CN105873087B - A kind of network index prediction technique, device and electronic equipment - Google Patents
A kind of network index prediction technique, device and electronic equipment Download PDFInfo
- Publication number
- CN105873087B CN105873087B CN201510033232.1A CN201510033232A CN105873087B CN 105873087 B CN105873087 B CN 105873087B CN 201510033232 A CN201510033232 A CN 201510033232A CN 105873087 B CN105873087 B CN 105873087B
- Authority
- CN
- China
- Prior art keywords
- users
- covering
- under
- accounting
- 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.)
- Active
Links
Abstract
The embodiment of the present invention provides a kind of network index prediction technique, device and electronic equipment.Network index prediction technique is used to predict the user service index in the first area under the covering of multiple wireless networks, multiple wireless networks are belonging respectively to multiple network standard, the user service index includes number of users, and the network index prediction technique includes: the whole numbers of users obtained in predetermined period in the first area under multiple wireless networks covering；Obtain first accounting of the number of users in whole numbers of users under the first wireless network covering in described predetermined period in the first area in multiple described wireless networks；According to whole numbers of users and first accounting, the first number of users in described predetermined period in the first area under the first wireless network covering is determined.The embodiment of the present invention makes the prediction for covering lower user service index to the wireless network of certain network formats be able to reflect the actual conditions that user service index mutually restricts under different network formats.
Description
Technical field
The present embodiments relate to wireless access network planning field more particularly to a kind of network index prediction techniques, device
And electronic equipment.
Background technique
User service index, for example, portfolio prediction be wireless network planning first step.It only accurately predicts not
Carry out one period the portfolio of (such as one month, half a year or 1 year), the carry out Radio Access Network money that can be shot the arrow at the target
Source configuration avoids that resource mispairing occurs, and causes the wasting of resources and influences user's perception.
Existing wireless access network planning traffic forecast scheme is mainly carried out as unit of the cell of wireless access network pre-
It surveys, is generally extrapolated using curvilinear trend.For example the monthly average traffic data that all cells go over every month in 1 year is chosen, often
A cell is carried out curve fitting using this 12 data, then choose the highest curve of fitting degree, using its parameter of curve into
Row trend extropolation obtains the average traffic amount prediction data of every month below.
Summary of the invention
The purpose of the embodiment of the present invention is that a kind of network index prediction technique, device and electronic equipment are provided, so as to certain
The prediction that the wireless network of network formats covers lower user service index is able to reflect user service index under different network formats
The actual conditions mutually restricted.
In order to solve the above technical problems, offer of embodiment of the present invention scheme is as follows:
The embodiment of the present invention provides a kind of network index prediction technique, for predicting first under the covering of multiple wireless networks
User service index in region, multiple wireless networks are belonging respectively to multiple network standard, and the user service index includes using
Amount, the network index prediction technique include:
Obtain whole numbers of users in predetermined period in the first area under multiple wireless networks covering；
Obtain the first wireless network covering in described predetermined period in the first area in multiple described wireless networks
Under first accounting of the number of users in whole numbers of users；
According to whole numbers of users and first accounting, determine described in the first area in described predetermined period
The first number of users under the covering of first wireless network.
Preferably, the whole use obtained in predetermined period in the first area under multiple wireless networks covering
Amount includes:
Use in the statistical history period in the first area in multiple described wireless networks under every wireless network covering
Amount；
The sum of each number of users of counting statistics obtains whole numbers of users.
Preferably, the first area includes in the multiple regions under the covering of multiple wireless networks, described in the acquisition
The number of users under the covering of the first wireless network in predetermined period in the first area in multiple described wireless networks is described
The first accounting in whole numbers of users includes:
According to the number of users under each wireless network covering in region each in multiple regions in history cycle respectively in institute
The second accounting in the total number of users in each region under the covering of multiple wireless networks is stated, multiple regions are divided at least two
Classification；
For each classification at least two classification, determines and be divided into the complete of each classification in history cycle
Use of the number of users in the whole region under the covering of multiple wireless networks in portion region under the first wireless network covering
Third accounting in the sum of family；
According to the corresponding third accounting of at least two classification, sort at least two classification；
First category belonging to determining the first area at least two classification；
Third accounting corresponding to second category of the heel row that will sort after the first category, is determined as described first
Accounting.
Preferably, the user according under each wireless network covering in region each in multiple regions in history cycle
The second accounting in the total number of users in each region under the covering of multiple wireless networks respectively is counted, multiple regions are divided
Include: at least two classifications
Using clustering algorithm, with corresponding second accounting of each wireless network in each region for each region
Corresponding algorithm input pointer, clusters the multiple region, obtains at least two classification.
Preferably, described according to whole numbers of users and first accounting, it determines described the in described predetermined period
The first number of users in one region under first wireless network covering includes:
The product for calculating the whole numbers of users and first accounting, obtains first number of users.
Preferably, the user service index further includes portfolio, the network index prediction technique further include:
Obtain the number of users and business in described predetermined period in the first area under the first wireless network covering
The first corresponding relationship between amount；
According to first number of users and first corresponding relationship, determine in described predetermined period in the first area
The first portfolio under the first wireless network covering.
Preferably, first corresponding relationship includes first wireless network in the first area in described predetermined period
First prediction user's average traffic under network covering, it is described to obtain in described predetermined period described first in the first area
Wireless network covering under number of users and portfolio between the first corresponding relationship include:
Calculate the portfolio in the history cycle in the first area under the first wireless network covering and user
The ratio between number, obtains first historical user's average traffic；
According to the first historical user average traffic and historical user's average traffic and prediction user's average traffic
The second corresponding relationship between amount determines the first prediction user's average traffic；
It is described according to first number of users and first corresponding relationship, determine firstth area in described predetermined period
The first portfolio in domain under first wireless network covering includes:
The product for calculating first number of users and the first prediction user's average traffic, obtains first business
Amount.
The embodiment of the present invention also provides a kind of network index prediction meanss, for predicting the under the covering of multiple wireless networks
User service index in one region, multiple wireless networks are belonging respectively to multiple network standard, and the user service index includes
Number of users, the network index prediction meanss include:
First obtains module, for obtaining in predetermined period in the first area under multiple wireless networks covering
Whole numbers of users；
Second obtains module, for obtaining in described predetermined period in the first area in multiple described wireless networks
First accounting of the number of users in whole numbers of users under the covering of first wireless network；
First determining module, for determining in described predetermined period according to whole numbers of users and first accounting
The first number of users in the first area under the first wireless network covering.
Preferably, the first acquisition module includes:
Statistic unit, for every wireless network in multiple wireless networks described in the first area in the statistical history period
Number of users under network covering；
First computing unit, the sum of each number of users for counting statistics obtain whole numbers of users.
Preferably, the first area includes in the multiple regions under the covering of multiple wireless networks, and described second obtains
Module includes:
Division unit, for according to the use under each wireless network covering in region each in multiple regions in history cycle
Amount respectively in each region multiple wireless networks covering under total number of users in the second accounting, by multiple regions draw
It is divided at least two classifications；
First determination unit, for determining in history cycle and dividing for each classification at least two classification
Number of users in the whole region of each classification under first wireless network covering in the whole region multiple
The third accounting in total number of users under wireless network covering；
Sequencing unit is used for according to the corresponding third accounting of at least two classification, at least two class
It does not sort；
Second determination unit, for determining first area first category affiliated at least two classification；
Third determination unit, for will sort, third corresponding to second category of the heel row after the first category is accounted for
Than being determined as first accounting.
Preferably, first determining module includes:
Second unit obtains first number of users for calculating the product of the whole numbers of users and first accounting.
Preferably, the user service index further includes portfolio, the network index prediction meanss further include:
Third obtains module, for obtaining the first wireless network covering in the first area in described predetermined period
Under number of users and portfolio between the first corresponding relationship；
Second determining module, for determining the prediction week according to first number of users and first corresponding relationship
The first portfolio in phase in the first area under the first wireless network covering.
The embodiment of the present invention also provides a kind of electronic equipment including above-described network index prediction meanss.
From the above as can be seen that the embodiment of the present invention at least has the following beneficial effects:
It realizes wireless to individual in the case where multiple wireless networks for adhering to multiple network standard separately cover the same area
Number of users under the network coverage is predicted, to enable the prediction for covering lower number of users to the wireless network of certain network formats
The actual conditions that number of users mutually restricts under reflection different network formats.
Detailed description of the invention
Fig. 1 shows a kind of step flow charts of network index prediction technique provided in an embodiment of the present invention；
Fig. 2 indicates the grid traffic forecast side based on the collaboration of Multi net voting standard of the better embodiment of the embodiment of the present invention
Method flow chart；
Fig. 3 indicates different network formats user collaborative development prediction in the grid of the better embodiment of the embodiment of the present invention
Flow chart；
Fig. 4 indicates a kind of structural block diagram of network index prediction meanss provided in an embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, real below in conjunction with attached drawing and specifically
Example is applied the embodiment of the present invention is described in detail.
Fig. 1 shows a kind of step flow charts of network index prediction technique provided in an embodiment of the present invention, referring to Fig.1, this
Inventive embodiments provide a kind of network index prediction technique, for predicting the use in the first area under the covering of multiple wireless networks
Family service indication, multiple wireless networks are belonging respectively to multiple network standard, and the user service index includes number of users, the net
Network index prediction technique includes the following steps:
Step 101, whole users in predetermined period in the first area under multiple wireless networks covering are obtained
Number；
Step 102, it obtains in described predetermined period in the first area first wireless in multiple described wireless networks
First accounting of the number of users in whole numbers of users under the network coverage；
Step 103, according to whole numbers of users and first accounting, firstth area in described predetermined period is determined
The first number of users in domain under the first wireless network covering.
As it can be seen that covering the same area in multiple wireless networks for adhering to multiple network standard separately by the above-mentioned means, realizing
In the case where the number of users lower to the covering of individual wireless network predict, to make to cover the wireless network of certain network formats
The prediction of lower number of users is able to reflect the actual conditions that number of users under different network formats mutually restricts.
Wherein, the user service index is for example: number of users or portfolio.Portfolio such as mobile data flow.
Network formats are for example: 4G, 3G or 2G.
The first area can be grid region, such as the square area that side length is 500 meters.
In the embodiment of the present invention, in described acquisition predetermined period in the first area under multiple wireless networks covering
Whole numbers of users can include:
Use in the statistical history period in the first area in multiple described wireless networks under every wireless network covering
Amount；
The sum of each number of users of counting statistics obtains whole numbers of users.
In the embodiment of the present invention, the first area may include the institute in the multiple regions under the covering of multiple wireless networks
State the use obtained under the covering of the first wireless network in described predetermined period in the first area in multiple described wireless networks
First accounting of the amount in whole numbers of users can include:
According to the number of users under each wireless network covering in region each in multiple regions in history cycle respectively in institute
The second accounting in the total number of users in each region under the covering of multiple wireless networks is stated, multiple regions are divided at least two
Classification；
For each classification at least two classification, determines and be divided into the complete of each classification in history cycle
Use of the number of users in the whole region under the covering of multiple wireless networks in portion region under the first wireless network covering
Third accounting in the sum of family；
According to the corresponding third accounting of at least two classification, sort at least two classification；
First category belonging to determining the first area at least two classification；
Third accounting corresponding to second category of the heel row that will sort after the first category, is determined as described first
Accounting.
Wherein, the multiple region can be grid region.
The number of users according under each wireless network covering in region each in multiple regions in history cycle is distinguished
The second accounting in total number of users in each region under the covering of multiple wireless networks, multiple regions are divided at least
Two classifications can include:
Using cluster (Cluster) algorithm, using corresponding second accounting of each wireless network in each region as institute
The corresponding algorithm input pointer in each region is stated, clustering is carried out to the multiple region, obtains at least two classification.
Clustering algorithm is for example: K-Means clustering algorithm.
It is described according to the corresponding third accounting of at least two classification, sort at least two classification specific
It can be carried out from low to high according to corresponding third accounting.
For example: at least two classification may include A classification, B classification and C classification these three classifications, right respectively
The third accounting answered is 30%, 15% and 5%, available is ordered as C classification, B by carrying out from low to high according to third accounting
Classification and A classification.
The second category can be any classification of the sequence heel row after the first category, referring also to upper example, such as
Fruit first category is C classification, then second category can be A classification or B classification, corresponding third accounting can for 30% or
15%；
Alternatively, the second category may be sequence heel row come in the classification after the first category it is most preceding
Classification, referring also to upper example, if first category is C classification, second category is B classification, and corresponding third accounting can be
15%.
Further, may also include that
Judge whether the first category comes finally；
When the first category comes last, default accounting is determined as first accounting；
When the first category does not come last, into it is described by sort heel row after the first category the
Third accounting corresponding to two classifications, the step of being determined as first accounting.
Wherein, the default accounting can be set by company according to market development final goal.
In the embodiment of the present invention, it may also include that
It obtains in described predetermined period in the first area under the wireless network covering of the first network standard
The first corresponding relationship between number of users and portfolio；
According to first number of users and first corresponding relationship, determine in described predetermined period in the first area
The first portfolio under the wireless network covering of the first network standard.
In this way, the prediction of portfolio is made to be able to reflect the actual conditions that portfolio under different network formats mutually restricts.
Wherein, first corresponding relationship may include first wireless network in the first area in described predetermined period
First prediction user's average traffic under network covering, it is described to obtain in described predetermined period described first in the first area
The first corresponding relationship between number of users and portfolio under wireless network covering can include:
Calculate the portfolio in the history cycle in the first area under the first wireless network covering and user
The ratio between number, obtains first historical user's average traffic；
According to the first historical user average traffic and historical user's average traffic and prediction user's average traffic
The second corresponding relationship between amount determines the first prediction user's average traffic；
It is described according to first number of users and first corresponding relationship, determine firstth area in described predetermined period
The first portfolio in domain under first wireless network covering includes:
The product for calculating first number of users and the first prediction user's average traffic, obtains first business
Amount.
Wherein, second corresponding relationship is for example: the ratio of prediction user's average traffic and historical user's average traffic
Value.The ratio can be set according to houses market target.
To illustrate to be more clearly understood the embodiment of the present invention, the preferable embodiment party of the embodiment of the present invention is provided below
Formula.
This better embodiment provides a kind of grid fining traffic forecast method based on multi-network cooperative.
There are apparent defects for existing traffic forecast: being unable to satisfy operator, there are multiple cordless communication networks (to deposit
In the network of different systems, for example there are the mobile communications networks of three kinds of standards such as 2G, 3G, 4G for China Mobile) resource distribution
Demand.
Existing business prediction technique has following defects that the business demand for isolating the network that considers often to throw the net, and does not consider as a whole
The influence of other standard networks.For example, the mobile 4G user of China is fast-developing, and 4G portfolio is driven rapidly to increase,
And newly-increased 4G user constitutes the inside, about 80% is transformed by original 2G, 3G subscription.It is obvious that the development of 4G can pole
The portfolio of big influence 2G and 3G increases.If the method that prediction 2G and 3G portfolio still uses trend extropolation, does not consider
4G influences it, it will causes prediction result to generate huge deviation, so as to cause Internet resources mispairing.
This better embodiment seeks to realize that there are the fining traffic forecasts under multiple network standard.
The user for the existing net 2G/3G/4G cell-level that this better embodiment is obtained from operator's performance analysis decorum, business
Data are measured, data are subjected to rasterizing mapping, and carry out the Mi-crocosmic forecast of lattice level based on this, it is wireless with carrier-supporting-carrier
The fining of Internet resources configures.
With reference to the accompanying drawing, detailed elaboration is made to this better embodiment.
Fig. 2 shows the grid traffic forecast method schematic diagrams of Multi net voting standard collaboration, relate generally to grid division, user
With portfolio be mapped to grid, different network formats user collaborative development prediction in grid, customer service model prediction in grid,
Grid Traffic prediction etc..
It is described as follows:
<grid division>
The division of grid is the basis for carrying out the prediction of Multi net voting standard cooperation service.The base station of different network formats is using frequency
Section is different, and the scope of business covered is also different.Therefore it needs whole network planning region (such as a province or a city
City) if being divided into dry lattice, so as to by the base station of existing different network formats, user, the corresponding each grid of portfolio.Grid
The criteria for classifying can be adjusted according to the actual situation, can generally be divided according to 500 meters * 500 meters (i.e. by entire area
Domain is divided into the square that several side lengths are 500 meters).
<existing user and portfolio are mapped to grid>
Due to the natural mobility feature of mobile communication, a large number of users is necessarily caused to appear in different grids daily simultaneously
And portfolio occurs.Therefore, it is necessary to fixed a cycle (such as one week or one months), count the heterogeneous networks in the grid
Standard user and the portfolio occurred, in this, as the radix of prediction.For example, with 1 day~2014 June in 2014
Being total to one month on June 30 is measurement period, certain grid shares 8000 2G customer consumptions 80000MB stream within the period
Amount, 2500 3G subscriptions have consumed 50000MB flow and 500 4G customer consumptions 50000MB flow, then by 10000 (7000
+ 2000+1000=10000) user base number of a user as the subsequent grid user in predicting.Table 1 is user and portfolio institute
The main indicator being related to.
Table 1
<different network formats user collaborative development prediction in grid>
Different network formats user collaborative development prediction process can refer to Fig. 3 in grid, include the following steps:
Step 301: calculating different systems user structure in all grids, (for example 2G user accounts in the example above grid
70%, 3G subscription accounts for 20%, 4G user and accounts for 10%)；
Step 302: use K-Means clustering method, with the total user's specific gravity of 2G user Zhan, the total user's specific gravity of 3G subscription Zhan,
Based on three indexs such as the total user's specific gravity of 4G user Zhan, grid division (is specifically divided into several classes, can regarded to be different classes of
Depending on situation, classify more, calculate more accurate), and calculate the average user structure of each cluster.For example three can be divided into
Classification: A classification grid shares 100, and feature is that 4G user's accounting is high, and 3G accounting is high；B classification grid shares 200, and feature is
4G user's accounting is high, and 2G user's accounting is low；C classification grid shares 300, and feature is that 4G user's accounting is low, and 2G user's accounting is high.
Calculate separately the average value of the user structure of all grids in each classification: such as A class grid 4G user is averaged accounting 25%, 3G
User is averaged accounting 30%, and 2G user is averaged accounting 45%；B class grid 4G user is averaged accounting 15%, and 3G subscription is averaged accounting
45%, 2G user are averaged accounting 40%；C class grid 4G user is averaged accounting 5%, and 3G subscription is averaged accounting 25%, and 2G user is flat
Equal accounting 70%
Step 303: using 4G user's accounting as main indicator, different classes of grid being sorted from low to high；In step 302
Data instance, 4G user's accounting of three classes grid is respectively 30%, 15%, 5%.Then sequence is respectively as follows: C class from low to high
Not, B classification, A classification.
Step 304: from low to high, the user structure of each classification is to develop mesh with the user structure of next higher classification
Mark.The user structure of highest classification is developed to be determined by houses market development final goal.Such as the total user 4G user of C classification grid
Accounting is 5%, and 3G subscription is averaged accounting 25%, and 2G user is averaged accounting 70%, due to same province/urban subscriber's structure evolution
There are similitudes in path, it is believed that its next ownership goal evolution target is B classification grid, i.e. 4G user's accounting develops to
15%, 3G subscription is averaged accounting 45%, and 2G user is averaged accounting 40%.
It is 30%, without next step evolution target due to A classification grid 4G user's accounting highest.Company's root is needed at this time
According to market development final goal, a numerical value is set, as its evolution target.
Step 305: the average user structure of each classification grid develops mesh as the user structure of its internal all grid
Mark.
Step 306: according to a upper module " existing user and portfolio are mapped to grid " the inner total user base number determined, multiplying
With user structure, the number of users prediction of different network formats inside each grid is obtained.
For example certain grid shares user 10,000 in C classification grid, 4G user is averaged accounting 5% (500), and 3G subscription averagely accounts for
Than 25% (2500), 2G user is averaged accounting 70% (7000).Then user structure evolves to the 4G user in B classification and is averaged accounting
15% (1500), 3G subscription are averaged accounting 45% (4500), and 2G user is averaged accounting 40% (4000), and grid 4G user increases
1000,3G subscription increases by 2000,2G user and 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.Increasing in predetermined period
Long rate is determined by houses market developing goal.For example, the 2G user DOU (data flow monthly consumed such as in a certain grid
Amount, the unit MB/ month) it is 10M, 3G subscription 20M, 4G user is 100M, and the market target of the following half a year company is by user
DOU promotes one times, then can be 2G user 20M, 3G subscription 40M, 4G user by user's DOU goal-setting in the grid
200M。
<different network formats Traffic prediction in grid>
Number of users is multiplied with customer consumption model in grid, then portfolio of the available grid in predetermined period.Than
Such as according to the number of users in a upper module " different network formats user collaborative development prediction in grid " step 306, then 2G business
Amount is 4000*20=80000MB, and 3G portfolio is 4500*40=180000MB, and 4G portfolio is 1500*200=
300000MB。
Traffic prediction directly can instruct wireless network resource to configure in grid.For example 2/3/4G network expands in grid
Hold.
This better embodiment carries out different network formats according to the coevolution between the user of heterogeneous networks development
The prediction of cooperation service amount.Specifically, user, the traffic data for now netting 2G/3G/4G cell-level are obtained, data are subjected to grid
Change mapping, then calculate the average user structure of each classification grid, finally makees the average user structure of each classification grid
For the user structure developing goal of all grids in its inside, development prediction is carried out.
This better embodiment, which compensates for isolate in existing wireless network planning traffic forecast, predicts individual network traffic
The problem of development be easy to cause gross differences.By considering the user of networks with different systems carrying, the association between portfolio as a whole
With developing, solves the radio network services requirement forecasting in the case of multiple generally existing networks with different systems of current operator and ask
Topic.
Fig. 4 indicates a kind of structural block diagram of network index prediction meanss provided in an embodiment of the present invention, referring to Fig. 4, this hair
Bright embodiment also provides a kind of network index prediction meanss, for predicting the use in the first area under the covering of multiple wireless networks
Family service indication, multiple wireless networks are belonging respectively to multiple network standard, and the user service index includes number of users, the net
Network index prediction meanss include:
First obtains module 401, for obtaining multiple wireless networks covering in the first area in predetermined period
Under whole numbers of users；
Second obtains module 402, for obtaining in described predetermined period multiple described wireless networks in the first area
In first accounting of the lower number of users of the first wireless network covering in the whole numbers of users；
First determining module 403, for determining described predetermined period according to whole numbers of users and first accounting
The first number of users in the interior first area under the first wireless network covering.
As it can be seen that covering the same area in multiple wireless networks for adhering to multiple network standard separately by the above-mentioned means, realizing
In the case where the number of users lower to the covering of individual wireless network predict, to make to cover the wireless network of certain network formats
The prediction of lower number of users is able to reflect the actual conditions that number of users under different network formats mutually restricts.
In the embodiment of the present invention, described first obtains module 401 can include:
Statistic unit, for every wireless network in multiple wireless networks described in the first area in the statistical history period
Number of users under network covering；
First computing unit, the sum of each number of users for counting statistics obtain whole numbers of users.
In the embodiment of the present invention, the first area include multiple wireless networks covering under multiple regions in, it is described
Second obtains module 402 can include:
Division unit, for according to the use under each wireless network covering in region each in multiple regions in history cycle
Amount respectively in each region multiple wireless networks covering under total number of users in the second accounting, by multiple regions draw
It is divided at least two classifications；
First determination unit, for determining in history cycle and dividing for each classification at least two classification
Number of users in the whole region of each classification under first wireless network covering in the whole region multiple
The third accounting in total number of users under wireless network covering；
Sequencing unit is used for according to the corresponding third accounting of at least two classification, at least two class
It does not sort；
Second determination unit, for determining first area first category affiliated at least two classification；
Third determination unit, for will sort, third corresponding to second category of the heel row after the first category is accounted for
Than being determined as first accounting.
In the embodiment of the present invention, first determining module 403 can include:
Second unit obtains first number of users for calculating the product of the whole numbers of users and first accounting.
In the embodiment of the present invention, the user service index may also include portfolio, and the network index prediction meanss are also
Can include:
Third obtains module, for obtaining the first wireless network covering in the first area in described predetermined period
Under number of users and portfolio between the first corresponding relationship；
Second determining module, for determining the prediction week according to first number of users and first corresponding relationship
The first portfolio in phase in the first area under the first wireless network covering.
The embodiment of the present invention also provides a kind of electronic equipment, and the electronic equipment includes above-described network index prediction
Device.
The above is only the embodiment of the embodiment of the present invention, it is noted that for the ordinary skill of the art
For personnel, without departing from the principles of the embodiments of the present invention, can also make several improvements and retouch, these improve and
Retouching also should be regarded as the protection scope of the embodiment of the present invention.
Claims (11)
1. a kind of network index prediction technique, which is characterized in that for predicting in the first area under the covering of multiple wireless networks
User service index, multiple wireless networks are belonging respectively to multiple network standard, and the user service index includes number of users, institute
Stating network index prediction technique includes:
Obtain whole numbers of users in predetermined period in the first area under multiple wireless networks covering；
It obtains under the first wireless network covering in described predetermined period in the first area in multiple described wireless networks
First accounting of the number of users in whole numbers of users；
According to whole numbers of users and first accounting, determine in described predetermined period described first in the first area
The first number of users under wireless network covering；
The first area includes the institute in described described predetermined period of acquisition in the multiple regions under the covering of multiple wireless networks
The number of users under the first wireless network covering in first area in multiple described wireless networks is stated in whole numbers of users
The first accounting include:
According to the number of users under each wireless network covering in region each in multiple regions in history cycle respectively described every
Multiple regions are divided at least two classes by the second accounting in total number of users in a region under the covering of multiple wireless networks
Not；
For each classification at least two classification, whole areas that each classification is divided into history cycle are determined
User of the number of users in the whole region under the covering of multiple wireless networks in domain under the first wireless network covering is total
Third accounting in number；
According to the corresponding third accounting of at least two classification, sort at least two classification；
First category belonging to determining the first area at least two classification；
Third accounting corresponding to second category of the heel row that will sort after the first category, is determined as described first and accounts for
Than.
2. network index prediction technique according to claim 1, which is characterized in that described in described acquisition predetermined period
Whole numbers of users in one region under multiple wireless networks covering include:
Number of users in the statistical history period in the first area in multiple described wireless networks under every wireless network covering；
The sum of each number of users of counting statistics obtains whole numbers of users.
3. network index prediction technique according to claim 1, which is characterized in that described according to areas multiple in history cycle
Multiple wireless networks cover number of users in domain in each region under each wireless network covering in each region respectively
Under total number of users in the second accounting, multiple regions, which are divided at least two classifications, includes:
It is that each region is corresponding with corresponding second accounting of each wireless network in each region using clustering algorithm
Algorithm input pointer, the multiple region is clustered, at least two classification is obtained.
4. network index prediction technique according to claim 1 or 2, which is characterized in that described according to whole users
Several and first accounting determines first under first wireless network covers in the first area in described predetermined period
Number of users includes:
The product for calculating the whole numbers of users and first accounting, obtains first number of users.
5. network index prediction technique according to claim 1 or 2, which is characterized in that the user service index is also wrapped
Include portfolio, the network index prediction technique further include:
Obtain in described predetermined period the first wireless network covering is lower in the first area number of users and portfolio it
Between the first corresponding relationship；
According to first number of users and first corresponding relationship, determine described in the first area in described predetermined period
The first portfolio under the covering of first wireless network.
6. network index prediction technique according to claim 5, which is characterized in that first corresponding relationship includes described
First prediction user's average traffic in predetermined period in the first area under the first wireless network covering, it is described to obtain
Take in described predetermined period the number of users in the first area under the first wireless network covering and the between portfolio
One corresponding relationship includes:
Calculate in the history cycle the first wireless network covering is lower in the first area portfolio and number of users it
Than obtaining first historical user's average traffic；
According to the first historical user average traffic and historical user's average traffic and prediction user's average traffic it
Between the second corresponding relationship, determine it is described first prediction user's average traffic；
It is described according to first number of users and first corresponding relationship, determine in described predetermined period in the first area
The first portfolio under first wireless network covering includes:
The product for calculating first number of users and the first prediction user's average traffic, obtains first portfolio.
7. a kind of network index prediction meanss, which is characterized in that for predicting in the first area under the covering of multiple wireless networks
User service index, multiple wireless networks are belonging respectively to multiple network standard, and the user service index includes number of users, institute
Stating network index prediction meanss includes:
First obtains module, for obtaining the whole in predetermined period in the first area under multiple wireless networks covering
Number of users；
Second obtains module, for obtaining in described predetermined period in the first area first in multiple described wireless networks
First accounting of the number of users in whole numbers of users under wireless network covering；
First determining module, it is described in described predetermined period for determining according to whole numbers of users and first accounting
The first number of users in first area under the first wireless network covering；
The first area includes in the multiple regions under the covering of multiple wireless networks, and the second acquisition module includes:
Division unit, for according to the number of users under each wireless network covering in region each in multiple regions in history cycle
The second accounting in total number of users in each region under the covering of multiple wireless networks respectively, multiple regions are divided into
At least two classifications；
First determination unit, for determining and being divided into institute in history cycle for each classification at least two classification
Stating first wireless network covering is lower in the whole region of each classification number of users, multiple are wirelessly in the whole region
Third accounting in total number of users under the network coverage；
Sequencing unit, for arranging at least two classification according to the corresponding third accounting of at least two classification
Sequence；
Second determination unit, for determining first area first category affiliated at least two classification；
Third determination unit, for the third accounting corresponding to second category of the heel row after the first category that will sort,
It is determined as first accounting.
8. network index prediction meanss according to claim 7, which is characterized in that described first, which obtains module, includes:
Statistic unit is covered for every wireless network in multiple wireless networks described in the first area in the statistical history period
Number of users under lid；
First computing unit, the sum of each number of users for counting statistics obtain whole numbers of users.
9. network index prediction meanss according to claim 7 or 8, which is characterized in that first determining module includes:
Second unit obtains first number of users for calculating the product of the whole numbers of users and first accounting.
10. network index prediction meanss according to claim 7 or 8, which is characterized in that the user service index is also wrapped
Include portfolio, the network index prediction meanss further include:
Third obtains module, for obtaining in described predetermined period in the first area under the first wireless network covering
The first corresponding relationship between number of users and portfolio；
Second determining module, for determining in described predetermined period according to first number of users and first corresponding relationship
The first portfolio in the first area under the first wireless network covering.
11. a kind of electronic equipment, which is characterized in that refer to including the network as described in any claim in claim 7 to 10
Mark prediction meanss.
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 CN105873087A (en) | 2016-08-17 |
| CN105873087B true 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) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| 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 |
| CN109981327B (en) * | 2017-12-28 | 2022-05-10 | 中移信息技术有限公司 | Method and system for predicting traffic |
| CN112055380B (en) * | 2019-06-06 | 2022-04-29 | 华为技术有限公司 | Method and apparatus for predicting traffic volume |
| CN112218263B (en) * | 2019-07-12 | 2022-05-13 | 华为技术有限公司 | Data processing method, device and system |
| 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 |
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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105873087A (en) | 2016-08-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105873087B (en) | A kind of network index prediction technique, device and electronic equipment | |
| CN101547449B (en) | Frequency sweep and mobile phone measurement report-based method for automatic frequency optimization | |
| CN102098684B (en) | System and method for allocating cross-layer resources in cognitive radio network | |
| CN106301984B (en) | A kind of mobile communications network capacity prediction methods and device | |
| CN101304590B (en) | Apparatus and method for determining wireless network capacitance of mobile communication network | |
| CN103369571B (en) | Propagation model revision based on many nets combined measurement and coverage self-optimization method | |
| CN103634807B (en) | WIFI data hotspot cell data monitoring method and WLAN deployment ordering method and device | |
| CN104486772B (en) | A kind of normalized LTE network evaluation optimal sysytem of end-to-end various dimensions | |
| CN110110881A (en) | Power customer requirement forecasting analysis method and system | |
| CN104980950A (en) | Network optimization server, mobile device of realizing network optimization and system of realizing network optimization | |
| CN110658725B (en) | Energy supervision and prediction system and method based on artificial intelligence | |
| CN110346661B (en) | Method and system for automatically inspecting abnormal user voltage | |
| CN105120486B (en) | A kind of evaluation method and device of communication network efficiency | |
| CN105101302A (en) | Flow management method based on use habits of users and system thereof | |
| CN102855525A (en) | System and method for forecasting and analyzing load of resident user | |
| Jha et al. | Techno-economic assessment of the potential for LTE based 4G mobile services in rural India | |
| CN105163344A (en) | Method for positioning TD-LTE intra-system interference | |
| CN106446345A (en) | Distribution network operation indicator processing method based on segmented geographic region | |
| CN104684091B (en) | Network architecture method of adjustment, device, network scheduling controller and base station | |
| CN107172623A (en) | A kind of TD LTE230 wireless private networks frequency resource planing method | |
| CN103002495A (en) | Assessment method and device of wireless network structure | |
| CN103826230B (en) | BRAN optimizes the method and system of fractional frequency reuse | |
| CN106714223A (en) | Method and device for building base station energy consumption model | |
| CN114710787A (en) | Network planning method, device, equipment and storage equipment | |
| CN107222871A (en) | A kind of wireless private network electric power base station planning methods of TD LTE 230 |
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 |