CN103580905B - A kind of method for predicting, system and flow monitoring method, system - Google Patents
A kind of method for predicting, system and flow monitoring method, system Download PDFInfo
- Publication number
- CN103580905B CN103580905B CN201210282405.XA CN201210282405A CN103580905B CN 103580905 B CN103580905 B CN 103580905B CN 201210282405 A CN201210282405 A CN 201210282405A CN 103580905 B CN103580905 B CN 103580905B
- Authority
- CN
- China
- Prior art keywords
- flow
- time
- range
- intended application
- business
- 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.)
- Active
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/50—Network service management, e.g. ensuring proper service fulfilment according to agreements
- H04L41/5003—Managing SLA; Interaction between SLA and QoS
- H04L41/5019—Ensuring fulfilment of SLA
- H04L41/5025—Ensuring fulfilment of SLA by proactively reacting to service quality change, e.g. by reconfiguration after service quality degradation or upgrade
-
- 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
- H04L41/147—Network analysis or design for predicting network behaviour
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0876—Network utilisation, e.g. volume of load or congestion level
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Environmental & Geological Engineering (AREA)
- Quality & Reliability (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The present invention provides a kind of method for predicting, system and flow monitoring method, system, Dynamic Baseline passage real-time monitoring abnormal flow is utilized by various applications, bandwidth etc., missing inspection, false retrieval phenomenon can be prevented effectively from, Network Abnormal situation can more accurately and real-time be monitored, analysis resource utilization, classification alarm is sent in advance, to find network failure in time, ensureing that limited resource can be applied rationally to major profit business, reduce economic loss, additional income and strong help is provided.
Description
Technical field
The present invention relates to communication technical field, more particularly to a kind of method for predicting, system and flow monitoring method, it is
System.
Background technology
Network carrying ability and the applied business scale for being provided always all are complementary, the construction of one side network
Effective implementing platform will be provided to the popularization of new opplication technology, another aspect applied business can also be needed as its own system develops
Want and resource requirement higher is proposed to existing network, so as to promote network infrastructure development to enter the new construction period.So such as
What clearly, is accurately mapped applied business with the resource (such as bandwidth) shared by it, how to ensure limited resource energy
It is enough rationally applied to being problem to be solved in major profit business.
With NetFlow, Sflow be representative Flow technologies exactly for respond this challenge and the new solution that occurs on the way
Footpath.Flow records can provide traditional SNMP, MIB incomparable abundant information.It at least includes following field:IP ground
Location, purpose IP address, source port, destination interface, IP layer protocols type, ToS COSs, input physical port, by these words
A lot of other field fields that we are concerned about that section can be derived, such as various applications, the bandwidth of application.And current flux
Detection method volume forecasting can only be carried out to single application, applicable scope is narrower;Meanwhile, during volume forecasting
Be typically based on it is certain it is assumed that or coefficient correlation etc., these are assumed or coefficient influences whether the accuracy of prediction.
The content of the invention
The present invention provides a kind of method for predicting, system and flow monitoring method, system.
In order to solve the above-mentioned technical problem, present invention employs following technical scheme, the present invention provides a kind of volume forecasting
Method, comprises the following steps:
The information of the current shared flow of collection intended application business;
According to the flow information, the normal flow data of the intended application business is formulated;
According to the normal flow data, the flow information of the intended application business is predicted.
Further, collection intended application service traffics information is specifically included:
Setting carries out the time range of flow collection to intended application business;
It is determined that in the time range flow collection time step;
The data on flows of the applied business is gathered according to the time step in the time range.
Further, the normal flow data of applied business of setting objectives is specifically included:
Determine that the intended application business includes the corresponding flow velocity average value of each preset time period in the time range;Institute
Stating time range includes multiple preset time periods, and the preset time period includes time step described at least one;
Normal flow data is determined according to the corresponding average value of each preset time period.
Further, the flow information for predicting intended application business according to the normal flow data is specifically included:
Function of the intended application service traffics according to time change is built according to the normal flow data, according to the letter
Number obtains the predicted flow rate information of the intended application business.
Further, intended application business at least includes an applied business.
Further, if the intended application business includes multiple applied business, in the multiple applied business extremely
The different application protocol of rare two correspondences.
The present invention also provides a kind of flow monitoring method, and the method includes:
According to the above-mentioned flow value to shared by intended application business in method for predicting prediction setting time;
To predict that the range of flow of the flow value and setting for obtaining is compared;
Judge whether flow value of the target service in the setting time be normal according to comparative result;
If the flow value in the range of flow, does not perform actuation of an alarm.
Further, will predict that the range of flow of the flow value and setting for obtaining is compared to specifically include:
To the target service, shared flow in the setting time is monitored;
The range of flow includes multiple different grades of range of flows, and the different grades of range of flow is each corresponded to
A kind of alarm level.
Further, if the flow value is not in the range of flow, perform actuation of an alarm and specifically include:According to prison
The flow for measuring is compared with different grades of range of flow is set, and performs different alarm levels according to comparative result.
The invention provides a kind of volume forecasting system, the system includes:
Flow collection module, for gathering intended application service traffics information, and the flow information is sent to standard
Data module;
Normal data module, for according to the flow information, formulating the normal flow data of the applied business, and will
The normal flow data is sent to volume forecasting module;
Volume forecasting module, the flow information for predicting the applied business according to the normal flow data.
Present invention also offers a kind of flow monitoring system, the system includes:
Above-mentioned volume forecasting system, for predicting the flow value in setting time shared by intended application business, and will
The flow value for predicting is sent to alarm module;
Processing module, the range of flow for will predict the flow value and setting for obtaining is compared, and will compare
Result is sent to alarm module;
Alarm module, for whether judging flow value of the target service in the setting time according to comparative result
Normally;If the flow value in the range of flow, does not perform actuation of an alarm.
The present invention provides a kind of method for predicting, system and flow monitoring method, system, by multi-protocols
Various applications, bandwidth under (NetFlow, sflow) support etc. carry out volume forecasting, can be prevented effectively from missing inspection, false retrieval phenomenon, can
More accurately and real-time to monitor Network Abnormal situation, resource utilization is analyzed, be to find that network failure, guarantee have in time
The resource of limit can rationally be applied to major profit business, reduce economic loss, additional income and strong help be provided.
Brief description of the drawings
Fig. 1 is the structural representation of an embodiment of inventive flow forecasting system;
Fig. 2 is the flow chart of an embodiment of inventive flow Forecasting Methodology;
Fig. 3 is the structural representation of an embodiment of inventive flow monitoring system.
Fig. 4 is the flow chart of an embodiment of inventive flow monitoring method;
Fig. 5 is inventive flow monitoring classification alarm schematic diagram.
Specific embodiment
Below in conjunction with the accompanying drawings, specific embodiment of the invention is described in further detail.
Inventive flow forecasting system as shown in figure 1, in a kind of embodiment of inventive flow forecasting system, including
:For gathering intended application service traffics information, and the flow information is sent to the flow collection of normal data module
Module;For according to the flow information, formulating the normal flow data of the applied business, and by the normal flow data
Send to the normal data module of volume forecasting module;Stream for predicting the applied business according to the normal flow data
The volume forecasting module of amount information.
The flow chart of inventive flow Forecasting Methodology is illustrated in figure 2, the method is at least comprised the following steps:Collection target
Applied business flow information;The information of the current shared flow of collection intended application business;According to the flow information, institute is formulated
State the normal flow data of intended application business;According to the normal flow data, the flow of the intended application business is predicted
Information.
In one embodiment, collection intended application service traffics information is specifically included:Setting is carried out to intended application business
The time range of flow collection;It is determined that in the time range flow collection time step;Pressed in the time range
The data on flows of the applied business is gathered according to the time step.
Specifically, the time range of flow collection refers to the overall time span in flow collection;And flow collection
Time step refer in the time range of flow collection every how long carrying out a collection for intended application service traffics,
Namely gather the flow in each time step.Herein, time range and time step can be carried out according to different schemes
Formulate.
In one embodiment, the normal flow data of applied business of setting objectives is specifically included:Determine the intended application
Business includes the corresponding flow velocity average value of each preset time period in the time range;When the time range includes multiple default
Between section, the preset time period include time step described at least one;According to the corresponding average value of each preset time period
Determine normal flow data.
Specifically, to normal flow data formulation, it is necessary to divide the time period in pre-determined time range, also
Being to determine will obtain how many flow speed values, each time period one flow speed value of correspondence.So the division to the time period is no specific
Limit, can be divided according to applicable cases in practice.Then these average values and corresponding time period are built into stream
Amount baseline, as normal flow data.
In one embodiment, the flow information for predicting intended application business according to the normal flow data is specifically included:
Intended application service traffics are built according to the function of time change according to the normal flow data, institute is obtained according to the function
State the predicted flow rate information of intended application business.
Specifically, in this embodiment, can be according to the average value of each resulting time period, as one by one
Point, and to these click-through row interpolation treatment, flow velocity and the functional relation between the time are obtained after interpolation processing, so just can be to mesh
The flow velocity of random time for marking applied business is predicted, and also according to the size of flow velocity, also to obtain the flow of correspondence time big
It is small.
In one embodiment, intended application business can be single application, or multiple application compositions should
With group.If intended application business includes multiple applied business, that is, during application group, then at least two agreement supports should
Using group.
In one embodiment, time range includes:1 hour, 6 hours, 12 hours, 24 hours, one week, one month, 1 year
In at least one.It should be noted that time range herein according to the difference in applied business object, and can be set
Calmly, several listed by being not limited in, listed several time ranges are that may be commonly used in technical solution of the present invention
Several time ranges for arriving.
With reference to above-mentioned various embodiments, and concrete example is further described, it is necessary to what is illustrated is following
A kind of simply citing is illustrated, technical solution of the present invention is not limited to that.
Do not have application field in NetFlow, SFlow message, but the various information included according to message can determine
Go out each application or apply group, illustrated by taking one way in which as an example below, for example:Message includes port and agreement word
Section, can be derived by the two fields:Port+agreement=application.Meanwhile, bandwidth=flow/time, so as to record each moment
The flow of application, then will be converged using or using group, calculated, that is, there is initial data.
Closely bound up with baseline in the formulation process of baseline is time range, and it needs to rely on the time of traffic statistics
The step-length of scope and record.Here the scope that we may be concerned about has 7 kinds, respectively Qi, i=0 ... 6 wherein Q0:1 hour, Q1:
6 hours, Q2:12 hours, Q3:24 hours, Q4:One week, Q5:One month, Q6:1 year.The step-length for recording flow can be designated as ti,
I=0 ... 6.
In order to realize standardization, all times are all with second note here;And 60 baseline values are taken, the value of each point is designated as
Bj, j=0 ... 59.So no matter time range is how many, the time step between each two baseline value(It is designated as T);Meanwhile, no
With time range Q0To Q6Corresponding time step tiCan be taken as respectively [10s, 6*10s, 12*10s ...], then no matter
Time range is how much can to record 360 points, and each flow value put is designated as x by wekm, wherein, k=0 ... K;m=
0 ... 359. subscript k here represents the flow of current time record and the flow of record in the record corresponding time before.With 24
As a example by hour, as k=1, expression has not only counted the flow information in current 24 hours, for the accuracy of empirical data, also
The flow information of correspondence time period in previous 24 hours is counted.
It should be noted that the quantity of above-mentioned middle baseline value, and in the range of different time step-length size, and remembered
The specific data such as number of point of record are not unique datas, only a kind of preferred scheme.
Us are analyzed more than can obtain in different time scope (Qi) different step-length (ti) under each time period stream
Fast (Byte/s), that is, baseline detailed numerical value (Bj) be:
①
From formula 1. in as can be seen that t hereiIt is our time steps set in advance, therefore once clear and definite time model
Enclose so tiJust specify that, therefore we only need to the flow value x of each time period of concern recordkm, herein, by every 6
Time step is used as a time period.
The formulation of baseline can be described as the fitting to empirical data, and 60 baseline values, certain baseline value are taken in this embodiment
Quantity can be chosen according to the difference of actual conditions, in fact by the distribution of baseline value just can be rough see outflow
Change, while can also be rough depict outflow tendency chart.
The above-mentioned acquisition methods to baseline value are a kind of preferably methods, it is also possible to 360 for directly recording to correspondence when
Between data on flows in step-length directly obtain 360 flow speed datas divided by correspondence time step, and from this 360 flow speed datas
Several are chosen as baseline value.
The empirical data in simply each time period be given in baseline, wants the more accurate traffic trends of acquisition pre-
Survey, then need to make further statistics and analysis by baseline.Here Lagrange's interpolation is used further to do
Data analysis, acquisition flow walks potential function y=B (t) with time relationship.Have function we when can just predict following any
Between the flow velocity put, while the time point where the peak value and valley of flow velocity can be predicted, while we can also calculate taking the post as
The flow of meaning time period, then can be carried out the monitoring of abnormal flow.
We have taken 60 baseline values, B=[B from above-mentioned specific embodiment0,B1... B59] corresponding independent variable
Value is respectively T=[T0,T1,...T59], that is, time step is equivalent incremental in baseline.
So there is flow velocity trend functionWherein Lagrangian fundamental polynomials 1jT () is:
②
Therefore, our anticipation functions to flow velocity tendency are:
③
Herein, we use Lagrange's interpolation and carry out the prediction of flow velocity, but this is only a kind of preferably square
Case, error is smaller.But flow velocity can be equally predicted using other interpolation methods, for example, Newton interpolating method, multinomial is inserted
Value method etc., herein, is not described in detail to these procedures.
The structural representation of an embodiment of inventive flow monitoring system is illustrated in figure 3, the system is at least included:
The flow value shared by intended application business in setting time is predicted, and the flow value that will be predicted is sent to alarm module
At least one volume forecasting system in above-mentioned various flow rate forecasting system;For the flow value and setting that obtain will to be predicted
Range of flow be compared, and comparative result is sent to the processing module of alarm module;For being judged according to comparative result
Whether flow value of the target service in the setting time be normal;If the flow value is not in the range of flow,
Then perform the alarm module of actuation of an alarm.
Be illustrated in figure 4 the flow chart of an embodiment of inventive flow monitoring method, at least including in the present invention according to
The method of inventive flow prediction is to the flow value shared by intended application business in prediction setting time;The institute for obtaining will be predicted
The range of flow for stating flow value and setting is compared;Judge the target service in the setting time according to comparative result
Flow value it is whether normal;If the flow value in the range of flow, does not perform actuation of an alarm.
To predict that the range of flow of the flow value and setting for obtaining is compared in one embodiment to specifically include:It is right
The shared flow in the setting time of the target service is monitored;The range of flow includes multiple different brackets
Range of flow, the different grades of range of flow each corresponds to a kind of alarm level.
In one embodiment, if the flow value is not in the range of flow, perform actuation of an alarm and specifically include:
It is compared with different grades of range of flow is set according to the flow for monitoring, and different alarms etc. is performed according to comparative result
Level.
If detecting the flow of intended application business, then to do is to first, the stream in random time section is predicted
Amount.After the function that we have flow velocity, the flow of any a period of time can be determined by the flow velocity in interval
Integrate to obtain.For example from flow L (a, b) time point a to time point b, as
④
Similarly, any n time period [ai,bi], the total flow in i=0 ..., n-1 is
⑤
In order to preferably control flow, detect exception, to current statistic to flow obtained with empirical data statistical analysis
To flow (i.e. 5. formula) carry out simple process, system provides the function of configuration flow bound, so that more arbitrary
Control flow.
It is assumed here that user concerns that time range is QiTraffic conditions, it is intended that in QiIn the range of this period
Random time section [a, b] in all without there is flow more than empirical data LPredictionThe upper limit P of=[a, b]max% is less than down
Limit Pmin% i.e. default range of flow, once there are above-mentioned two situations, system can make early warning at once, while and equipment
Linkage, using deep packet Detection Techniques automatic dynamic strategy, speed limit is carried out to flow.
Base-line data channel monitoring abnormal flow is constructed here by baseline bound, it is exactly following two public affairs to summarize
Formula:
LCurrently[a, b] > (1+Pmax%) LPrediction[a, b]; ⑥
Or
LCurrently[a, b] < (1-Pmin%) LPrediction[a, b]; ⑦
Abnormal flow dynamic monitoring flow under multi protocol supporting to various applications and application group may refer to Fig. 5.Dynamic
Time channel is the limitation of regular and time period, first Real-time Collection to present flow rate carry out time change, it is current when
Between be set to regular time section on position.Classified Monitoring range of flow, flow not at the same level are set up on dynamic time passage
Scope represents different alarm levels.Either go up more than normal condition when more than default range of flow, or more than just
Reason condition declines, and is carried out corresponding alarm.
Comparison behavior should be carried out in a minimum comparison time scope in time step.It is possible to prevente effectively from survey by mistake
And test leakage, and the accuracy of monitoring can be improved.
With the propulsion of current time, the mobile change on passage of monitoring reference point updates monitoring foundation, completes to current
The comparing and the supposition in future of flow monitor the effect of abnormal flow to reach.
Above content is to combine specific embodiment further description made for the present invention, it is impossible to assert this hair
Bright specific implementation is confined to these explanations;Therefore, for general technical staff of the technical field of the invention,
On the premise of not departing from present inventive concept, some simple deduction or replace can also be made, should be all considered as belonging to of the invention
Protection domain.
Claims (10)
1. a kind of method for predicting, it is characterised in that the Forecasting Methodology includes:
The information of the current shared flow of collection intended application business;The collection intended application service traffics information is specifically wrapped
Include:
Setting carries out the time range Q of flow collection to intended application businessi, it is determined that the flow collection in the time range
Time step ti, in the time range QiIt is interior according to the time step tiGather the data on flows X of the applied businesskm;
According to the flow information, the normal flow data of the intended application business is formulated;The described formulation target should
Included with the normal flow data of business:
Determine that the intended application business includes the corresponding flow velocity average value B of each preset time period in the time rangej,The m=0 ... M-1, the M are characterized in the time range and acquire M time point
Flow value;The j=0,1 ... J-1, the J characterize the sum of baseline value;The P is characterized and is calculated needed for a baseline value
Data on flows XkmNumber, the P=M/J, the P be natural number;The k is k time range before current time;Institute
Stating time range includes multiple preset time periods, and the preset time period includes time step described at least one;According to described
The corresponding average value of each preset time period determines normal flow data;
According to the normal flow data, the flow information of the intended application business is predicted;The prediction intended application
The flow information of business includes:
Function of the intended application service traffics according to time change is built according to the normal flow data
Wherein,It is Lagrangian fundamental polynomials, T is the time step between two baseline values;According to described
Function obtains the predicted flow rate information of the intended application business.
2. method for predicting as claimed in claim 1, it is characterised in that the intended application business at least include one should
Use business.
3. method for predicting as claimed in claim 2, it is characterised in that if the intended application business includes multiple application
During business, the different application protocol of at least two correspondences in the multiple applied business.
4. a kind of flow monitoring method, it is characterised in that methods described includes:
Intended application business institute in method for predicting prediction setting time as claimed in any of claims 1 to 3
The flow value of occupancy;
To predict that the range of flow of the flow value and setting for obtaining is compared;
Judge whether flow value of the target service in the setting time be normal according to comparative result;
If the flow value in the range of flow, does not perform actuation of an alarm.
5. flow monitoring method as claimed in claim 4, it is characterised in that it is described will predict the flow value that obtains and
The range of flow of setting is compared and specifically includes:
To the target service, shared flow in the setting time is monitored;
The range of flow includes multiple different grades of range of flows, and the different grades of range of flow each corresponds to one kind
Alarm level.
6. flow monitoring method as claimed in claim 5, it is characterised in that if the flow value is not in the flow
In the range of, then perform actuation of an alarm and specifically include:
It is compared with different grades of range of flow is set according to the flow for monitoring, and different reports is performed according to comparative result
Alert grade.
7. a kind of volume forecasting system, it is characterised in that described system includes:
Flow collection module, for gathering intended application service traffics information, and the flow information is sent to normal data
Module;The flow collection module collection intended application service traffics information is specifically included:
Setting carries out the time range Q of flow collection to intended application businessi, it is determined that the flow collection in the time range
Time step ti, in the time range QiIt is interior according to the time step tiGather the data on flows X of the applied businesskm;
Normal data module, for according to the flow information, formulating the normal flow data of the applied business, and will be described
Normal flow data is sent to volume forecasting module;The normal data module formulates the normal flow of the intended application business
Data include:
Determine that the intended application business includes the corresponding flow velocity average value B of each preset time period in the time rangej,The m=0 ... M-1, the M are characterized in the time range and acquire M
The flow value at time point;The j=0,1 ... J-1, the J characterize the sum of baseline value;The P is characterized and is calculated a base
Data on flows X needed for line valuekmNumber, the P=M/J, the P be natural number;When the k is for k before current time
Between scope;The time range includes multiple preset time periods, and the preset time period includes time step described at least one;
Normal flow data is determined according to the corresponding average value of each preset time period;
Volume forecasting module, the flow information for predicting the applied business according to the normal flow data;The flow
Prediction module predicts that the flow information of the intended application business includes:
Function of the intended application service traffics according to time change is built according to the normal flow data
Wherein,It is Lagrangian fundamental polynomials, T is the time step between two baseline values;According to described
Function obtains the predicted flow rate information of the intended application business.
8. a kind of flow monitoring system, it is characterised in that the system includes:
Volume forecasting system as claimed in claim 7, predicts the flow value shared by intended application business in setting time, and
The flow value that will be predicted is sent to alarm module;
Processing module, for that will predict that the flow value that obtains and the range of flow of setting are compared, and by comparative result
Send to alarm module;
Alarm module, for whether just to judge flow value of the target service in the setting time according to comparative result
Often;If the flow value in the range of flow, does not perform actuation of an alarm.
9. flow monitoring system as claimed in claim 8, it is characterised in that it is described will predict the flow value that obtains and
The range of flow of setting is compared and specifically includes:
To the target service, shared flow in the setting time is monitored;
The range of flow includes multiple different grades of range of flows, and the different grades of range of flow each corresponds to one kind
Alarm level.
10. flow monitoring system as claimed in claim 9, it is characterised in that if the flow value is not in the stream
In the range of amount, then perform actuation of an alarm and specifically include:
It is compared with different grades of range of flow is set according to the flow for monitoring, and different reports is performed according to comparative result
Alert grade.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210282405.XA CN103580905B (en) | 2012-08-09 | 2012-08-09 | A kind of method for predicting, system and flow monitoring method, system |
PCT/CN2013/081072 WO2014023245A1 (en) | 2012-08-09 | 2013-08-08 | Flow prediction method and system and flow monitoring method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210282405.XA CN103580905B (en) | 2012-08-09 | 2012-08-09 | A kind of method for predicting, system and flow monitoring method, system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103580905A CN103580905A (en) | 2014-02-12 |
CN103580905B true CN103580905B (en) | 2017-05-31 |
Family
ID=50051890
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210282405.XA Active CN103580905B (en) | 2012-08-09 | 2012-08-09 | A kind of method for predicting, system and flow monitoring method, system |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN103580905B (en) |
WO (1) | WO2014023245A1 (en) |
Families Citing this family (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105530219B (en) * | 2014-09-28 | 2019-12-10 | 腾讯科技(深圳)有限公司 | Connection detection method and device |
CN104349367A (en) * | 2014-11-12 | 2015-02-11 | 深圳市中兴移动通信有限公司 | Mobile terminal and predicting reminding method and device of flow consumption of mobile terminal |
CN107231268B (en) * | 2016-03-25 | 2020-05-01 | 北京京东尚科信息技术有限公司 | Method and device for testing website performance |
CN106100928B (en) * | 2016-06-21 | 2019-02-26 | 北京百度网讯科技有限公司 | The transmission method and device of monitoring data applied to data center |
CN105979538A (en) * | 2016-07-19 | 2016-09-28 | 浪潮软件集团有限公司 | Method for analyzing lost telephone traffic and flow during cell interruption |
CN106230633A (en) * | 2016-08-01 | 2016-12-14 | 中体彩科技发展有限公司 | The Forecasting Methodology of newly-increased high frequency sports lottery ticket game data flow and device |
CN107040475B (en) * | 2016-11-14 | 2020-10-02 | 平安科技(深圳)有限公司 | Resource scheduling method and device |
CN111225404B (en) | 2018-11-23 | 2021-08-31 | 华为技术有限公司 | Network quality monitoring method and device |
CN111262750B (en) * | 2020-01-09 | 2021-08-27 | 中国银联股份有限公司 | Method and system for evaluating baseline model |
CN113992496B (en) * | 2020-07-10 | 2023-11-17 | 中国移动通信集团湖北有限公司 | Abnormal alarm method and device based on quartile algorithm and computing equipment |
CN114143266B (en) * | 2021-11-29 | 2023-07-07 | 中国平安财产保险股份有限公司 | Flow control method, device, equipment and medium based on machine learning |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1617512A (en) * | 2004-11-25 | 2005-05-18 | 中国科学院计算技术研究所 | Adaptive network flow forecasting and abnormal alarming method |
CN101155085A (en) * | 2006-09-29 | 2008-04-02 | 中兴通讯股份有限公司 | Method and device for real-time flux prediction and real-time flux monitoring and early warning |
CN102014031A (en) * | 2010-12-31 | 2011-04-13 | 湖南神州祥网科技有限公司 | Method and system for network flow anomaly detection |
CN102104509A (en) * | 2011-02-17 | 2011-06-22 | 浪潮(北京)电子信息产业有限公司 | Method and device for predicting server load in cloud operation system |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN100561984C (en) * | 2007-09-21 | 2009-11-18 | 烽火通信科技股份有限公司 | A kind of Dynamic Bandwidth Allocation and control system based on multiservice transport platform |
CN102369689B (en) * | 2011-08-11 | 2014-05-07 | 华为技术有限公司 | Long-term forecasting method and device of network flow |
-
2012
- 2012-08-09 CN CN201210282405.XA patent/CN103580905B/en active Active
-
2013
- 2013-08-08 WO PCT/CN2013/081072 patent/WO2014023245A1/en active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1617512A (en) * | 2004-11-25 | 2005-05-18 | 中国科学院计算技术研究所 | Adaptive network flow forecasting and abnormal alarming method |
CN101155085A (en) * | 2006-09-29 | 2008-04-02 | 中兴通讯股份有限公司 | Method and device for real-time flux prediction and real-time flux monitoring and early warning |
CN102014031A (en) * | 2010-12-31 | 2011-04-13 | 湖南神州祥网科技有限公司 | Method and system for network flow anomaly detection |
CN102104509A (en) * | 2011-02-17 | 2011-06-22 | 浪潮(北京)电子信息产业有限公司 | Method and device for predicting server load in cloud operation system |
Also Published As
Publication number | Publication date |
---|---|
CN103580905A (en) | 2014-02-12 |
WO2014023245A1 (en) | 2014-02-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103580905B (en) | A kind of method for predicting, system and flow monitoring method, system | |
CN101155085B (en) | Method and device for real-time flux prediction and real-time flux monitoring and early warning | |
CN102130800B (en) | Device and method for detecting network access abnormality based on data stream behavior analysis | |
KR100748246B1 (en) | Multi-step integrated security monitoring system and method using intrusion detection system log collection engine and traffic statistic generation engine | |
CN105429977B (en) | Deep packet inspection device abnormal flow monitoring method based on comentropy measurement | |
CN103581186B (en) | A kind of network security situational awareness method and system | |
CN100356729C (en) | Method and system for monitoring network service performance | |
KR100617310B1 (en) | Apparatus for detecting abnormality of traffic in network and method thereof | |
EP2894813A1 (en) | Technique for creating a knowledge base for alarm management in a communications network | |
CN107454143B (en) | Intelligent inspection method for metering performance of digital electric energy meter in wide-area measurement mode | |
CN110868425A (en) | Industrial control information safety monitoring system adopting black and white list for analysis | |
CN103714057A (en) | Real-time monitoring method and device for online web information | |
CN103544093A (en) | Monitoring and alarm control method and system | |
CN104427549B (en) | A kind of network problem analysis method and system | |
CN105187228A (en) | Network quality detection method and router | |
CN106921507A (en) | The method and apparatus being predicted to customer complaint within a wireless communication network | |
CN104361658B (en) | The detection method and device of a kind of region Nei Ge places people information | |
CN107395382A (en) | A kind of network quality performance methods of exhibiting and device, system | |
WO2013010404A1 (en) | Device performance prediction processing method and apparatus | |
CN106973012A (en) | A kind of computer network loop detecting method | |
CN106254318A (en) | A kind of Analysis of Network Attack method | |
CN109995599A (en) | A kind of intelligent alarm method of network performance exception | |
CN105530243A (en) | Realizing method of network attack event quantitative hierarchical algorithm | |
CN109936487A (en) | A kind of real-time analysis and monitoring method and system of Web broadcast packet | |
JP2013179491A (en) | Network quality monitoring device and network quality monitoring method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |