CN104378219A - Intelligent analysis method and device for router flow data - Google Patents
Intelligent analysis method and device for router flow data Download PDFInfo
- Publication number
- CN104378219A CN104378219A CN201310350422.7A CN201310350422A CN104378219A CN 104378219 A CN104378219 A CN 104378219A CN 201310350422 A CN201310350422 A CN 201310350422A CN 104378219 A CN104378219 A CN 104378219A
- Authority
- CN
- China
- Prior art keywords
- data
- flows
- router
- analysis
- cycle
- 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.)
- Withdrawn
Links
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses an intelligent analysis method for router flow data. The method comprises the steps that the router flow data are received, the data period of the flow data is analyzed, and a normal data section is determined according to the data period; abnormal data points of the flow data are predicted according to the data period and the normal data section and are output. The invention further discloses an intelligent analysis device for the router flow data. According to the scheme, association rules between the data can be effectively analyzed, historical data periodicity and the normal data section are fully mined, the abnormal data points are detected, so that early warning is carried out on the router abnormal data points in advance, and therefore network segments with large mutual communication flow are prevented from being blocked to a great degree, and the phenomenon that flow is blocked and lost in the future peak period is avoided to a great degree.
Description
Technical field
The present invention relates to technical field of data processing, be related specifically to a kind of method and apparatus of router traffic intelligent data analysis.
Background technology
In communication network, router is responsible for connecting multiple network segment so that the transmission of the information of carrying out, if the data via router carry out depth analysis can provide a lot of information for user, such as congestion times, data cycle, abnormal traffic detection and data correlation rule etc., these information can provide further technical support for user optimization network.At present, network operator is usually according to real-time traffic Sampling network, analysis of history data traffic, and this detection analysis means exists following limitation:
1, data analysing method limitation, generally presents data by statistical.It effectively can not analyze the correlation rule between data, fully can not excavate out the periodicity of historical data, the interval of normal data, can not detect exceptional data point.
2, the trend prediction analysis of missing data, can not carry out early warning by routers exceptional data point in advance.
Summary of the invention
Main purpose of the present invention, for providing a kind of method and apparatus of router traffic intelligent data analysis, can reduce the large network segment of mutual communication traffic and occur blocking, and the following phenomenon that flow occurred obstruction and lost peak period.
The invention provides a kind of method of router traffic intelligent data analysis, comprise step:
Receiving router data on flows, analyzes the data cycle of described data on flows, and determines that normal data is interval according to this data cycle;
According to described data cycle and normal data interval, predict the exceptional data point of described data on flows, export this exceptional data point.
Preferably, the data cycle of described analysis data on flows, and determine that the step in normal data interval specifically comprises according to this data cycle:
Analyze the described data on flows received, obtain the data cycle of data on flows;
According to the described data cycle, data on flows is carried out segmentation, the data on flows of the same time point of comparison, according to minimum value and the maximum in comparison result determination normal data interval.
Preferably, described according to data cycle and normal data interval, predict that the step of the exceptional data point of described data on flows specifically comprises:
According to the described data cycle, trend prediction algorithm is adopted to obtain the future period data value of described data on flows;
Interval according to described normal data, predict the exceptional data point in described future period data value.
Preferably, in the data cycle of the described data on flows of described analysis, and, also comprise according to the step in this data computation of Period normal data interval simultaneously:
Analyze the relevance of described data on flows, and obtain the correlation rule of described data on flows according to this relevance, export this correlation rule.
Preferably, the relevance of described analysis data on flows, and the step obtaining the correlation rule of described data on flows according to this relevance specifically comprises:
Qualitative analysis is carried out to the described data on flows received, the relevance between the data rows obtaining data on flows;
According to obtained relevance, quantitative analysis is carried out to the data rows of data on flows, obtains the correlation rule of the data rows of described data on flows.
Preferably, described according to data cycle and normal data interval, predict the exceptional data point of described data on flows, after exporting the step of this exceptional data point, also comprise:
According to described exceptional data point and correlation rule, the collocation strategy of adjustment router, sends the router configuration data after adjustment to router device.
The present invention also provides a kind of device of router traffic intelligent data analysis, comprising:
Data reception module, for receiving router data on flows;
According to this data cycle, data detection module, for analyzing the data cycle of described data on flows, and determines that normal data is interval;
Trend prediction module, for according to described data cycle and normal data interval, predicts the exceptional data point of described data on flows, exports this exceptional data point.
Preferably, described data detection module specifically comprises:
Cycle acquiring unit, for analyzing the described data on flows of reception, obtains the data cycle of data on flows;
Interval determination unit, for according to the described data cycle, carries out segmentation by data on flows, the data on flows of the same time point of comparison, according to minimum value and the maximum in comparison result determination normal data interval.
Preferably, described trend prediction module specifically comprises:
Future value acquiring unit, for according to the described data cycle, adopts trend prediction algorithm to obtain the future period data value of described data on flows;
Predicting abnormality unit, for interval according to described normal data, predicts the exceptional data point in described future period data value.
Preferably, the device of router traffic intelligent data analysis also comprises:
Data analysis module, for analyzing the relevance of described data on flows, and obtaining the correlation rule of described data on flows according to this relevance, exporting this correlation rule.
Preferably, described data analysis module specifically comprises:
Qualitative analysis unit, for carrying out qualitative analysis to the described data on flows received, the relevance between the data rows obtaining data on flows;
Quantitative analysis unit, for according to obtained relevance, carries out quantitative analysis to the data rows of data on flows, obtains the correlation rule of the data rows of described data on flows.
Preferably, the device of router traffic intelligent data analysis also comprises:
Policy management module, for according to described exceptional data point and correlation rule, adjusts the collocation strategy of router, sends the router configuration data after adjustment to router device.
According to this data cycle, the present invention by carrying out the analysis in data cycle to reception router traffic data, and determines that normal data is interval; According to data cycle and normal data interval, the exceptional data point of predicted flow rate data, export this exceptional data point, effectively can analyze the correlation rule between data, and fully excavate out the periodicity of historical data, the interval of normal data, detect exceptional data point, so that routers exceptional data point carries out early warning in advance, thus the network segment appearance reducing mutual communication traffic to a great extent large is blocked, and following flow appearance peak period is blocked and the phenomenon of loss.
Accompanying drawing explanation
Fig. 1 is the schematic flow sheet of method first embodiment of router traffic intelligent data analysis of the present invention;
Fig. 2 is the data cycle analyzing data on flows in the method for router traffic intelligent data analysis of the present invention, determines the schematic flow sheet in normal data interval according to the data cycle;
Fig. 3 is the schematic flow sheet according to the exceptional data point of data cycle and normal data interval prediction data on flows in the method for router traffic intelligent data analysis of the present invention;
Fig. 4 is the schematic flow sheet of method second embodiment of router traffic intelligent data analysis of the present invention;
Fig. 5 is the relevance analyzing data on flows in the method for router traffic intelligent data analysis of the present invention, and obtains the schematic flow sheet of the correlation rule of data on flows according to relevance;
Fig. 6 is the schematic flow sheet of method the 3rd embodiment of router traffic intelligent data analysis of the present invention;
Fig. 7 is the structural representation of device first embodiment of router traffic intelligent data analysis of the present invention;
Fig. 8 is the schematic flow sheet of the data detection module of the device of router traffic intelligent data analysis of the present invention;
Fig. 9 is the schematic flow sheet of the trend prediction module of the device of router traffic intelligent data analysis of the present invention;
Figure 10 is the structural representation of device second embodiment of router traffic intelligent data analysis of the present invention;
Figure 11 is the structural representation of the data analysis module of the device of router traffic intelligent data analysis of the present invention;
Figure 12 is the structural representation of device the 3rd embodiment of router traffic intelligent data analysis of the present invention.
The realization of the object of the invention, functional characteristics and advantage will in conjunction with the embodiments, are described further with reference to accompanying drawing.
Embodiment
Should be appreciated that specific embodiment described herein only in order to explain the present invention, be not intended to limit the present invention.
The invention provides a kind of method of router traffic intelligent data analysis.Routers data on flows carries out degree of depth intellectual analysis, as extracted data model, carrying out trend prediction and excavate exceptional data point, and according to the result analyzed with excavate exceptional data point, adjustment network device policy, and regulating strategy is passed to router device control for it.
With reference to the schematic flow sheet that Fig. 1, Fig. 1 are method first embodiment of router traffic intelligent data analysis of the present invention.
The method of the router traffic intelligent data analysis that the present embodiment provides, comprising:
Step S10, receiving router data on flows, analyzes the data cycle of data on flows, and determines that normal data is interval according to this data cycle;
In the present embodiment, by router data collecting device Real-time Obtaining router traffic data, after receiving the router traffic data that router data collecting device collects, analyze this data on flows, draw its data cycle, then determine that the normal data of data on flows is interval according to the obtained data cycle, the data on flows namely in this interval range is normal data, and the data on flows exceeding this interval range can be defined as abnormal data.
Be the data cycle analyzing data on flows in the method for router traffic intelligent data analysis of the present invention with further reference to Fig. 2, Fig. 2, determine the schematic flow sheet in normal data interval according to the data cycle.
In the present embodiment, step S10 comprises further:
Step S11, analyzes the data on flows received, and obtains the data cycle of data on flows;
Step S12, according to the data cycle, carries out segmentation by data on flows, the data on flows of the same time point of comparison, according to minimum value and the maximum in comparison result determination normal data interval.
After receiving router traffic data, this data on flows is analyzed, to obtain the data cycle of data on flows, such as, after Fourier expansion is carried out for given time series data, utilize the method for regression analysis to obtain Parseval relational expression, and then try to achieve Fourier frequency, thus obtain the data cycle of data on flows.
Obtaining the data week after date of data on flows, according to the obtained data cycle, according to the time, segmentation is carried out to data on flows, and comparison is positioned at the data on flows of same time point, and then according to the minimum value in comparison result determination normal data interval and maximum, obtain normal data interval.Like this, the data on flows in normal data interval range is normal data, and the data on flows exceeding normal data interval range is then abnormal data.
Step S20, according to data cycle and normal data interval, the exceptional data point of predicted flow rate data, exports this exceptional data point.
Obtain the data cycle of data on flows, and after determining normal data interval, further according to data cycle and normal data interval, the data on flows of future period is predicted, to obtain the exceptional data point of future value, and export the exceptional data point predicted.
It is the schematic flow sheet according to the exceptional data point of data cycle and normal data interval prediction data on flows in the method for router traffic intelligent data analysis of the present invention with further reference to Fig. 3, Fig. 3.
In the present embodiment, step S20 comprises further:
Step S21, according to the data cycle, adopts trend prediction algorithm to obtain the future period data value of data on flows;
Step S22, interval according to normal data, the exceptional data point in prediction future period data value.
Analyze the data week after date of data on flows, according to the data cycle, trend prediction algorithm is used to predict in advance data on flows, namely the data value in the future period of data on flows is obtained by trend prediction algorithm, ARIMA(Autoregressive Integrated Moving AverageModel can be adopted in the present embodiment, difference ARMA model) method the data value in future period is predicted; After obtaining the data value in future period, interval according to the normal data determined, further the data value in future period is predicted, predict the exceptional data point that may occur in future period data value.
According to this data cycle, the present embodiment by carrying out the analysis in data cycle to reception router traffic data, and determines that normal data is interval; According to data cycle and normal data interval, the exceptional data point of predicted flow rate data, export this exceptional data point, fully can excavate out the periodicity of historical data, the interval of normal data, and can exceptional data point be detected, so that routers exceptional data point carries out early warning in advance, thus the network segment appearance reducing mutual communication traffic to a great extent large is blocked, and following flow appearance peak period is blocked and the phenomenon of loss.
With reference to the schematic flow sheet that Fig. 4, Fig. 4 are method second embodiment of router traffic intelligent data analysis of the present invention.
On the basis of method first embodiment of router traffic intelligent data analysis of the present invention, while performing step S10, the method also comprises:
Step S30, analyzes the relevance of data on flows, and obtains the correlation rule of data on flows according to this relevance, exports this correlation rule.
After receiving router data collecting device Real-time Obtaining router traffic data, correlation analysis is carried out to data on flows, exclude the data on flows that correlation is less, then strong to correlation data on flows collection carries out the calculating of correlation rule, and the correlation rule calculated the most at last exports.
Be the relevance analyzing data on flows in the method for router traffic intelligent data analysis of the present invention with further reference to Fig. 5, Fig. 5, and obtain the schematic flow sheet of the correlation rule of data on flows according to relevance.
In the present embodiment, step S30 comprises further:
Step S31, carries out qualitative analysis to the data on flows received, the relevance between the data rows obtaining data on flows;
Step S32, according to obtained relevance, carries out quantitative analysis to the data rows of data on flows, obtains the correlation rule of the data rows of data on flows.
After receiving data on flows, first qualitative analysis is carried out to data on flows, obtain the relevance between data rows, exclude without the need to the less data on flows of the correlation of concern, such as calculate the coefficient correlation between data on flows by the method for Pearson correlation coefficients (Pearson correlation coefficient), according to result of calculation, data on flows less for correlation is got rid of from data rows.For the data rows that correlation is strong, then carry out quantitative analysis further, obtain the correlation rule of the data rows of these datas on flows, such as can according to FPGrowth algorithm tree, excavating the association mode of the data rows of data on flows, namely by pre-setting min confidence parameter, and filtering according to set confidence level condition, the association mode that final acquisition confidence level is high, as the correlation rule of the data rows of data on flows.
After receiving router traffic data, first qualitative analysis is carried out to data on flows, relevance between the data rows obtaining data on flows, and according to this relevance, quantitative analysis is carried out to the data rows of data on flows, obtain the correlation rule of the data rows of data on flows, effectively can analyze the correlation rule between data, thus occur blocking for reducing the large network segment of mutual communication traffic, and flow will occur that the phenomenon of blocking and losing provides the foundation peak period in future.
With reference to the schematic flow sheet that Fig. 6, Fig. 6 are method the 3rd embodiment of router traffic intelligent data analysis of the present invention.
On the basis of method first and second embodiment of router traffic intelligent data analysis of the present invention, after execution step S20 and step S30, the method also comprises:
Step S40, according to exceptional data point and correlation rule, the collocation strategy of adjustment router, sends the router configuration data after adjustment to router device.
In the present embodiment, after the exceptional data point receiving output and correlation rule, according to the tactful configuration rule of corresponding router, configuration of routers strategy between the adjustment network segment, and router device corresponding to the exceptional data point after adjustment and correlation rule export to, control for router device.Decision rule tree can be created according to several institute's model of historical traffic data and experience in the present embodiment, and obtain optimum configuration of routers strategy according to decision rule tree is final.
After the exceptional data point receiving output and correlation rule, the collocation strategy of adjustment router, sends the router configuration data after adjustment to router device for control; Obtain optimum configuration of routers strategy according to the intellectual analysis result of routers data on flows, and send to router device, achieve the object that routers equipment carries out countercharging.
The present invention also provides a kind of device of router traffic intelligent data analysis.
With reference to the structural representation that Fig. 7, Fig. 7 are device first embodiment of router traffic intelligent data analysis of the present invention.
The device of the router traffic intelligent data analysis that the present embodiment provides, comprising:
Data reception module 10, for receiving router data on flows;
According to this data cycle, data detection module 20, for analyzing the data cycle of data on flows, and determines that normal data is interval;
Trend prediction module 30, for interval according to data cycle and normal data, the exceptional data point of predicted flow rate data, exports this exceptional data point.
In the present embodiment, by router data collecting device Real-time Obtaining router traffic data, after data reception module 10 receives the router traffic data that router data collecting device collects, data detection module 20 analyzes this data on flows, draw its data cycle, then determine that the normal data of data on flows is interval according to the obtained data cycle, the data on flows namely in this interval range is normal data, and the data on flows exceeding this interval range can be defined as abnormal data.
It is the schematic flow sheet of the data detection module of the device of router traffic intelligent data analysis of the present invention with further reference to Fig. 8, Fig. 8.
In the present embodiment, data detection module 20 specifically comprises:
Cycle acquiring unit 21, for analyzing the data on flows of reception, obtains the data cycle of data on flows;
Interval determination unit 22, for according to the data cycle, carries out segmentation by data on flows, the data on flows of the same time point of comparison, according to minimum value and the maximum in comparison result determination normal data interval.
After receiving router traffic data, cycle acquiring unit 21 is analyzed this data on flows, to obtain the data cycle of data on flows, such as, after Fourier expansion is carried out for given time series data, utilize the method for regression analysis to obtain Parseval relational expression, and then try to achieve Fourier frequency, thus obtain the data cycle of data on flows.
Obtaining the data week after date of data on flows, interval determination unit 22 is according to the obtained data cycle, according to the time, segmentation is carried out to data on flows, and comparison is positioned at the data on flows of same time point, and then according to the minimum value in comparison result determination normal data interval and maximum, obtain normal data interval.Like this, the data on flows in normal data interval range is normal data, and the data on flows exceeding normal data interval range is then abnormal data.
Obtain the data cycle of data on flows, and after determining normal data interval, further according to data cycle and normal data interval, the data on flows of future period is predicted, to obtain the exceptional data point of future value, and export the exceptional data point predicted.
It is the schematic flow sheet of the trend prediction module of the device of router traffic intelligent data analysis of the present invention with further reference to Fig. 9, Fig. 9.
In the present embodiment, trend prediction module 30 specifically comprises:
Future value acquiring unit 31, for according to the data cycle, adopts trend prediction algorithm to obtain the future period data value of data on flows;
Predicting abnormality unit 32, for interval according to normal data, the exceptional data point in prediction future period data value.
Analyze the data week after date of data on flows, future value acquiring unit 31 is according to the data cycle, trend prediction algorithm is used to predict in advance data on flows, namely the data value in the future period of data on flows is obtained by trend prediction algorithm, ARIMA(AutoregressiveIntegrated Moving Average Model can be adopted in the present embodiment, difference ARMA model) method the data value in future period is predicted; After obtaining the data value in future period, predicting abnormality unit 32 is interval according to the normal data determined, predicts further, predict the exceptional data point that may occur in future period data value to the data value in future period.
According to this data cycle, the present embodiment by carrying out the analysis in data cycle to reception router traffic data, and determines that normal data is interval; According to data cycle and normal data interval, the exceptional data point of predicted flow rate data, export this exceptional data point, fully can excavate out the periodicity of historical data, the interval of normal data, and can exceptional data point be detected, so that routers exceptional data point carries out early warning in advance, thus the network segment appearance reducing mutual communication traffic to a great extent large is blocked, and following flow appearance peak period is blocked and the phenomenon of loss.
With reference to the structural representation that Figure 10, Figure 10 are device second embodiment of router traffic intelligent data analysis of the present invention.
On the basis of device first embodiment of router traffic intelligent data analysis of the present invention, this device also comprises:
Data analysis module 40, for analyzing the relevance of data on flows, and obtaining the correlation rule of data on flows, exporting this correlation rule according to this relevance.
After receiving router data collecting device Real-time Obtaining router traffic data, data analysis module 40 pairs of datas on flows carry out correlation analysis, exclude the data on flows that correlation is less, then strong to correlation data on flows collection carries out the calculating of correlation rule, and the correlation rule calculated the most at last exports.
It is the structural representation of the data analysis module of the device of router traffic intelligent data analysis of the present invention with further reference to Figure 11, Figure 11.
In the present embodiment, data analysis module 40 specifically comprises:
Qualitative analysis unit 41, for carrying out qualitative analysis to the data on flows received, the relevance between the data rows obtaining data on flows;
Quantitative analysis unit 42, for according to obtained relevance, carries out quantitative analysis to the data rows of data on flows, obtains the correlation rule of the data rows of data on flows.
After receiving data on flows, first qualitative analysis unit 41 carries out qualitative analysis to data on flows, obtain the relevance between data rows, exclude without the need to the less data on flows of the correlation of concern, such as calculate the coefficient correlation between data on flows by the method for Pearson correlation coefficients (Pearson correlation coefficient), according to result of calculation, data on flows less for correlation is got rid of from data rows.For the data rows that correlation is strong, then quantitative analysis unit 42 carries out quantitative analysis further, obtain the correlation rule of the data rows of these datas on flows, such as can according to FPGrowth algorithm tree, excavating the association mode of the data rows of data on flows, namely by pre-setting min confidence parameter, and filtering according to set confidence level condition, the association mode that final acquisition confidence level is high, as the correlation rule of the data rows of data on flows.
After receiving router traffic data, first qualitative analysis is carried out to data on flows, relevance between the data rows obtaining data on flows, and according to this relevance, quantitative analysis is carried out to the data rows of data on flows, obtain the correlation rule of the data rows of data on flows, effectively can analyze the correlation rule between data, thus occur blocking for reducing the large network segment of mutual communication traffic, and flow will occur that the phenomenon of blocking and losing provides the foundation peak period in future.
With reference to the structural representation that Figure 12, Figure 12 are device the 3rd embodiment of router traffic intelligent data analysis of the present invention.
On the basis of device first and second embodiment of router traffic intelligent data analysis of the present invention, this device also comprises:
Policy management module 50, for according to exceptional data point and correlation rule, adjusts the collocation strategy of router, sends the router configuration data after adjustment to router device.
In the present embodiment, after the exceptional data point receiving output and correlation rule, policy management module 50 is according to the tactful configuration rule of corresponding router, configuration of routers strategy between the adjustment network segment, and router device corresponding to the exceptional data point after adjustment and correlation rule export to, control for router device.Decision rule tree can be created according to several institute's model of historical traffic data and experience in the present embodiment, and obtain optimum configuration of routers strategy according to decision rule tree is final.
After the exceptional data point receiving output and correlation rule, the collocation strategy of adjustment router, sends the router configuration data after adjustment to router device for control; Obtain optimum configuration of routers strategy according to the intellectual analysis result of routers data on flows, and send to router device, achieve the object that routers equipment carries out countercharging.
The foregoing is only the preferred embodiments of the present invention; not thereby the scope of the claims of the present invention is limited; every utilize specification of the present invention and accompanying drawing content to do equivalent structure or equivalent flow process conversion; or be directly or indirectly used in other relevant technical fields, be all in like manner included in scope of patent protection of the present invention.
Claims (12)
1. a method for router traffic intelligent data analysis, is characterized in that, comprises step:
Receiving router data on flows, analyzes the data cycle of described data on flows, and determines that normal data is interval according to this data cycle;
According to described data cycle and normal data interval, predict the exceptional data point of described data on flows, export this exceptional data point.
2. the method for router traffic intelligent data analysis according to claim 1, is characterized in that, the data cycle of described analysis data on flows, and determines that the step in normal data interval specifically comprises according to this data cycle:
Analyze the described data on flows received, obtain the data cycle of data on flows;
According to the described data cycle, data on flows is carried out segmentation, the data on flows of the same time point of comparison, according to minimum value and the maximum in comparison result determination normal data interval.
3. the method for router traffic intelligent data analysis according to claim 1, is characterized in that, described according to data cycle and normal data interval, predicts that the step of the exceptional data point of described data on flows specifically comprises:
According to the described data cycle, trend prediction algorithm is adopted to obtain the future period data value of described data on flows;
Interval according to described normal data, predict the exceptional data point in described future period data value.
4. the method for router traffic intelligent data analysis according to any one of claim 1 to 3, is characterized in that, in the data cycle of the described data on flows of described analysis, and, also comprises according to the step in this data computation of Period normal data interval simultaneously:
Analyze the relevance of described data on flows, and obtain the correlation rule of described data on flows according to this relevance, export this correlation rule.
5. the method for router traffic intelligent data analysis according to claim 4, is characterized in that, the relevance of described analysis data on flows, and the step obtaining the correlation rule of described data on flows according to this relevance specifically comprises:
Qualitative analysis is carried out to the described data on flows received, the relevance between the data rows obtaining data on flows;
According to obtained relevance, quantitative analysis is carried out to the data rows of data on flows, obtains the correlation rule of the data rows of described data on flows.
6. the method for router traffic intelligent data analysis according to claim 5, is characterized in that, described according to data cycle and normal data interval, predict the exceptional data point of described data on flows, after exporting the step of this abnormal data, also comprises:
According to described exceptional data point and correlation rule, the collocation strategy of adjustment router, sends the router configuration data after adjustment to router device.
7. a device for router traffic intelligent data analysis, is characterized in that, comprising:
Data reception module, for receiving router data on flows;
According to this data cycle, data detection module, for analyzing the data cycle of described data on flows, and determines that normal data is interval;
Trend prediction module, for according to described data cycle and normal data interval, predicts the exceptional data point of described data on flows, exports this exceptional data point.
8. the device of router traffic intelligent data analysis according to claim 7, is characterized in that, described data detection module specifically comprises:
Cycle acquiring unit, for analyzing the described data on flows of reception, obtains the data cycle of data on flows;
Interval determination unit, for according to the described data cycle, carries out segmentation by data on flows, the data on flows of the same time point of comparison, according to minimum value and the maximum in comparison result determination normal data interval.
9. the device of router traffic intelligent data analysis according to claim 7, is characterized in that, described trend prediction module specifically comprises:
Future value acquiring unit, for according to the described data cycle, adopts trend prediction algorithm to obtain the future period data value of described data on flows;
Predicting abnormality unit, for interval according to described normal data, predicts the exceptional data point in described future period data value.
10. the device of the router traffic intelligent data analysis according to any one of claim 7 to 9, is characterized in that, also comprise:
Data analysis module, for analyzing the relevance of described data on flows, and obtaining the correlation rule of described data on flows according to this relevance, exporting this correlation rule.
The device of 11. router traffic intelligent data analysis according to claim 10, it is characterized in that, described data analysis module specifically comprises:
Qualitative analysis unit, for carrying out qualitative analysis to the described data on flows received, the relevance between the data rows obtaining data on flows;
Quantitative analysis unit, for according to obtained relevance, carries out quantitative analysis to the data rows of data on flows, obtains the correlation rule of the data rows of described data on flows.
The device of 12. router traffic intelligent data analysis according to claim 11, is characterized in that, also comprise:
Policy management module, for according to described exceptional data point and correlation rule, adjusts the collocation strategy of router, sends the router configuration data after adjustment to router device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310350422.7A CN104378219A (en) | 2013-08-12 | 2013-08-12 | Intelligent analysis method and device for router flow data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310350422.7A CN104378219A (en) | 2013-08-12 | 2013-08-12 | Intelligent analysis method and device for router flow data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104378219A true CN104378219A (en) | 2015-02-25 |
Family
ID=52556900
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310350422.7A Withdrawn CN104378219A (en) | 2013-08-12 | 2013-08-12 | Intelligent analysis method and device for router flow data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104378219A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107463904A (en) * | 2017-08-08 | 2017-12-12 | 网宿科技股份有限公司 | A kind of method and device for determining periods of events value |
| CN109191846A (en) * | 2018-10-12 | 2019-01-11 | 国网浙江省电力有限公司温州供电公司 | A kind of traffic trip method for predicting |
| CN111092891A (en) * | 2019-12-20 | 2020-05-01 | 杭州安恒信息技术股份有限公司 | Method, system and related device for detecting abnormal point in network |
| CN111226575A (en) * | 2018-11-28 | 2020-06-05 | 株式会社久保田 | Harvester and flow calculation method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1768311A (en) * | 2003-03-31 | 2006-05-03 | 英国电讯有限公司 | Data analysis system and method |
| US20090185503A1 (en) * | 2008-01-18 | 2009-07-23 | Oki Electric Industry Co., Ltd. | Network traffic analyzing device, network traffic analyzing method and network traffic analyzing system |
| CN101651568A (en) * | 2009-07-01 | 2010-02-17 | 青岛农业大学 | Method for predicting network flow and detecting abnormality |
| CN102930178A (en) * | 2012-11-26 | 2013-02-13 | 慈溪市供电局 | Method for detecting abnormal load data |
-
2013
- 2013-08-12 CN CN201310350422.7A patent/CN104378219A/en not_active Withdrawn
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1768311A (en) * | 2003-03-31 | 2006-05-03 | 英国电讯有限公司 | Data analysis system and method |
| US20090185503A1 (en) * | 2008-01-18 | 2009-07-23 | Oki Electric Industry Co., Ltd. | Network traffic analyzing device, network traffic analyzing method and network traffic analyzing system |
| CN101651568A (en) * | 2009-07-01 | 2010-02-17 | 青岛农业大学 | Method for predicting network flow and detecting abnormality |
| CN102930178A (en) * | 2012-11-26 | 2013-02-13 | 慈溪市供电局 | Method for detecting abnormal load data |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107463904A (en) * | 2017-08-08 | 2017-12-12 | 网宿科技股份有限公司 | A kind of method and device for determining periods of events value |
| CN107463904B (en) * | 2017-08-08 | 2021-05-25 | 网宿科技股份有限公司 | Method and device for determining event period value |
| CN109191846A (en) * | 2018-10-12 | 2019-01-11 | 国网浙江省电力有限公司温州供电公司 | A kind of traffic trip method for predicting |
| CN111226575A (en) * | 2018-11-28 | 2020-06-05 | 株式会社久保田 | Harvester and flow calculation method |
| CN111226575B (en) * | 2018-11-28 | 2023-09-12 | 株式会社久保田 | Harvester and flow calculation method |
| CN111092891A (en) * | 2019-12-20 | 2020-05-01 | 杭州安恒信息技术股份有限公司 | Method, system and related device for detecting abnormal point in network |
| CN111092891B (en) * | 2019-12-20 | 2022-04-01 | 杭州安恒信息技术股份有限公司 | Method, system and related device for detecting abnormal point in network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116304766B (en) | Multi-sensor-based quick assessment method for state of switch cabinet | |
| CN102957579B (en) | A kind of exception flow of network monitoring method and device | |
| JP6141235B2 (en) | How to detect anomalies in time series data | |
| CN104378219A (en) | Intelligent analysis method and device for router flow data | |
| CN110932899B (en) | Intelligent fault compression research method and system applying AI | |
| CN101789899A (en) | Network service quality analysis method and system | |
| CN110650052A (en) | Customer reason fault identification processing method and system based on intelligent algorithm | |
| CN101304479B (en) | Method and apparatus for detecting motion in video sequence | |
| CN103957118A (en) | Real-time intelligent analysis method for network flow of electric power data communication network and system thereof | |
| KR101187023B1 (en) | A network abnormal traffic analysis system | |
| CN102891761A (en) | Method and device for predicting equipment performance | |
| CN116216819A (en) | Intelligent water affair data analysis management system and method | |
| CN106680574B (en) | A kind of perception of substation equipment overvoltage and data processing method | |
| CN109142979B (en) | Method and device for detecting abnormal state of power distribution network | |
| CN117194171A (en) | Heterogeneous cloud resource panoramic anomaly detection system | |
| CN106022977A (en) | Transformer substation job site safety analysis method | |
| CN105867353A (en) | Oscillation monitoring method and system | |
| CN103326875B (en) | A kind of teleservice performance management method based on thresholding, system and webmaster | |
| CN106209404A (en) | Analyzing abnormal network flow method and system | |
| CN104573864A (en) | Data analysis alarm method based on autoregressive prediction | |
| CN111914000A (en) | Server power capping method and system based on power consumption prediction model | |
| CN113931270B (en) | Intercepting well intelligent monitoring system and method based on deep learning | |
| CN116030955A (en) | Medical equipment state monitoring method and related device based on Internet of things | |
| CN106487570A (en) | A kind of method and apparatus of assessment network performance index variation tendency | |
| CN109388512A (en) | For the assessment and analysis system of large-scale computer cluster intensity of anomaly |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20150225 |