CN105873087A - Network index prediction method, device and electronic device - Google Patents
Network index prediction method, device and electronic device Download PDFInfo
- Publication number
- CN105873087A CN105873087A CN201510033232.1A CN201510033232A CN105873087A CN 105873087 A CN105873087 A CN 105873087A CN 201510033232 A CN201510033232 A CN 201510033232A CN 105873087 A CN105873087 A CN 105873087A
- Authority
- CN
- China
- Prior art keywords
- users
- under
- network
- accounting
- user
- 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
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiments of the invention provide a network index prediction method, a network index prediction device and an electronic device. The network index prediction method is used for predicting user service indexes in a first region covered by a plurality of wireless networks, wherein the plurality of wireless networks respectively belong to a variety of network types, and the user service indexes include the number of users. The network index prediction method includes the following steps that: the total number of users under the coverage of the plurality of wireless networks in the first region is predicted in a prediction cycle; the first proportion of the number of users under the coverage of a first wireless network in the plurality of wireless networks in the first region in the total number of the users in the prediction cycle is obtained; and the number of first users under the coverage of the first wireless network in the first region in the prediction cycle is determined according to the total number of the users and the first proportion. According to the network index prediction method and the network index prediction device provided by the embodiments of the invention, the prediction of the user service indexes under the coverage of the wireless network of a certain network type can reflect the actual situation of mutual restriction of user service indexes under different network types.
Description
Technical field
The present embodiments relate to wireless access network planning field, particularly relate to a kind of network index prediction side
Method, device and electronic equipment.
Background technology
The prediction of user's service indication, such as portfolio is the first step of wireless network planning.The most accurately
The portfolio of following one period (such as month, half a year or a year) of prediction, can shoot the arrow at the target
Carry out radio access network resource configuration, it is to avoid resource mispairing occurs, cause the wasting of resources and affect user's sense
Know.
Existing wireless access network planning traffic forecast scheme is mainly in units of the community of wireless access network
It is predicted, general employing curvilinear trend extrapolation.Such as choose all communities moon of every month in 1 year in the past
Average traffic amount data, each community utilizes these 12 data to carry out curve fitting, then chooses matching journey
Spending the highest curve, utilizing its parameter of curve to carry out trend extropolation, to obtain the average traffic amount of every month below pre-
Survey data.
Summary of the invention
The purpose of the embodiment of the present invention is to provide a kind of network index Forecasting Methodology, device and electronic equipment, with
The prediction enabling the wireless network to certain network formats to cover lower user's service indication reflects heterogeneous networks system
The practical situation that under formula, user's service indication mutually restricts.
For solving above-mentioned technical problem, the embodiment of the present invention provides scheme as follows:
The embodiment of the present invention provides a kind of network index Forecasting Methodology, under being used for predicting that multiple wireless networks cover
First area in user's service indication, multiple wireless networks are belonging respectively to multiple network standard, described use
Family service indication includes that number of users, described network index Forecasting Methodology include:
Whole numbers of users under multiple wireless networks described cover in described first area in acquisition predetermined period;
The first wireless network in multiple wireless networks described in described first area in obtaining described predetermined period
The number of users under network covering the first accounting in described whole numbers of users;
According to described whole numbers of users and described first accounting, described first area in determining described predetermined period
First user number under interior described first wireless network covering.
Preferably, under in described acquisition predetermined period, in described first area, multiple wireless networks described cover
All number of users includes:
In the statistical history cycle, in described first area, in multiple wireless networks described, every wireless network covers
Under number of users;
Each number of users sum of counting statistics, obtains described whole number of users.
Preferably, described first area be included in multiple wireless networks cover under multiple regions in, described in obtain
In taking described predetermined period, in described first area, the first wireless network in multiple wireless networks described covers
Under the number of users the first accounting in described whole numbers of users include:
Divide according to the number of users under each wireless network covers in each region in regions multiple in history cycle
The second accounting in total number of users under multiple wireless networks do not cover in described each region, by multiple districts
Territory is divided at least two classification;
For each classification in described at least two classification, in determining history cycle, it is divided into described each class
Number of users multiple nothings in described Zone Full under described first wireless network covers in other Zone Full
The 3rd accounting in total number of users under the line network coverage;
According to each self-corresponding 3rd accounting of described at least two classification, described at least two classification is sorted;
Determine the first category belonging to described first area is in described at least two classification;
By the 3rd accounting corresponding to sequence heel row second category after described first category, it is defined as institute
State the first accounting.
Preferably, described according under each wireless network covering in each region in regions multiple in history cycle
Number of users total number of users under multiple wireless networks cover in described each region respectively in second account for
Multiple regions are divided at least two classification and include by ratio:
Use clustering algorithm, with the second accounting that each wireless network in described each region is corresponding be described often
The algorithm input pointer that individual region is corresponding, clusters the plurality of region, obtains described at least two class
Not.
Preferably, described according to described whole numbers of users with described first accounting, in determining described predetermined period
First user number under described first wireless network covers in described first area includes:
Calculate described whole number of users and described first accounting is long-pending, obtain described first user number.
Preferably, described user's service indication also includes that portfolio, described network index Forecasting Methodology also include:
Number of users under described first wireless network covers in described first area in obtaining described predetermined period
And the first corresponding relation between portfolio;
According to described first user number and described first corresponding relation, in determining described predetermined period described first
The first portfolio under described first wireless network covers in region.
Preferably, in described first corresponding relation includes described predetermined period in described first area described first
Wireless network covers lower first and predicts user's average traffic, in the described predetermined period of described acquisition described the
The first corresponding relation bag between number of users and portfolio under described first wireless network covers in one region
Include:
Portfolio under described first wireless network covers in described first area in calculating described history cycle
With the ratio of number of users, obtain the first historic user average traffic;
Put down with prediction user according to described first historic user average traffic and historic user average traffic
All the second corresponding relations between portfolio, determine described first prediction user's average traffic;
Described according to described first user number with described first corresponding relation, described in determining described predetermined period
The first portfolio under described first wireless network covers in first area includes:
Calculate described first user number and described first prediction user's average traffic is long-pending, obtain described first
Portfolio.
The embodiment of the present invention also provides for a kind of network index prediction means, is used for predicting that multiple wireless networks cover
Under first area in user's service indication, multiple wireless networks are belonging respectively to multiple network standard, described
User's service indication includes that number of users, described network index prediction means include:
First acquisition module, in being used for obtaining predetermined period, in described first area, multiple wireless networks described cover
Whole numbers of users under Gai;
Second acquisition module, multiple wireless networks described in described first area in being used for obtaining described predetermined period
The number of users under the first wireless network covering in network the first accounting in described whole numbers of users;
First determines module, for according to described whole numbers of users and described first accounting, determines described prediction
First user number under described first wireless network covers in described first area in cycle.
Preferably, described first acquisition module includes:
Statistic unit, within the statistical history cycle in described first area in multiple wireless networks described every
Number of users under wireless network covering;
First computing unit, for each number of users sum of counting statistics, obtains described whole number of users.
Preferably, described first area is included in the multiple regions under multiple wireless networks cover, and described the
Two acquisition modules include:
Division unit, for covering according to each wireless network in each region in regions multiple in history cycle
Under number of users respectively in described each region multiple wireless networks cover under total number of users in second
Multiple regions are divided at least two classification by accounting;
First determines unit, for for each classification in described at least two classification, determines history cycle
Number of users under described first wireless network covers in being inside divided into the Zone Full of described each classification is in institute
State the 3rd accounting in the total number of users under Zone Full multiple wireless networks interior cover;
Sequencing unit, for according to each self-corresponding 3rd accounting of described at least two classification, to described at least
Two classification sequences;
Second determines unit, for determine described first area in described at least two classification belonging to first
Classification;
3rd determines unit, for by corresponding to sequence heel row second category after described first category
3rd accounting, is defined as described first accounting.
Preferably, described first determines that module includes:
Second unit, is used for calculating described whole number of users and described first accounting is long-pending, obtain described first
Number of users.
Preferably, described user's service indication also includes that portfolio, described network index prediction means also include:
3rd acquisition module, described first wireless network in described first area in being used for obtaining described predetermined period
The first corresponding relation between number of users and portfolio under network covering;
Second determines module, for according to described first user number and described first corresponding relation, determines described
The first portfolio under described first wireless network covers in described first area in predetermined period.
The embodiment of the present invention also provides for a kind of electronic equipment including above-described network index prediction means.
From the above it can be seen that the embodiment of the present invention at least has the advantages that
Achieve in the case of multiple wireless networks adhering to multiple network standard separately cover the same area list
The number of users opened under wireless network covers is predicted, so that under the wireless network covering of certain network formats
The prediction of number of users can reflect the practical situation that under different network formats, number of users mutually restricts.
Accompanying drawing explanation
Fig. 1 represents the flow chart of steps of a kind of network index Forecasting Methodology that the embodiment of the present invention provides;
Fig. 2 represents the grid industry collaborative based on Multi net voting standard of the better embodiment of the embodiment of the present invention
Business Forecasting Methodology flow chart;
Fig. 3 represents different network formats user collaborative in the grid of the better embodiment of the embodiment of the present invention
Development prediction flow chart;
Fig. 4 represents the structured flowchart of a kind of network index prediction means that the embodiment of the present invention provides.
Detailed description of the invention
For making the purpose of the embodiment of the present invention, technical scheme and advantage clearer, below in conjunction with accompanying drawing and
The embodiment of the present invention is described in detail by specific embodiment.
Fig. 1 represents the flow chart of steps of a kind of network index Forecasting Methodology that the embodiment of the present invention provides, reference
Fig. 1, the embodiment of the present invention provides a kind of network index Forecasting Methodology, is used for predicting that multiple wireless networks cover
Under first area in user's service indication, multiple wireless networks are belonging respectively to multiple network standard, described
User's service indication includes that number of users, described network index Forecasting Methodology comprise the steps:
Step 101, obtain under in described first area, multiple wireless networks described cover in predetermined period is complete
Portion's number of users;
Step 102, in obtaining described predetermined period in described first area in multiple wireless networks described the
The number of users under one wireless network covering the first accounting in described whole numbers of users;
Step 103, according to described whole numbers of users and described first accounting, determines institute in described predetermined period
First user number under described first wireless network covers in stating first area.
Visible, by the way, it is achieved that to cover same at multiple wireless networks adhering to multiple network standard separately
Number of users under in the case of one region covering individual wireless network is predicted, to certain network system
The wireless network of formula covers the prediction of lower number of users can reflect that under different network formats, number of users mutually restricts
Practical situation.
Wherein, described user's service indication is such as: number of users or portfolio.Portfolio such as moves data stream
Amount.
Network formats is such as: 4G, 3G or 2G.
Described first area can be grid region, the such as length of side be the square area of 500 meters.
In the embodiment of the present invention, multiple wireless networks described in described first area in described acquisition predetermined period
Whole numbers of users under Fu Gaiing comprise the steps that
In the statistical history cycle, in described first area, in multiple wireless networks described, every wireless network covers
Under number of users;
Each number of users sum of counting statistics, obtains described whole number of users.
In the embodiment of the present invention, described first area may be included in the multiple regions under multiple wireless networks cover
In, first wireless in multiple wireless networks described in described first area in the described predetermined period of described acquisition
The number of users under the network coverage the first accounting in described whole numbers of users comprises the steps that
Divide according to the number of users under each wireless network covers in each region in regions multiple in history cycle
The second accounting in total number of users under multiple wireless networks do not cover in described each region, by multiple districts
Territory is divided at least two classification;
For each classification in described at least two classification, in determining history cycle, it is divided into described each class
Number of users multiple nothings in described Zone Full under described first wireless network covers in other Zone Full
The 3rd accounting in total number of users under the line network coverage;
According to each self-corresponding 3rd accounting of described at least two classification, described at least two classification is sorted;
Determine the first category belonging to described first area is in described at least two classification;
By the 3rd accounting corresponding to sequence heel row second category after described first category, it is defined as institute
State the first accounting.
Wherein, the plurality of region can be grid region.
Described according to the user under each wireless network covers in each region in regions multiple in history cycle
Number the second accounting in the total number of users under the covering of multiple wireless networks in described each region respectively, will be many
Individual region is divided at least two classification and comprises the steps that
Use cluster (Cluster) algorithm, with corresponding second the accounting for of each wireless network in described each region
Than the algorithm input pointer corresponding for described each region, the plurality of region is carried out cluster analysis, obtains
Described at least two classification.
Clustering algorithm is such as: K-Means clustering algorithm.
Described according to each self-corresponding 3rd accounting of described at least two classification, described at least two classification is arranged
Sequence specifically can be carried out according to the 3rd corresponding accounting from low to high.
Illustrate: described at least two classification can include A classification, B classification and C classification these three
Classification, the 3rd corresponding respectively accounting is 30%, 15% and 5%, is entered from low to high by according to the 3rd accounting
Row can obtain being ordered as C classification, B classification and A classification.
Described second category can be the sequence heel row arbitrary classification after described first category, referring also to upper
Example, if first category is C classification, then second category can be A classification or B classification, corresponding the
Three accountings can be 30% or 15%;
Or, described second category can also be for coming in sequence heel row classification after described first category
The most front classification, referring also to upper example, if first category is C classification, then second category is B classification,
The 3rd corresponding accounting can be 15%.
Further, may also include that
Judge whether described first category comes finally;
When described first category comes last, default accounting is defined as described first accounting;
When described first category does not come last, enter described will sequence heel row described first category it
After the 3rd accounting corresponding to second category, be defined as the step of described first accounting.
Wherein, described default accounting can be set according to market development final goal by company.
In the embodiment of the present invention, may also include that
In obtaining described predetermined period, in described first area, wireless network in described first network standard covers
The first corresponding relation between number of users and portfolio under Gai;
According to described first user number and described first corresponding relation, in determining described predetermined period described first
The first portfolio under the wireless network covering of described first network standard in region.
So so that the prediction of portfolio can reflect the reality that under different network formats, portfolio mutually restricts
Situation.
Wherein, in described first corresponding relation can include described predetermined period in described first area described first
Wireless network covers lower first and predicts user's average traffic, in the described predetermined period of described acquisition described the
The first corresponding relation between number of users and portfolio under described first wireless network covers in one region can
Including:
Portfolio under described first wireless network covers in described first area in calculating described history cycle
With the ratio of number of users, obtain the first historic user average traffic;
Put down with prediction user according to described first historic user average traffic and historic user average traffic
All the second corresponding relations between portfolio, determine described first prediction user's average traffic;
Described according to described first user number with described first corresponding relation, described in determining described predetermined period
The first portfolio under described first wireless network covers in first area includes:
Calculate described first user number and described first prediction user's average traffic is long-pending, obtain described first
Portfolio.
Wherein, described second corresponding relation is such as: prediction user's average traffic and historic user average traffic
The ratio of amount.This ratio can set according to houses market target.
For illustrating clearer by the embodiment of the present invention, provide below the preferable real of the embodiment of the present invention
Execute mode.
This better embodiment provides a kind of grid based on multi-network cooperative to become more meticulous traffic forecast method.
There is obvious defect in existing traffic forecast: cannot meet operator and there are multiple cordless communication networks
(i.e. there is the network of different systems, such as China Mobile and there is the shifting of three kinds of standards such as 2G, 3G, 4G
Dynamic communication network) resource distribution demand.
Existing business Forecasting Methodology has following defects that isolated consideration is often thrown the net the business demand of network, not system
Raise the impact considering other standard networks.For example, it is fast-developing that China moves 4G user, band
Dynamic 4G portfolio rapidly increases, and newly-increased 4G user constitutes the inside, about 80% be by original 2G,
3G subscription is transformed.It is obvious that the development of 4G can strong influence 2G and the portfolio growth of 3G.
If the method that prediction 2G and 3G portfolio still uses trend extropolation, do not consider that it is affected by 4G,
The huge deviation of generation that predicts the outcome will be caused, thus cause Internet resources mispairing.
This better embodiment seeks to the traffic forecast that becomes more meticulous realizing existing under multiple network standard.
The existing network 2G/3G/4G cell-level that this better embodiment obtains from operator's operation analysis decorum
Data are carried out rasterizing mapping, and carry out the microcosmic of lattice level based on this by user, traffic data
Prediction, with the configuration that becomes more meticulous of carrier-supporting-carrier wireless network resource.
Below in conjunction with the accompanying drawings, this better embodiment is made detailed elaboration.
Fig. 2 shows the grid traffic forecast method schematic diagram that Multi net voting standard is collaborative, relates generally to grid and draws
Divide, user is mapped to different network formats user collaborative development prediction, grid in grid, grid with portfolio
Interior customer service model prediction, grid Traffic prediction etc..
It is described as follows:
<grid division>
The division of grid is by the basis of Multi net voting standard cooperation service prediction.The base station of different network formats
Employing frequency range is different, and the scope of business covered is the most different.It is thus desirable to by whole network planning region (ratio
Such as a province or a city) if being divided into dry lattice, in order to by base station, the use of existing different network formats
Each grid that family, portfolio are corresponding.The criteria for classifying of grid can be adjusted according to practical situation, and one
As can carry out dividing according to 500 meters * 500 meters (will to be divided into several length of sides be 500 in whole region
The square of rice).
<existing user and portfolio are mapped to grid>
Due to the mobility feature that mobile communication is natural, a large number of users is necessarily caused to appear in different every day
Grid and portfolio occurs.Accordingly, it would be desirable to fix a cycle (such as one week or one month), statistics
Different network formats user in this grid and the portfolio occurred, in this, as the radix of prediction.
For example, with on June 1st, 2014~on June 30th, 2014 common one month as measurement period,
Within this cycle, certain grid has 8000 2G customer consumptions 80000MB flow, 2500 3G use
50000MB flow and 500 4G customer consumptions 50000MB flow has been consumed at family, then by 10000
(7000+2000+1000=10000) individual user is as the user base number of this grid user in predicting follow-up.Table 1
It is user and the leading indicator involved by portfolio.
Table 1
<different network formats user collaborative development prediction in grid>
In grid, different network formats user collaborative development prediction flow process can refer to Fig. 3, comprises the steps:
Step 301 the: calculate (2G in such as the example above grid of different systems user structure in all grids
User accounts for 70%, and 3G subscription accounts for 20%, and 4G user accounts for 10%);
Step 302: use K-Means clustering method, account for total user's proportion, 3G subscription with 2G user
Account for total user's proportion, based on 4G user accounts for three indexs such as total user's proportion, be different by grid division
Classification (is specifically divided into a few class, can depend on the circumstances, classify the most, calculate the most accurate), and calculates
The average user structure of each cluster.Such as can be divided into three classifications: A classification grid has 100,
Feature is that 4G user's accounting is high, and 3G accounting is high;B classification grid has 200, and feature is 4G user
Accounting is high, and 2G user's accounting is low;C classification grid has 300, and feature is that 4G user's accounting is low,
2G user's accounting is high.The meansigma methods of the user structure of all grids in calculating each classification respectively: such as A
The average accounting of class grid 4G user 25%, the average accounting of 3G subscription 30%, the average accounting of 2G user 45%;
The B class average accounting of grid 4G user 15%, the average accounting of 3G subscription 45%, the average accounting of 2G user 40%;
The C class average accounting of grid 4G user 5%, the average accounting of 3G subscription 25%, the average accounting of 2G user 70%
Step 303: with 4G user's accounting as leading indicator, different classes of grid is sorted from low to high;
With the data instance in step 302,4G user's accounting of three class grids is respectively 30%, and 15%, 5%.
Sequence the most from low to high is respectively as follows: C classification, B classification, A classification.
Step 304: from low to high, the user structure of each classification with the user structure of next higher classification is
Develop target.The user structure of the highest classification develops and is determined by houses market development final goal.Such as C
Classification grid total user 4G user's accounting is 5%, and the average accounting of 3G subscription 25%, 2G user averagely accounts for
Ratio 70%, owing to same province/urban subscriber's structure evolution path exists similarity, it is believed that its next
Individual ownership goal evolution target is that B classification grid, i.e. 4G user's accounting develop into 15%, and 3G subscription is put down
All accounting 45%, average accountings of 2G user 40%.
Owing to A classification grid 4G user's accounting is the highest, it is 30%, there is no next step evolution target.Now
Need company according to market development final goal, set a numerical value, as its evolution target.
Step 305: the average user structure of each classification grid is as the user structure of all grids in its inside
Developing goal.
Step 306: according to the inner total use determined of a upper module " existing user and portfolio are mapped to grid "
Family radix, is multiplied by user structure, obtains the number of users prediction of the internal different network formats of each grid.
In such as C classification grid, certain grid has user 10,000, the average accounting of 4G user 5% (500),
The average accounting of 3G subscription 25% (2500), the average accounting of 2G user 70% (7000).Then user structure is drilled
Enter the average accounting of the 4G user in B classification 15% (1500), the average accounting of 3G subscription 45% (4500),
The average accounting of 2G user 40% (4000), this grid 4G user increases by 1000, and 3G subscription increases by 2000,
2G user reduces 3000.
<different network formats customer consumption model prediction in grid>
Existing customer consumption model in grid can be calculated by portfolio and number of users.Predetermined period
Interior rate of increase is determined by houses market developing goal.For example, 2G user in the most a certain grid
DOU (data traffic monthly consumed, the unit MB/ month) is 10M, and 3G subscription is that 20M, 4G use
Family is 100M, and following half a year, the market target of company was that the DOU of user is promoted one times, then can be by
User's DOU goal setting in this grid is 2G user 20M, 3G subscription 40M, 4G user 200M.
<different network formats Traffic prediction in grid>
In grid, number of users is multiplied with customer consumption model, then can obtain grid business in predetermined period
Amount.Such as according to a upper module " different network formats user collaborative development prediction in grid " step 306
In number of users, then 2G portfolio is that 4000*20=80000MB, 3G portfolio is
4500*40=180000MB, 4G portfolio is 1500*200=300000MB.
In grid, Traffic prediction can directly instruct wireless network resource to configure.2/3/4G in such as grid
The network capacity extension.
This better embodiment carries out heterogeneous networks according to the coevolution between user's development of heterogeneous networks
The cooperation service amount prediction of standard.Specifically, the user of existing network 2G/3G/4G cell-level, portfolio are obtained
Data are carried out rasterizing mapping by data, then calculate the average user structure of each classification grid, finally
Using the average user structure of each classification grid as the user structure developing goal of all grids in its inside, enter
Row development prediction.
This better embodiment compensate for isolated individual network of prediction in existing wireless network planning traffic forecast
Portfolio develops the problem easily causing gross differences.By considering the use of networks with different systems carrying as a whole
Coevolution between family, portfolio, solves current operator and generally there are multiple networks with different systems feelings
Radio network services requirement forecasting problem under condition.
Fig. 4 represents the structured flowchart of a kind of network index prediction means that the embodiment of the present invention provides, with reference to figure
4, the embodiment of the present invention also provides for a kind of network index prediction means, is used for predicting that multiple wireless networks cover
Under first area in user's service indication, multiple wireless networks are belonging respectively to multiple network standard, described
User's service indication includes that number of users, described network index prediction means include:
First acquisition module 401, multiple wireless networks described in described first area in being used for obtaining predetermined period
Whole numbers of users under network covering;
Second acquisition module 402, multiple nothings described in described first area in being used for obtaining described predetermined period
The number of users under the first wireless network covering in gauze network the first accounting in described whole numbers of users;
First determines module 403, for according to described whole numbers of users and described first accounting, determines described
First user number under described first wireless network covers in described first area in predetermined period.
Visible, by the way, it is achieved that to cover same at multiple wireless networks adhering to multiple network standard separately
Number of users under in the case of one region covering individual wireless network is predicted, to certain network system
The wireless network of formula covers the prediction of lower number of users can reflect that under different network formats, number of users mutually restricts
Practical situation.
In the embodiment of the present invention, described first acquisition module 401 comprises the steps that
Statistic unit, within the statistical history cycle in described first area in multiple wireless networks described every
Number of users under wireless network covering;
First computing unit, for each number of users sum of counting statistics, obtains described whole number of users.
In the embodiment of the present invention, described first area is included in the multiple regions under multiple wireless networks cover
In, described second acquisition module 402 comprises the steps that
Division unit, for covering according to each wireless network in each region in regions multiple in history cycle
Under number of users respectively in described each region multiple wireless networks cover under total number of users in second
Multiple regions are divided at least two classification by accounting;
First determines unit, for for each classification in described at least two classification, determines history cycle
Number of users under described first wireless network covers in being inside divided into the Zone Full of described each classification is in institute
State the 3rd accounting in the total number of users under Zone Full multiple wireless networks interior cover;
Sequencing unit, for according to each self-corresponding 3rd accounting of described at least two classification, to described at least
Two classification sequences;
Second determines unit, for determine described first area in described at least two classification belonging to first
Classification;
3rd determines unit, for by corresponding to sequence heel row second category after described first category
3rd accounting, is defined as described first accounting.
In the embodiment of the present invention, described first determines that module 403 comprises the steps that
Second unit, is used for calculating described whole number of users and described first accounting is long-pending, obtain described first
Number of users.
In the embodiment of the present invention, described user's service indication may also include portfolio, and described network index is predicted
Device may also include that
3rd acquisition module, described first wireless network in described first area in being used for obtaining described predetermined period
The first corresponding relation between number of users and portfolio under network covering;
Second determines module, for according to described first user number and described first corresponding relation, determines described
The first portfolio under described first wireless network covers in described first area in predetermined period.
The embodiment of the present invention also provides for a kind of electronic equipment, and described electronic equipment includes that above-described network refers to
Mark prediction means.
The above is only the embodiment of the embodiment of the present invention, it is noted that general for the art
For logical technical staff, on the premise of without departing from embodiment of the present invention principle, it is also possible to make some improvement
And retouching, these improvements and modifications also should be regarded as the protection domain of the embodiment of the present invention.
Claims (13)
1. a network index Forecasting Methodology, it is characterised in that under being used for predicting that multiple wireless networks cover
First area in user's service indication, multiple wireless networks are belonging respectively to multiple network standard, described use
Family service indication includes that number of users, described network index Forecasting Methodology include:
Whole numbers of users under multiple wireless networks described cover in described first area in acquisition predetermined period;
The first wireless network in multiple wireless networks described in described first area in obtaining described predetermined period
The number of users under network covering the first accounting in described whole numbers of users;
According to described whole numbers of users and described first accounting, described first area in determining described predetermined period
First user number under interior described first wireless network covering.
Network index Forecasting Methodology the most according to claim 1, it is characterised in that described acquisition is pre-
Whole numbers of users under multiple wireless networks described cover in described first area in the survey cycle include:
In the statistical history cycle, in described first area, in multiple wireless networks described, every wireless network covers
Under number of users;
Each number of users sum of counting statistics, obtains described whole number of users.
Network index Forecasting Methodology the most according to claim 1 and 2, it is characterised in that described
One region is included in the multiple regions under multiple wireless networks cover, institute in the described predetermined period of described acquisition
The first wireless network stated in first area in multiple wireless networks described cover under number of users described entirely
The first accounting in portion's number of users includes:
Divide according to the number of users under each wireless network covers in each region in regions multiple in history cycle
The second accounting in total number of users under multiple wireless networks do not cover in described each region, by multiple districts
Territory is divided at least two classification;
For each classification in described at least two classification, in determining history cycle, it is divided into described each class
Number of users multiple nothings in described Zone Full under described first wireless network covers in other Zone Full
The 3rd accounting in total number of users under the line network coverage;
According to each self-corresponding 3rd accounting of described at least two classification, described at least two classification is sorted;
Determine the first category belonging to described first area is in described at least two classification;
By the 3rd accounting corresponding to sequence heel row second category after described first category, it is defined as institute
State the first accounting.
Network index Forecasting Methodology the most according to claim 3, it is characterised in that described basis is gone through
Number of users under each wireless network covers in each region in multiple regions in the history cycle respectively described often
In individual region multiple wireless networks cover under total number of users in the second accounting, multiple regions are divided into
Few two classifications include:
Use clustering algorithm, with the second accounting that each wireless network in described each region is corresponding be described often
The algorithm input pointer that individual region is corresponding, clusters the plurality of region, obtains described at least two class
Not.
Network index Forecasting Methodology the most according to claim 1 and 2, it is characterised in that described
According to described whole numbers of users and described first accounting, described in described first area in determining described predetermined period
First user number under first wireless network covers includes:
Calculate described whole number of users and described first accounting is long-pending, obtain described first user number.
Network index Forecasting Methodology the most according to claim 1 and 2, it is characterised in that described use
Family service indication also includes that portfolio, described network index Forecasting Methodology also include:
Number of users under described first wireless network covers in described first area in obtaining described predetermined period
And the first corresponding relation between portfolio;
According to described first user number and described first corresponding relation, in determining described predetermined period described first
The first portfolio under described first wireless network covers in region.
Network index Forecasting Methodology the most according to claim 6, it is characterised in that described first right
First under described first wireless network covers in described first area in including described predetermined period should be related to
Prediction user's average traffic, described first wireless in described first area in the described predetermined period of described acquisition
The first corresponding relation between number of users and portfolio under the network coverage includes:
Portfolio under described first wireless network covers in described first area in calculating described history cycle
With the ratio of number of users, obtain the first historic user average traffic;
Put down with prediction user according to described first historic user average traffic and historic user average traffic
All the second corresponding relations between portfolio, determine described first prediction user's average traffic;
Described according to described first user number with described first corresponding relation, described in determining described predetermined period
The first portfolio under described first wireless network covers in first area includes:
Calculate described first user number and described first prediction user's average traffic is long-pending, obtain described first
Portfolio.
8. a network index prediction means, it is characterised in that under being used for predicting that multiple wireless networks cover
First area in user's service indication, multiple wireless networks are belonging respectively to multiple network standard, described use
Family service indication includes that number of users, described network index prediction means include:
First acquisition module, in being used for obtaining predetermined period, in described first area, multiple wireless networks described cover
Whole numbers of users under Gai;
Second acquisition module, multiple wireless networks described in described first area in being used for obtaining described predetermined period
The number of users under the first wireless network covering in network the first accounting in described whole numbers of users;
First determines module, for according to described whole numbers of users and described first accounting, determines described prediction
First user number under described first wireless network covers in described first area in cycle.
Network index prediction means the most according to claim 8, it is characterised in that described first obtains
Delivery block includes:
Statistic unit, within the statistical history cycle in described first area in multiple wireless networks described every
Number of users under wireless network covering;
First computing unit, for each number of users sum of counting statistics, obtains described whole number of users.
Network index prediction means the most according to claim 8 or claim 9, it is characterised in that described
One region is included in the multiple regions under multiple wireless networks cover, and described second acquisition module includes:
Division unit, for covering according to each wireless network in each region in regions multiple in history cycle
Under number of users respectively in described each region multiple wireless networks cover under total number of users in second
Multiple regions are divided at least two classification by accounting;
First determines unit, for for each classification in described at least two classification, determines history cycle
Number of users under described first wireless network covers in being inside divided into the Zone Full of described each classification is in institute
State the 3rd accounting in the total number of users under Zone Full multiple wireless networks interior cover;
Sequencing unit, for according to each self-corresponding 3rd accounting of described at least two classification, to described at least
Two classification sequences;
Second determines unit, for determine described first area in described at least two classification belonging to first
Classification;
3rd determines unit, for by corresponding to sequence heel row second category after described first category
3rd accounting, is defined as described first accounting.
11. network index prediction meanss according to claim 8 or claim 9, it is characterised in that described
One determines that module includes:
Second unit, is used for calculating described whole number of users and described first accounting is long-pending, obtain described first
Number of users.
12. network index prediction meanss according to claim 8 or claim 9, it is characterised in that described use
Family service indication also includes that portfolio, described network index prediction means also include:
3rd acquisition module, described first wireless network in described first area in being used for obtaining described predetermined period
The first corresponding relation between number of users and portfolio under network covering;
Second determines module, for according to described first user number and described first corresponding relation, determines described
The first portfolio under described first wireless network covers in described first area in predetermined period.
13. 1 kinds of electronic equipments, it is characterised in that include that right arbitrary in claim 8 to 12 such as is wanted
Seek described network index prediction means.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510033232.1A CN105873087B (en) | 2015-01-22 | 2015-01-22 | A kind of network index prediction technique, device and electronic equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510033232.1A CN105873087B (en) | 2015-01-22 | 2015-01-22 | A kind of network index prediction technique, device and electronic equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105873087A true CN105873087A (en) | 2016-08-17 |
CN105873087B CN105873087B (en) | 2019-06-28 |
Family
ID=56624060
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510033232.1A Active CN105873087B (en) | 2015-01-22 | 2015-01-22 | A kind of network index prediction technique, device and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105873087B (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106507406A (en) * | 2016-11-30 | 2017-03-15 | 四川九洲电器集团有限责任公司 | A kind of equipment of wireless network accesses the Forecasting Methodology of number and equipment |
CN106888502A (en) * | 2017-03-31 | 2017-06-23 | 中国联合网络通信集团有限公司 | A kind of Poewr control method and device of wideband multimode device |
CN107124768A (en) * | 2017-04-13 | 2017-09-01 | 中国联合网络通信集团有限公司 | A kind of method and device of power distribution |
CN109981327A (en) * | 2017-12-28 | 2019-07-05 | 中移信息技术有限公司 | A kind of prediction technique and system of portfolio |
CN112055380A (en) * | 2019-06-06 | 2020-12-08 | 华为技术有限公司 | Method and apparatus for predicting traffic volume |
WO2021008270A1 (en) * | 2019-07-12 | 2021-01-21 | 华为技术有限公司 | Data processing method, apparatus and system |
CN115314908A (en) * | 2022-09-06 | 2022-11-08 | 中国联合网络通信集团有限公司 | Network planning method and device, electronic equipment and storage medium |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101568127A (en) * | 2008-04-22 | 2009-10-28 | 中国移动通信集团设计院有限公司 | Method and device for determining traffic distribution in network simulation |
CN104010316A (en) * | 2014-06-16 | 2014-08-27 | 南京华苏科技股份有限公司 | Method for telephone traffic prediction through cell-level wireless network |
-
2015
- 2015-01-22 CN CN201510033232.1A patent/CN105873087B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101568127A (en) * | 2008-04-22 | 2009-10-28 | 中国移动通信集团设计院有限公司 | Method and device for determining traffic distribution in network simulation |
CN104010316A (en) * | 2014-06-16 | 2014-08-27 | 南京华苏科技股份有限公司 | Method for telephone traffic prediction through cell-level wireless network |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106507406A (en) * | 2016-11-30 | 2017-03-15 | 四川九洲电器集团有限责任公司 | A kind of equipment of wireless network accesses the Forecasting Methodology of number and equipment |
CN106507406B (en) * | 2016-11-30 | 2020-01-07 | 四川九洲电器集团有限责任公司 | Method and device for predicting device access number of wireless network |
CN106888502B (en) * | 2017-03-31 | 2020-02-04 | 中国联合网络通信集团有限公司 | Power control method and device of broadband multimode equipment |
CN106888502A (en) * | 2017-03-31 | 2017-06-23 | 中国联合网络通信集团有限公司 | A kind of Poewr control method and device of wideband multimode device |
CN107124768A (en) * | 2017-04-13 | 2017-09-01 | 中国联合网络通信集团有限公司 | A kind of method and device of power distribution |
CN107124768B (en) * | 2017-04-13 | 2019-12-06 | 中国联合网络通信集团有限公司 | Power distribution method and device |
CN109981327A (en) * | 2017-12-28 | 2019-07-05 | 中移信息技术有限公司 | A kind of prediction technique and system of portfolio |
CN109981327B (en) * | 2017-12-28 | 2022-05-10 | 中移信息技术有限公司 | Method and system for predicting traffic |
CN112055380A (en) * | 2019-06-06 | 2020-12-08 | 华为技术有限公司 | Method and apparatus for predicting traffic volume |
CN112055380B (en) * | 2019-06-06 | 2022-04-29 | 华为技术有限公司 | Method and apparatus for predicting traffic volume |
WO2021008270A1 (en) * | 2019-07-12 | 2021-01-21 | 华为技术有限公司 | Data processing method, apparatus and system |
CN115314908A (en) * | 2022-09-06 | 2022-11-08 | 中国联合网络通信集团有限公司 | Network planning method and device, electronic equipment and storage medium |
CN115314908B (en) * | 2022-09-06 | 2023-09-05 | 中国联合网络通信集团有限公司 | Network planning method, device, electronic equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN105873087B (en) | 2019-06-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105873087A (en) | Network index prediction method, device and electronic device | |
Li et al. | Development of low voltage network templates—Part I: Substation clustering and classification | |
CN104484993B (en) | Processing method of cell phone signaling information for dividing traffic zones | |
CN102938742B (en) | Communication bandwidth forecasting method and device based on power business requirements | |
CN109492950B (en) | Prediction method capable of meeting space saturation load of large area range based on GIS technology | |
CN106651161A (en) | Acquisition operation and maintenance and dynamic tasking method | |
CN105069527A (en) | Zone area reasonable line loss prediction method based on data mining technology | |
CN105556554A (en) | Multiple device correlation | |
CN106301984A (en) | A kind of mobile communications network capacity prediction methods and device | |
Barceló et al. | Robustness and computational efficiency of Kalman filter estimator of time-dependent origin–destination matrices: Exploiting traffic measurements from information and communications technologies | |
CN106612511A (en) | Wireless network throughput evaluation method and device based on support vector machine | |
CN108805727A (en) | method and device for data processing | |
CN109948844A (en) | A kind of optimization method, device, equipment and the medium of break indices robustness | |
CN108446842B (en) | Power management and distribution wind control management method and system | |
Bachir et al. | Using mobile phone data analysis for the estimation of daily urban dynamics | |
CN112559167A (en) | Method for optimizing base station maintenance resource allocation based on Voronoi dynamic graph | |
CN109816017A (en) | Power grid missing data complementing method based on fuzzy clustering and Lagrange's interpolation | |
CN112862172A (en) | State network 95598 power failure complaint prediction method and device, computer equipment and storage medium | |
CN101895898A (en) | Method and system for inspecting cell identical and adjacent frequency interference | |
CN109587721A (en) | A kind of subzone network coverage evaluating method and device | |
Zhou et al. | High-resolution estimation of building energy consumption at the city level | |
CN104502692A (en) | Power abnormality detection method and central processing device | |
CN104092215A (en) | Distribution transformer capacity control method and system | |
CN109635996A (en) | Room rate tendency look-forward model construction method, device and storage medium | |
CN104299041A (en) | Signaling-based regional flow rate value evaluation method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |