization processing is standardized using Min-Max：Default MinA and MaxA is respectively attribute A minimum value and maximum
Value, an A original value x is mapped to the value x ' in section [0,1] by Min-Max standardization, its formula is：New data
=(former data-minimum)/(maximum-minimum).
6. one kind according to claim 1 is based on ADMM algorithm network flow abnormal detecting methods, it is characterised in that：It is described
In S5, the network flow data after detection and analysis is categorized as low-rank matrix and sparse matrix, and low-rank matrix is normal discharge
Matrix, sparse matrix are abnormal flow matrix.
7. one kind according to claim 2 is based on ADMM algorithm network flow abnormal detecting methods, it is characterised in that：It is described
The cleaning of network flow data includes the cleaning of wrong data, incomplete data and duplicate data etc., the network flow data
Conversion is to convert the data into the form for meeting data format requirement, main to include standardization, conclusion, switching, rotation and projection
Deng operation, the stipulations of the network flow data use Attributions selection method, remove the redundant attributes in data set and uncorrelated category
Property.
8. one kind according to claim 6 is based on ADMM algorithm network flow abnormal detecting methods, it is characterised in that：S5
In, abnormality detection is carried out to sparse matrix, when matrix all elements are zero, then normal flow or network attack are no different, work as square
When battle array all elements are not zero, then abnormal flow or network attack are there may be.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710217331.4A CN107404471A (en) | 2017-04-05 | 2017-04-05 | One kind is based on ADMM algorithm network flow abnormal detecting methods |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710217331.4A CN107404471A (en) | 2017-04-05 | 2017-04-05 | One kind is based on ADMM algorithm network flow abnormal detecting methods |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107404471A true CN107404471A (en) | 2017-11-28 |
Family
ID=60404666
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710217331.4A Pending CN107404471A (en) | 2017-04-05 | 2017-04-05 | One kind is based on ADMM algorithm network flow abnormal detecting methods |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107404471A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107992449A (en) * | 2017-12-05 | 2018-05-04 | 北京工业大学 | A kind of subway anomalous traffic detection method based on low-rank representation |
| CN108566306A (en) * | 2018-04-28 | 2018-09-21 | 广东电网有限责任公司 | A kind of real-time method for detecting abnormality of network security based on data balancing technology |
| CN109246761A (en) * | 2018-09-11 | 2019-01-18 | 北京工业大学 | Consider the discharging method based on alternating direction multipliers method of delay and energy consumption |
| CN111970156A (en) * | 2020-08-27 | 2020-11-20 | 广州华多网络科技有限公司 | Network fault root cause analysis method and device, computer equipment and storage medium |
| CN112202771A (en) * | 2020-09-29 | 2021-01-08 | 中移（杭州）信息技术有限公司 | Network flow detection method, system, electronic device and storage medium |
| CN112398844A (en) * | 2020-11-10 | 2021-02-23 | 国网浙江省电力有限公司双创中心 | Flow analysis implementation method based on internal and external network real-time drainage data |
| CN112637118A (en) * | 2020-11-10 | 2021-04-09 | 国网浙江省电力有限公司双创中心 | Flow analysis implementation method based on internal and external network drainage abnormity |
| CN118141356A (en) * | 2024-04-30 | 2024-06-07 | 天津工业大学 | Depth ADMM unfolding EIT imaging method based on model driving |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101686235A (en) * | 2008-09-26 | 2010-03-31 | 中联绿盟信息技术(北京)有限公司 | Device and method for analyzing abnormal network flow |
| CN102118273A (en) * | 2009-12-31 | 2011-07-06 | 蓝盾信息安全技术股份有限公司 | Man-machine interaction type network abnormality diagnosis method |
| CN102158486A (en) * | 2011-04-02 | 2011-08-17 | 华北电力大学 | Method for rapidly detecting network invasion |
| CN103023725A (en) * | 2012-12-20 | 2013-04-03 | 北京工业大学 | Anomaly detection method based on network flow analysis |
| CN103078760A (en) * | 2009-12-31 | 2013-05-01 | 蓝盾信息安全技术股份有限公司 | Online diagnosis method for abnormal network flow |
| CN105335653A (en) * | 2014-07-21 | 2016-02-17 | 华为技术有限公司 | Abnormal data detection method and apparatus |
| CN105553998A (en) * | 2015-12-23 | 2016-05-04 | 中国电子科技集团公司第三十研究所 | Network attack abnormality detection method |
| CN105809119A (en) * | 2016-03-03 | 2016-07-27 | 厦门大学 | Sparse low-rank structure based multi-task learning behavior identification method |
| US9418318B2 (en) * | 2013-08-30 | 2016-08-16 | Siemens Aktiengesellschaft | Robust subspace recovery via dual sparsity pursuit |
| CN105897517A (en) * | 2016-06-20 | 2016-08-24 | 广东电网有限责任公司信息中心 | Network traffic abnormality detection method based on SVM (Support Vector Machine) |
| CN106066994A (en) * | 2016-05-24 | 2016-11-02 | 北京工业大学 | A kind of face identification method of the rarefaction representation differentiated based on Fisher |
| CN106790050A (en) * | 2016-12-19 | 2017-05-31 | 北京启明星辰信息安全技术有限公司 | A kind of anomalous traffic detection method and detecting system |
-
2017
- 2017-04-05 CN CN201710217331.4A patent/CN107404471A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101686235A (en) * | 2008-09-26 | 2010-03-31 | 中联绿盟信息技术(北京)有限公司 | Device and method for analyzing abnormal network flow |
| CN102118273A (en) * | 2009-12-31 | 2011-07-06 | 蓝盾信息安全技术股份有限公司 | Man-machine interaction type network abnormality diagnosis method |
| CN103078760A (en) * | 2009-12-31 | 2013-05-01 | 蓝盾信息安全技术股份有限公司 | Online diagnosis method for abnormal network flow |
| CN102158486A (en) * | 2011-04-02 | 2011-08-17 | 华北电力大学 | Method for rapidly detecting network invasion |
| CN103023725A (en) * | 2012-12-20 | 2013-04-03 | 北京工业大学 | Anomaly detection method based on network flow analysis |
| US9418318B2 (en) * | 2013-08-30 | 2016-08-16 | Siemens Aktiengesellschaft | Robust subspace recovery via dual sparsity pursuit |
| CN105335653A (en) * | 2014-07-21 | 2016-02-17 | 华为技术有限公司 | Abnormal data detection method and apparatus |
| CN105553998A (en) * | 2015-12-23 | 2016-05-04 | 中国电子科技集团公司第三十研究所 | Network attack abnormality detection method |
| CN105809119A (en) * | 2016-03-03 | 2016-07-27 | 厦门大学 | Sparse low-rank structure based multi-task learning behavior identification method |
| CN106066994A (en) * | 2016-05-24 | 2016-11-02 | 北京工业大学 | A kind of face identification method of the rarefaction representation differentiated based on Fisher |
| CN105897517A (en) * | 2016-06-20 | 2016-08-24 | 广东电网有限责任公司信息中心 | Network traffic abnormality detection method based on SVM (Support Vector Machine) |
| CN106790050A (en) * | 2016-12-19 | 2017-05-31 | 北京启明星辰信息安全技术有限公司 | A kind of anomalous traffic detection method and detecting system |
Non-Patent Citations (3)
| Title |
|---|
| MASOUMEH AZGHANI: ""Low-rank block sparse decomposition algorithm for anomaly detection in networks"", 《2015 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA) 》 * |
| WENCAI YE: ""Anomaly-Tolerant Traffic Matrix Estimation via Prior Information Guided Matrix Completion"", 《JOURNALS & MAGAZINES》 * |
| 樊重俊等: "《大数据分析与应用》", 31 January 2016 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107992449B (en) * | 2017-12-05 | 2021-04-30 | 北京工业大学 | Subway abnormal flow detection method based on low-rank representation |
| CN107992449A (en) * | 2017-12-05 | 2018-05-04 | 北京工业大学 | A kind of subway anomalous traffic detection method based on low-rank representation |
| CN108566306A (en) * | 2018-04-28 | 2018-09-21 | 广东电网有限责任公司 | A kind of real-time method for detecting abnormality of network security based on data balancing technology |
| CN108566306B (en) * | 2018-04-28 | 2020-08-04 | 广东电网有限责任公司 | Network security real-time anomaly detection method based on data equalization technology |
| CN109246761B (en) * | 2018-09-11 | 2022-03-29 | 北京工业大学 | Unloading method based on alternating direction multiplier method considering delay and energy consumption |
| CN109246761A (en) * | 2018-09-11 | 2019-01-18 | 北京工业大学 | Consider the discharging method based on alternating direction multipliers method of delay and energy consumption |
| CN111970156A (en) * | 2020-08-27 | 2020-11-20 | 广州华多网络科技有限公司 | Network fault root cause analysis method and device, computer equipment and storage medium |
| CN111970156B (en) * | 2020-08-27 | 2023-04-18 | 广州华多网络科技有限公司 | Network fault root cause analysis method and device, computer equipment and storage medium |
| CN112202771A (en) * | 2020-09-29 | 2021-01-08 | 中移（杭州）信息技术有限公司 | Network flow detection method, system, electronic device and storage medium |
| CN112398844A (en) * | 2020-11-10 | 2021-02-23 | 国网浙江省电力有限公司双创中心 | Flow analysis implementation method based on internal and external network real-time drainage data |
| CN112637118A (en) * | 2020-11-10 | 2021-04-09 | 国网浙江省电力有限公司双创中心 | Flow analysis implementation method based on internal and external network drainage abnormity |
| CN118141356A (en) * | 2024-04-30 | 2024-06-07 | 天津工业大学 | Depth ADMM unfolding EIT imaging method based on model driving |
| CN118141356B (en) * | 2024-04-30 | 2024-07-02 | 天津工业大学 | Depth ADMM unfolding EIT imaging method based on model driving |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107404471A (en) | One kind is based on ADMM algorithm network flow abnormal detecting methods | |
| CN110895526A (en) | Method for correcting data abnormity in atmosphere monitoring system | |
| CN110210512A (en) | A kind of automation daily record method for detecting abnormality and system | |
| CN109615004A (en) | A kind of anti-electricity-theft method for early warning of multisource data fusion | |
| CN102891761B (en) | Equipment performance prediction processing method and device | |
| CN107257351A (en) | One kind is based on grey LOF Traffic anomaly detections system and its detection method | |
| Zhou et al. | Anomaly detection method of daily energy consumption patterns for central air conditioning systems | |
| CN110942137A (en) | Power grid information operation and maintenance monitoring method based on deep learning | |
| CN103198147A (en) | Method for distinguishing and processing abnormal automatized monitoring data | |
| CN106570779A (en) | Method and system for analyzing reliability of direct-current power distribution network | |
| CN112766301B (en) | Oil extraction machine indicator diagram similarity judging method | |
| CN105626502A (en) | Plunger pump health assessment method based on wavelet packet and Laplacian Eigenmap | |
| CN102801548B (en) | A kind of method of intelligent early-warning, device and information system | |
| Song et al. | Real-time anomaly traffic monitoring based on dynamic k-NN cumulative-distance abnormal detection algorithm | |
| CN116155581A (en) | Network intrusion detection method and device based on graph neural network | |
| CN105354622A (en) | Fuzzy comprehensive evaluation based enterprise production management evaluation method | |
| CN105827611A (en) | Distributed rejection service network attack detection method and system based on fuzzy inference | |
| CN117560300B (en) | Intelligent internet of things flow prediction and optimization system | |
| CN103529337B (en) | The recognition methods of nonlinear correlation relation between equipment failure and electric quantity information | |
| CN110956281A (en) | Power equipment abnormity detection alarm system based on Log analysis | |
| CN117274827B (en) | Intelligent environment-friendly remote real-time monitoring and early warning method and system | |
| CN111612054A (en) | User electricity stealing behavior identification method based on non-negative matrix factorization and density clustering | |
| CN109936487A (en) | A kind of real-time analysis and monitoring method and system of Web broadcast packet | |
| CN114186764A (en) | Transformer substation monitoring information feature extraction method and device | |
| Liu et al. | Method for network anomaly detection based on Bayesian statistical model with time slicing |
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 |
Application publication date: 20171128 |
|
| RJ01 | Rejection of invention patent application after publication |