CN109495317A - Data network method for predicting and device - Google Patents
Data network method for predicting and device Download PDFInfo
- Publication number
- CN109495317A CN109495317A CN201811526034.9A CN201811526034A CN109495317A CN 109495317 A CN109495317 A CN 109495317A CN 201811526034 A CN201811526034 A CN 201811526034A CN 109495317 A CN109495317 A CN 109495317A
- Authority
- CN
- China
- Prior art keywords
- under
- user
- flow
- bandwidth
- data network
- 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.)
- Granted
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
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
-
- 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)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The present invention provides a kind of data network method for predicting and device, this method comprises: obtaining the history online user number under data network total flow historical data, different service types and different bandwidth;Determine that the user's history under different service types and different bandwidth averagely uses flow according to the history online user number under the data network total flow historical data, different service types and different bandwidth based on the flux prediction model constructed;Flow is averagely used according to the user's history under the different service types and different bandwidth, the data network total flow based on the goal-selling user expansion number under different service types and different bandwidth, after predicting dilatation.The program can reflect out data network flow entirety traffic conditions, and can reflect data network entirety flow growth trend;The user behavior of each bandwidth under type of service can be embodied, foundation can be provided for broadband speed raising.
Description
Technical field
The present invention relates to field of communication technology, in particular to a kind of data network method for predicting and device.
Background technique
Volume forecasting is paying close attention to a little for each IP operator, and accurate volume forecasting has the dilatation of network great
Directive significance can instruct operator that the promoting service more refined is unfolded in region by the volume forecasting of refinement.How
Realize that most accurate volume forecasting is the problem of current each IP operator faced using minimum cost, at present IP operator
It is main in volume forecasting that there are two thinkings:
One: scale prediction being done according to overall data over the years, counts the flow value of past few years, extrapolates the flow in next year
Big probable value such as obtains the traffic conditions that certain data network exports 2009 to 2017 by network management system, according to annual variation feelings
Condition goes out flow growth trend in 2018 with certain formula to calculating.The network capacity extension is carried out on this basis.The drawbacks of this thinking
It is that data are too general, has ignored user behavior, region etc. influences, and the prediction result accuracy obtained cannot be guaranteed, be easy to make
At the waste of dilatation.
Two: selection equipment deployment depth packet detection device (the DPI Deep Packet in important equipment level
Inspection), by the true content in the packet capturing analysis application stream of DPI equipment, user behavior is analyzed, fine with progress
Flow analysis.Such thinking predicts the result come generally more accurately, and drawback is that cost is too high, is to need to dispose first
DPI equipment, followed by DPI technology be not it is static constant, with the development of detection technique, the concealing technology of improper application
It encrypts in evolution, such as data portion, hide tagged word and detection is hidden by tunneling technique, technical costs also has phase
The raising answered.
Summary of the invention
The embodiment of the invention provides a kind of data network method for predicting and devices, and it is whole to can reflect out data network flow
Body traffic conditions, and can reflect data network entirety flow growth trend;The use of each bandwidth under type of service can be embodied
Family behavior can provide foundation for broadband speed raising.
The embodiment of the invention provides a kind of data network method for predicting, this method comprises:
Obtain the history online user number under data network total flow historical data, different service types and different bandwidth;
Based on the flux prediction model constructed, according to the data network total flow historical data, different service types and
History online user number under different bandwidth determines the user's history under different service types and different bandwidth averagely using stream
Amount;
Flow is averagely used according to the user's history under the different service types and different bandwidth, is based on different business class
Goal-selling user expansion number under type and different bandwidth, the data network total flow after predicting dilatation.
The embodiment of the invention also provides a kind of data network volume forecasting device, which includes:
Data obtaining module, for obtaining under data network total flow historical data, different service types and different bandwidth
History online user number;
Flow rate calculation module, for based on the flux prediction model constructed, according to the data network total flow history number
According to the history online user number under, different service types and different bandwidth, the use under different service types and different bandwidth is determined
Family history averagely uses flow;
Data network total flow prediction module, for flat according to the user's history under the different service types and different bandwidth
Flow is used, the data based on the goal-selling user expansion number under different service types and different bandwidth, after predicting dilatation
Net total flow.
The embodiment of the invention also provides a kind of computer equipments, including memory, processor and storage are on a memory
And the computer program that can be run on a processor, the processor realize data described above when executing the computer program
Net method for predicting.
The embodiment of the invention also provides a kind of computer readable storage medium, the computer-readable recording medium storage
There is the computer program for executing data network method for predicting described above.
In embodiments of the present invention, by obtaining data network total flow historical data, different service types and different bandwidth
Under history online user number;Based on the flux prediction model constructed, according to the data network total flow historical data, difference
History online user number under type of service and different bandwidth determines that the user's history under different service types and different bandwidth is flat
Use flow;Flow is averagely used according to the user's history under the different service types and different bandwidth, based on not of the same trade or business
Goal-selling user expansion number under service type and different bandwidth, the data network total flow after predicting dilatation.With prior art phase
Compare, the present invention can reflect out data network flow entirety traffic conditions, and can reflect that data network entirety flow increases and become
Gesture;The user behavior of each bandwidth under type of service can be embodied, foundation can be provided for broadband speed raising.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is a kind of data network group-network construction schematic diagram;
Fig. 2 is a kind of data network method for predicting flow chart (one) provided in an embodiment of the present invention;
Fig. 3 is a kind of data network method for predicting flow chart (two) provided in an embodiment of the present invention;
Fig. 4 is the bandwidth average flow rate that a kind of flux prediction model proposed by the present invention provided in an embodiment of the present invention determines
Value obtains the comparative result schematic diagram of the fluctuation situation of first line of a couplet entirety flow with physical device;
Fig. 5 is a kind of wide deep eastern Buddhist IPTV user's uplink and downlink flow velocity schematic diagram provided in an embodiment of the present invention;
Fig. 6 is that a kind of Pearl River Delta internet provided in an embodiment of the present invention changed with IPTV online user number 24 hours
(BRAS sampling rate 5%) schematic diagram;
Fig. 7 is a kind of Pearl River Delta Internet user average flow rate schematic diagram provided in an embodiment of the present invention;
Fig. 8 is a kind of data network volume forecasting apparatus structure block diagram (one) provided in an embodiment of the present invention;
Fig. 9 is a kind of data network volume forecasting apparatus structure block diagram (two) provided in an embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that the described embodiment is only a part of the embodiment of the present invention, instead of all the embodiments.Based on this
Embodiment in invention, every other reality obtained by those of ordinary skill in the art without making creative efforts
Example is applied, shall fall within the protection scope of the present invention.
The data network group-network construction of current each IP operator is substantially as shown in Figure 1.In Fig. 1, BAS Broadband Access Server
(Broadband Access Server/Broadband Remote Access Server, BAS/BRAS, it is unified below to use
It BRAS) is the novel access gateway towards broad band network application.It is located at the convergence layer or marginal layer of backbone network, can complete
The data access of (or high speed) IP/ATM net of user bandwidth.It is linked to BRAS on after access layer equipment converges in each data network,
The upper data of BRAS are communicated with backbone or other data network again by egress router.BRAS lower link networks, first line of a couplet data network
Outlet analyzes the component flow of each type of service in BRAS, up can analyze out the bulk flow situation of data network, down may be used
To analyze the various bandwidth users behavior situations of various businesses person.
Based on this, the invention proposes a kind of data network method for predicting, the Integral Thought of this method is to be with BRAS
Unit, by obtaining user's average flow rate under the various bandwidth under each type of service of BRAS, data, establish mould based on this
Type, such as region piece section model, device link model etc. goes out region section according to model analysis, and the traffic conditions of device link are folded
Add the data such as user's speed-raising, forms the network capacity extension, the analysis foundation of promoting service.
As shown in Fig. 2, the data network method for predicting includes:
Step 201: the history obtained under data network total flow historical data, different service types and different bandwidth is used online
Amount;
Step 202: based on the flux prediction model constructed, according to the data network total flow historical data, not of the same trade or business
History online user number under service type and different bandwidth determines that the user's history under different service types and different bandwidth is average
Use flow;
Step 203: flow averagely being used according to the user's history under the different service types and different bandwidth, based on not
Data network total flow with the goal-selling user expansion number under type of service and different bandwidth, after predicting dilatation.
In embodiments of the present invention, it is found in O&M, the whole flow of BRAS is with the public internet business in BRAS
And (IPTV, that is, Interactive Internet TV is a kind of to IPTV using broadband cable net, collects internet, multimedia, communication etc.
Multiple technologies provide the brand-new technology of a variety of interactive services including DTV in one, to domestic consumer.It is international
On to the definition of IPTV be controllably can pipe safe transmission and with QoS certification wired or wireless Ip network, provide including video,
Audio (including voice), text, the multimedia service including the business such as figure and data.) service traffics have biggish relationship,
The basic energy conversion unit entirety traffic conditions of the flow of two kinds of business.And it is directed to the BRAS to be analyzed, user is pressed into bandwidth partition
Bandwidth class, such as: 4M or less -4B, 4M-4,6M-6,8M-8,10M-10,12M-12,20M and the above 20B etc..For this situation,
The present invention specifically executes as follows:
Step 201 (specific): data network total flow is obtained according to user region or different device links and is gone through
The history online user number under different bandwidth under history data, public internet business, the history under the different bandwidth under IPTV
Online user number;
Step 202 (specific): pre- based on the zone flow prediction model constructed or the device link flow constructed
Model is surveyed, is used online according to the history under the different bandwidth under the data network total flow historical data, public internet business
History online user number under different bandwidth under amount, IPTV, determines the use under the different bandwidth under public internet business
Family history averagely uses the user's history under the different bandwidth under flow, IPTV averagely to use flow;
Step 203 (specific): according to the user's history under the different bandwidth under public internet business averagely using stream
The user's history under different bandwidth under amount, IPTV averagely uses flow, based under the different bandwidth under public internet business
Goal-selling user expansion number, the goal-selling user expansion number under the different bandwidth under IPTV, the data after predicting dilatation
Net total flow.
Illustratively how flux prediction model constructs below.
Firstly, realizing that, to the periodical acquisition function of connecting relay traffic on BRAS, collection period is 5 minutes.Realize BRAS
The acquisition function of the online user number of separate service type, collection period are 10 minutes.The acquisition time of the two was at 10 minutes
Integral multiple is overlapped, and is corresponded to according to identical acquisition time to the two, as analysis sample.
Before analyzing real data, by preliminary analysis, it is believed that:
1) online user number of public internet and IPTV to connect on BRAS relay traffic (downlink traffic, it is mentioned below
Flow all refers to the downlink traffic for connecting relaying on BRAS) there is larger impact, it is assumed that a flux prediction model are as follows:
BARSFlow=a × w+b × h+c;
Wherein, BARSFlowIndicate data network total flow;A indicates that public internet user averagely uses flow;W indicates the public
The online user number of internet;B indicates that IPTV user averagely uses flow;The online user number of h expression IPTV;C indicates other
Use flow.
2) because of the internet behavior of the user of different zones, there may be bigger differences, in different zones, or even not
With on BRAS, there may be relatively big differences for the correlation of the two (connecting relay traffic on online user number and BRAS), it is contemplated that
Regional model is established, selects multiple devices sampling analysis in region.
3) the online user number acquisition that can be refined, the bandwidth situation for acquiring data network any active ues in advance (can refer to
Sampling acquires each bandwidth users traffic scheme), the bandwidth situation on superposition in each collection period, you can get it online user's
Bandwidth distribution situation, then 1) in model can become:
BARSFlow=a1×w1+a2×w2+a3×w3+b1×h1+b2×h2+b3×h3+c;
Wherein, a1、a2、a3Indicate that the public internet user of each bandwidth averagely uses flow;w1、w2、w3Indicate that the public is mutual
The online user number for each bandwidth of networking;b1、b2、b3Indicate that the average of the IPTV user of each bandwidth uses flow;h1、h2、h3It indicates
The online user number of each bandwidth of IPTV;C indicates that other use flow.
This model can form system of linear equations by multipoint data, finally solve a1、a2、a3、b1、b2、b3Etc. under each bandwidth
Average user flow.
It is found according to real data by preliminary analysis:
1) there are apparent linear relationships with total online user number for flow, respectively to 163 (referring to public internet)
There is also similarity relations with IPTV number of users.
If 2) relationship of comprehensive analysis three, discovery is all linear positive phase in most cases to 163 numbers of users
It closes (a>0), is positively correlated (b>0) negatively correlated (b<0) sometimes sometimes to IPTV number of users.
3) either to total number of users or 163 numbers of users, the intercept that linear analysis obtains all is negative (c < 0), meaning
Number of users be 0 when, be minus flow.It may be because certain user hangs over online but is not take up flow.
The analysis of superposition correlation can make predicted flow rate more accurate.
It is that select the data analysis result that wherein an equipment is done as shown in table 1 below:
Table 1
In embodiments of the present invention, the flux prediction model of building may include zone flow prediction model, device link
Flux prediction model.
1) zone flow prediction model
It is to analyze the average flow rate shape of bandwidth distribution situation and each bandwidth in section under type of service that it, which formulates purpose,
Condition.To determine, section changes in flow rate brought by the speed-raising of broadband influences in section, adjusts dilatation index.
Acquisition scheme presses equipment based on original, and type of service, bandwidth mode acquisition, is still each business on specific installation
The user of each bandwidth of type selects 100 at random, and offline user fill up with type of service with the user of bandwidth.And
Need to obtain user account information with the corresponding relationship of section.
Its marketing center, region branch company are determined for user after the completion of acquiring data, and carry out marketing center, area
The data of domain branch company store, and with type of service when summarizing, region branch company, marketing center, bandwidth summarizes, in region branch company
For the upper layer of marketing center, increases when summarizing and summarize by marketing center's mode of region branch company.Pay attention to pressing in selection equipment
Device distribution is selected, and each center is about selected 2-3 platform BRAS and acquired.
Substantially summarize as shown in table 2:
Table 2
Districts and cities | Region branch company | Marketing center | Bandwidth (mbps) | Mean Speed |
Foshan | Shuande | Nan Zhuan marketing service center | 4 | 164.19 |
Foshan | Shuande | Great Liang marketing service center | 4 | 164.19 |
Foshan | The South Sea | Yan Bu marketing service center | 4 | 164.19 |
2) device link flux prediction model
This model need to obtain account with the binding relationship of device port, and do some analyses early period, analyze binding
Accounting relationship of the account of device port in all users, table 3 are primary analyses therein:
Table 3
Device IP | Total number of users | User bound sum | Bind accounting |
1xx.xxx.xxx.xxx | 4564 | 3579 | 78.42 |
Sampling analysis is done in the binding higher equipment of accounting, obtains the more port of user bound, as shown in table 4:
Table 4
Device IP | Port | Port user sum | Port user sum accounting |
1xx.xxx.xxx.xxx | 1//2 | 479 | 13.38 |
1xx.xxx.xxx.xxx | 1//3 | 38 | 1.06 |
1xx.xxx.xxx.xxx | 1//4 | 17 | 0.47 |
1xx.xxx.xxx.xxx | 1/0/1 | 4 | 0.11 |
1xx.xxx.xxx.xxx | 1/0/2 | 1092 | 30.51 |
1xx.xxx.xxx.xxx | 1/0/3 | 1065 | 29.76 |
1xx.xxx.xxx.xxx | 1/0/4 | 881 | 24.62 |
1xx.xxx.xxx.xxx | 14/0/2 | 3 | 0.08 |
Device port user bound number is more, and binding accounting reaches 78%, can select the end under representational equipment
Mouthful 1/0/2,1/0/3,1/0/4 corresponding user, when acquisition, track this crowd of user, analyze the bandwidth distribution situation of user, press
Bandwidth types analyze the average flow rate of each bandwidth, to count the traffic conditions of exit port respective links, then press accounting recurrence layer by layer,
Recurrence goes out the traffic conditions of equipment.Count the bandwidth average flow rate in outgoing link, the bandwidth average flow rate in equipment, if analysis into
The speed-raising of row bandwidth obtains the relevant information of port links, analysis present flow rate benefit from network management to the increased influence of the flow of link
It is calculated with the flow utilization rate of rate, the telephone circuit of bandwidth dilatation, then retrodicts out dilatation to equipment flow demand by accounting.
In embodiments of the present invention, as shown in figure 3, the data network volume forecasting can also include:
Step 204: acquiring the user under different service types and different bandwidth according to preset acquisition mode and averagely use
Flow;
Step 205: the user under the different service types of acquisition and different bandwidth averagely being used into flow and calculates gained
That user's history under different service types and different bandwidth is averagely compared using flow, verified according to comparison result described in
The accuracy of the flux prediction model constructed.
Specifically, step 104 acquires each bandwidth users flow according to sampling, particularly acquisition obtains the whole province pppoe and uses
Family bandwidth and user districts and cities access BRAS information.
It is as shown in table 5 to acquire data:
Table 5
Account | Districts and cities | Bandwidth information (mbps) | Access BRAS |
fsDSL38X8X82@163.gd | Foshan | 1 | XX-XXXX-BRAS-4.MAN.SE800 |
fsDSL8382X229@163.gd | Foshan | 2 | XX-XXXX-BRAS-4.MAN.SE800 |
fswiXXnway@163.gd | Foshan | 6 | XX-XXXX-BRAS-4.MAN.SE800 |
7X7064266X | Foshan | 6 | XX-XXXX-BRAS-4.MAN.SE800 |
fsDSLX6X484X7 | Foshan | 6 | XX-XXXX-BRAS-4.MAN.SE800 |
fsDSL28XX7638 | Foshan | 12 | XX-XXXX-BRAS-4.MAN.SE800 |
fsDSL13XX690260@163.gd | Foshan | 6 | XX-XXXX-BRAS-4.MAN.SE800 |
fsDSL1X916X80697 | Foshan | 4 | XX-XXXX-BRAS-4.MAN.SE800 |
7X7047XX3381 | Foshan | 4 | XX-XXXX-BRAS-4.MAN.SE800 |
Above data is by processing.
BRAS mainstream equipment is the SE800 of the ME60 and RedBack of Huawei at present, is situated between by taking both equipment as an example below
Continue lower acquisition logic:
ME60:
Need to have the permission that logging device executes related command.
A. all online users for checking corresponding service type are executed in equipment:
display access-user domain XXX
XXX is the corresponding domain of type of service, is returned:
128fsDSLXX712525@163.gd GE2/0/8.3972 14.157.240.167 f4ec-386f-8461
128 access id for user.
B. particular user details are checked:
display access-user user-id 125647
It can get the detailed user's name of user, bandwidth, the information such as access interface:
User name corresponds to username information, and Outbound corresponds to user's download bandwidth speed-limiting messages.
SE800:
Need to have the permission that logging device executes related command.
A. current all online users to come up by ppoe dialing are searched (user name may show incomplete)
sh subscribers all|in pppoe
pppoe 1/1vlan-id 3357:1116pppo fsDXX4362068@163.g 163Mar 3 21:07:41
B. it shows and searches all online users (comprising non-ppoe user, but user's name is shown completely)
show sub act all|grep o'-E'^[0-9a-zA-Z]
075785557048
075781826670@163.gd
C. the information such as user and its vlan interface qos are shown
show sub act username fsDSLXXX7110@163.gd
fsDSL2XX7110@163.gd
Session state Up
qos-metering-policy 12M_MTR(applied)
qos-policing-policy 512K-PLC(applied)
Wherein fsDSL2XX7110@163.gd is account information, qos-metering-policy 12M_MTR
It (applied) is bandwidth information.
For the BRAS to be analyzed, every kind of bandwidth selection user's progress flow is adopted in the specified services type of every BRAS
Collection, by user press bandwidth partition bandwidth class, such as: 4M or less -4B, 4M-4,6M-6,8M-8,10M-10,12M-12,20M and with
Upper 20B, 10 minutes are a granularity, in equipment by type of service (public internet and IPTV) with the bandwidth of each grade with
Machine selects 100 users and carries out flow collection, excludes the offline and online user that goes offline again in midway, is acquired every time
When user less than 100 when in ad eundem bandwidth users random polishing, collect the user bandwidth number of original 10 minutes granularities
According to acquisition method is as follows:
ME60:
A. current all online users are checked:
display access-user domain XXX
XXX is the corresponding domain of type of service, is returned:
128fsDSLXX712525@163.gd GE2/0/8.3972 14.157.240.167f4ec-386f-8461
B. the value of customer flow counter is checked:
display access-user user-id 125647
Up packets number(high,low):(0,2961075)
Up bytes number(high,low):(0,957532975)
Down packets number(high,low):(0,3928670)
Down bytes number(high,low):(0,3902569914)
SE800:
A. current all online users to come up by ppoe dialing are searched (user name may show incomplete)
sh subscribers all|in pppoe
pppoe 1/1vlan-id 3357:1116pppo fsDXX4362068@163.g 163Mar 3 21:07:41
B. it shows and searches all online users (comprising non-ppoe user, but user's name is shown completely)
show sub act all|grep o'-E'^[0-9a-zA-Z]
075785557048
075781826670@163.gd
C. the information such as user and its vlan interface are shown
show sub act username fsDSLXXX7110@163.gd
fsDSL2XX7110@163.gd
Circuit 1/1vlan-id 3357:1103pppoe 6101
D. the details such as the rate of display single user are searched
how cir count 1/1vlan-id 2407:245pppoe 1307detail
Circuit:1/1vlan-id 2407:245pppoe 1307,Internal id:6/2/14145,Encap:
ether-dot1q-tunnel-pppoe-ppp
Packets Bytes
-----------------------------------------------------------------------------
--
Receive:693711Receive:142784741
Above-mentioned acquisition be customer flow counter value, using total stream of the difference between collection point between two collection points
Amount, total flow/collection point time difference obtains the average flow rate between collection point, and acquires total online number of current 163 business.
Summarizing for data is carried out after the completion of raw data acquisition:
10 minutes initial data are pressed into districts and cities, bandwidth types, type of service, granularity time point is summarized within ten minutes, is converged
The districts and cities' bandwidth for always going out ten minutes granularities be averaged uplink and downlink flow velocity and maximum uplink and downlink flow velocity.
Data will be summarized within 10 minutes by districts and cities, bandwidth types, type of service, hour granularity time point summarized, summarized
Districts and cities' bandwidth of hour granularity is averaged uplink and downlink flow velocity and maximum uplink and downlink flow velocity out.
Hour is summarized into data by districts and cities, bandwidth types, type of service, day granularity time point summarized, summarize day out
Districts and cities' bandwidth of granularity is averaged uplink and downlink flow velocity and maximum uplink and downlink flow velocity.
For type of service: 163, districts and cities: Guangzhou, statistics granularity: 10 minutes, bandwidth: the acquisition summarized results of 4M such as table 6
It is shown:
Table 6
It gives an actual example below and illustrates the accuracy of flux prediction model proposed by the present invention.
1, the flux prediction model proposed through the invention carries out each bandwidth users flow analysis.
Acquire the BARS on June 30th, 1 day 1 June in 2013Flow, the online user number of public internet, IPTV
Online user number, other use flow, the flux prediction model then proposed through the invention determines bandwidth average flow rate value, so
Afterwards from physical device obtain on June 30,1 day to 2013 June in 2013 first line of a couplet entirety flow fluctuation situation, by the two into
Row compares, and comparison result is as shown in Figure 4.It can be found that the wave of the bandwidth average flow rate value obtained by flux prediction model
Emotionally condition with physical device first line of a couplet entirety flow fluctuation situation coincide, and according to historical data speculate predicted flow rate also compared with
It is accurate.
2, lead to each bandwidth users flow analysis of oversampling acquisition.
Xx December surveys 24 hours flows of public internet user and IPTV user on 4 ground of wide deep eastern Buddhist, random to select
30 BRAS are taken to measure the uplink/downlink mean flow rate of 2 class users, IPTV user 1000, public user sum nearly 300,000.
The measurement of public internet user's flow velocity: the actual measurement of 4 30, ground BRAS flows 24 hours, sampling interval 30 divide (sampling rate
5%, cover 19 general-purpose families), Internet user night peak averaging downstream rate about 508kbps, peak averaging upstream rate is about
182kbps (has detained IPTV flow);
The measurement of IPTV user's flow velocity: 1000 IPTV user account numbers 12 hours in 4 BRAS are monitored, the sampling interval 15
Minute, IPTV user's night downstream rate is basically stable at 1.6Mbps (for 3 times of Internet user), uplink Mean Speed
70kbps;
IPTV number of users vs internet online user number is 1:10, and the general clear user 1:10 of high definition user vs is (clear far below general
User).
Wherein, Fig. 5 is that (wherein, abscissa indicates time, ordinate to wide deep eastern Buddhist IPTV user's uplink and downlink flow velocity schematic diagram
Indicate flow velocity), Fig. 6 is Pearl River Delta internet and IPTV online user number 24 hours variation (BRAS sampling rate 5%) schematic diagram (its
In, internet online user number indicates that IPTV online user number uses the ordinate number on the right using the Y value on the left side
Value indicates that abscissa indicates the time), Fig. 7 is Pearl River Delta Internet user's average flow rate schematic diagram (wherein, BARS downlink flow velocity
It being indicated using the Y value on the left side, downlink average flow rate and uplink average flow rate use the Y value on the right to indicate,
Abscissa indicates the time).According to Fig. 5 to Fig. 7 it is found that the first line of a couplet flow analysis of joint BRAS equipment, BRAS equipment entirety flow
Fluctuation situation and sampling analysis result coincide substantially.
It is considered that two methods analyze the result come can react the actual traffic conditions of existing net substantially, data have reference
Value.
Based on the same inventive concept, a kind of data network volume forecasting device is additionally provided in the embodiment of the present invention, it is such as following
Embodiment described in.Since the principle that data network volume forecasting device solves the problems, such as is similar to data network method for predicting, because
The implementation of this data network volume forecasting device may refer to the implementation of data network method for predicting, and overlaps will not be repeated.
Used below, the combination of the software and/or hardware of predetermined function may be implemented in term " unit " or " module ".Although with
Device described in lower embodiment is preferably realized with software, but the combined realization of hardware or software and hardware
It may and be contemplated.
Fig. 8 is the structural block diagram of the data network volume forecasting device of the embodiment of the present invention, as shown in Figure 8, comprising:
Data obtaining module 801, for obtaining under data network total flow historical data, different service types and different bandwidth
History online user number;
Flow rate calculation module 802, for based on the flux prediction model constructed, according to the data network total flow history
History online user number under data, different service types and different bandwidth, determines under different service types and different bandwidth
User's history averagely uses flow;
Data network total flow prediction module 803, for being gone through according to the user under the different service types and different bandwidth
History averagely uses flow, based on the goal-selling user expansion number under different service types and different bandwidth, after predicting dilatation
Data network total flow.
The structure is illustrated below.
In embodiments of the present invention, the type of service includes public internet business and Interactive Internet TV IPTV;
The data obtaining module 801 is specifically used for:
Data network total flow historical data, public internet are obtained according to user region or different device links
The history online user number under the different bandwidth under history online user number, IPTV under different bandwidth under business;
The flow rate calculation module 802 is specifically used for:
It is total according to the data network based on the zone flow prediction model constructed or the equipment chain drive test model constructed
The history online user number under different bandwidth under flow histories data, public internet business, under the different bandwidth under IPTV
History online user number, determine that the user's history under the different bandwidth under public internet business averagely uses flow, IPTV
Under different bandwidth under user's history averagely use flow;
The data network total flow prediction module 803 is specifically used for:
The different band under flow, IPTV is averagely used according to the user's history under the different bandwidth under public internet business
User's history under wide averagely uses flow, based on the goal-selling user expansion under the different bandwidth under public internet business
The goal-selling user expansion number under different bandwidth under number, IPTV, the data network total flow after predicting dilatation.
In embodiments of the present invention, the flux prediction model concrete form constructed is as follows:
BARSFlow=a1×w1+a2×w2+a3×w3+b1×h1+b2×h2+b3×h3+c;
Wherein, a1、a2、a3Indicate that the public internet user of each bandwidth averagely uses flow;w1、w2、w3Indicate that the public is mutual
The online user number for each bandwidth of networking;b1、b2、b3Indicate that the average of the IPTV user of each bandwidth uses flow;h1、h2、h3It indicates
The online user number of each bandwidth of IPTV;C indicates that other use flow.
In embodiments of the present invention, the data obtaining module 801 is also used to:
The user under different service types and different bandwidth, which is acquired, according to preset acquisition mode averagely uses flow;
As shown in figure 9, the data network volume forecasting device further include:
Authentication module 804, for by the user under the different service types of acquisition and different bandwidth averagely use flow with
Calculating gained is that the user's history under different service types and different bandwidth is averagely compared using flow, according to comparison result
The accuracy of the verifying flux prediction model constructed.
The embodiment of the invention also provides a kind of computer equipments, including memory, processor and storage are on a memory
And the computer program that can be run on a processor, the processor realize data described above when executing the computer program
Net method for predicting.
The embodiment of the invention also provides a kind of computer readable storage medium, the computer-readable recording medium storage
There is the computer program for executing data network method for predicting described above.
In conclusion data network method for predicting proposed by the present invention and device have the advantages that;
By obtaining the history online user under data network total flow historical data, different service types and different bandwidth
Number;Based on the flux prediction model constructed, according to the data network total flow historical data, different service types and different band
History online user number under wide, determines that the user's history under different service types and different bandwidth averagely uses flow;According to
User's history under the different service types and different bandwidth averagely uses flow, is based on different service types and different bandwidth
Under goal-selling user expansion number, predict dilatation after data network total flow.Compared with prior art, the present invention can be anti-
Data network flow entirety traffic conditions are mirrored, and can reflect data network entirety flow growth trend;Business can be embodied
The user behavior of each bandwidth under type can provide foundation for broadband speed raising.
It should be understood by those skilled in the art that, the embodiment of the present invention can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the present invention, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the embodiment of the present invention can have various modifications and variations.All within the spirits and principles of the present invention, made
Any modification, equivalent substitution, improvement and etc. should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of data network method for predicting characterized by comprising
Obtain the history online user number under data network total flow historical data, different service types and different bandwidth;
Based on the flux prediction model constructed, according to the data network total flow historical data, different service types and difference
History online user number under bandwidth determines that the user's history under different service types and different bandwidth averagely uses flow;
Averagely use flow according to the user's history under the different service types and different bandwidth, based on different service types and
Goal-selling user expansion number under different bandwidth, the data network total flow after predicting dilatation.
2. data network method for predicting as described in claim 1, which is characterized in that the type of service includes public's interconnection
Network service and Interactive Internet TV IPTV;
Obtain the history online user number under data network total flow historical data, different service types and different bandwidth, comprising:
Data network total flow historical data, public internet business are obtained according to user region or different device links
Under different bandwidth under history online user number, the history online user number under the different bandwidth under IPTV;
Based on the flux prediction model constructed, according to the data network total flow historical data, different service types and difference
History online user number under bandwidth determines that the user's history under different service types and different bandwidth averagely uses flow, packet
It includes:
Based on the zone flow prediction model constructed or the device link flux prediction model constructed, according to the data network
The history online user number under different bandwidth under total flow historical data, public internet business, the different bandwidth under IPTV
Under history online user number, determine the user's history under the different bandwidth under public internet business averagely use flow,
The user's history under different bandwidth under IPTV averagely uses flow;
Averagely use flow according to the user's history under the different service types and different bandwidth, based on different service types and
Goal-selling user expansion number under different bandwidth, the data network total flow after predicting dilatation, comprising:
It is averagely used according to the user's history under the different bandwidth under public internet business under the different bandwidth under flow, IPTV
User's history averagely use flow, based under the different bandwidth under public internet business goal-selling user expansion number,
Goal-selling user expansion number under different bandwidth under IPTV, the data network total flow after predicting dilatation.
3. data network method for predicting as claimed in claim 2, which is characterized in that the flux prediction model constructed
Concrete form is as follows:
BARSFlow=a1×w1+a2×w2+a3×w3+b1×h1+b2×h2+b3×h3+c;
Wherein, BARSFlowIndicate data network total flow;a1、a2、a3Indicate the public internet user of each bandwidth averagely using stream
Amount;w1、w2、w3Indicate the online user number of each bandwidth of public internet;b1、b2、b3Indicate being averaged for the IPTV user of each bandwidth
Use flow;h1、h2、h3Indicate the online user number of each bandwidth of IPTV;C indicates that other use flow.
4. data network method for predicting as described in claim 1, which is characterized in that further include:
The user under different service types and different bandwidth, which is acquired, according to preset acquisition mode averagely uses flow;
By the user under the different service types of acquisition and different bandwidth averagely using flow and calculate gained be different business class
User's history under type and different bandwidth is averagely compared using flow, according to the comparison result verifying flow constructed
The accuracy of prediction model.
5. a kind of data network volume forecasting device characterized by comprising
Data obtaining module, for obtaining the history under data network total flow historical data, different service types and different bandwidth
Online user number;
Flow rate calculation module, for based on the flux prediction model constructed, according to the data network total flow historical data, no
With the history online user number under type of service and different bandwidth, the user's history under different service types and different bandwidth is determined
Averagely use flow;
Data network total flow prediction module, for averagely being made according to the user's history under the different service types and different bandwidth
With flow, based on the goal-selling user expansion number under different service types and different bandwidth, the data network after predicting dilatation is total
Flow.
6. data network volume forecasting device as claimed in claim 5, which is characterized in that the type of service includes public's interconnection
Network service and Interactive Internet TV IPTV;
The data obtaining module is specifically used for:
Data network total flow historical data, public internet business are obtained according to user region or different device links
Under different bandwidth under history online user number, the history online user number under the different bandwidth under IPTV;
The flow rate calculation module is specifically used for:
Based on the zone flow prediction model constructed or the device link flux prediction model constructed, according to the data network
The history online user number under different bandwidth under total flow historical data, public internet business, the different bandwidth under IPTV
Under history online user number, determine the user's history under the different bandwidth under public internet business averagely use flow,
The user's history under different bandwidth under IPTV averagely uses flow;
The data network total flow prediction module is specifically used for:
It is averagely used according to the user's history under the different bandwidth under public internet business under the different bandwidth under flow, IPTV
User's history averagely use flow, based under the different bandwidth under public internet business goal-selling user expansion number,
Goal-selling user expansion number under different bandwidth under IPTV, the data network total flow after predicting dilatation.
7. data network volume forecasting device as claimed in claim 6, which is characterized in that the flux prediction model constructed
Concrete form is as follows:
BARSFlow=a1×w1+a2×w2+a3×w3+b1×h1+b2×h2+b3×h3+c;
Wherein, BARSFlowIndicate data network total flow;a1、a2、a3Indicate the public internet user of each bandwidth averagely using stream
Amount;w1、w2、w3Indicate the online user number of each bandwidth of public internet;b1、b2、b3Indicate being averaged for the IPTV user of each bandwidth
Use flow;h1、h2、h3Indicate the online user number of each bandwidth of IPTV;C indicates that other use flow.
8. data network volume forecasting device as claimed in claim 5, which is characterized in that the data obtaining module is also used to:
The user under different service types and different bandwidth, which is acquired, according to preset acquisition mode averagely uses flow;
Further include:
Authentication module, for the user under the different service types of acquisition and different bandwidth averagely to be used flow and calculates gained
That user's history under different service types and different bandwidth is averagely compared using flow, verified according to comparison result described in
The accuracy of the flux prediction model constructed.
9. a kind of computer equipment including memory, processor and stores the meter that can be run on a memory and on a processor
Calculation machine program, which is characterized in that the processor realizes any number of Claims 1-4 when executing the computer program
According to net method for predicting.
10. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage has perform claim
It is required that the computer program of 1 to 4 any data network method for predicting.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811526034.9A CN109495317B (en) | 2018-12-13 | 2018-12-13 | Data network flow prediction method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811526034.9A CN109495317B (en) | 2018-12-13 | 2018-12-13 | Data network flow prediction method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109495317A true CN109495317A (en) | 2019-03-19 |
CN109495317B CN109495317B (en) | 2022-01-18 |
Family
ID=65710083
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811526034.9A Active CN109495317B (en) | 2018-12-13 | 2018-12-13 | Data network flow prediction method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109495317B (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109978627A (en) * | 2019-03-29 | 2019-07-05 | 电子科技大学中山学院 | Modeling method for big data of user internet access behavior of broadband access network |
CN110300014A (en) * | 2019-04-17 | 2019-10-01 | 中国联合网络通信集团有限公司 | A kind of flow analysis method and device |
CN110380904A (en) * | 2019-07-23 | 2019-10-25 | 腾讯科技(深圳)有限公司 | Bandwidth allocation methods, device, electronic equipment and storage medium |
CN110932993A (en) * | 2019-11-21 | 2020-03-27 | 中盈优创资讯科技有限公司 | Bandwidth speed regulation management method and device |
CN111212337A (en) * | 2019-12-27 | 2020-05-29 | 中国联合网络通信集团有限公司 | Port classification method and device |
CN111865628A (en) * | 2019-04-25 | 2020-10-30 | 中国移动通信集团河北有限公司 | Statistical system, method, server and storage medium for influencing user by home wide fault |
CN112187498A (en) * | 2019-07-03 | 2021-01-05 | 中国电信股份有限公司 | Bypass protection method, device and system thereof and Deep Packet Inspection (DPI) system |
CN114449569A (en) * | 2020-11-02 | 2022-05-06 | 中国移动通信集团广东有限公司 | User traffic usage processing method, network device and service processing system |
CN114531706A (en) * | 2020-10-30 | 2022-05-24 | 中国移动通信集团江西有限公司 | Regional user traffic monitoring method and device, storage medium and computer equipment |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103200114A (en) * | 2013-04-18 | 2013-07-10 | 湖北邮电规划设计有限公司 | Metropolitan area network planning method |
CN105024875A (en) * | 2014-04-30 | 2015-11-04 | 中国电信股份有限公司 | Method and system for measuring network flow rate of broadband classified users |
CN105407494A (en) * | 2015-10-23 | 2016-03-16 | 中国联合网络通信集团有限公司 | Network capacity expansion method and apparatus |
CN108259263A (en) * | 2017-12-01 | 2018-07-06 | 国家电网公司 | Data analysing method, apparatus and system |
-
2018
- 2018-12-13 CN CN201811526034.9A patent/CN109495317B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103200114A (en) * | 2013-04-18 | 2013-07-10 | 湖北邮电规划设计有限公司 | Metropolitan area network planning method |
CN105024875A (en) * | 2014-04-30 | 2015-11-04 | 中国电信股份有限公司 | Method and system for measuring network flow rate of broadband classified users |
CN105407494A (en) * | 2015-10-23 | 2016-03-16 | 中国联合网络通信集团有限公司 | Network capacity expansion method and apparatus |
CN108259263A (en) * | 2017-12-01 | 2018-07-06 | 国家电网公司 | Data analysing method, apparatus and system |
Non-Patent Citations (1)
Title |
---|
谢美德: "城域数据网方案设计及优化", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109978627A (en) * | 2019-03-29 | 2019-07-05 | 电子科技大学中山学院 | Modeling method for big data of user internet access behavior of broadband access network |
CN109978627B (en) * | 2019-03-29 | 2023-08-08 | 电子科技大学中山学院 | Modeling method for big data of broadband access network user surfing behavior |
CN110300014A (en) * | 2019-04-17 | 2019-10-01 | 中国联合网络通信集团有限公司 | A kind of flow analysis method and device |
CN111865628A (en) * | 2019-04-25 | 2020-10-30 | 中国移动通信集团河北有限公司 | Statistical system, method, server and storage medium for influencing user by home wide fault |
CN111865628B (en) * | 2019-04-25 | 2023-04-07 | 中国移动通信集团河北有限公司 | Statistical system, method, server and storage medium for influencing user by home wide fault |
CN112187498B (en) * | 2019-07-03 | 2022-09-06 | 中国电信股份有限公司 | Bypass protection method, device and system thereof and Deep Packet Inspection (DPI) system |
CN112187498A (en) * | 2019-07-03 | 2021-01-05 | 中国电信股份有限公司 | Bypass protection method, device and system thereof and Deep Packet Inspection (DPI) system |
CN110380904A (en) * | 2019-07-23 | 2019-10-25 | 腾讯科技(深圳)有限公司 | Bandwidth allocation methods, device, electronic equipment and storage medium |
CN110932993A (en) * | 2019-11-21 | 2020-03-27 | 中盈优创资讯科技有限公司 | Bandwidth speed regulation management method and device |
CN111212337B (en) * | 2019-12-27 | 2022-02-25 | 中国联合网络通信集团有限公司 | Port classification method and device |
CN111212337A (en) * | 2019-12-27 | 2020-05-29 | 中国联合网络通信集团有限公司 | Port classification method and device |
CN114531706A (en) * | 2020-10-30 | 2022-05-24 | 中国移动通信集团江西有限公司 | Regional user traffic monitoring method and device, storage medium and computer equipment |
CN114531706B (en) * | 2020-10-30 | 2023-11-10 | 中国移动通信集团江西有限公司 | Regional user traffic monitoring method and device, storage medium and computer equipment |
CN114449569A (en) * | 2020-11-02 | 2022-05-06 | 中国移动通信集团广东有限公司 | User traffic usage processing method, network device and service processing system |
CN114449569B (en) * | 2020-11-02 | 2024-01-16 | 中国移动通信集团广东有限公司 | User traffic usage processing method, network equipment and service processing system |
Also Published As
Publication number | Publication date |
---|---|
CN109495317B (en) | 2022-01-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109495317A (en) | Data network method for predicting and device | |
Pau et al. | A cloud-based smart metering infrastructure for distribution grid services and automation | |
Alavikia et al. | A comprehensive layered approach for implementing internet of things-enabled smart grid: A survey | |
US8880604B2 (en) | Determination of a spammer through social network characterization | |
CN103200114B (en) | Metropolitan area network planing method | |
EP2905931B1 (en) | Method and apparatus for determining data flow rate of service access port | |
Balachandran et al. | Bandwidth analysis of smart meter network infrastructure | |
CN107169640A (en) | A kind of power distribution network key index analysis method based on big data technology | |
US11277768B2 (en) | Data congestion management system and method | |
CN105335476B (en) | A kind of focus incident classification method and device | |
Ramirez et al. | Performance evaluation of future AMI applications in smart grid neighborhood area networks | |
CN101714929B (en) | Method and system for quantitatively calculating network availability indexes | |
Fageda et al. | Determinants of broadband access: Is platform competition always the key variable to success? | |
Yeom et al. | LSTM-based collaborative source-side DDoS attack detection | |
Rao et al. | Performance of non-homogeneous communication networks with Poisson arrivals and dynamic bandwidth allocation | |
Armendariz et al. | Method to design optimal communication architectures in advanced metering infrastructures | |
Rea et al. | Italian QoS Monitoring network: impact on SLA control | |
US20150172157A1 (en) | Method and apparatus for determining data flow rate on service access port | |
Bian | An expert-based approach for demand curtailment allocation subject to communications and cyber security limitations | |
Hammoudeh | Comparative analysis of communication architectures and technologies for smart grid distribution network | |
Amarasekara et al. | Analysis of ip-based communication backbone over shared wide area-network for Smart Grid applications | |
Noh | A Study of Security QoS (Quality of Service) Measurement Methodology for Network Security Efficiency | |
Zabasta et al. | Wireless sensor networks based control system development for water supply infrastructure | |
Dahunsi et al. | Communication Network Simulation for Smart Metering Applications: A Review | |
Le | Opportunistic hybrid network coding (ohnc) method and qos metrics modeling for smart grid wireless neighborhood area networks |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |