CN112202585B - Wireless network flow prediction method and device and electronic equipment - Google Patents
Wireless network flow prediction method and device and electronic equipment Download PDFInfo
- Publication number
- CN112202585B CN112202585B CN201910609413.2A CN201910609413A CN112202585B CN 112202585 B CN112202585 B CN 112202585B CN 201910609413 A CN201910609413 A CN 201910609413A CN 112202585 B CN112202585 B CN 112202585B
- Authority
- CN
- China
- Prior art keywords
- flow
- wireless network
- prediction
- cluster
- data
- 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
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/147—Network analysis or design for predicting network behaviour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/142—Network analysis or design using statistical or mathematical methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/06—Testing, supervising or monitoring using simulated traffic
Abstract
The embodiment of the invention relates to the technical field of communication, and discloses a wireless network flow prediction method, a wireless network flow prediction device and electronic equipment. The method comprises the following steps: collecting historical wireless network flow data; dividing the communication networks with similar flow growth speed into Cluster small groups based on Kmeans big data clustering; and carrying out Gompertz model flow prediction by taking a Cluster group as a unit, wherein the Gompertz model is provided with a flow fluctuation correction coefficient. Through the mode, the embodiment of the invention avoids the coarse precision caused by one growth coefficient in the whole network and also avoids the random fluctuation of one coefficient in each cell. And moreover, correction matrix factors are established for different festivals and holidays and different scenes, so that the flow prediction is more accurate.
Description
Technical Field
The embodiment of the invention relates to the technical field of communication, in particular to a wireless network flow prediction method, a wireless network flow prediction device and electronic equipment.
Background
With the development of LTE (Long Term Evolution ) networks, new application layers of various internet networks are endless, and new packages are continuously developed, which brings about continuous increase of traffic. The flow change is influenced by various factors such as internet service change, marketing expense change and the like. In the existing resource prediction mode, a prediction model cannot predict the cell-level flow, a whole-network one-cutting growth model is generally adopted for resource delivery, according to a market development plan, a sales target provided by a market is used as a growth coefficient, a uniform growth coefficient is set in the whole network, and all cells use uniform growth factors. The prediction precision of the mode in the prior art is low.
Disclosure of Invention
In view of the foregoing problems, embodiments of the present invention provide a wireless network traffic prediction method, apparatus, and electronic device, which overcome the foregoing problems or at least partially solve the foregoing problems.
According to an aspect of the embodiments of the present invention, there is provided a wireless network traffic prediction method, where the method includes: collecting historical wireless network flow data; dividing the communication networks with similar flow growth speed into Cluster small groups based on Kmeans big data clustering; and carrying out Gompertz model flow prediction by taking a Cluster group as a unit, wherein the Gompertz model is provided with a flow fluctuation correction coefficient.
In an optional manner, the communication network with similar traffic growth speed is divided into Cluster groups based on Kmeans big data clustering, which specifically comprises: and performing Kmeans clustering on the same coverage scene, and dividing the communication networks with similar flow growth speeds into Cluster groups.
In an alternative approach, the gompertz model is:
where y (t) is flow data, k, a, and b are undetermined parameters, t is a time sequence (t ═ 1,2,3,4, … n, n is a positive integer, for example, t may be a month, and t ═ 1 represents the th timeOne month), and K is the flow fluctuation correction coefficient.
In an alternative, when holidays and market factors fluctuate, K is 1; and when holidays and market factors fluctuate, K is the holidays and the market factor flow/the holidays and the market factor normal flow.
In an alternative mode, the holiday and market factor traffic, the holiday and market factor normal traffic are values counted according to historical wireless network traffic data.
In an alternative mode, the step of performing the gompertz model flow prediction by using the Cluster group as a unit specifically comprises the following steps: dividing the sample data in each Cluster group into N groups with equal quantity; taking logarithm of the flow data yi in each group; summing the logarithmic data of each group; according to the summed value lny ═ lnk + btlna, solving the calculation equations of b, lna and lnk; looking up an inverse logarithm table according to the calculation equations of b, lna and lnk to obtain parameters a, b and k; substituting the obtained parameters a, b and k into a formula
Obtaining the Gompertz prediction model.
In an alternative mode, the communication networks with similar traffic growth speeds are communication networks with traffic growth speeds within the same preset range.
According to another aspect of the embodiments of the present invention, there is provided a wireless network traffic prediction apparatus, including: the data collection module is used for collecting historical wireless network flow data; the Cluster dividing module is used for dividing the communication networks with similar flow growth speed into Cluster groups based on Kmeans big data clustering; and the flow prediction module is used for carrying out Gompertz model flow prediction by taking a Cluster group as a unit, wherein the Gompertz model is provided with a flow fluctuation correction coefficient.
According to another aspect of the embodiments of the present invention, there is provided an electronic device including: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus; the memory is configured to store at least one executable instruction that causes the processor to perform the operations of the wireless network traffic prediction method as described above.
According to another aspect of the embodiments of the present invention, there is provided a computer storage medium having at least one executable instruction stored therein, the executable instruction causing a processor to perform the operations of the wireless network traffic prediction method as described above.
The embodiment of the invention divides the communication network with similar flow rate increase speed into Cluster groups, performs Gompertz model flow prediction by taking the Cluster groups as units, and the Gompertz model is provided with the flow fluctuation correction coefficient, so that the increase coefficient is refined into a single Cluster group, thereby not only avoiding the coarse precision caused by one increase coefficient of the whole network, but also avoiding the random fluctuation of one coefficient of each cell. And moreover, correction matrix factors are established for different festivals and holidays and different scenes, so that the flow prediction is more accurate.
The foregoing description is only an overview of the technical solutions of the embodiments of the present invention, and the embodiments of the present invention can be implemented according to the content of the description in order to make the technical means of the embodiments of the present invention more clearly understood, and the detailed description of the present invention is provided below in order to make the foregoing and other objects, features, and advantages of the embodiments of the present invention more clearly understandable.
Drawings
Various additional advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
fig. 1 is a flowchart illustrating a method for predicting wireless network traffic according to an embodiment of the present invention;
FIG. 2 shows a flow chart for Gompertz model flow prediction in Cluster group units;
FIGS. 3a-3d are schematic diagrams illustrating the variation of the Gompertz curve when various parameters are taken;
fig. 4 is a schematic structural diagram illustrating a wireless network traffic prediction apparatus according to an embodiment of the present invention;
fig. 5 shows a schematic structural diagram of an electronic device provided in an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
The embodiment of the invention provides a wireless network flow prediction method based on an improved Gompertz model. According to the embodiment of the invention, according to the flow increasing condition of the whole network cell, a Kmeans algorithm is adopted to divide the cells with similar flow increasing speed into small clusters, the prediction of cell resource increase is carried out by taking the small clusters as a unit, and a holiday increasing factor is established for different holidays to carry out correction of holiday flow increase.
Fig. 1 shows a flowchart of a wireless network traffic prediction method according to an embodiment of the present invention. As shown in fig. 1, the method includes:
step 101: historical wireless network traffic data is collected.
The embodiment of the invention can predict the increase of the flow of the whole network, scene and cell level. Specifically, through statistics of monthly flow data, flow increase in a future period of time can be predicted through the flow data of a plurality of months.
Step 102: and dividing the communication networks with similar flow growth speeds into Cluster small groups based on Kmeans big data clustering.
The traffic growth difference of the same coverage scene in the existing network is large, the traffic prediction is directly carried out by the coverage scene, and the accuracy is poor. In this step, Kmeans big data clustering (also called k-means clustering algorithm) is performed on the same coverage scene, and communication networks with similar traffic growth speed are divided into Cluster groups. The Gompertz model flow prediction is carried out by taking the Cluster group with similar flow growth rate as a unit, and the prediction precision is higher. On the basis, the same Cluster group uses the same growth coefficient to perform cell-level traffic prediction.
The communication networks with similar traffic growth speeds are communication networks with traffic growth speeds within the same preset range. For example, different range intervals can be preset, such as intervals of less than 0, 0 to 0.2, 0.2 to 0.4, 0.4 to 0.6, 0.6 to 0.8, 0.8 to 1, more than 1 and the like, and 100 cells are provided in total, wherein the flow rate increase speed of 20 cells is in the interval of 0.2 to 0.4, and the 20 cells are divided into a Cluster group.
Step 103: and carrying out Gompertz model flow prediction by taking a Cluster group as a unit, wherein the Gompertz model is provided with a flow fluctuation correction coefficient.
Specifically, the gompertz model is a formula (1):
where y (t) is flow data, K, a, and b are undetermined parameters, t is a time sequence (t ═ 1,2,3,4, … n, n is a positive integer, for example, t may be a month, and t ═ 1 represents a first month), and K is a flow fluctuation correction coefficient. When holidays and market factors fluctuate, the K is 1; and when holidays and market factors fluctuate, K is the holidays and the market factor flow/the holidays and the market factor normal flow. The holiday and market factor flow, the holiday without holiday and the normal market factor flow are values counted according to historical wireless network flow data.
Fig. 2 is a flow chart showing the flow prediction of the gompertz model in units of Cluster group, and as shown in fig. 2, the flow prediction can be specifically performed as follows:
step A1: and dividing the sample data in each Cluster group into N groups with equal number.
Step A2: the flow data yi in each group is logarithmized.
Step A3: the logarithmized data of each group are summed.
Step A4: according to the sum lny ═ lnk + btlna, calculating equations of b, lna and lnk are obtained.
Step A5: and looking up an inverse logarithm table according to the calculation equations of b, lna and lnk to obtain parameters a, b and k.
Step A6: substituting the obtained parameters a, b and k into a formula
Obtaining the Gompertz prediction model.
Where y (t) is flow data, K, a, and b are undetermined parameters, t is a time sequence (t ═ 1,2,3,4, … n, n is a positive integer, for example, t may be a month, and t ═ 1 represents a first month), and K is a flow fluctuation correction coefficient.
The flow prediction process is described in detail below with a specific application example:
firstly, the Gompertz model is also called as a Gompertz growth curve model, is suitable for predicting the growth trend of mobile services, and is characterized in that the new services grow more slowly in the initial stage and the terminal stage, and grow exponentially and rapidly in the middle stage. The formula of the Gompertz growth curve is formula (2):
where y (t) is flow data, k, a, and b are parameters to be determined, and t is a time sequence (t ═ 1,2,3,4, … n, n is a positive integer, for example, t may be a month, and t ═ 1 represents the first month). k. a and b determine different forms of the Gompertz curve and represent the growth and change trends of different development stages of products or businesses.
Taking logarithm on both sides of the formula (2) to obtain a formula (3):
lgy＝lgk+btlga (3)
k. the parameters a and b are different, and the gompertz curves are different, and fig. 3a-3d show schematic diagrams of the change condition of the gompertz curves when the various parameters are taken. As shown in fig. 3a, the curve tends to saturate at lga <0, 0< b < 1. As shown in FIG. 3b, the curve falls from saturation when lga <0, b > 1. Lga >0, b >1, the curve grows rapidly from the lowest level, as shown in FIG. 3 c. Lga >0, 0< b <1, the curve rapidly falls near the lowest level as shown in FIG. 3 d.
Solving the coefficients of the Gompertz model:
grouping and solving the parameters of the Gompertz curves a, b and k:
historical statistical data is collected firstly, and the number of samples is selected to be integer multiples of 3, including y1, y2, … and y3 n.
The collected historical statistical sample data is divided into 3 groups with equal number:
group 1, y1, y2, …, yn;
group 3, y2n +1, y2n +2, …, y3 n.
Taking logarithm of sample data yi in each group:
group 1, lgy1, lgy2, …, the sum of which is I
Group 3, lgy2n +1, lgy2n +2, …, lgy3n the sum of which is III
The sum of the above components is marked as I, II and III, and is represented by lny ═ lnk + btlna, the following system of equations can be obtained:
b＝((III-II)/(II-I))1/n Ⅳ
lna＝(II-I)*(b-1)/(b*(bn-1)2) Ⅴ
lnk＝1/n*(I-(bn-1)/(b-1)*b*lna) Ⅵ
looking up the inverse logarithm table to obtain parameters a, b and k, substituting them into formula
The Gompertz prediction model can be obtained.
The development trend of the specific scene business is relatively stable, and can be directly predicted through a Gompertz model. When holidays and market strategy adjustment are met, correction of holiday and market factors is needed for flow fluctuation at the moment. That is, the above formula (1) is adopted
On the basis of a common prediction curve, the flow fluctuation caused by holiday and market factor fluctuation is corrected by K.
Due to the existence of holidays, the current network flow fluctuates in different degrees, in order to better adapt to the prediction of the Gompertz algorithm on the flow change under different scenes, the correction is performed on the K of the Gompertz model, and the specific K value can refer to the value shown in the table 1:
TABLE 1 correction factor for flow fluctuation K value
It can be understood that the specific K value can be customized according to the application, and is not limited to the values in the table. The values in the table above are for reference only.
The above embodiment describes a process of traffic prediction by taking a cell as an example. The scenario and the whole-network level traffic prediction are similar to the cell level traffic prediction process, and are not described herein again.
The embodiment of the invention divides the communication network with similar flow rate growth speed into Cluster groups, performs Gompertz model flow prediction by taking the Cluster groups as a unit, sets the flow fluctuation correction coefficient on the Gompertz model, and refines the growth coefficient into a single Cluster group, thereby not only avoiding the coarse precision caused by one growth coefficient of the whole network, but also avoiding the random fluctuation of one coefficient of each cell. And moreover, correction matrix factors are established for different festivals and holidays and different scenes, so that the flow prediction is more accurate.
Fig. 4 shows a schematic structural diagram of a wireless network traffic prediction apparatus according to an embodiment of the present invention. As shown in fig. 4, the apparatus 400 includes: a data collection module 401, a cluster partitioning module 402, and a traffic prediction module 403.
The data collection module 401 is configured to collect historical wireless network traffic data; the Cluster dividing module 402 is used for dividing the communication networks with similar flow growth speed into Cluster groups based on Kmeans big data clustering; the flow prediction module 403 is configured to perform gompertz model flow prediction by using a Cluster group as a unit, where the gompertz model is provided with a flow fluctuation correction coefficient.
In an optional manner, the cluster dividing module 402 is specifically configured to: and performing Kmeans clustering on the same coverage scene, and dividing the communication networks with similar flow growth speeds into Cluster groups.
In an alternative approach, the gompertz model is:
where y (t) is flow data, K, a, and b are undetermined parameters, t is a time sequence (t ═ 1,2,3,4, … n, n is a positive integer, for example, t may be a month, and t ═ 1 represents a first month), and K is a flow fluctuation correction coefficient.
In an alternative, when holidays and market factors fluctuate, K is 1; when the holiday and the market factor fluctuate, K is the holiday and the market factor flow/holiday without festivals and the market factor normal flow.
In an alternative mode, the holiday and market factor traffic, the holiday and market factor normal traffic are values counted according to historical wireless network traffic data.
In an optional manner, the traffic prediction module 403 is specifically configured to:
dividing the sample data in each Cluster group into N groups with equal quantity;
taking logarithm of the flow data yi in each group;
summing the logarithmic data of each group;
according to the summed value lny ═ lnk + btlna, solving the calculation equations of b, lna and lnk;
looking up an inverse logarithm table according to the calculation equations of b, lna and lnk to obtain parameters a, b and k;
substituting the obtained parameters a, b and k into a formula
Obtaining the Gompertz prediction model.
In an alternative mode, the communication networks with similar traffic growth speeds are communication networks with traffic growth speeds within the same preset range.
The embodiment of the invention divides the communication network with similar flow rate increase speed into Cluster groups, performs Gompertz model flow prediction by taking the Cluster groups as units, and the Gompertz model is provided with the flow fluctuation correction coefficient, so that the increase coefficient is refined into a single Cluster group, thereby not only avoiding the coarse precision caused by one increase coefficient of the whole network, but also avoiding the random fluctuation of one coefficient of each cell. And moreover, correction matrix factors are established for different festivals and holidays and different scenes, so that the flow prediction is more accurate.
An embodiment of the present invention provides a computer storage medium, where at least one executable instruction is stored in the storage medium, and the executable instruction causes a processor to execute the steps of the wireless network traffic prediction method in any of the above method embodiments.
The embodiment of the invention divides the communication network with similar flow rate increase speed into Cluster groups, performs Gompertz model flow prediction by taking the Cluster groups as units, and the Gompertz model is provided with the flow fluctuation correction coefficient, so that the increase coefficient is refined into a single Cluster group, thereby not only avoiding the coarse precision caused by one increase coefficient of the whole network, but also avoiding the random fluctuation of one coefficient of each cell. And moreover, correction matrix factors are established for different festivals and holidays and different scenes, so that the flow prediction is more accurate.
Embodiments of the present invention provide a computer program product comprising a computer program stored on a computer storage medium, the computer program comprising program instructions that, when executed by a computer, cause the computer to perform the steps of the wireless network traffic prediction method in any of the above-mentioned method embodiments.
The embodiment of the invention divides the communication network with similar flow rate increase speed into Cluster groups, performs Gompertz model flow prediction by taking the Cluster groups as units, and the Gompertz model is provided with the flow fluctuation correction coefficient, so that the increase coefficient is refined into a single Cluster group, thereby not only avoiding the coarse precision caused by one increase coefficient of the whole network, but also avoiding the random fluctuation of one coefficient of each cell. And moreover, correction matrix factors are established for different festivals and holidays and different scenes, so that the flow prediction is more accurate.
Fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, and the specific embodiment of the present invention does not limit the specific implementation of the electronic device.
As shown in fig. 5, the electronic device may include: a processor (processor)502, a Communications Interface 504, a memory 506, and a communication bus 508.
Wherein: the processor 502, communication interface 504, and memory 506 communicate with each other via a communication bus 508. A communication interface 504 for communicating with network elements of other devices, such as clients or other servers. The processor 502 is configured to execute the program 510, and may specifically execute the transmission loop fault analysis and scheduling method in any of the method embodiments described above.
In particular, program 510 may include program code comprising computer operating instructions.
The processor 502 may be a central processing unit CPU, or an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits configured to implement an embodiment of the present invention. The electronic device comprises one or more processors, which can be the same type of processor, such as one or more CPUs; or may be different types of processors such as one or more CPUs and one or more ASICs.
And a memory 506 for storing a program 510. The memory 506 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
The embodiment of the invention divides the communication network with similar flow rate increase speed into Cluster groups, performs Gompertz model flow prediction by taking the Cluster groups as units, and the Gompertz model is provided with the flow fluctuation correction coefficient, so that the increase coefficient is refined into a single Cluster group, thereby not only avoiding the coarse precision caused by one increase coefficient of the whole network, but also avoiding the random fluctuation of one coefficient of each cell. And moreover, correction matrix factors are established for different festivals and holidays and different scenes, so that the flow prediction is more accurate.
The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. In addition, embodiments of the present invention are not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the invention and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names. The steps in the above embodiments should not be construed as limiting the order of execution unless specified otherwise.
Claims (10)
1. A method for predicting wireless network traffic, the method comprising:
collecting historical wireless network flow data;
dividing the communication networks with similar flow growth speeds into Cluster groups based on Kmeans big data clustering;
and carrying out Gompertz model flow prediction by taking a Cluster group as a unit, wherein the Gompertz model is provided with a flow fluctuation correction coefficient.
2. The method according to claim 1, wherein the communication networks with similar traffic growth speed are divided into Cluster groups based on Kmeans big data clustering, specifically:
and performing Kmeans clustering on the same coverage scene, and dividing the communication networks with similar flow growth speeds into Cluster groups.
3. The method of claim 1 wherein said Gompertz model is:
y(t)＝kabt*K；
wherein, y (t) is flow data, K, a and b are undetermined parameters, t is a time sequence, and K is a flow fluctuation correction coefficient.
4. The method of claim 3, wherein when holidays and market factors fluctuate, said K ═ 1; and when holidays and market factors fluctuate, K is the holidays and the market factor flow/the holidays and the market factor normal flow.
5. The method of claim 4, wherein the holiday and market factor traffic, holiday and market factor normal traffic are values counted from historical wireless network traffic data.
6. The method according to any one of claims 3 to 5, wherein the Gompertz model flow prediction is performed in units of Cluster's group, specifically:
dividing the sample data in each Cluster group into N groups with equal quantity;
taking logarithm of the flow data yi in each group;
summing the logarithmic data of each group;
according to the summed value lny ═ lnk + btlna, solving the calculation equations of b, lna and lnk;
looking up an inverse logarithm table according to the calculation equations of b, lna and lnk to obtain parameters a, b and k;
substituting the obtained parameters a, b, and k into the formula y (t) ═ kabtK, resulting in a gompertz predictive model.
7. The method according to claim 1, wherein the communication networks with similar traffic growth speeds are communication networks with traffic growth speeds within the same preset range.
8. A wireless network traffic prediction apparatus, the apparatus comprising:
the data collection module is used for collecting historical wireless network flow data;
the Cluster dividing module is used for dividing the communication networks with similar flow growth speed into Cluster groups based on Kmeans big data clustering;
and the flow prediction module is used for carrying out Gompertz model flow prediction by taking a Cluster group as a unit, wherein the Gompertz model is provided with a flow fluctuation correction coefficient.
9. An electronic device, comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is configured to store at least one executable instruction that causes the processor to perform the operations of the wireless network traffic prediction method according to any one of claims 1-7.
10. A computer storage medium having stored therein at least one executable instruction for causing a processor to perform the operations of the wireless network traffic prediction method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910609413.2A CN112202585B (en) | 2019-07-08 | 2019-07-08 | Wireless network flow prediction method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910609413.2A CN112202585B (en) | 2019-07-08 | 2019-07-08 | Wireless network flow prediction method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112202585A CN112202585A (en) | 2021-01-08 |
| CN112202585B true CN112202585B (en) | 2022-07-01 |
Family
ID=74004579
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910609413.2A Active CN112202585B (en) | 2019-07-08 | 2019-07-08 | Wireless network flow prediction method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112202585B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012163387A1 (en) * | 2011-05-27 | 2012-12-06 | Telefonaktiebolaget L M Ericsson (Publ) | A method of conditioning communication network data relating to a distribution of network entities across a space |
| JP2015097334A (en) * | 2013-11-15 | 2015-05-21 | Kddi株式会社 | Communication traffic prediction device and program |
| CN106301984A (en) * | 2015-06-01 | 2017-01-04 | 中国移动通信集团公司 | A kind of mobile communications network capacity prediction methods and device |
| CN109495318A (en) * | 2018-12-17 | 2019-03-19 | 广东宜通世纪科技股份有限公司 | A kind of mobile communications network method for predicting, device and readable storage medium storing program for executing |
| CN109711865A (en) * | 2018-12-07 | 2019-05-03 | 恒安嘉新（北京）科技股份公司 | A method of prediction is refined based on the mobile radio communication flow that user behavior excavates |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130225156A1 (en) * | 2012-02-29 | 2013-08-29 | Cerion Optimization Services, Inc. | Systems and Methods for Convergence and Forecasting for Mobile Broadband Networks |
-
2019
- 2019-07-08 CN CN201910609413.2A patent/CN112202585B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012163387A1 (en) * | 2011-05-27 | 2012-12-06 | Telefonaktiebolaget L M Ericsson (Publ) | A method of conditioning communication network data relating to a distribution of network entities across a space |
| JP2015097334A (en) * | 2013-11-15 | 2015-05-21 | Kddi株式会社 | Communication traffic prediction device and program |
| CN106301984A (en) * | 2015-06-01 | 2017-01-04 | 中国移动通信集团公司 | A kind of mobile communications network capacity prediction methods and device |
| CN109711865A (en) * | 2018-12-07 | 2019-05-03 | 恒安嘉新（北京）科技股份公司 | A method of prediction is refined based on the mobile radio communication flow that user behavior excavates |
| CN109495318A (en) * | 2018-12-17 | 2019-03-19 | 广东宜通世纪科技股份有限公司 | A kind of mobile communications network method for predicting, device and readable storage medium storing program for executing |
Non-Patent Citations (4)
| Title |
|---|
| Dynamic Virtual Resource Management in Clouds Coping with Traffic Burst;Heng lu, etc.;《2014 IEEE International Conference on Services Computing》;20141020;第590-596页 * |
| IP网络流量分析预测工具的设计与实现;彭伟;《华中科技大学硕士学位论文》;20141231;全文 * |
| 基于K-means优化算法的通信业务分析预测;文凤等;《电视技术》;20131231;第37卷(第23期);第119-121页 * |
| 数据挖掘技术在网络质量优化体系中的应用;王磊等;《电信工程技术与标准化》;20121231(第11期);第57-61页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112202585A (en) | 2021-01-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6803403B2 (en) | Dedicated agent pool allocation method, electronics and computer readable storage media | |
| CN109829332B (en) | Joint calculation unloading method and device based on energy collection technology | |
| CN104756467B (en) | CDN traffic managements in cloud | |
| CN108090208A (en) | Fused data processing method and processing device | |
| CN108062573A (en) | Model training method and device | |
| CN113347267B (en) | MEC server deployment method in mobile edge cloud computing network | |
| CN113099474B (en) | Method and device for predicting short-term traffic demand of satellite internet user terminal | |
| CN110020741A (en) | The method, apparatus and electronic equipment of data prediction | |
| CN112202585B (en) | Wireless network flow prediction method and device and electronic equipment | |
| CN116701001B (en) | Target task allocation method and device, electronic equipment and storage medium | |
| CN106776614A (en) | The display methods and device of sharing platform | |
| CN107153677B (en) | Data processing method and system for searching value user | |
| CN112241820B (en) | Risk identification method and device for key nodes in fund flow and computing equipment | |
| CN112243247B (en) | Base station optimization priority determining method and device and computing equipment | |
| CN112884189A (en) | Order quantity prediction model training method, device and equipment | |
| CN114866462A (en) | Internet of things communication routing method and system for smart campus | |
| CN114723071A (en) | Federal learning method and device based on client classification and information entropy | |
| CN111490889B (en) | Method and device for estimating wireless service growth | |
| CN103595783B (en) | Cloud computing scheduling system and cloud computing scheduling method | |
| CN114584476A (en) | Traffic prediction method, network training device and electronic equipment | |
| CN114040013B (en) | Book flow distribution method, calculation device and computer storage medium | |
| CN115150290B (en) | Internet of things network traffic prediction method, system and storage medium | |
| US9817880B1 (en) | Social-aware resource allocation for large-scale distributed systems | |
| CN113626282B (en) | Cloud computing physical node load monitoring method, device, terminal and storage medium | |
| CN112711699B (en) | User division method, system, computer device and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |